The DOI matches its Crossref record; 73 of the 73 references it cites were found in a registry or an index; none of the 3 sources its claims cite is checked for support yet.
AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove
Open accessAbstract
Sign language recognition, especially the sentence recognition, is of great significance for lowering the communication barrier between the hearing/speech impaired and the non-signers. The general glove solutions, which are employed to detect motions of our dexterous hands, only achieve recognizing discrete single gestures (i.e., numbers, letters, or words) instead of sentences, far from satisfying the meet of the signers’ daily communication. Here, we propose an artificial intelligence enabled sign language recognition and communication system comprising sensing gloves, deep learning block, and virtual reality interface. Non-segmentation and segmentation assisted deep learning model achieves the recognition of 50 words and 20 sentences. Significantly, the segmentation approach splits entire sentence signals into word units. Then the deep learning model recognizes all word elements and reversely reconstructs and recognizes sentences. Furthermore, new/never-seen sentences created by new-order word elements recombination can be recognized with an average correct rate of 86.67%. Finally, the sign language recognition results are projected into virtual space and translated into text and audio, allowing the remote and bidirectional communication between signers and non-signers.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
The paper presents an AI-enabled sign language recognition and communication system using a 15-channel triboelectric smart glove, deep learning, and a VR interface. It recognizes 50 words and 20 sentences, and with segmentation can reconstruct sentences and recognize new/never-seen sentences at an average correct rate of 86.67%.
Key findings
- Nonsegmentation CNN achieved 91.3% accuracy for 50 words and 95% for sentences; the abstract/discussion report 20 sentences, while Results and Fig. 3j describe 17 sentences.
- Segmentation with a hierarchy classifier achieved 82.81% accuracy for word fragments and 85.58% average correct rate for sentence reconstruction; the single classifier achieved 81.9% and 79.41%, respectively.
- New/never-seen sentences created by recombining learned word units in new orders were recognized at 86.67% average correct rate with the hierarchy classifier, versus 60% with the single classifier.
- The glove uses 15 triboelectric sensors; hand motion accounts for 43% of sign language motions, with finger bending (56%), wrist motion (18%), fingertip touch (16%), and palm interaction (10%) among hand motions.
- The VR interface enables bidirectional communication: sign language is translated into text/audio and sent via TCP/IP to a nonsigner, who can type responses; a greeting conversation between avatars Lily and Mary is demonstrated.
Methods
- Triboelectric sensors were fabricated from Ecoflex and wrinkled nitrile with conductive textile electrodes, encapsulated, and stitched/glued onto a cotton glove; 15 sensors were placed on fingers, wrists, right index/middle fingertips, and left palm.
- For nonsegmentation, 100 samples per word and sentence were collected, with 80% training and 20% testing, yielding 5000 word samples and 2000 sentence samples. For segmentation, 50 samples per sentence for 17 sentences (850 total) were split with a 200-point sliding window at 50-point steps, producing 13 elements per 800-point sentence; 60%/20%/20% were used for training/validation/testing, and 5 samples for 3 new sentences tested new-sentence recognition.
- Main analysis used an optimized 1D CNN (5 kernels, 64 filters, 4 convolutional layers), PCA and t-SNE for visualization, single and hierarchy classifiers for segmentation, and a Unity VR interface with TCP/IP client–server communication.
Limitations
- No dedicated Limitations section is present. The paper states that the nonsegmentation method cannot distinguish new/never-seen sentences even when they contain the same word elements in a different order, and it introduces recognition time latency; the segmentation method has compromised recognition accuracy.
- The paper states the demonstration is limited to 50 words and 20 sentences from an American Sign Language phrase book and says the database can be broadened; new-sentence recognition reaches 86.67%, not perfect, and the single classifier is lower at 60%.
- Evident from the text: the VR communication demonstration is a greeting scenario between two avatars under an identical LAN, so broader real-world deployment and larger user populations are not tested in the paper.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures
Verification
Claims the paper makes
35 Own result · 13 Own interpretation · 8 No basis given · 3 Not checked yet · 1 Own method
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“the mean correlation coefficient 0.53 > 0.3 (threshold value for high similarity) by extracting the average value of 100 data samples and correlating it with the new input, which means the similarity is high between different ‘Get’ data samples.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Results > Data analysis of signals of 50 words and 20 sentences
plaincorrelationaln = 100- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Therefore, a high sentence recognition accuracy of 95% is obtained, as indicated in Fig. 3j.”
- Also stated in: § Word and sentence recognition upon nonsegmentation method · plain
“j Confusion map of recognizing 17 sentences.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Results > Word and sentence recognition upon nonsegmentation method
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § Word and sentence recognition upon nonsegmentation method · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The system successfully realizes the recognition of 50 words and 20 sentences.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Introduction
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“the sentence can be inversely reconstructed and recognition at an average correct rate of 85.58% within hierarchy classifier.”
- Also stated in: § Introduction · plain
“the whole sentence’s information can be reconstructed and recognized with an accuracy of 85.58% upon established correlation between word units and sentences.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Results > Word and sentence recognition upon segmentation method
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § Introduction · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“showing an insufficient average correct rate of 79.41%.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Results > Word and sentence recognition upon segmentation method
plainn = 10- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The nonsegmentation AI framework achieves high accuracy for 50 words (91.3%) and 20 sentences (95%) by independently identifying word and sentence signals.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Introduction
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The nonideal consequence for other sentences, such as Y03, Y04, and Y16, is observed as well.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Results > Word and sentence recognition upon segmentation method
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“a high recognition accuracy of these 50 words is achieved with the value of 91.3%, as shown in the confusion matrix in Fig. 3g.”
