An Evolving TinyML Compression Algorithm for IoT Environments Based on Data Eccentricity
Open accessThe DOI matches its Crossref record; 65 of the 66 references it cites were found in a registry or an index.
Abstract
Currently, the applications of the Internet of Things (IoT) generate a large amount of sensor data at a very high pace, making it a challenge to collect and store the data. This scenario brings about the need for effective data compression algorithms to make the data manageable among tiny and battery-powered devices and, more importantly, shareable across the network. Additionally, considering that, very often, wireless communications (e.g., low-power wide-area networks) are adopted to connect field devices, user payload compression can also provide benefits derived from better spectrum usage, which in turn can result in advantages for high-density application scenarios. As a result of this increase in the number of connected devices, a new concept has emerged, called TinyML. It enables the use of machine learning on tiny, computationally restrained devices. This allows intelligent devices to analyze and interpret data locally and in real time. Therefore, this work presents a new data compression solution (algorithm) for the IoT that leverages the TinyML perspective. The new approach is called the Tiny Anomaly Compressor (TAC) and is based on data eccentricity. TAC does not require previously established mathematical models or any assumptions about the underlying data distribution. In order to test the effectiveness of the proposed solution and validate it, a comparative analysis was performed on two real-world datasets with two other algorithms from the literature (namely Swing Door Trending (SDT) and the Discrete Cosine Transform (DCT)). It was found that the TAC algorithm showed promising results, achieving a maximum compression rate of 98.33%. Additionally, it also surpassed the two other models regarding the compression error and peak signal-to-noise ratio in all cases.
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
Figures





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
“However, inference of DL in edge devices is not yet prepared enough to be fully executed [3,4,6].”
From TinyML: Enabling of Inference Deep Learning Models on Ultra-Low-Power IoT Edge Devices for AI Applications (2022) · cites this paper as [3]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“In (Signoretti et al., 2021), a tiny anomaly compressor (TAC) model is proposed on top of the typicality and eccentricity data analytics (TEDA) mathematical framework (also known as the empirical data analysis -EDA).”
From A review on TinyML: State-of-the-art and prospects (2022) · cites this paper as Signoretti et al., 2021
The cited source says what the claim attributes to it.
In the citing paper
“The TAC aims to compress user data without prior knowledge about any established mathematical models.”
From A review on TinyML: State-of-the-art and prospects (2022) · cites this paper as Signoretti et al., 2021
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
Representation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001 · cited 1×
“These are a class of models that are not explicitly instructed to predict something specific; rather, the patterns in the data are identified by the algorithm itself, and it is left to the user to interpret the output and reach a conclusion [34,35].”
BackgroundInternet of Things for Smart Cities
Zanella, A., Bui, N., Castellani, A., Vangelista, L., & Zorzi, M. (2014) · IEEE Internet of Things Journal · doi:10.1109/jiot.2014.2306328 · Cited by 6,292 · cited 1×
“The Internet of Things (IoT) allows the continuous monitoring of environments and machines using small and inexpensive sensors [1,2].”
BackgroundA Survey on Mobile Edge Computing: The Communication Perspective
Mao, Y., You, C., Zhang, J., Huang, K., & Letaief, K. B. (2017) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2017.2745201 · Cited by 5,607 · cited 1×
“For all these reasons, decreasing the time-on-air of each transmission can reduce collisions, save bandwidth, and allow a higher number of coexisting nodes (for high-density applications [25]) Therefore, it is clear that the new trend is to add “intelligence” to IoT devices so that they process data and make decisions…”
BackgroundFast Normalized Cross-Correlation
Yoo, J.-C., & Han, T. H. (2009) · Circuits, Systems and Signal Processing · doi:10.1007/s00034-009-9130-7 · Cited by 1,115
Machine Learning for Internet of Things Data Analysis: A Survey
Mahdavinejad, M. S., Rezvan, M., Barekatain, M., Adibi, P., Barnaghi, P. M., & Sheth, A. (2017) · Surrey Research Insight Open Access (The University of Surrey) · Cited by 1,008
Machine learning for internet of things data analysis: a survey
Mahdavinejad, M. S., Rezvan, M., Barekatain, M., Adibi, P., Barnaghi, P., & Sheth, A. P. (2018) · Digital Communications and Networks · doi:10.1016/j.dcan.2017.10.002 · Cited by 921 · cited 1×
“However, in those proposals, the algorithms were not structured with Machine Learning (ML) techniques, which is the conjunction of methods for data analysis that automates the construction of analytical models [31].”
