A Lite Distributed Semantic Communication System for Internet of Things
Open accessThe DOI matches its Crossref record; 45 of the 45 references it cites were found in a registry or an index.
Abstract
The rapid development of deep learning (DL) and widespread applications of Internet-of-Things (IoT) have made the devices smarter than before, and enabled them to perform more intelligent tasks. However, it is challenging for any IoT device to train and run DL models independently due to its limited computing capability. In this paper, we consider an IoT network where the cloud/edge platform performs the DL based semantic communication (DeepSC) model training and updating while IoT devices perform data collection and transmission based on the trained model. To make it affordable for IoT devices, we propose a lite distributed semantic communication system based on DL, named L-DeepSC, for text transmission with low complexity, where the data transmission from the IoT devices to the cloud/edge works at the semantic level to improve transmission efficiency. Particularly, by pruning the model redundancy and lowering the weight resolution, the L-DeepSC becomes affordable for IoT devices and the bandwidth required for model weight transmission between IoT devices and the cloud/edge is reduced significantly. Through analyzing the effects of fading channels in forward-propagation and back-propagation during the training of L-DeepSC, we develop a channel state information (CSI) aided training processing to decrease the effects of fading channels on transmission. Meanwhile, we tailor the semantic constellation to make it implementable on capacity-limited IoT devices. Simulation demonstrates that the proposed L-DeepSC achieves competitive performance compared with traditional methods, especially in the low signal-to-noise (SNR) region. In particular, while it can reach as large as $40\times $ compression ratio without performance degradation.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“For instance, edge DL approach has been developed in [58] to deliver low-latency semantic tasks (e.g., text messages) by learning the communication strategies in an end-to-end fashion based on JSCC.”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [58]
Experimental — accuracy not yet measuredIn the citing paper
“Edge AI can also help design AI-native communication strategies for the physical layer (e.g., task-oriented semantic communication [58]) and medium access control layer (e.g., random access protocol [59]).”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [58]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
A Mathematical Theory of Communication
Shannon, C. E. (1948) · Bell System Technical Journal · doi:10.1002/j.1538-7305.1948.tb00917.x · Cited by 48,949
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344 · cited 1×
“The bilingual evaluation understudy (BLEU) score is used to measure the performance [36].”
MethodThe Internet of Things: A survey
Atzori, L., Iera, A., & Morabito, G. (2010) · Computer Networks · doi:10.1016/j.comnet.2010.05.010 · Cited by 15,613
Fundamentals of Wireless Communication
Tse, D., & Viswanath, P. (2005) · doi:10.1017/cbo9780511807213 · Cited by 13,162 · cited 1×
“To make a decision from the received information, there are usually three steps, i) the traditional communication receiver to recover the raw data [7], ii) the feature extractor to obtain and interpret the meanings of the raw data for the decision [8], and iii) the effects due to decisions…”
BackgroundBeyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
Zhang, K., Zuo, W., Chen, Y., Meng, D., & Zhang, L. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2662206 · Cited by 8,983 · cited 1×
“Then, we adopt the deep de-noise network to increase the resolution of LS estimator as in [31] shown in Fig.”
MethodQuantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
Jacob, B., Kligys, S., Chen, B., Zhu, M., Tang, M., Howard, A., Adam, H., & Kalenichenko, D. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00286 · Cited by 4,114
Computer vision: algorithms and applications
(2011) · Choice Reviews Online · doi:10.5860/choice.48-5140 · Cited by 3,911
Bleu: a method for automatic evaluation of machine translation
Papineni, K. (2024) · doi:10.57702/ljteqmrb · Cited by 3,672
Polynomial Codes Over Certain Finite Fields
Reed, I. S., & Solomon, G. (1960) · Journal of the Society for Industrial and Applied Mathematics · doi:10.1137/0108018 · Cited by 3,662 · cited 1×
“Turbo coding and Reed-Solomon (RS) coding [44] for channel coding, where turbo decoding method is log-MAP algorithm with 5 iterations, and quadrature amplitude modulation (QAM).”
Method(2005) · Cited by 3,125
Research works printed but not linked: 2
- goodfellow, 2016, Deep Learning
- 10.1017/cbo9780511807213 · DOI · Paper page
Cited by
Items 201–300 of 585
Xu, R., Yang, Z., Mao, Y., Huang, C., Yang, Q., Xu, L., Xu, W., & Zhang, Z. (2025) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2025.3528943 · Cited by 18
“Although the theory of SemCom has been initially developed, and in practice SemCom systems have been deployed in many transmission tasks and improved system performance [14], the physical representation of semantic information is unclear for different communication tasks.”
Reliable Extraction of Semantic Information and Rate of Innovation Estimation for Graph Signals
Kalfa, M., Yetim, S. Y., Atalık, A., Gok, M., Ge, Y., Li, R., Tong, W., Duman, T. M., & Arıkan, O. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2022.3221950 · Cited by 18
“The conversion into and from knowledge graphs offer an intuitive and explainable semantic extraction compared to [12], [67].”