- Also stated in: § Introduction · plain
“The nonsegmentation AI framework achieves high accuracy for 50 words (91.3%)”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Results > Word and sentence recognition upon nonsegmentation method
plainn = 20- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § Introduction · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The confusion matrix in Fig. 4e shows an accuracy of 81.9% for the single classifier recognizing word units W01–W20.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Results > Word and sentence recognition upon segmentation method
plainn = 170- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“the segmentation approach assisted AI brings the capability of recognizing new/never-seen sentences (average correct rate: 86.67%) that are not included in the database and are created by word element recombination in new orders.”
- Also stated in: § Abstract · plain
“new/never-seen sentences created by new-order word elements recombination can be recognized with an average correct rate of 86.67%.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Introduction
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption: New/never-seen sentences created by new-order word element recombination are valid sign language sentences that a signer would use.
- Also stated in: § Abstract · plain
- It may state two separate claims as one. 23
- Probably not a substantial claim. 6
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Eventually, it positively contributes to the sentence recognition, which is indicated by the improved average correct rate of 85.58% with a reduced false area in Fig. 4i.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Results > Word and sentence recognition upon segmentation method
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“the voltage output increases when sensor area, force, bending degree, and bending speed increase.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Results > Glove configuration and sensor characterization
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The mean correlation coefficient of 0.37 is larger than 0.3, indicating the high signal similarity between ‘Get’ and ‘Must’ as well”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Results > Data analysis of signals of 50 words and 20 sentences
plaincorrelationaln = 100- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“hand motions fall into four categories, including finger bending (56%), wrist motion (18%), touch with fingertips (16%), and interaction with palm (10%).”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Results > Glove configuration and sensor characterization
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“the recognition latency is significantly reduced due to small-distance sliding (50 data points per sliding) as the recognition process will be triggered with each sliding.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Results > Word and sentence recognition upon segmentation method
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“the 3rd and 5–10th samples of sentence Y01 are wrongly classified with a poor correct rate of 30%.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Results > Word and sentence recognition upon segmentation method
plainn = 10- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It shows the performance of feature clustering is poor with category overlaps before going through the CNN network. After undergoing the feature extraction and classification of CNN, the visualization result realized by t-SNE in Fig. 3f indicates a desirable classification performance of the developed CNN model with clear boundaries among these 50 classes with less overlap.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Results > Word and sentence recognition upon nonsegmentation method
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Then the deep learning model recognizes all word elements and reversely reconstructs and recognizes sentences.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Abstract
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“the data analysis proclaims the high similarities of word-to-word and sentence-to-sentence signals.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Results > Data analysis of signals of 50 words and 20 sentences
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“the sign language recognition results are projected into virtual space and translated into text and audio, allowing the remote and bidirectional communication between signers and non-signers.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Abstract
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The system enables the separate and independent recognition of words (i.e., single gestures) and sentences (i.e., continuous multiple gestures) with high accuracies of 91.3% and 95% within nonsegmentation frame.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Discussion
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In comparison, the hierarchy classifier achieves precise identification of 5 samples of New1, 3 samples of New2, and 5 samples of New3.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Results > Recognizing new sentences upon segmentation approach
plainn = 3- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In other words, the hierarchy classifier achieves an average correct rate of 86.67% (see Supplementary Fig. 6b), superior to 60% of the single classifier.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Results > Recognizing new sentences upon segmentation approach
plainn = 5- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Moving forward to the translation (i.e., recognition) stage (see Supplementary Fig. 6a), the single classifier correctly predicts 2 samples of New1, 3 samples of New2, 4 samples of New3 (average correct rate of 60%).”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Results > Recognizing new sentences upon segmentation approach
plainn = 3- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As provided in Supplementary Table 2, both classifiers render the label series prediction for the total 15 inputs of these 3 new sentences, although the CNN model never sees or learns the true label series before.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Results > Recognizing new sentences upon segmentation approach
plainn = 5- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In the first step Fig. 5b(i), the speech-impaired user Lily performs sign language ‘How are you?’, which is recognized and converted to text and audio by the deep learning model.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Results > VR communication interface for the signer and nonsigner
plaindirectSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Overall, the nonsegmentation approach possesses better performance in the aspect of recognition accuracy either for words or sentences but with the shortcoming of apparent recognition time latency and incapability of new sentence recognition.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Results > Recognizing new sentences upon segmentation approach
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The VR interface for two-way remote communication, linked with the AI front end for sign language recognition, shows a potential prototype of a future intelligent sign language recognition and communication system.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Introduction
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The long-length signal of sentence provides more distinguishable features than the single-word signal. Therefore, a high sentence recognition accuracy of 95% is obtained”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Results > Word and sentence recognition upon nonsegmentation method
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Overall, the hierarchy classifier improves both the accuracy of recognizing word elements and that of identifying ever-seen/trained sentences.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Results > Word and sentence recognition upon segmentation method
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“the single classifier may not be effective enough when reconstructing and recognizing sentences that existed in the dataset, which may hinder the identification of new/never-seen sentences.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Results > Word and sentence recognition upon segmentation method
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The VR communication interface linked with AI allows interaction of the speech/hearing disordered and healthy people closely and even remotely, providing a promising platform for the immense interactions between two population groups.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Results > VR communication interface for the signer and nonsigner
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may state two separate claims as one.
- Rests on an assumption: Most current sign language translation systems simply display recognition results on visualized interfaces such as mobile phones and portable displays.