MethodSurvey on Multi-Access Edge Computing for Internet of Things Realization
Porambage, P., Okwuibe, J., Liyanage, M., Ylianttila, M., & Taleb, T. (2018) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2018.2849509 · Cited by 795 · cited 1×
“Often, IoT devices work with low-frequency processors and have limited local data storage capacity, severe memory restrictions [23,24], simple protocols, and inefficient medium access strategies (e.”
BackgroundLow Power Wide Area Network Analysis: Can LoRa Scale?
Georgiou, O., & Raza, U. (2017) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2016.2647247 · Cited by 729 · cited 1×
“In this manner, some challenges regarding the amount of data generated per second are encountered, especially when using low-power transmission protocols as LoRaWAN [18–20].”
Edge Computing for the Internet of Things: A Case Study
Premsankar, G., Di Francesco, M., & Taleb, T. (2018) · IEEE Internet of Things Journal · doi:10.1109/jiot.2018.2805263 · Cited by 697
Balanda, K. P., & Macgillivray, H. L. (1988) · The American Statistician · doi:10.1080/00031305.1988.10475539 · Cited by 482 · cited 1×
“It is a scaled version of the distribution’s forth moment [57].”
BackgroundJayasankar, U., Thirumal, V., & Ponnurangam, D. (2021) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2018.05.006 · Cited by 279 · cited 4×
“Alternatively, more domain-specific compression algorithms for different types of data began to emerge, such as text, image, audio, video [17], and, more recently, for IoT [40].”
BackgroundInfluentialAn energy efficient IoT data compression approach for edge machine learning
Azar, J., Makhoul, A., Barhamgi, M., & Couturier, R. (2019) · Future Generation Computer Systems · doi:10.1016/j.future.2019.02.005 · Cited by 267 · cited 7×
“In the work [9], they proposed to adapt the SZ algorithm for IoT devices by considering only the floating-point data type, which makes the code smaller and easier to compile on resource-constrained devices.”
BackgroundMethodInfluentialA note on using the F-measure for evaluating record linkage algorithms
Hand, D., & Christen, P. (2018) · Statistics and Computing · doi:10.1007/s11222-017-9746-6 · Cited by 247 · cited 2×
“Therefore, when both rates have an equal weight (β = 1), the F1 score reverts to being a simple harmonic mean between the two values used [63].”
BackgroundChebyshev Inequality with Estimated Mean and Variance
Saw, J. G., Yang, M. C. K., & Mo, T. C. (1984) · The American Statistician · doi:10.1080/00031305.1984.10483182 · Cited by 216 · cited 1×
“Assuming a sufficiently large set of samples from any data distribution, Chebyshev’s inequality ensures that no more than 1/ m 2 samples will be more than an m σ distance away from the mean [56].”
BackgroundBanbury, C., Zhou, C., Fedorov, I., Navarro, R. M., Thakker, U., Gope, D., Reddi, V. J., Mattina, M., & Whatmough, P. N. (2020) · arXiv · doi:10.48550/arxiv.2010.11267 · Cited by 183
Wang, X., Magno, M., Cavigelli, L., & Benini, L. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2976702 · Cited by 162 · cited 1×
“In this scenario, data processing is pushed to the “edge” of the network, even to IoT devices and sensors used primarily for data acquisition [27–29].”
MethodAdaptive Wiener filtering of noisy images and image sequences
Jin, F., Fieguth, P., Winger, L. L., & Jernigan, E. (2004) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2003.1247253 · Cited by 147 · cited 1×
“Its a commonly applied technique in fields such as digital image processing, where it can be used to measure the quality of images after passing through noise reduction filters [60].”
MethodAnomaly detection based on eccentricity analysis
Angelov, P. (2014) · 2014 IEEE Symposium on Evolving and Autonomous Learning Systems (EALS) · doi:10.1109/eals.2014.7009497 · Cited by 111 · cited 9×
“This is shown in Equations (9) and (10) [37].”
BackgroundMethodInfluentialSpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers
Fedorov, I., Adams, R. P., Mattina, M., & Whatmough, P. N. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.12107 · Cited by 109 · cited 1×
“Often, IoT devices work with low-frequency processors and have limited local data storage capacity, severe memory restrictions [23,24], simple protocols, and inefficient medium access strategies (e.”