BackgroundResultInterference Suppressed NOMA for Semantic-Aware Communication Networks
Zhang, Y., Zhong, R., Liu, Y., Xu, W., & Zhang, P. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3371775 · Cited by 17
“Meanwhile, due to this characteristic of semantic symbols, the syntactic-level interference among SUs will not be mitigated perfectly, thereby aggravating the difficulty of the semantic-level interference [14], [23].”
BackgroundResource Allocation for Semantic-Aware Wireless Communication Networks With Imperfect CSI
Zhao, J., Chen, M., Yang, Z., Pan, Y., Niyato, D. T., & Pham, Q. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3575444 · Cited by 17
“This shift has motivated increased exploration of SemCom technologies across diverse applications [8], [9], [10].”
Cache-enabled Knowledge Base Construction Strategy in Semantic Communications
Che, Y., Xiong, H., Han, S., & Xu, X. (2022) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps56602.2022.10008494 · Cited by 17
“Current research works on semantic communication systems only consider the case of limited computing resources in the network [6], [7].”
Background6G: Vision, Applications, and Challenges
da Costa, D. B., Zhao, Q., Chafii, M., Bader, F., & Debbah, M. A. (2023) · Signals and communication technology · doi:10.1007/978-3-031-37920-8_2 · Cited by 16
Two-Way Semantic Communications Without Feedback
Yu, K., He, Q., & Wu, G. (2024) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2024.3352666 · Cited by 16
“Assisted by deep learning methods, semantic communication systems have been shown to perform effectively in text transmission [7], [8], speech transmission [9], image transmission [10], [11], intelligence tasks [12], [13], etc. Specifically, with joint source-channel coding (JSCC), the transceiver…”
Deep Learning Enabled Video Semantic Transmission Against Multi-Dimensional Noise
Niu, H., Wang, L., Lu, Z., Du, K., & Wen, X. (2023) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps58843.2023.10464432 · Cited by 16
“To address the challenges associated with IoT devices, a lite distributed text semantic communication system is developed [4].”
MethodXie, P., Chen, Q., Wu, J., Gao, X., Xing, L., Zhang, Y., & Sun, H. (2025) · Ad Hoc Networks · doi:10.1016/j.adhoc.2025.103762 · Cited by 16
Computation Offloading for Tasks With Bound Constraints in Multiaccess Edge Computing
Li, K., Wang, X., He, Q., Ni, Q., Yang, M., & Dustdar, S. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3264484 · Cited by 16
“Typically, the loss function can be expressed as the mean square measure of the Bellman equation error [29].”
Semantic Communications for Image-Based Sign Language Transmission
Kouvakis, V., Trevlakis, S. E., & Boulogeorgos, A. A. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3360191 · Cited by 16
“Building upon this architecture, a significant research effort has been conducted in a wide range of domains, such as textual data [6], [7], [8], speech signals [9], visual images [10], [11], [12], [13], [14], and video content [15].”
BackgroundBandwidth and Power Allocation for Task-Oriented SemanticCommunicationPreprint
Liu, C., Guo, C., Yang, Y., & Chen, J. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2201.10795 · Cited by 16
“Based on [4], the authors in [5] further proposed a lite disributed semantic communication system, making the model easier to deploy at the Internet of things (IoT) devices.”
BackgroundSEECAD: Semantic End-to-End Communication for Autonomous Driving
Ribouh, S., & Hadid, A. (2024) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv55156.2024.10588546 · Cited by 15
“In [22], the authors proposed a lite distributed semantic communication system, named L-DeepSC designed for text transmission.”
BackgroundAlternate Learning-Based SNR-Adaptive Sparse Semantic Visual Transmission
Tong, S., Yu, X., Li, R., Lu, K., Zhao, Z., & Zhang, H. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3512652 · Cited by 15
“For example, Long Short-Term Memory (LSTM) and Transformer [36]-based natural language processing techniques have been extensively leveraged to design JSCC [29] for text transmission [5], [6], [7].”
A highly reliable encoding and decoding communication framework based on semantic information
Zhang, Y., Zhao, H., Cao, K., Zhou, L., Wang, Z., Liu, Y., & Wei, J. (2023) · Digital Communications and Networks · doi:10.1016/j.dcan.2023.04.002 · Cited by 15
Data Utilization Versus Privacy Protection in Semantic Communications
Zhao, L., Wu, D., & Zhou, L. (2023) · IEEE Wireless Communications · doi:10.1109/mwc.007.2200503 · Cited by 15
“However, the benefits of the large-scale semantic-aware codec in data compression and signal reconstruction are on the basis of huge parameter tensors and high computation overhead, which makes not suitable for deployment on IoT devices with limited computing capabilities or energy resources [7].”