- Rests on an assumption: Most works do not allow interaction between signers and nonsigners.
- Rests on an assumption: There is an acute demand for effective two-way communication between signers and nonsigners.
- Rests on an assumption: The emerging VR interface is an ideal platform for advanced sign language interpretation, visualization, and communication interface.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Finally, the embedded VR interface can act as the bridge of user terminals, transmitting messages back and forth, configuring a closed-loop communication system with gloves and AI component.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Discussion
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
- Rests on an assumption: Most current sign language translation systems simply display recognition results on visualized interfaces such as mobile phones and portable displays.
- Rests on an assumption: Most works do not allow interaction between signers and nonsigners.
- Rests on an assumption: There is an acute demand for effective two-way communication between signers and nonsigners.
- Rests on an assumption: The emerging VR interface is an ideal platform for advanced sign language interpretation, visualization, and communication interface.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Besides, the intelligent system consist of smart gloves, AI-assisted recognition, and TCP/IP enabled server-client LAN communication in virtual space, providing a reliable and appealing platform for the seamless and immense interactions between nonsigners and signers either remotely or proximately.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Discussion
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
- Rests on an assumption: Most current sign language translation systems simply display recognition results on visualized interfaces such as mobile phones and portable displays.
- Rests on an assumption: Most works do not allow interaction between signers and nonsigners.
- Rests on an assumption: There is an acute demand for effective two-way communication between signers and nonsigners.
- Rests on an assumption: The emerging VR interface is an ideal platform for advanced sign language interpretation, visualization, and communication interface.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“The authors affirm that the participant provide informed consent for publication of the images in Figs. 2a, 5b, Supplementary Figs. 2a, 8a, and the videos in Supplementary Movies 1, 2, 3.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Methods > VR communication interface building and demonstration
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Although few works have employed AI-enabled advanced data analytics to achieve highly precise sign language translation, they are still limited to the classification of discrete words that cannot meet the requirement of practical communication in the signer’s daily lives.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Discussion
What the sources say
- Not checked yetcites Supplementary Table 3
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Besides, the small-distance sliding induced recognition brings the potential of the real-time recognition or translation of sentences.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Results > Recognizing new sentences upon segmentation approach
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper relies on this without support.
New/never-seen sentences created by new-order word element recombination are valid sign language sentences that a signer would use.
“new/never-seen sentences created by new-order word elements recombination can be recognized with an average correct rate of 86.67%.”
The paper relies on this without support.
The 50 gestures and 20 sentences selected are representative of daily sign language communication.
“we select 50 gestures that are daily used in the signer’s life as demonstration.”
“20 daily sentences are sorted out for subsequent study.”
The paper relies on this without support.
Sign language is not as prevalent as spoken language and is difficult for nonsigners to understand without prior learning.
“sign language is not as prevalent as the speaking language and difficult for nonsigners to understand without prior learning.”
The paper relies on this without support.
Most current sign language translation systems simply display recognition results on visualized interfaces such as mobile phones and portable displays.
“Most current sign language translation systems simply display the recognition result on visualized interfaces such as mobile phones and portable displays.”
The paper relies on this without support.
Most works do not allow interaction between signers and nonsigners.
“since most of works do not allow the interaction between signers and nonsigners.”
The paper relies on this without support.
There is an acute demand for effective two-way communication between signers and nonsigners.
“However, the acute demand of effective two-way communication between the signers and nonsigners is neglected”
The paper relies on this without support.
The emerging VR interface is an ideal platform for advanced sign language interpretation, visualization, and communication interface.
“which would be an ideal platform for an advanced sign language interpretation, visualization, and communication interface.”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The deep learning algorithm initially identifies word components, followed by the reconstruction of the original sentences, achieving respective accuracies of 82.81% and 85.58%.”
From Artificial intelligence enhanced sensors - enabling technologies to next-generation healthcare and biomedical platform (2023) · cites this paper as Wen, F. et al. 2021
In the citing paper
“In addition, the segmentation method opens new avenues for recognizing novel or previously unseen sentences.”
From Artificial intelligence enhanced sensors - enabling technologies to next-generation healthcare and biomedical platform (2023) · cites this paper as Wen, F. et al. 2021
In the citing paper
“Therefore, as shown in Fig. 9e Wen et al. demonstrate a sign language recognition and communication system based on smart glove sensors (Wen, F. et al. 2021).”
From Artificial intelligence enhanced sensors - enabling technologies to next-generation healthcare and biomedical platform (2023) · cites this paper as Wen, F. et al. 2021
In the citing paper
“This breakthrough in recognizing both existing and new sentences enhances the practicality of sign language recognition systems, marking a significant step towards minimizing communication obstacles between sign language users and non-signers.”
From Artificial intelligence enhanced sensors - enabling technologies to next-generation healthcare and biomedical platform (2023) · cites this paper as Wen, F. et al. 2021
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Introduction
“The nonsegmentation AI framework achieves high accuracy for 50 words (91.3%) and 20 sentences (95%) by independently identifying word and sentence signals.”
§ AI enabled sign language recognition and VR space bidirectional communication using triboelectric smart glove > Results > Word and sentence recognition upon nonsegmentation method
“Therefore, a high sentence recognition accuracy of 95% is obtained, as indicated in Fig. 3j.”