BackgroundEmpirical Approach to Machine Learning
Angelov, P. P., & Gu, X. (2018) · Studies in computational intelligence · doi:10.1007/978-3-030-02384-3 · Cited by 108 · cited 3×
“These are a class of intelligent methods that can be defined as autonomous and data-driven, with the ability to evolve both their structure and internal parameters dynamically according to the new data received [36].”
BackgroundMethodThe evaluation of normalized cross correlations for defect detection
Tsai, D., Lin, C.-T., & Chen, J.-F. (2003) · Pattern Recognition Letters · doi:10.1016/s0167-8655(03)00098-9 · Cited by 105 · cited 1×
“It is another metric common in the fields of signal and image processing [61,62].”
BackgroundXu, Z. (2008) · International Journal of Intelligent Systems · doi:10.1002/int.20330 · Cited by 103 · cited 1×
“In turn, the harmonic mean is an average measure generally considered as a fusion technique of numerical data information [64].”
BackgroundSodhro, A. H., Sangaiah, A. K., Sodhro, G. H., Lohano, S., & Pirbhulal, S. (2018) · Sensors · doi:10.3390/s18030923 · Cited by 100 · cited 1×
“Likewise, several other sensors such as magnetometer, pressure, temperature, humidity, and ambient light sensors, among many others, measure the physical conditions wherever they are installed, in addition to those that have been developed for the health area [8,13].”
BackgroundCompiling KB-sized machine learning models to tiny IoT devices
Gopinath, S., Ghanathe, N., Seshadri, V., & Sharma, R. (2019) · Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation · doi:10.1145/3314221.3314597 · Cited by 92 · cited 1×
“Most of the work performed in the field of TinyML has been focused on the reduction and optimization of existing models, such as Artificial Neural Networks (ANNs), to fit into these tiny devices and commodity microcontrollers, despite their computational restrictions [7,32,33].”
MethodOutside the box: an alternative data analytics framework
Angelov, P. P. (2014) · Journal of Automation Mobile Robotics & Intelligent Systems · doi:10.14313/jamris_2-2014/16 · Cited by 92 · cited 10×
“However, the biggest motivation for the development of this new methodology is the fact that real processes are, for the most part, not purely random [48].”
BackgroundMethodInfluentialLoRaWAN Range Extender for Industrial IoT
Sisinni, E., Ferrari, P., Carvalho, D. F., Rinaldi, S., Pasetti, M., Flammini, A., & Depari, A. (2019) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2958620 · Cited by 92
Self-citationSwinging Door Trending : Adaptive Trend Recording?
Bristol, E. H. (1990) · Medical Entomology and Zoology · Cited by 82
A Novel Adaptive Battery-Aware Algorithm for Data Transmission in IoT-Based Healthcare Applications
Magsi, H., Sodhro, A. H., Al-Rakhami, M. S., Zahid, N., Pirbhulal, S., & Wang, L. (2021) · Electronics · doi:10.3390/electronics10040367 · Cited by 69 · cited 2×
“Due to the low cost of IoT hardware, the sensors are being deployed on a large scale to monitor machines and, in general, public and residential spaces [6–8].”
BackgroundThe Nature and Use of the Harmonic Mean
Ferger, W. F. (1931) · Journal of the American Statistical Association · doi:10.1080/01621459.1931.10503148 · Cited by 65 · cited 1×
“It differs from the traditional arithmetic mean by giving more weight to smaller values being averaged and is preferred when averaging rates or ratios [65].”
BackgroundA new task offloading algorithm in edge computing
Zhang, Z., Li, C., Peng, S., & Pei, X. (2021) · EURASIP Journal on Wireless Communications and Networking · doi:10.1186/s13638-021-01895-6 · Cited by 63
A Customer Feedback Platform for Vehicle Manufacturing Compliant with Industry 4.0 Vision
Silva, M., Vieira, E., Signoretti, G., Silva, I., Silva, D., & Ferrari, P. (2018) · Sensors · doi:10.3390/s18103298 · Cited by 58 · cited 1×
“From this perspective, advances in the technologies of sensors, microcontrollers, and communication protocols have made the mass production of IoT platforms with many connectivity options possible, and at affordable prices [3–5].”