BackgroundKnowledge-Aware Semantic Communication System Design and Data Allocation
Kadam, S., & Kim, D. I. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3333350 · Cited by 15
“The overhead reduction is performed with high accuracy in the literature [19], [20].”
BackgroundYi, P., Cao, Y., Kang, X., & Liang, Y. (2024) · IEEE Transactions on Communications · doi:10.1109/tcomm.2024.3468215 · Cited by 15
“Specifically, three primary approaches were explored at the transmitter end, i.e., the utilization of channel state information (CSI) [24], the investigation of semantic importance distribution [25], and the shared knowledge base [26].”
BackgroundSemantic Communications: the New Paradigm Behind Beyond 5G TechnologiesPreprint
Fernandes, G., Fontes, H., & Campos, R. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2406.00754 · Cited by 15
“Considering the resources constraints of Internet of Things (IoT) devices, [70] proposed the L-DeepSC as a lite distributed version of the DeepSC model.”
MethodEnhanced Semantic Information Transfer on RIS-Assisted Communication Systems
Ma, J., Li, Q., Liu, R., Pandharipande, A., & Ge, X. (2024) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2024.3408420 · Cited by 14
“Building upon DeepSC, a lite streamlined distributed SC system was introduced in [4] to simplify the semantic model by constructing and quantizing the neural network parameters.”
MethodYu, T., Yang, H., Yao, Q., Wang, Z., Zhang, J., Vasilakos, A. V., & Cheriet, M. (2025) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2025.3556375 · Cited by 14
“With increasing demand for higher data rates, low latency, and high reliability, scarce communication resources like spectrum and energy, along with Shannon limit constraints, have driven a shift from bit-based to context-based semantic communication (SemCom) [33].”
Bayesian Inverse Contextual Reasoning for Heterogeneous Semantics- Native Communication
Seo, H., Kang, Y., Bennis, M., & Choi, W. (2023) · IEEE Transactions on Communications · doi:10.1109/tcomm.2023.3327771 · Cited by 14
“For instance, image-to-text embedding via Transformer [7], [8] and conversion from system states into the state evolution law using the Koopman operator [17].”
BackgroundMethodLMaaS: Exploring Pricing Strategy of Large Model as a Service for Communication
Wu, P., Liu, Q., Dong, Y., Wang, Z., & Wang, F. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3418881 · Cited by 14
“Xie et al. [33] design a special distributed lite semantic communication system with limited power consumption to meet the needs of IoT devices.”
BackgroundTang, M., & Lau, V. K. N. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3312331 · Cited by 13
“Digital Object Identifier 10.1109/JIOT.2023.3312331 of Internet of Things (IoT) technologies [4], [5], [6], [7], [8], [9], the heterogeneous devices within furnace systems can be swiftly deployed at scattered positions and easily interconnected through wireless networks.”
BackgroundInfluentialResource Allocation for Semantic Communication Under Physical-layer Security
Lil, Y., Zhou, X., & Zhao, J. (2023) · Globecom · doi:10.1109/globecom54140.2023.10437297 · Cited by 13
SC-PNC: Semantic Communication-Empowered Physical-Layer Network Coding
Pan, H., Yang, S., Chan, T.-T., Wang, Z., Leung, V. C. M., & Li, J. (2024) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2024.3375506 · Cited by 13
“In other words, the network-coded symbols broadcast back to the end nodes are directly obtained from the output of a well-trained DNN. Prior work [29] pointed out that when training a DNN-based decoder (in fact, joint training of both encoder and decoder), the stochastic nature of the channel…”
Optimization of Image Transmission in UAV-Enabled Semantic Communication Networks
Yao, X., Zheng, J., Zheng, X., Dai, H., & Yang, X. (2023) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc59590.2023.10507296 · Cited by 13
“In [6], the authors designed a lightweight distributed semantic communication system.”
BackgroundPost-Deployment Fine-Tunable Semantic Communication
Si, P., Liu, R., Qian, L., Zhao, J., & Lam, K. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3433479 · Cited by 13
Query-Aware Semantic Encoder-Based Resource Allocation in Task-Oriented Communications
Cai, Q., Zhou, Y., Liu, L., Yu, H., Wu, Y., Shi, N., & Shi, J. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3541636 · Cited by 13
“Deep learning (DL) networks such as long short-term memory (LSTM) [5], Transformer [6], [7], [8], [9] and bidirectional encoder representations from Transformers (BERT) [10] have been introduced to design the encoder-decoder architecture.”
Security and Privacy Challenges in Semantic Communication Networks
Do, Q. T., Won, D., Do, T. S., Truong, T. P., & Cho, S. (2025) · International Conference on Artificial Intelligence in Information and Communication (ICAIIC) · doi:10.1109/icaiic64266.2025.10920721 · Cited by 13
“Similarly, in industrial IoT, semantic communication enables smart decision-making by sending context-aware summaries of sensor data rather than raw measurements [2].”