Citations
Cites
Double-slit photoelectron interference in strong-field ionization of the neon dimer
Kunitski, M., Eicke, N., Huber, P., Köhler, J., Zeller, S., Voigtsberger, J., Schlott, N., Henrichs, K., Sann, H., Trinter, F., et al. (2019) · Institutional Repository of Leibniz Universität Hannover (Leibniz Universität Hannover) · doi:10.15488/5174 · Cited by 8,378
Double-slit photoelectron interference in strong-field ionization of the neon dimer
Kunitski, M., Eicke, N., Huber, P., Köhler, J., Zeller, S., Voigtsberger, J., Schlott, N., Henrichs, K., Sann, H., Trinter, F., et al. (2019) · Nature Communications · doi:10.1038/s41467-018-07882-8 · Cited by 8,162
U1 snRNP regulates cancer cell migration and invasion in vitro
Oh, J.-M., Venters, C. C., Di, C., Pinto, A. M., Wan, L., Younis, I., Cai, Z., Arai, C., So, B. R., Duan, J., et al. (2020) · Nature Communications · doi:10.1038/s41467-019-13993-7 · Cited by 7,157
Flexible triboelectric generator
Fan, F.-R., Tian, Z.-Q., & Lin Wang, Z. (2012) · Nano Energy · doi:10.1016/j.nanoen.2012.01.004 · Cited by 6,705
Fully integrated wearable sensor arrays for multiplexed in situ perspiration analysis
Gao, W., Emaminejad, S., Nyein, H. Y. Y., Challa, S., Chen, K., Peck, A., Fahad, H. M., Ota, H., Shiraki, H., Kiriya, D., et al. (2016) · Nature · doi:10.1038/nature16521 · Cited by 5,087
Yang, J. C., Mun, J., Kwon, S. Y., Park, S., Bao, Z., & Park, S. (2019) · Advanced Materials · doi:10.1002/adma.201904765 · Cited by 1,641
Grammar, Gesture, and Meaning in American Sign Language
Liddell, S. K. (2003) · Cambridge University Press eBooks · doi:10.1017/cbo9780511615054 · Cited by 1,390
Learning the signatures of the human grasp using a scalable tactile glove
Sundaram, S., Kellnhofer, P., Li, Y., Zhu, J.-Y., Torralba, A., & Matusik, W. (2019) · Nature · doi:10.1038/s41586-019-1234-z · Cited by 1,162
Skin-integrated wireless haptic interfaces for virtual and augmented reality
Yu, X., Xie, Z., Yu, Y., Lee, J., Vazquez-Guardado, A., Luan, H., Ruban, J., Ning, X., Akhtar, A., Li, D., et al. (2019) · Nature · doi:10.1038/s41586-019-1687-0 · Cited by 1,025
Self-citationHergenrother, C. W., Maleszewski, C., Nolan, M. C., Li, J., d’Aubigny, C. D., Shelly, F. C., Howell, E. S., Kareta, T., Izawa, M. R. M., Barucci, M. A., et al. (2019) · Nature Communications · doi:10.1038/s41467-019-09213-x · Cited by 902
Cited by
Sorted by citations
Items 401–500 of 507
Applying Machine Learning for American Sign Language Recognition: A Brief Survey
Singh, S. K., & Chaturvedi, A. (2023) · Lecture notes in networks and systems · doi:10.1007/978-981-99-2322-9_22 · Cited by 2
Guo, X., & Lee, C. (2023) · IEEE International Conference on Micro Electro Mechanical Systems (MEMS) · doi:10.1109/mems49605.2023.10052121 · Cited by 1
Self-citationGreek sign language recognition using machine learning
(2024) · International Journal of Advanced Computer Research · doi:10.19101/ijacr.2023.1362022 · Cited by 1
Nanophotonic Edge Computing System For Ultra-Low Latency Human-Machine Interface
Ren, Z., Zhang, Z., Zhuge, Y., Xiao, Z., Xu, S., Zhou, J., & Lee, C. (2025) · IEEE International Conference on Micro Electro Mechanical Systems (MEMS) · doi:10.1109/mems61431.2025.10917903 · Cited by 1
Self-citationFlexible Strain Sensor Enabled by Back Propagation Neural Network for Gesture Recognition
Wu, Y., Wang, J., Wang, C., Xia, L., & Wang, J. (2025) · Advanced Intelligent Systems · doi:10.1002/aisy.202500165 · Cited by 1
A High-Performance Flexible Strain Sensor for Smart Glove in Human-Machine Interaction
Yu, L., Huo, W., Sun, Y., Ji, T., Li, A., Liu, H., & Li, D. (2025) · IEEE International Conference on Nano/Micro Engineered and Molecular Systems · doi:10.1109/nems67320.2025.11170032 · Cited by 1
Multimodal Smart Glove System Based on Flexible Optical Fibers and Inertia Sensor Hybrid
Hao, Z., Xie, J., Zhang, Y., Wu, Q., Liu, J., Yang, H. L., Hu, Y., & Liu, B. F. (2025) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2025.3642434 · Cited by 1
Liu, C., Xin, P., Wang, L., Jiang, S., & Yue, L. (2026) · Microchimica Acta · doi:10.1007/s00604-026-07938-3 · Cited by 1
Orchestrating the post‑silicon revolution of electronics through material-enabled intelligence
Wang, B., Li, X., Yu, L., & Lu, Y. (2026) · Chemical Engineering Journal · doi:10.1016/j.cej.2026.175242 · Cited by 1
An ultra-sensitive humidity sensor for silent speech intelligent recognition
yang, H., Zhang, Q., Chen, S., Liu, S., Chen, S., Guo, Q., Chen, G., Liu, X., Zhou, N., Li, W., et al. (2026) · International Journal of Extreme Manufacturing · doi:10.1088/2631-7990/ae6c6e · Cited by 1