BackgroundSelf-citationEvaluating fidelity of lossy compression on spatiotemporal data from an IoT enabled smart farm
Moon, A., Kim, J.-Y., Zhang, J., & Son, S. W. (2018) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2018.08.045 · Cited by 55 · cited 4×
“On another front, the authors in [41] made use of transform-based lossy compression algorithms to compress the data from IoT weather stations.”
BackgroundMethodInfluentialAutonomously evolving classifier TEDAClass
Kangin, D., Angelov, P. P., & Iglesias, J. A. (2016) · Information Sciences · doi:10.1016/j.ins.2016.05.012 · Cited by 50 · cited 3×
“The mathematical proof of these calculations was presented for Euclidean and Mahalanobis distance in [52].”
BackgroundMethodMikhaylov, K., Petrov, V., Gupta, R., Lema, M. A., Galinina, O., Andreev, S. D., Koucheryavy, Y. A., Valkama, M., Pouttu, A., & Döhler, M. (2019) · IEEE Communications Magazine · doi:10.1109/mcom.2019.1800394 · Cited by 41 · cited 1×
“For all these reasons, decreasing the time-on-air of each transmission can reduce collisions, save bandwidth, and allow a higher number of coexisting nodes (for high-density applications [25]) Therefore, it is clear that the new trend is to add “intelligence” to IoT devices so that they process data and make decisions…”
BackgroundBenchmarking Distributed Stream Processing Platforms for IoT Applications
Shukla, A., & Simmhan, Y. L. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-54334-5_7 · Cited by 40
Performance Evaluation of IoT Encryption Algorithms: Memory, Timing, and Energy
Maitra, S., Richards, D., Abdelgawad, A., & Yelamarthi, K. (2019) · 2019 IEEE Sensors Applications Symposium (SAS) · doi:10.1109/sas.2019.8706017 · Cited by 39 · cited 1×
“In this scenario, data processing is pushed to the “edge” of the network, even to IoT devices and sensors used primarily for data acquisition [27–29].”
MethodData compression and prediction using machine learning for industrial IoT
Park, J., Park, H., & Choi, Y. (2018) · International Conference on Information Networking · doi:10.1109/icoin.2018.8343232 · Cited by 38 · cited 1×
“In [47], they proposed to compress industrial data using neural network regression into a representative vector with lossy compression.”
MethodTwo-Level Data Compression using Machine Learning in Time Series Database
Yu, X., Peng, Y., Li, F., Wang, S., Shen, X., Mai, H., & Xie, Y. H. (2020) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde48307.2020.00119 · Cited by 38 · cited 3×
“[39] no yes no yes Proposed Work yes yes yes no”
BackgroundInfluentialProActive Fintech: Using Intelligent IoT to Deliver Positive InsurTech Feedback
Marafie, Z., Lin, K.-J., Zhai, Y., & Li, J. (2018) · IEEE Conference on Business Informatics · doi:10.1109/cbi.2018.10048 · Cited by 36 · cited 1×
“The Internet of Things (IoT) allows the continuous monitoring of environments and machines using small and inexpensive sensors [1,2].”
BackgroundA Generalization Performance Study Using Deep Learning Networks in Embedded Systems
Gorospe, J., Mulero, R., Arbelaitz, O., Muguerza, J., & Antón, M. Á. (2021) · Sensors · doi:10.3390/s21041031 · Cited by 32 · cited 5×
“Most of the work performed in the field of TinyML has been focused on the reduction and optimization of existing models, such as Artificial Neural Networks (ANNs), to fit into these tiny devices and commodity microcontrollers, despite their computational restrictions [7,32,33].”