Cooperative and Collaborative Multi-Task Semantic Communication for Distributed Sources
Razlighi, A. H., Tillmann, M. H. V., Beck, E., Bockelmann, C., & Dekorsy, A. (2025) · International Conference on Communications · doi:10.1109/icc52391.2025.11161271 · Cited by 13
“In total 11 models are trained, with SNR ranges in dB: [3 , 5] , [6 , 8] , [9 , 11] , [12 , 14] , [15 , 17] , and [18 , 20] .”
MethodUplink NOMA Semantic Communications: Semantic Reconstruction for SIC
Chen, B., Wang, X., Li, D., Jiang, R., & Xu, Y. (2023) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/iccc57788.2023.10233614 · Cited by 13
“Further, they proposed a lightweight semantic communication system, named L-DeepSC, for communication devices with limited capacity [12].”
BackgroundIs Semantic Communication for Autonomous Driving Secured against Adversarial Attacks?
Ribouh, S., & Hadid, A. (2024) · IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS) · doi:10.1109/aicas59952.2024.10595916 · Cited by 13
“To achieve this, artificial intelligence is expected to play an important role, by evolving towards an AI-based wireless systems that facilitate the development of end-to-end wireless communication [4] [5].”
BackgroundSelf-Critical Alternate Learning-Based Semantic Broadcast Communication
Lu, Z., Li, R., Lei, M., Wang, C., Zhao, Z., & Zhang, H. (2024) · IEEE Transactions on Communications · doi:10.1109/tcomm.2024.3487513 · Cited by 13
“Since then, SemCom has attracted a lot of attention and many works utilize JSCC frameworks to transmit sentence semantics [6], [7], [26], such as UT [22] based semantic coding system [6], [24], and mutual information (MI) based performance optimization between semantic compression and semantic…”
MethodGetu, T. M., Kaddoum, G., & Bennis, M. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2308.01913 · Cited by 13
Wan, Z., Liu, S., Xu, Z., Ni, W., Chen, Z., & Wang, F. (2023) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2023.3328905 · Cited by 12
“In the feature extraction phase, deep neural networks are used for feature extraction [9].”
MethodTinyAirNet: TinyML Model Transmission for Energy-Efficient Image Retrieval From IoT Devices
Shiraishi, J., Thorsager, M., Pandey, S. R., & Popovski, P. (2024) · IEEE Communications Letters · doi:10.1109/lcomm.2024.3436816 · Cited by 12
“The ML model transmission over the wireless channel has been considered in the edge networks [16] and in IoT networks in the context of semantic communication [17].”
MethodOn Forecasting-Oriented Time Series Transmission: A Federated Semantic Communication System
Zhao, B., Xing, H., Xu, L., Li, Y., Feng, L., Peng, J., & Xiao, Z. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3438285 · Cited by 12
“Xie et al. [28] emphasized the constrained resources on numerous IoT devices and proposed a lite distributed SC system for text transmission, called L-DeepSC.”
BackgroundQoE-Driven Multi-Task Offloading for Semantic-Aware Edge Computing Systems
Chen, X., Feng, D., Jiang, W., Luo, Q., Chen, G., & Sun, Y. (2026) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2026.3662899 · Cited by 12
“…information theory [9], has demonstrated great potential for enhancing the efficiency and reliability of data transmission across various task scenarios, including text/audio [10], [11], [12], [13], image [14], [15], [16], video [17], [18], [19], XR [4], [20], [21], and multi-modal [22], [23], [24].”
InfluentialFeature-Driven Semantic Communication for Efficient Image Transmission
Zhang, J., Zhang, Y., Ji, B., Chen, A., Liu, A., & Xu, H. (2025) · Entropy · doi:10.3390/e27040369 · Cited by 12
Distributed Hierarchical Deep Reinforcement Learning for Semantic-Aware Resource Allocation
Yu, K., He, Q., Yu, C., Yang, X., & Wu, G. (2025) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2025.3571485 · Cited by 12
“Based on the joint source-channel coding, semantic communications for text [12], [22], [23], speech [24], image [25], and video [26] modalities have been proposed, which show better performance than traditional communications.”
Wali, S., Khan, M. I., & Imran, M. (2025) · Scientific Reports · doi:10.1038/s41598-025-26500-4 · Cited by 12
“A lightweight semantic-communication framework using an attention-based U-Net (LSSC) was proposed for image transmission on IoT devices, balancing low complexity with efficient semantic feature extraction via CBAM modules 23 .”
Semantic Sensing Performance Analysis: Assessing Keyword Coverage in Text Data
Yang, Y., Zhang, B., Guo, D., Xu, R., Wang, W. W., Xiong, Z., & Niyato, D. T. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3282742 · Cited by 12
“…analysis of semantic communication mainly concentrate on the interference modeling [2] among different signals, i.e., how to accurately model the fading channels of the semantic channels, such as Fisher-Snedecor fading channel [3], Rayleigh fading channel [4], and Rician fading channel [5].”