Zhao, H., Qu, X., Yang, B., Cheng, T., Cheng, X., Li, M., Tang, B., Kang, X., Lai, Z., Shen, J., et al. (2026) · Advanced Functional Materials · doi:10.1002/adfm.76572 · Cited by 1
Lin, W., Chen, J., Miao, Y., Kong, J., Chen, Z., & Liao, X. (2026) · Materials Horizons · doi:10.1039/d6mh00815a · Cited by 2
Bengali sign language translator with location tracking system
Rahman, T., Chowdhury, T., & Sultana, J. (2024) · Indonesian Journal of Electrical Engineering and Computer Science · doi:10.11591/ijeecs.v33.i3.pp1760-1767 · Cited by 1
Hand Speak: An AI-Powered Real-Time System for Sign Language Recognition and Seamless Translation
Kanungo, T., Aswini, S., Neha, S., & Ramasamy, V. (2025) · Advances in computer science research · doi:10.2991/978-94-6463-858-5_247 · Cited by 1
Digital Perspectives & Global Narratives in New Media Communication
Albuquerque, A., & Bouzaine, K. (2026) · CEOS Edições eBooks · doi:10.56002/ceos.0106ba · Cited by 1
Manufacturing, Sensing, and Applications of Data Gloves: A Review
Shao, S., Li, M., Hu, Y., & Li, M. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3681433 · Cited by 1
Self‐Powered Neuromorphic Systems Based on Tribotronics Synaptic Devices
Shrestha, K., Akbari, M. K., Anbari, A. P., Pandey, P., & Zhuiykov, S. (2026) · Small · doi:10.1002/smll.74180 · Cited by 1
A Comprehensive Review of SLR Systems: Challenges, Datasets, and Unresolved Gaps
Yerimbetova, A., Berzhanova, U., Miłosz, M., Sakenov, B., Daiyrbayeva, E., & Cherikbayeva, L. (2026) · Journal of Imaging · doi:10.3390/jimaging12080357 · Cited by 1
Li, J., Yin, G., Gu, C., Mo, Y., Li, C., Wang, S., Zhang, X., Xu, X., Guo, Z., & Wei, S. (2026) · Chemical Engineering Journal · doi:10.1016/j.cej.2026.181086 · Cited by 1
Santia, I., Muzaki, M. N., Handayani, A. D., & Murtafiah, W. (2026) · Journal of Advanced Sciences and Mathematics Education · doi:10.58524/jasme.v6i3.1443 · Cited by 1
Cutting-edge Piezo/Triboelectric-based Wearable Physical Sensor Platforms
Park, J., Shin, J., Hur, S., Kang, C., Cho, K., & Song, H. (2022) · Journal of Sensor Science and Technology · doi:10.46670/jsst.2022.31.5.301 · Cited by 1
Gaoming, 蒋. J., Chaoyu, 陈. C., Lijun, 陈. C., & Ma, P. (2023) · Laser & Optoelectronics Progress · doi:10.3788/lop231453 · Cited by 1
Faruk, O., Islam, M. R., Rana, S. M. S., Shrestha, K., & Park, J. Y. (2023) · International Conference on Micro and Nanotechnology for Power Generation and Energy Conversion Applications (PowerMEMS) · doi:10.1109/powermems59329.2023.10417521 · Cited by 1
Using augmented intelligence to improve long term outcomes
Zahavi, I., Shitrit, I. B., & Einav, S. (2024) · Current Opinion in Critical Care · doi:10.1097/mcc.0000000000001185 · Cited by 1
Jiang, Y. (2024) · Journal of Computational Methods in Sciences and Engineering · doi:10.3233/jcm-247360 · Cited by 1
Self-Powered Visible Light Communication for Batteryless IoT via Vibration Energy Harvesting
Shen, S., Ding, W., & Wu, C. (2024) · International Workshop on Energy Harvesting & Energy-Neutral Sensing Systems (ENSsys) · doi:10.1145/3698384.3699611 · Cited by 2
Sign Language Recognition System – A Review
Sahayaraj, J., Kaviyapriya, K., & Vasuki, P. (2024) · IFIP advances in information and communication technology · doi:10.1007/978-3-031-73617-9_20 · Cited by 1
Hand Gesture Vision: Integrating Computer Vision and Machine Learning for Enhanced Communication
Kukreja, S., Singh, A. P., & Chauhan, V. (2024) · International Conference on Advances in Computing, Communication and Networking (ICAC2N) · doi:10.1109/icac2n63387.2024.10895070 · Cited by 1
Luxembourg, N., Marew, R., Teitelbaum, D., Ben-Dov, D., Siegelmann, H. T., & Hanein, Y. (2025) · APL Bioengineering · doi:10.1063/5.0270645 · Cited by 1
Irhebhude, M. E., Kolawole, A. O., & Zubair, W. M. (2024) · Journal of Computing and Social Informatics · doi:10.33736/jcsi.7986.2025 · Cited by 1
Virtual emotional gestures to assist in the examination of the mental health of the deaf‐mutes
Liang, H., Xu, H., Wang, Y., Pan, J., Fu, J., & Pang, X. (2023) · Computer Animation and Virtual Worlds · doi:10.1002/cav.2165 · Cited by 1
Foam Nickel-Pdms Composite Film Based Triboelectric Nanogenerator for Speed and Acceleration SensingPreprint
Wang, P., Ni, Q., He, L., & Liao, Q. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4162757 · Cited by 1
A Piezoelectric Bulk Wave Resonant Humidity Sensor for Noncontact Human-Machine Interaction
Le, X., Shi, Q., Sun, Z., Xie, J., & Lee, C. (2022) · IEEE International Conference on Micro Electro Mechanical Systems (MEMS) · doi:10.1109/mems51670.2022.9699460
Self-citationArtificial Intelligence Algorithm for Flexible Sensors
(2022) · Wiley eBooks · doi:10.1002/9783527833115.ch11