BackgroundMethodInfluentialOnline fault detection based on Typicality and Eccentricity Data Analytics
Costa, B. S. J., Bezerra, C. G., Guedes, L. A., & Angelov, P. P. (2015) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2015.7280712 · Cited by 32 · cited 1×
“…are shown and what makes it so flexible that it can be used for the development of a variety of algorithms, such as: anomalies and failure detection [49], image processing, clustering [50,51], classification [52], regression [53], forecast, control, filtering, big data [54], and traffic analysis [55],…”
BackgroundHomssi, B. A., Al‐Hourani, A., Magowe, K., Delaney, J. R., Tom, N., Ying, J., Wolf, H., Maselli, S., Kandeepan, S., Wang, K., et al. (2020) · IEEE Internet of Things Magazine · doi:10.1109/iotm.001.2000179 · Cited by 30
A new evolving clustering algorithm for online data streams
Bezerra, C. G., Costa, B. S. J., Guedes, L. A., & Angelov, P. P. (2016) · IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS) · doi:10.1109/eais.2016.7502508 · Cited by 28 · cited 2×
“In the following subsections, the main mathematical concepts behind the methodology are shown and what makes it so flexible that it can be used for the development of a variety of algorithms, such as: anomalies and failure detection [49], image processing, clustering [50,51], classification [52], regression [53], fore…”
BackgroundMethodda Silva, I. M. D., Guedes, L. A., & Vasques, F. (2008) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa.2008.4638468 · Cited by 24 · cited 1×
“The algorithm creates an area of coverage in the shape of a parallelogram between the last stored value and the most recent value [42], which it uses to classify the samples as relevant or not: samples that fall inside a window are considered similar to the original sample, thus potentially redundant, and can be disca…”
BackgroundSelf-citationFlammini, A., Pasetti, M., Rinaldi, S., Bellagente, P., Ciribini, A. C., Tagliabue, L. C., Zavanella, L. E., Zanoni, S., Oggioni, G., & Pedrazzi, G. (2018) · AEIT International Annual Conference · doi:10.23919/aeit.2018.8577329 · Cited by 24 · cited 1×
“The datasets used in this work were obtained from a huge experiment currently ongoing at the eLUX laboratory at the University of Brescia, Italy. eLUX is a living laboratory for smart energy, smart grids, and smart environments for Industry 4.0 [58].”
MethodInfluentialA Testing Framework for the Monitoring and Performance Analysis of Distributed Energy Systems
Rinaldi, S., Pasetti, M., Flammini, A., Ferrari, P., Sisinni, E., & Simoncini, F. (2019) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2019.2911733 · Cited by 24 · cited 1×
“Since 2017, eLUX has run the energy supervision and management system of the entire Engineering Campus [59].”
Self-citationTowards a WirelessHART module for the ns-3 simulator
Nobre, M., da Silva, I. M. D., Guedes, L. A., & Portugal, P. (2010) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa.2010.5641011 · Cited by 23 · cited 1×
“Furthermore, it is known that most of the battery consumption of a device that communicates using a wireless medium is in the transmission of the data and not in the processing of the information, which makes it advantageous in terms of energy to compress data locally before transmission [16,21,22].”
BackgroundSelf-citationCompression Techniques Used in Iot: A Comparitive Study
Hamdan, S., Awaian, A., & Almajali, S. (2019) · International Conference on New Trends in Computing Sciences (ICTCS) · doi:10.1109/ictcs.2019.8923112 · Cited by 23 · cited 3×
“For this type of scenario, lossy compression algorithms appear to generally achieve better compression efficiency, taking advantage of the existence of redundant information, as there is no need to recover it later [40].”
BackgroundEvolving Classifier TEDAClass for Big Data
Kangin, D., Angelov, P. P., Iglesias, J. A., & Sanchis, A. (2015) · Procedia Computer Science · doi:10.1016/j.procs.2015.07.274 · Cited by 20 · cited 1×
“…what makes it so flexible that it can be used for the development of a variety of algorithms, such as: anomalies and failure detection [49], image processing, clustering [50,51], classification [52], regression [53], forecast, control, filtering, big data [54], and traffic analysis [55], among others.”
BackgroundDracena: A Real-Time IoT Service Platform Based on Flexible Composition of Data Streams
Yamaoka, H., Itakura, K., Takahashi, E., Nakagawa, G., Michaelis, J., Kanemasa, Y., Ueki, M., Matsumoto, T., Take, R., Tanie, S., et al. (2019) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii.2019.8700465 · Cited by 20 · cited 1×
“The sample rate, for example, may vary from once a day to every millisecond depending on the context [14].”
BackgroundAdaptively Compressing IoT Data on the Resource-constrained Edge
Lü, T., Xia, W., Zou, X., & Xia, Q. (2020) · Cited by 20
Typicality distribution function — A new density-based data analytics tool
Angelov, P. P. (2015) · doi:10.1109/ijcnn.2015.7280438 · Cited by 19 · cited 3×
“It is very important to note that the functions of eccentricity and typicality are bounded and, therefore, have normalized versions [53].”