BackgroundAsymmetric Semantic Communication System Based on Diffusion Model in IoT
Ren, T., & Wu, H. (2023) · IEEE International Conference on Communication Technology (ICCT) · doi:10.1109/icct59356.2023.10419809 · Cited by 12
“Considering the limitations of computational resources in IoT, [8] used methods like pruning to compress models.”
MethodDigital-Analog Transmission Framework for Task-Oriented Semantic Communications
Fu, Y., Cheng, W., Zhang, W., & Wang, J. (2024) · IEEE Network · doi:10.1109/mnet.2024.3435848 · Cited by 12
“In addition, the analog approach needs to map the semantic feature vector with full-resolution constellation into a finite space, which makes it possible to implement in the existing radio frequency system [10] but leads to the saturation effect .”
BackgroundMethodLearning-Based Task-Centric Multi-User Semantic Communication Solution for Vehicle Networks
Yuan, Y., Zhang, J., Xu, X., Wang, B., Han, S., Sun, M., & Zhang, P. (2025) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2025.3541019 · Cited by 12
“Utilizing vehicle intelligence, SemCom extracts and transmits only essential semantic data, proving valuable in contexts like UAV optimization and IoT applications with limited communication resources [8], [9].”
Knowledge-Aware Semantic Communication System Design
Kadam, S., & Kim, D. I. (2023) · International Conference on Communications · doi:10.1109/icc45041.2023.10278770 · Cited by 11
“Deep learning based SemCom technologies are proposed in [10], [11].”
BackgroundMethodClassification-Driven Discrete Neural Representation Learning for Semantic Communications
Hua, W., Xiong, L., Liu, S., Chen, L., Hong, X., Mota, J. F. C., & Cheng, X. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3354312 · Cited by 11
“Scalar quantization is typically ineffective in terms of compression performance [11].”
BackgroundEnergy-efficient data collection in UAV-assisted semantic awareness IoT network
Xie, P., Sun, H., Li, F., Gao, X., Xing, L., & Ma, H. (2024) · Internet of Things · doi:10.1016/j.iot.2024.101262 · Cited by 11
Personalized Federated Learning for GAI-Assisted Semantic Communications
Peng, Y., Jiang, F., Dong, L., Wang, K., & Yang, K. (2025) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2025.3586904 · Cited by 10
Zeng, W., Xu, X., Zhang, Q., Shi, J., Guan, Z., Li, S., & Qin, Z. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3664479 · Cited by 10
Self-citationA Mathematical Structure Underlying Sentences and Its Connection with Short–Term Memory
Matricciani, E. (2024) · AppliedMath · doi:10.3390/appliedmath4010007 · Cited by 10
SNN-SC: A Spiking Semantic Communication Framework for Collaborative Intelligence
Wang, M., Li, J., Ma, M., & Fan, X. (2024) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2024.3506119 · Cited by 10
“Withthe emergenceofDeepLearning(DL)[8],severalDL-enabledSC modelshaveshowngreatpotentialfortransmittingimages[9], [10],[11],[12],texts[13],[14],[15],anddeepfeatures[16], [17],[18],[19].”
SCDM: Score-Based Channel Denoising Model for Digital Semantic Communications
Mo, H., Sun, Y., Yao, S., Chen, H., Chen, Z., Xu, X., Ma, N., Tao, M., & Cui, S. R. (2025) · International Conference on Communications · doi:10.1109/icc52391.2025.11161428 · Cited by 10
“The first simply converts each element in the continuous-valued feature vectors into bits with full-precision and transmits them using digital modulation [5], [6].”
Sun, X., Chen, J., & Guo, C. (2022) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon49645.2022.9969083 · Cited by 10
“Semantic communication, as a revolution of traditional communication, focuses on the difference between the content of the transmitted information and the content recovered at the receiving end, rather than the problem of accurately recovering information symbols [3][4].”
BackgroundWang, Y., & Guo, S. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2301.03133 · Cited by 10
“The parameter compression can not only reduce the communication overhead of the parameter sharing but also can improve the inference speed [11].”
BackgroundMethodSemantic communication-based convolutional neural network for enhanced image classification
Güler, N., & Hazem, Z. B. (2024) · Franklin Open · doi:10.1016/j.fraope.2024.100192 · Cited by 9
Content-aware robust semantic transmission of images over wireless channels with GANs
Chen, X., Feng, D., He, Q., Sun, Y., Chen, G., & Xia, X. (2024) · Digital Communications and Networks · doi:10.1016/j.dcan.2024.12.001 · Cited by 9
Large Language Model-Based Semantic Communication System for Image Transmission
Ribouh, S., & Saleem, O. (2026) · IEEE Vehicular Technology Conference · doi:10.48550/arxiv.2501.12988 · Cited by 9
Semantic Feature Division Multiple Access for Digital Semantic Broadcast Channels
Ma, S., Sun, Z., Shen, B., Wu, Y., Li, H., Shi, G., Li, S., & Al‐Dhahir, N. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3538764 · Cited by 9
“For data reconstruction tasks, various deep joint source-channel coding (JSCC) semantic communication schemes were designed for different data modalities, such as text [12], [21], [22], speech [13], [23], image [24]–[26] and video [27], [28].”
