Search Results (64)

TinyML/DL is a new subfield of ML that allows for the deployment of ML algorithms on low-power devices to process their own data. The lack of resources restricts the aforementioned devices to running only inference tasks (static TinyML), while training is handled by a more computationally efficient system, such as the cloud. In recent literature, the focus has been on conducting real-time on-device training tasks (Reformable TinyML) while being wirelessly connected. With data processing being shift to edge devices, the development of decentralized federated learning (DFL) schemes becomes justified. Within these setups, nodes work together to train a neural network model, eliminating the necessity of a central coordinator. Ensuring secure communication among nodes is of utmost importance for protecting data privacy during edge device training. Swarm Learning (SL) emerges as a DFL paradigm that promotes collaborative learning through peer-to-peer interaction, utilizing edge computing and blockchain technology. While SL provides a robust defense against adversarial attacks, it comes at a high computational expense. In this survey, we emphasize the current literature regarding both DFL and TinyML/DL fields. We explore the obstacles encountered by resource-starved devices in this collaboration and provide a brief overview of the potential of transitioning to Swarm Learning. Full article

Replacing mechanical utility meters with digital ones is crucial due to the numerous benefits they offer, including increased time resolution in measuring consumption, remote monitoring capabilities for operational efficiency, real-time data for informed decision-making, support for time-of-use billing, and integration with smart grids, leading to enhanced customer service, reduced energy waste, and progress towards environmental sustainability goals. However, the cost associated with replacing mechanical meters with their digital counterparts is a key factor contributing to the relatively slow roll-out of such devices. In this paper, we present a low-cost and power-efficient solution for retrofitting the existing metering infrastructure, based on state-of-the-art communication and artificial intelligence technologies. The edge device we developed contains a camera for capturing images of a dial meter, a 32-bit microcontroller capable of running the digit recognition algorithm, and an NB-IoT module with (E)GPRS fallback, which enables nearly ubiquitous connectivity even in difficult radio conditions. Our digit recognition methodology, based on the on-device training and inference, augmented with federated learning, achieves a high level of accuracy (97.01%) while minimizing the energy consumption and associated communication overhead (87 $\mathsf{\mu }$Wh per day on average). Full article

Federated learning (FL) has emerged as a crucial technology in today’s data-centric environment, enabling decentralized machine learning while safeguarding user privacy. This study introduces “Federated Learning ML Operations (FedOps) Mobile”, a novel FL framework optimized for the dynamic and heterogeneous ecosystem of mobile devices. FedOps Mobile addresses the inherent challenges of FL—such as system scalability, device heterogeneity, and operational efficiency—through advanced on-device training using TensorFlow Lite and CoreML. The framework’s innovative approach includes sophisticated client selection mechanisms that assess device readiness and capabilities, ensuring equitable and efficient participation across the network. Additionally, FedOps Mobile leverages remote device control for seamless task management and continuous learning, all without compromising the user experience. The main contribution of this study is the demonstration that federated learning across heterogeneous devices, especially those using different operating systems, can be both practical and efficient using the FedOps Mobile framework. This was validated through experiments that evaluated three key areas: operational efficiency, model personalization, and resource optimization in multi-device settings. The results showed that the proposed method excels in client selection, energy consumption, and model optimization, establishing a new benchmark for federated learning in diverse and complex environments. Full article

In this paper, we introduce a security approach for on-device learning Edge AIs designed to detect abnormal conditions in factory machines. Since Edge AIs are easily accessible by an attacker physically, there are security risks due to physical attacks. In particular, there is a concern that the attacker may tamper with the training data of the on-device learning Edge AIs to degrade the task accuracy. Few risk assessments have been reported. It is important to understand these security risks before considering countermeasures. In this paper, we demonstrate a data poisoning attack against an on-device learning Edge AI. Our attack target is an on-device learning anomaly detection system. The system adopts MEMS accelerometers to measure the vibration of factory machines and detect anomalies. The anomaly detector also adopts a concept drift detection algorithm and multiple models to accommodate multiple normal patterns. For the attack, we used a method in which measurements are tampered with by exposing the MEMS accelerometer to acoustic waves of a specific frequency. The acceleration data falsified by this method were trained on an anomaly detector, and the result was that the abnormal state could not be detected. Full article

Data-driven models used for predictive classification and regression tasks are commonly computed using floating-point arithmetic and powerful computers. We address constraints in distributed sensor networks like the IoT, edge, and material-integrated computing, providing only low-resource embedded computers with sensor data that are acquired and processed locally. Sensor networks are characterized by strong heterogeneous systems. This work introduces and evaluates a virtual machine architecture that provides ML as a service layer (MLaaS) on the node level and addresses very low-resource distributed embedded computers (with less than 20 kB of RAM). The VM provides a unified ML instruction set architecture that can be programmed to implement decision trees, ANN, and CNN model architectures using scaled integer arithmetic only. Models are trained primarily offline using floating-point arithmetic, finally converted by an iterative scaling and transformation process, demonstrated in this work by two tests based on simulated and synthetic data. This paper is an extended version of the FedCSIS 2023 conference paper providing new algorithms and ML applications, including ANN/CNN-based regression and classification tasks studying the effects of discretization on classification and regression accuracy. Full article