BackgroundSwinging Door Trending Compression Algorithm for IoT Environments
Correa, J. D. A., Pinto, A. S. R., Montez, C., & Leão, É. (2019) · doi:10.5753/sbesc_estendido.2019.8650 · Cited by 17
Into the Unknown: Unsupervised Machine Learning Algorithms for Anomaly-Based Intrusion Detection
Zoppi, T., Ceccarelli, A., & Bondavalli, A. (2020) · IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume (DSN-S) · doi:10.1109/dsn-s50200.2020.00044 · Cited by 16 · cited 1×
“These are a class of models that are not explicitly instructed to predict something specific; rather, the patterns in the data are identified by the algorithm itself, and it is left to the user to interpret the output and reach a conclusion [34,35].”
BackgroundA customer feedback platform for vehicle manufacturing in Industry 4.0
Silva, M., Vieira, E., da Silva, I. M. D., Silva, D., Ferrari, P., Rinaldi, S., & Carvalho, D. F. (2018) · IEEE Symposium on Computers and Communications (ISCC) · doi:10.1109/iscc.2018.8538554 · Cited by 12 · cited 1×
“From this perspective, advances in the technologies of sensors, microcontrollers, and communication protocols have made the mass production of IoT platforms with many connectivity options possible, and at affordable prices [3–5].”
BackgroundSelf-citationDifferential Compression for Mobile Edge Computing in Internet of Vehicles
Hu, Z., Wang, D., Li, Z., Sun, M., & Wang, W. (2019) · IEEE International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob) · doi:10.1109/wimob.2019.8923430 · Cited by 11 · cited 2×
“Thus, to enable services such as those mentioned previously, some solutions are available in the literature, such as [11,21,30], which proposed different data compression algorithms.”
BackgroundMethodAutonomous Data Density based clustering method
Angelov, P. P., Gu, X., Gutiérrez, G., Iglesias, J. A., & Sanchis, A. (2016) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2016.7727498 · Cited by 10 · cited 1×
“In the following subsections, the main mathematical concepts behind the methodology are shown and what makes it so flexible that it can be used for the development of a variety of algorithms, such as: anomalies and failure detection [49], image processing, clustering [50,51], classification [52], regression [53], fore…”
BackgroundAssessing compression algorithms on IoT sensor nodes
Guberović, E., Krišto, F., Krivić, P., & Čavrak, I. (2019) · International Convention on Information and Communication Technology, Electronics and Microelectronics · doi:10.23919/mipro.2019.8756995 · Cited by 10 · cited 2×
“Thus, to enable services such as those mentioned previously, some solutions are available in the literature, such as [11,21,30], which proposed different data compression algorithms.”
BackgroundMethodAutomatic Detection of Computer Network Traffic Anomalies based on Eccentricity Analysis
Martins, R. S., Angelov, P. P., & Costa, B. S. J. (2018) · IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) · doi:10.1109/fuzz-ieee.2018.8491507 · Cited by 8 · cited 1×
“…what makes it so flexible that it can be used for the development of a variety of algorithms, such as: anomalies and failure detection [49], image processing, clustering [50,51], classification [52], regression [53], forecast, control, filtering, big data [54], and traffic analysis [55], among others.”
BackgroundPerformance Evaluation of an evolving data compression algorithm embedded into an OBD-II edge device
Signoretti, G., Silva, M., Araújo, J., Guedes, L. A., da Silva, I. M. D., Sisinni, E., & Ferrari, P. (2020) · IEEE International Workshop on Metrology for Industry 4.0 & IoT (MetroInd4.0&IoT) · doi:10.1109/metroind4.0iot48571.2020.9138270 · Cited by 8 · cited 1×
“In information and code theory, data compression is one of the most relevant direct applications [17,38].”
BackgroundSelf-citationLounas, R., Salhi, D. E., Mokrani, H., Djerbi, R., & Bennai, M. T. (2019) · International Conference on Theoretical and Applicative Aspects of Computer Science (ICTAACS) · doi:10.1109/ictaacs48474.2019.8988119 · Cited by 7 · cited 4×
“[11] yes * no yes no Moon et al. [41] no no no yes Gibson et al. [46] yes no no yes Lounas et al. [10] no no no yes Park et al. [47] no yes no yes Azar et al. [9] yes no yes yes Yu et al. [39] no yes no yes Proposed Work yes yes yes no * Requires a training phase.”