Safarnejad, S., Soheilian, M. H., & Safaei, B. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3559435 · Cited by 9
“As a result, utilizing complex neural networks for conducting the computations is in conflict with their nature [11].”
Balancing communication overhead and accuracy in compression integration: a survey
Yang, A., Liu, J., Yang, B., Mo, Z., & Li, K. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07451-z · Cited by 9
Semantic Importance-Aware Image Transmission in V2X Networks
Cai, A., Wang, L., Lin, Y., Liu, C., & Qian, P. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3582442 · Cited by 9
“Fortunately, deep learning (DL) has proven to be an effective solution for addressing these challenges, enabling the automatic extraction and compression of semantic features while minimizing redundancy [8], [9], [10].”
Zia, M. F., Ouameur, M. A., Bagaa, M., Massicotte, D., & Ksentini, A. (2025) · Physical Communication · doi:10.1016/j.phycom.2025.102857 · Cited by 9
“This adaptability is vital in systems where semantic communication must respond quickly to new interaction modalities or user behaviors [152,153].”
A Semantic Approach to Successive Interference Cancellation for Multiple Access Networks
Li, M., Shen, K., & Cui, S. R. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3532484 · Cited by 9
“Moreover, a universal Transformer is used to extract semantic features in [36], while a lite distributed implementation of the DeepSC is proposed in [37].”
Partial Sampling-Based Semantic Communications
Yu, K., He, Q., Wu, G., & Qin, Z. (2025) · IEEE Transactions on Communications · doi:10.1109/tcomm.2025.3579701 · Cited by 9
“Data recovery-oriented research aims to transmit text [10], [11], [12], speech [13], and image [14], [27], which demonstrate better performance than traditional meth-ods.”
Self-citationWanasekara, S. H., Nguyen, V., Wong, K., Nguyen, M.-D., Chatzinotas, S., & Dobre, O. A. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3600434 · Cited by 9
“Moreover, achieving near-perfect reconstruction often necessitates massive labeled training datasets, which are difficult to acquire and maintain in dynamic and heterogeneous IoT environments [9].”
Generative AI Driven Task-Oriented Adaptive Semantic Communications
Fu, Y., Cheng, W., Wang, J., Yin, L., & Zhang, W. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3644355 · Cited by 9
“In practice, a range of NN parameter quantization strategies can be integrated into the JSCC schemes [25], [26], thereby enabling the direct mapping of floating-point semantic feature vectors onto a finite set of complex-valued IQ modulation symbols, thus enabling the integration of the JSCC codec…”
Adaptive Semantic Video Conferencing for OFDM Systems
Jiang, P., Wen, C.-K., & Jin, S. (2022) · Machine learning for signal processing ... · doi:10.1109/mlsp55214.2022.9943493 · Cited by 9
“With the development of deep learning (DL), many state-of-art designs of semantic communications appears for different contents, such as text[4, 5], image[6, 7], and video[8, 9].”
BackgroundInnovative semantic communication systemPreprint
Chen, D., Liang, H., Xu, X., Han, S., Wang, B., & Zhang, P. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2202.09595 · Cited by 9
“Different from the existing semantic communication system architecture proposed in [15], [16], and [17], it is based on the traditional Shannon communication system and does not affect each module of Shannon physical layer.”
BackgroundMethodInfluentialLi, Y., Wang, X., Shi, Z., & Fu, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.14615 · Cited by 9
“Similarly, [21] utilizes channel state information (CSI) to assist in training, effectively mitigating the adverse impact of fading channels on transmission performance.”
Generative Semantic Communications for Robust Speech-to-Text Translation
Weng, Z., Wang, Z., Qin, Z., & Tao, X. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3590671 · Cited by 8
“Therefore, inspired by the three communications levels of the receiver [6], we propose an efficient semantic communication paradigm for S2TT by developing the joint deep semantic-channel coding mechanism to enable E2E semantic exchange.”
Self-citationTan, Z., Liu, C., Xie, K., Ouyang, Y., Wen, J., Zhang, G., Chen, D., Xie, G., & Li, K. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3600880 · Cited by 8
“Although DeepJSCC can mitigate the “cliff effect” and reduce the bandwidth usage under low SNRs and bandwidth-constrained conditions, most existing methods [7], [21], [24], [25] are unable to adapt to the variable SNR and bandwidth conditions caused by unstable communication environments.”
Semantic-Aware Resource Allocation in Constrained Networks with Limited User Participation
Marnissi, O., Hammouti, H. E., & Bergou, E. H. (2024) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc57260.2024.10571093 · Cited by 8
“Semantic communication has been considered for various applications including text [2]–[4], speech [5], and image transmissions [6].”
