An Adaptable and Unsupervised TinyML Anomaly Detection System for Extreme Industrial Environments

Enabling Seamless Connectivity: Networking Innovations in Wireless Sensor Networks for Industrial Application

The wide-ranging applications of the Internet of Things (IoT) show that it has the potential to revolutionise industry, improve daily life, and overcome global challenges. This study aims to evaluate the performance scalability of mature industrial wireless sensor networks (IWSNs). A new classification approach for IoT in the industrial sector is proposed based on multiple factors and we introduce the integration of 6LoWPAN (IPv6 over low-power wireless personal area networks), message queuing telemetry transport for sensor networks (MQTT-SN), and ContikiMAC protocols for sensor nodes in an industrial IoT system to improve energy-efficient connectivity. The Contiki COOJA WSN simulator was applied to model and simulate the performance of the protocols in two static and moving scenarios and evaluate the proposed novelty detection system (NDS) for network intrusions in order to identify certain events in real time for realistic dataset analysis. The simulation results show that our method is an essential measure in determining the number of transmissions required to achieve a certain reliability target in an IWSNs. Despite the growing demand for low-power operation, deterministic communication, and end-to-end reliability, our methodology of an innovative sensor design using selective surface activation induced by laser (SSAIL) technology was developed and deployed in the FTMC premises to demonstrate its long-term functionality and reliability. The proposed framework was experimentally validated and tested through simulations to demonstrate the applicability and suitability of the proposed approach. The energy efficiency in the optimised WSN was increased by 50%, battery life was extended by 350%, duplicated packets were reduced by 80%, data collisions were reduced by 80%, and it was shown that the proposed methodology and tools could be used effectively in the development of telemetry node networks in new industrial projects in order to detect events and breaches in IoT networks accurately. The energy consumption of the developed sensor nodes was measured. Overall, this study performed a comprehensive assessment of the challenges of industrial processes, such as the reliability and stability of telemetry channels, the energy efficiency of autonomous nodes, and the minimisation of duplicate information transmission in IWSNs.

Study of the Impact of Data Compression on the Energy Consumption Required for Data Transmission in a Microcontroller-Based System

As the number of Internet of Things (IoT) devices continues to rise dramatically each day, the data generated and transmitted by them follow similar trends. Given that a significant portion of these embedded devices operate on battery power, energy conservation becomes a crucial factor in their design. This paper aims to investigate the impact of data compression on the energy consumption required for data transmission. To achieve this goal, we conduct a comprehensive study using various transmission modules in a severely resource-limited microcontroller-based system designed for battery power. Our study evaluates the performance of several compression algorithms, conducting a detailed analysis of computational and memory complexity, along with performance metrics. The primary finding of our study is that by carefully selecting an algorithm for compressing different types of data before transmission, a significant amount of energy can be saved. Moreover, our investigation demonstrates that for a battery-powered embedded device transmitting sensor data based on the STM32F411CE microcontroller, the recommended transmission module is the nRF24L01+ board, as it requires the least amount of energy to transmit one byte of data. This module is most effective when combined with the LZ78 algorithm for optimal energy and time efficiency. In the case of image data, our findings indicate that the use of the JPEG algorithm for compression yields the best results. Overall, our research underscores the importance of selecting appropriate compression algorithms tailored to specific data types, contributing to enhanced energy efficiency in IoT devices.

Anomaly Detection in Multi-Wavelength Photoplethysmography Using Lightweight Machine Learning Algorithms

Over the past few years, there has been increased interest in photoplethysmography (PPG) technology, which has revealed that, in addition to heart rate and oxygen saturation, the pulse shape of the PPG signal contains much more valuable information. Lately, the wearable market has shifted towards a multi-wavelength and multichannel approach to increase signal robustness and facilitate the extraction of other intrinsic information from the signal. This transition presents several challenges related to complexity, accuracy, and reliability of algorithms. To address these challenges, anomaly detection stages can be employed to increase the accuracy and reliability of estimated parameters. Powerful algorithms, such as lightweight machine learning (ML) algorithms, can be used for anomaly detection in multi-wavelength PPG (MW-PPG). The main contributions of this paper are (a) proposing a set of features with high information gain for anomaly detection in MW-PPG signals in the classification context, (b) assessing the impact of window size and evaluating various lightweight ML models to achieve highly accurate anomaly detection, and (c) examining the effectiveness of MW-PPG signals in detecting artifacts.

Integrated Edge Deployable Fault Diagnostic Algorithm for the Internet of Things (IoT): A Methane Sensing Application

The Internet of Things (IoT) is seen as the most viable solution for real-time monitoring applications. But the faults occurring at the perception layer are prone to misleading the data driven system and consume higher bandwidth and power. Thus, the goal of this effort is to provide an edge deployable sensor-fault detection and identification algorithm to reduce the detection, identification, and repair time, save network bandwidth and decrease the computational stress over the Cloud. Towards this, an integrated algorithm is formulated to detect fault at source and to identify the root cause element(s), based on Random Forest (RF) and Fault Tree Analysis (FTA). The RF classifier is employed to detect the fault, while the FTA is utilized to identify the source. A Methane (CH4) sensing application is used as a case-study to test the proposed system in practice. We used data from a healthy CH4 sensing node, which was injected with different forms of faults, such as sensor module faults, processor module faults and communication module faults, to assess the proposed model's performance. The proposed integrated algorithm provides better algorithm-complexity, execution time and accuracy when compared to FTA or standalone classifiers such as RF, Support Vector Machine (SVM) or K-nearest Neighbor (KNN). Metrics such as Accuracy, True Positive Rate (TPR), Matthews Correlation Coefficient (MCC), False Negative Rate (FNR), Precision and F1-score are used to rank the proposed methodology. From the field experiment, RF produced 97.27% accuracy and outperformed both SVM and KNN. Also, the suggested integrated methodology's experimental findings demonstrated a 27.73% reduced execution time with correct fault-source and less computational resource, compared to traditional FTA-detection methodology.

DDD TinyML: A TinyML-Based Driver Drowsiness Detection Model Using Deep Learning

Driver drowsiness is one of the main causes of traffic accidents today. In recent years, driver drowsiness detection has suffered from issues integrating deep learning (DL) with Internet-of-things (IoT) devices due to the limited resources of IoT devices, which pose a challenge to fulfilling DL models that demand large storage and computation. Thus, there are challenges to meeting the requirements of real-time driver drowsiness detection applications that need short latency and lightweight computation. To this end, we applied Tiny Machine Learning (TinyML) to a driver drowsiness detection case study. In this paper, we first present an overview of TinyML. After conducting some preliminary experiments, we proposed five lightweight DL models that can be deployed on a microcontroller. We applied three DL models: SqueezeNet, AlexNet, and CNN. In addition, we adopted two pretrained models (MobileNet-V2 and MobileNet-V3) to find the best model in terms of size and accuracy results. After that, we applied the optimization methods to DL models using quantization. Three quantization methods were applied: quantization-aware training (QAT), full-integer quantization (FIQ), and dynamic range quantization (DRQ). The obtained results in terms of the model size show that the CNN model achieved the smallest size of 0.05 MB using the DRQ method, followed by SqueezeNet, AlexNet MobileNet-V3, and MobileNet-V2, with 0.141 MB, 0.58 MB, 1.16 MB, and 1.55 MB, respectively. The result after applying the optimization method was 0.9964 accuracy using DRQ in the MobileNet-V2 model, which outperformed the other models, followed by the SqueezeNet and AlexNet models, with 0.9951 and 0.9924 accuracies, respectively, using DRQ.