Nawaz, A., Choi, H. W., Sarwar, N., & Yoon, D. H. (2023) · Journal of Materials Science Materials in Electronics · doi:10.1007/s10854-022-09640-5
Triboelectric Nanogenerator as Wearable Sensing Devices
Wen, F., He, T., Yang, Y., Wang, C., & Lee, C. (2023) · Springer eBooks · doi:10.1007/978-3-031-05722-9_42-1
Self-citationDeep learning assisted mat-type triboelectric nanogenerator for personnel monitoring
Zhou, L., Wang, Y., Hu, Z., Wang, Y., Wang, J., & Xu, M. (2022) · China Automation Congress (CAC) · doi:10.1109/cac57257.2022.10055113
Nanogenerator applications: Self-powered systems
Pu, X., Liu, J., Li, S., & Wei, D. (2023) · Scientia Sinica Technologica · doi:10.1360/sst-2023-0082
A Survey on Sign Language Recognition with Video Chat
Masood, N. M., Mrs. Kavyashree, J., Arshiya, M., Baig, M. A. A., & Haleema, N. (2023) · INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT · doi:10.55041/ijsrem19011
Sensores Inteligentes em Sistemas Assistivos para Surdos: Uma Revisão Sistemática da Literatura
Soares, C. C. S., da Silva, E. A., Fernandes, A. M. D. R., & Parreira, W. D. (2023) · Anais do Computer on the Beach · doi:10.14210/cotb.v14.p518-520
ARICAK, F., & ÇAĞLARER, E. (2023) · the Journal of Academic Social Sciences · doi:10.29228/asos.69553
Remote Teleoperated Micromanipulation System for Electrophysiology
Yang, S., So, C. H., Zou, X., Li, X., & Lai, K. W. C. (2023) · IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems · doi:10.1109/cyber59472.2023.10256619
Hybrid Sign Language Interpreter Development Using Machine Learning Approach
Walia, D., Jakhmola, H., Nainwal, A., & Dubey, S. K. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-981-99-5997-6_28
Asma’ak: An Emarati Sign Language Translator
Ahmed, M., Jasem, S., Saleh, K., Khattak, A. M., & Alfandi, O. (2023) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc58733.2023.10392859
Development of Triboelectric Nanoenergy and Nanosystem (Tribo-NENS)
Lee, C., Sun, Z., & Zhang, Z. (2024) · IEEE International Conference on Nanotechnology (IEEE-NANO) · doi:10.1109/nano61778.2024.10628879
Self-citationHuang, J., Chen, L., Zheng, S., & Wu, J. (2024) · IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) · doi:10.1109/ispa63168.2024.00120
Zi, Y., Guo, H., Wang, J., Zhang, C., Chen, X., & Zhao, Q. (2025) · Wiley eBooks · doi:10.1002/9783527837908.ch10
Tactile Sensing of Extensor Tendons and Near-Sensor Gesture Recognition for Control of Robotic Hand
Hu, Y., Zhang, Z., Lei, T., & Wong, M. (2025) · IEEE International Conference on Micro Electro Mechanical Systems (MEMS) · doi:10.1109/mems61431.2025.10917969
Self-citationChen, C., Wang, W., Shen, Y., Zhao, Y., Su, Z., Wang, K., Cong, H., Jiang, G., Zhang, A., Yu, H., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5243892
Indian Sign Language Detection in Virtual Reality using Leap Motion Controller
Chunawale, A., Anant, A., Ahmed, P., Singh, A., Pokharkar, P., & Sirsikar, S. (2025) · International Conference on Emerging Smart Computing and Informatics (ESCI) · doi:10.1109/esci63694.2025.10988451
Automated Hand Gesture Recognition for Enhancing Sign Language Communication
Junn, L. T., Egambaram, A., & Jayapal, V. (2024) · IEEE-EMBS Conference on Biomedical Engineering and Sciences · doi:10.1109/iecbes61011.2024.10990669
Modular Soft Sensor Made of Eutectogel and Its Application in Gesture Recognition
Fan, F., Deng, M., & Wei, X. (2025) · Biosensors · doi:10.3390/bios15060339
Yu, W., Tan, J., Chen, X., & Wang, X. (2025) · Global Cases & Practices of Vocational Education · doi:10.64345/374918526
Huang, Y., Li, D., Lian, Z., Xu, X., Liang, L., Zhou, X., Zhang, J., Liang, Y., & Li, H. (2025) · IEEE International Conference on Real-time Computing and Robotics (RCAR) · doi:10.1109/rcar65431.2025.11139581
Recognition of Brazilian Sign Language Through Surface Electromyography Using Deep Learning Models
Carneiro, M. T., Faxina, L. C., Dias, T. S., Campos, D. P., & Mendes, J. J. A. (2025) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-3-031-94934-0_72
Bôas, L. S. V., Silva, G. G., Faxina, L. C., Inafuco, A. T. P., Dias, T. S., & Mendes, J. J. A. (2025) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-3-031-94934-0_91
Dias, T. S., Inafuco, A. T. P., Mendes, J. J. A., & Pichorim, S. F. (2025) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-3-031-94934-0_78
Dias, T. S., Mendes, J. J. A., Lopes, H. S., Silva, T. H., & Pichorim, S. F. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.108736
Integrating ML Approaches for Photodetectors
Bhattacharya, S., Ghosh, S., Deb, D., Hiremath, P., & Nath, D. (2025) · Progress in optical science and photonics · doi:10.1007/978-981-95-1687-2_9