BackgroundResource Allocation for Semantic Relay Aided Wireless Networks with Probability Graph
Zhao, J., Chen, M., Yang, Z., You, C., & Chen, M. (2024) · International Conference on Communications · doi:10.1109/icc51166.2024.10622653 · Cited by 8
Heterogeneous Gateway Planning for Semantic Communication in Industrial Networks
Sun, Y., Xing, F., Guo, Z., Chen, H., & He, S. (2025) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2025.3544282 · Cited by 8
“ADNET was used in [17] and the authors designed a sparsification model based on attention-guided denoising convolutional neural network.”
Chen, X., Xu, J. Y., Ni, W., Hu, S., Qin, Z., & Zhang, S. (2025) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2025.3548677 · Cited by 8
“With the ongoing evolution of semantic theory, a variety of semantic communication systems have been developed to manage different types of data sources, e.g., text, image, and video [1], [2], [3].”
Self-citationDiff-GO+: An Efficient Diffusion Goal-Oriented Communication System With Local Feedback
Wijesinghe, A., Zhang, S., Wanninayaka, S., Wang, W., & Ding, Z. J. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3554442 · Cited by 8
“Additional AI-enabled communication designs include multi-modal semantic communications [15], [22], [23], joint semantic source-channel coding [16], [24], [25] and distributed semantic system [26].”
Enhancing Communication Reliability from the Semantic Level under Low SNR
Liu, Y., Zhang, Y., Luo, P., Jiang, S., Cao, K., Zhao, H., & Wei, J. (2022) · Electronics · doi:10.3390/electronics11091358 · Cited by 8
“To lower the cost of IoT devices, a lite distributed semantic communication system for IoT networks was developed to achieve better performance on text transmission in [19].”
BackgroundMultitask Semantic Communication: A Mutual Information-Aided Semi-Supervised Approach
Wang, Y., Yi, W., Han, S., Xu, X., Zhang, P., & Nallanathan, A. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3607792 · Cited by 7
“…to remove the quantization outliers whose value exceeds [0 , 2 q − 1], which is defined as In this way, each element of the semantic representation vector is quantized into q -bit integer z , thereby narrowing the size of constellation into ( 2 q − 1 ) with identifiable amplitudes and phases [33].”
Semantic-Oriented Modulation for Wireless Communication
Wang, Y., Zhang, X., Sun, Y., Cui, Q., & Tao, X. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3565017 · Cited by 7
“1) Comparison With Bit-Oriented Modulation: Bit-oriented modulation is widely adopted in the current digital communication systems [6], [7], [23].”
Modeling and Performance Analysis for Semantic Communications Based on Empirical Results
Ma, S., Shen, B., Chuanhui, Z., Wu, Y., Li, H., Li, S., Shi, G., & Al‐Dhahir, N. (2025) · IEEE Transactions on Communications · doi:10.1109/tcomm.2025.3566982 · Cited by 7
“Specifically, for data reconstruction tasks, various deep joint source-channel coding (JSCC) semantic communication schemes were designed for different data modalities, such as text [12], [13], [14], [15], [16], speech [17], [18], image [19], [20], [21], [22], [23] and video [24], [25], [26].”
Resource-Efficient Multiview Perception: Integrating Semantic Masking with Masked Autoencoders
Dakic, K., Thilakarathna, K., Calheiros, R. N., & Lim, T. J. (2025) · IEEE International Conference on Pervasive Computing and Communications · doi:10.1109/percom64205.2025.00034 · Cited by 7
“The modified levels are normalized to create a probability distribution for patch selection.”
Topic Enhanced Semantic Communication System for Reliable Semantic Recovery
Zhang, Y., Zhang, Y., Zhao, H., Luo, P. H., Tan, K., Deng, J., & Wei, J. (2025) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2025.3579558 · Cited by 7
“To make DL models affordable for Internet of Things, Xie and Qin [8] further developed L-DeepSC, which focuses on optimizing transmission with minimal computational overhead.”
InfluentialSun, Y., Yang, Q., Xing, F., Liu, Y., & He, S. (2025) · IEEE Network · doi:10.1109/mnet.2025.3600261 · Cited by 7
“A lightweight SemCom system L-DeepSC [5] was designed for IoT networks, which enabled IoT devices with limited computing capabilities to perform intelligent tasks more effectively.”