BackgroundInfluentialA Dependability Evaluation for OBD-II Edge Devices: An Internet of Intelligent Vehicles Perspective
Signoretti, G., Silva, M., Araújo, J., da Silva, I. M. D., Silva, D. A. S., Ferrari, P., & Sisinni, E. (2019) · Latin-American Symposium on Dependable Computing · doi:10.1109/ladc48089.2019.8995679 · Cited by 7 · cited 1×
“Note that these data streams can form a large volume of data very rapidly, and as a consequence, they generate the need for a vast amount of disk storage space [11,12].”
BackgroundSelf-citationDynamic Online Performance Optimization in Streaming Data Compression
Gibson, J. K., Lee, D., Choi, J., & Sim, A. (2018) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2018.8621867 · Cited by 6 · cited 2×
“In the work of [46], the authors proposed an online algorithm for streaming data compression, which took into account the generally concave trend of the compression ratio curve and optimized the key operation parameters (block size) through this metric.”
BackgroundThe Research and Improvement of SDT Algorithm for Historical Data in SCADA
Xu, X., & Fu, Y. (2017) · ITM Web of Conferences · doi:10.1051/itmconf/20171101009 · Cited by 2 · cited 1×
“It is important to keep in mind that, due to its popularity, several alternative implementations of the SDT exist in the literature, such as the ones proposed in [11,44,45].”
Using LoRaWAN smart city infrastructure as backup network for Industry 4.0 enabled vehicles
Ferrari, P., Sisinni, E., Carvalho, D. F., Signoretti, G., Silva, M., da Silva, I. M. D., & Silva, D. (2019) · doi:10.5753/sbesc_estendido.2019.8646 · Cited by 2
Self-citation
Research works printed but not linked: 1
- Neto, E.J.M., Augusto, L., Souza, D.C., and Guedes, L.A. (2014, January 20–24). Adaptive Swinging Door Trending: Um Algoritmo Adaptativo para Compressão de Dados em Tempo Real. Proceedings of the Anais do XX Congresso Brasileiro de Automática, Belo Horizonte, Brazil.
Cited by
A review on TinyML: State-of-the-art and prospects
Ray, P. P. (2022) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2021.11.019 · Cited by 460
“In (Signoretti et al., 2021), a tiny anomaly compressor (TAC) model is proposed on top of the typicality and eccentricity data analytics (TEDA) mathematical framework (also known as the empirical data analysis - EDA).”
TinyML for Ultra-Low Power AI and Large Scale IoT Deployments: A Systematic Review
Schizas, N., Karras, A., Karras, C., & Sioutas, S. (2022) · Future Internet · doi:10.3390/fi14120363 · Cited by 215
Alajlan, N. N., & Ibrahim, D. M. (2022) · Micromachines · doi:10.3390/mi13060851 · Cited by 224
“However, inference of DL in edge devices is not yet prepared enough to be fully executed [3,4,6].”
BackgroundIslam, M. M., Nooruddin, S., Karray, F., & Muhammad, G. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3228795 · Cited by 183
“Lossless compression models can also be researched to transmit huge volumes of data over IoT networks [189].”
BackgroundDeep Reinforcement Learning-Based Energy-Efficient Edge Computing for Internet of Vehicles
Kong, X., Duan, G., Hou, M., Shen, G., Wang, H., Yan, X., & Collotta, M. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3155162 · Cited by 166
Metadata
- Authors
- Signoretti, G., Silva, M., Andrade, P., Silva, I., Sisinni, E., & Ferrari, P.
- Affiliations
- Universidade Federal do Rio Grande do Norte (BR)
- University of Brescia (IT)
- Corresponding author
- Silva, Marianne
- Silva, Ivanovitch
- ORCID
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2021-06-17
- Volume
- 21
- Issue
- 12
- Pages
- 4153
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC8235329
- OpenAlex
- W3177140588
- Cited by
- 73
- References
- 66
- Citations by year
- 2026: 7 · 2025: 9 · 2024: 22 · 2023: 13 · 2022: 16 · 2021: 6
- FWCI
- 5.12
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Institutional Research Information System (Università degli Studi di Brescia) (submittedVersion)
- Funders
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (001)
- Conselho Nacional de Desenvolvimento Científico e Tecnológico (435683/2018-7)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Data Compression Techniques
- Physical Sciences › Engineering › Electrical and Electronic Engineering › IoT Networks and Protocols
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Keywords
- TinyML, data compression, Internet of Things, sensor data, battery-powered devices, low-power wide-area networks, anomaly detection, compression rate, PSNR
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.