Odia Sign Language Detection for Deaf and Hard-Of-Hearing Community
Hota, S., Chaudhury, P., & Rai, S. C. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-05117-2_25
Constant Charge Characteristics of TENG in Wireless Energy Transmission
Sun, J., Sun, H., Gao, W., Qi, C., Zhi, J., Ma, J., Yang, Z., Liu, S., & Qin, Y. (2025) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.5c17256
Luxembourg, N., Vėbraitė, I., Siegelmann, H. T., & Hanein, Y. (2025) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc58623.2025.11254337
184185Chapter 10 Revolutionizing interaction with AI-driven enhancements in AR and VR
Mehrotra, M., & Bhattacharya, R. (2025) · De Gruyter eBooks · doi:10.1515/9783111388588-010
Lin, Z., Gu, M., Chen, K. M., & Pan, K. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3644894
Novel Biological Prompting Technology: Automatic Directional Control by Eye-Tracking Sensor
Liu, G., Wang, J., Wu, H.-C., Huang, G., Kumar, A., Wu, Y., Chang, S. Y., & Luo, Y. (2025) · IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB) · doi:10.1109/bmsb65076.2025.11165641
American Sign Language Identification Using Deep Convolutional Neural Networks
Kalaivani, K. S., Sundar, K. S., Pranav, A. S., & Vishnu, S. (2025) · Algorithms for intelligent systems · doi:10.1007/978-981-96-5265-5_66
Gao, W., Zhi, J., Cheng, L., Liu, D., & Qin, Y. (2025) · Nano Energy · doi:10.1016/j.nanoen.2025.111511
AI-Enhanced Nanosensors for Advanced Diagnostics
Chaudhary, D., Gupta, S., Usha, & Kaushal, A. (2025) · Smart nanomaterials technology · doi:10.1007/978-981-96-6091-9_14
An Integrated Sign Language Recognition and Health Monitoring System for Physically Challenged
Tharshini, S., Sathya, T., Parimaladevi, M., M.Priyadharshini, M. P., Vinith, S., & Sibiraj, R. (2026) · Lecture notes in networks and systems · doi:10.1007/978-981-95-3671-9_19
Contact Sensing Along Soft Catheter Robots in Minimally Invasive Surgery Based on Magnetic Signals
Hu, J., Gu, W., Hu, J., Xiao, J., Fu, J., & Hu, S. (2026) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2026.3658557
A High‐Sensitivity Wearable Sensor for Precision Recognition of Human Arm Joint Movements Using CNN
Wang, J., Geng, T., Kang, X., & Hu, G. (2026) · Advanced Materials Technologies · doi:10.1002/admt.202502063
Yang, L., Wang, P., Kim, H. J., Kim, S., Lee, J., Yang, Y., Li, Y., & Kim, J. (2026) · Chemical Engineering Journal · doi:10.1016/j.cej.2026.175535
Few-shot sign language recognition using contrastive learning
Hofman-Zweig, M., & Ben‐Assuli, O. (2026) · Technology and Disability · doi:10.1177/10554181261441139 · Cited by 1
Li, J., Wang, L., Ni, S., & Al‐qaness, M. A. A. (2026) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.70092
Advancing flexible sensing systems: Deep learning-driven insights and future perspectives
Xiao, Y., Zhang, B., Han, L., Cui, Y., Shi, X., Liu, W., & Zhang, K. (2026) · Sensors and Actuators A Physical · doi:10.1016/j.sna.2026.117951
Divakaran, N. C., Kara, Y., Mahmoud, H. A., Hill, E., Ayoub, H., & Gilles Lubineau, A. (2026) · Materials & Design · doi:10.1016/j.matdes.2026.116194
Sign Language Recognition Using Computer Vision-Based Deep Learning
Premaratne, P., Li, M., Ye, Z., & Vial, P. J. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-7090-4_30
Han, D., Zhang, X., Zhao, L., Wang, J., & Xu, W. (2026) · Nano Research · doi:10.26599/nr.2026.94908909
Multimodal Sign Language Generation Using Deep Learning and Hybrid Optimization-Based Framework
Santhanakrishnan, G., & Kumaravel, S. (2026) · Journal of Circuits Systems and Computers · doi:10.1142/s0218126626502282
Smart wristband for instrument and athletic training via triboelectric sensing and machine learning
Song, N., Yan, C., Zhuang, Z., Zhao, D., She, X., Chen, T., & Wu, H. (2026) · Nanotechnology and Precision Engineering · doi:10.1063/5.0321888
Bioinspired heliconical auxetic biofibers for intelligent biomechanical surveillance
Zhou, Y., Wang, X., Wang, Y., Xie, L., Qiang, Y., Wang, W., Li, L., Yue, O., & Liu, X. (2026) · Science Advances · doi:10.1126/sciadv.aed6233
Silent Voice: Wearable Glove for Gesture-to-Speech Conversion
Bhagwat, S., Shinde, V., Shindikar, B., Shelke, S., & Bahirat, S. (2026) · International Conference on Computing, Communication and Green Engineering (CCGE) · doi:10.1109/ccge67142.2026.11581848
Harnessing cracks in metal films: Design strategies for stretchable conductors
Zhu, T., Wu, K., Liu, G. W., & Sun, J. F. (2026) · InfoMat · doi:10.1002/inf2.70169
A landmark-based temporal pipeline for real-time adjective recognition in Indian sign language