Chen, Y., Hong, X., Cui, B., & Peng, R. (2023) · Journal of Marine Science and Engineering · doi:10.3390/jmse11122280 · Cited by 7
A semantic communication model for the task of high quality image transmission to edge-end devices
Wen, Z., Fang, J., & Wang, X. (2024) · Internet of Things · doi:10.1016/j.iot.2024.101384 · Cited by 7
IoT Enabled Smart Logistics Vehicle using Semantic Communication
Sujatha, R., Mahaboob Basha, S., Sarala, B., Hephzipah, J. J., Praveena, N. G., & Raja, D. S. S. (2022) · International Journal of Intelligent Systems and Applications in Engineering · Cited by 7
Computationally Efficient Approach for 6G‐AI‐IoT Network Slicing and Error‐Free Transmission
Qi, Y. (2025) · International Journal of Network Management · doi:10.1002/nem.70007 · Cited by 6
“…(EH) technology, using underground renewable energy (including wind energy [9], radio frequency signal energy [21], and mechanical energy [22]) as a source of green power supply, which is in response to the national initiative of “carbon neutrality, carbon peaking” effective measures to…”
Multi-Modal Semantic Communication With Point Cloud Diffusion
Feng, W., & Shi, Z. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888756 · Cited by 6
Semantic communication based on bi-level routing attention in IoT environment
Xiao, Y., Xiumei, F., Yau, K. A., Xie, Z., & Rui, M. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07062-8 · Cited by 6
“L-DeepSC L-DeepSC, a lightweight version designed for IoT networks, further extended these ideas by allowing IoT devices to transmit semantic-level data efficiently through cloud and edge platforms [18].”
Semantic aware intelligent optimization for IRS/UAV-enabled MEC in wideband cognitive radio networks
Zheng, W., Ren, P., & Li, Q. (2025) · EURASIP Journal on Wireless Communications and Networking · doi:10.1186/s13638-025-02478-5 · Cited by 6
Computation-Resource-Efficient Task-Oriented Communications
Fu, J., Xiao, M., Ren, C., & Skoglund, M. (2025) · IEEE Transactions on Communications · doi:10.1109/tcomm.2025.3587076 · Cited by 6
“A separate line of work improves computational resource allocation by employing smaller NN models, such as in [6], which reduces model size to lower transmission overhead.”
A Multi-Hop Semantic Communication System Enhanced by Semantic Importance
Huang, X., Wang, C., Tian, X., Li, Z., Zhao, C., & Xiao, M. (2025) · IEEE Access · doi:10.1109/access.2025.3593341 · Cited by 6
“[11], [12], [13], [14], [15], natural language processing [16], [17], [18], [19], video analysis [20], [21], and visual question answering [22], [23] have also been demonstrated.”
Digital twin-driven semantic offloading for LEO-MEC-enabled remote IoT networks
Wondmagegn, A. B., Won, D., Lee, D., Kim, J., Kim, J., & Cho, S. (2025) · Internet of Things · doi:10.1016/j.iot.2025.101831 · Cited by 6
Towards high-reliability communication in smart grid 2.0: Semantic communications
Gao, P., Zhao, G., Li, Y., & Liu, R. (2025) · Electric Power Systems Research · doi:10.1016/j.epsr.2025.112639 · Cited by 6
A GenAI-Driven Framework for Context-Aware Semantic Communication in Digital Twin Networks
Luo, P. H., Zhou, L., Zhao, H., Li, N., Cao, K., Liu, Y., Zhang, Y., & Wei, J. (2026) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2026.3657769 · Cited by 6
“Variants such as L-DeepSC [20] and universal-transformer-based designs [18] further reduce complexity or adapt computation depth to enhance robustness across different channel models.”
SNR-aware semantic image transmission with deep learning-based channel estimation in fading channels
Salim, M. M., Abdalzaher, M. S., Muqaibel, A. H., Elsayed, H. A. E. A., Rabei, K. M., & Lee, I. (2026) · Physical Communication · doi:10.1016/j.phycom.2026.103116 · Cited by 6
IoT‐Assisted Metaverse Services
Han, Y., Leung, C., & Kim, D. I. (2023) · Wiley eBooks · doi:10.1002/9781394160013.ch10 · Cited by 6
Hashing-Based Multi-Modal Semantic Communication
Zhu, Y., Gu, H., Nie, J., Tang, J., Jin, J., & Zhang, Y. (2024) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc57260.2024.10570632 · Cited by 6
Metadata
- Authors
- Xie, H., & Qin, Z.
- Affiliations
- Queen Mary University of London (GB)
- Venue
- IEEE Journal on Selected Areas in Communications
- Published
- 2021-01
- Volume
- 39
- Issue
- 1
- Pages
- 142-153
- ISSN
- 0733-8716 (ISSN-L)
- 1558-0008
- OpenAlex
- W3113050802
- Cited by
- 497
- References
- 44
- Citations by year
- 2026: 73 · 2025: 129 · 2024: 114 · 2023: 101 · 2022: 53 · 2021: 27
- FWCI
- 21.27
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Journal on Selected Areas in Communications (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Queen Mary Research Online (Queen Mary University of London) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Wireless Communication Technologies
- Physical Sciences › Engineering › Electrical and Electronic Engineering › IoT Networks and Protocols
- Keywords
- semantic communication, Internet of Things, deep learning, model compression, weight quantization, model pruning, channel state information, fading channels, textual transmission, edge computing, cloud computing, spectral efficiency
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.
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.