Arora, T., Girija, R., Yaswanth, K. V. V., & Kumari, P. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21808-3
Wearable Glove: Sign Language Interpretation with AI-Enabled Finger - Mounted Sensors
Valarmathi, R., Begum, K. G., & Manoj, R. D. (2026) · International Research Journal of Multidisciplinary Technovation · doi:10.54392/irjmt26415
Adaryani, H. R., Shanbeh, M., & Safayani, M. (2026) · Measurement · doi:10.1016/j.measurement.2026.122658
Shao, B., Lu, M., Peng, W., Yang, W., Chen, Y., Fong, J., Lu, T., Wu, T., Yan, Z., Hsiao, K., et al. (2026) · Advanced Science · doi:10.1002/advs.77038
Wearable system using conductive fiber gloves and reservoir computing algorithms
Thongking, W., Wiranata, A., Yamaguchi, Y., Kuwajima, Y., Sukegawa, T., Nabae, H., Hosoya, N., Maeda, S., & Premachandra, C. (2026) · Measurement · doi:10.1016/j.measurement.2026.122808
Liu, X., Wang, Z., Tan, X., Meng, L., li, C., Guo, H., Lv, M., & Tang, X. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3724049
Chan, Y. K., Song, H. W., Wong, J., & Chiu, D. K. W. (2026) · The Journal of Academic Librarianship · doi:10.1016/j.acalib.2026.103329
Li, L., Dai, J., Guo, Y., Du, L., Lyu, J., Shen, Y., Li, D., & Wang, K. (2026) · Processes · doi:10.3390/pr14172683
Flexible Silicon Nanowire Bidirectional Bending Sensors for Wearable Wrist-Posture MonitoringPreprint
Wang, S., Qin, Z., Gu, Y., Song, X., & Yu, L. (2026) · doi:10.20517/scierxiv202609.0756.v1
Osman, A., Bakhbergen, U., Aakyiir, M., Lü, J., & Araby, S. (2026) · Nano Materials Science · doi:10.1016/j.nanoms.2026.06.014
Comprehensive survey of sign language recognition and its future through computer vision
Li, M., Premaratne, P., Ye, Z., & Vial, P. J. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.134913
Data Glove and Inception-CSRA Network for Sign Language Recognition
Wu, W.-C., Zhang, Y.-A., & Liu, Y. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-31236-5_24
Skin-Conformal Inertial Sensing Interface for Continuous Silent Speech Recognition
Wang, Z., Liu, Y., Xie, Y., Ding, L., Xue, C., Su, Z., Wang, Y., Yan, J., Tao, L., Yang, Y., et al. (2026) · ACS Sensors · doi:10.1021/acssensors.6c01556
Dynamic BI-Handed Sign Recognition Using 3D-CNN and Gated Recurrent Unit for Indian Sign Language
Naqvi, S. F., Ramteke, S. H., Sreemathy, R., Jagdale, J., & Sayed, A. A. (2026) · Automatic Control and Computer Sciences · doi:10.3103/s014641162670046x
Lei, T., Zhu, B., Hu, Y., Li, T., & Wong, M. (2026) · FlexMat. · doi:10.1002/flm2.70150
Topological Dielectric Fiber Networks for Self‐Powered Teleperception
Du, Y., Zhang, Z., Li, C., Wang, Z., Guo, J., Wang, Z. L., & Wei, D. (2026) · Advanced Intelligent Systems · doi:10.1002/aisy.70583
Self-citationXiang, J., Lei, Y., Chen, K., Wang, B., Liu, H., Ge, Q., Novoselov, K. S., & Liu, Y. (2026) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.6c12862
Metadata
- Authors
- Wen, F., Zhang, Z., He, T., & Lee, C.
- Affiliations
- National University of Singapore (SG)
- Corresponding author
- Lee, Chengkuo
- Venue
- Nature Communications
- Published
- 2021-09-10
- Volume
- 12
- Issue
- 1
- Pages
- 5378-5378
- ISSN
- 2041-1723 (ISSN-L)
- PMC
- PMC8433305
- OpenAlex
- W3197059061
- Semantic Scholar
- 8ee7ba1cc742cb5bfdeeabebcaa913e57a8ec42c
- Cited by
- 494
- References
- 73
- Citations by year
- 2026: 58 · 2025: 121 · 2024: 121 · 2023: 107 · 2022: 78 · 2021: 9
- FWCI
- 48.31
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- Nature Communications (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, other-oa)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- National University of Singapore (submittedVersion, cc-by)
- RePEc: Research Papers in Economics (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Key Research and Development Program of China (2019YFB2004800, R‐2020‐S‐002)
- Topics
- Physical Sciences › Computer Science › Human-Computer Interaction › Hand Gesture Recognition Systems
- Physical Sciences › Engineering › Biomedical Engineering › Advanced Sensor and Energy Harvesting Materials
- Life Sciences › Neuroscience › Cognitive Neuroscience › Tactile and Sensory Interactions
- Keywords
- sign language recognition, sentence recognition, virtual reality communication, two-way communication, hearing loss, word segmentation, gesture sensing, deep learning
- MeSH terms
- Virtual Reality, Wearable Electronic Devices, Deep Learning, Communication Devices for People with Disabilities, Communication Aids for Disabled, Deafness, Gestures, Humans, Sign Language
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-09, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-09 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