Pressure ulcers are serious healthcare concerns, especially for the elderly with reduced mobility. Severe pressure ulcers are accompanied by pain, degrading patients’ quality of life. Thus, speedy and accurate detection and classification of pressure ulcers are vital for timely treatment. The conventional visual examination method requires professional expertise for diagnosing pressure ulcer severity but it is difficult for the lay carer in domiciliary settings. In this study, we present a mobile healthcare platform incorporated with a light-weight deep learning model to exactly detect pressure ulcer regions and classify pressure ulcers into six severities such as stage 1–4, deep tissue pressure injury, and unstageable. YOLOv8 models were trained and tested using 2800 annotated pressure ulcer images. Among the five tested YOLOv8 models, the YOLOv8m model exhibited promising detection performance with overall classification accuracy of 84.6% and a mAP@50 value of 90.8%. The mobile application (app) was also developed applying the trained YOLOv8m model. The mobile app returned the diagnostic result within a short time (≒3 s). Accordingly, the proposed on-device AI app can contribute to early diagnosis and systematic management of pressure ulcers. Full article

Federated Learning (FL) is a decentralized machine learning method in which individual devices compute local models based on their data. In FL, devices periodically share newly trained updates with the central server, rather than submitting their raw data. The key characteristics of FL, including on-device training and aggregation, make it interesting for many communication domains. Moreover, the potential of new systems facilitating FL in sixth generation (6G) enabled Passive Optical Networks (PON), presents a promising opportunity for integration within this domain. This article focuses on the interaction between FL and PON, exploring approaches for effective bandwidth management, particularly in addressing the complexity introduced by FL traffic. In the PON standard, advanced bandwidth management is proposed by allocating multiple upstream grants utilizing the Dynamic Bandwidth Allocation (DBA) algorithm to be allocated for an Optical Network Unit (ONU). However, there is a lack of research on studying the utilization of multiple grant allocation. In this paper, we address this limitation by introducing a novel DBA approach that efficiently allocates PON bandwidth for FL traffic generation and demonstrates how multiple grants can benefit from the enhanced capacity of implementing PON in carrying out FL flows. Simulations conducted in this study show that the proposed solution outperforms state-of-the-art solutions in several network performance metrics, particularly in reducing upstream delay. This improvement holds great promise for enabling real-time data-intensive services that will be key components of 6G environments. Furthermore, our discussion outlines the potential for the integration of FL and PON as an operational reality capable of supporting 6G networking. Full article

Neuromorphic computing, a brain-inspired non-Von Neumann computing system, addresses the challenges posed by the Moore’s law memory wall phenomenon. It has the capability to enhance performance while maintaining power efficiency. Neuromorphic chip architecture requirements vary depending on the application and optimising it for large-scale applications remains a challenge. Neuromorphic chips are programmed using spiking neural networks which provide them with important properties such as parallelism, asynchronism, and on-device learning. Widely used spiking neuron models include the Hodgkin–Huxley Model, Izhikevich model, integrate-and-fire model, and spike response model. Hardware implementation platforms of the chip follow three approaches: analogue, digital, or a combination of both. Each platform can be implemented using various memory topologies which interconnect with the learning mechanism. Current neuromorphic computing systems typically use the unsupervised learning spike timing-dependent plasticity algorithms. However, algorithms such as voltage-dependent synaptic plasticity have the potential to enhance performance. This review summarises the potential neuromorphic chip architecture specifications and highlights which applications they are suitable for. Full article

This study proposes an edge computing-based facial expression recognition system that is low cost, low power, and privacy preserving. It utilizes a minimally obtrusive cap-based system designed for the continuous and real-time monitoring of a user’s facial expressions. The proposed method focuses on detecting facial skin deformations accompanying changes in facial expressions. A multi-zone time-of-flight (ToF) depth sensor VL53L5CX, featuring an 8 × 8 depth image, is integrated into the front brim of the cap to measure the distance between the sensor and the user’s facial skin surface. The distance values corresponding to seven universal facial expressions (neutral, happy, disgust, anger, surprise, fear, and sad) are transmitted to a low-power STM32F476 microcontroller (MCU) as an edge device for data preprocessing and facial expression classification tasks utilizing an on-device pre-trained deep learning model. Performance evaluation of the system is conducted through experiments utilizing data collected from 20 subjects. Four deep learning algorithms, including Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM) networks, and Deep Neural Networks (DNN), are assessed. These algorithms demonstrate high accuracy, with CNN yielding the best result, achieving an accuracy of 89.20% at a frame rate of 15 frames per second (fps) and a maximum latency of 2 ms. Full article

This paper presents an on-device semi-supervised human activity detection system that can learn and predict human activity patterns in real time. The clinical objective is to monitor and detect the unhealthy sedentary lifestyle of a user. The proposed semi-supervised learning (SSL) framework uses sparsely labelled user activity events acquired from Inertial Measurement Unit sensors installed as wearable devices. The proposed cluster-based learning model in this approach is trained with data from the same target user, thus preserving data privacy while providing personalized activity detection services. Two different cluster labelling strategies, namely, population-based and distance-based strategies, are employed to achieve the desired classification performance. The proposed system is shown to be highly accurate and computationally efficient for different algorithmic parameters, which is relevant in the context of limited computing resources on typical wearable devices. Extensive experimentation and simulation study have been conducted on multi-user human activity data from the public domain in order to analyze the trade-off between classification accuracy and computation complexity of the proposed learning paradigm with different algorithmic hyper-parameters. With 4.17 h of training time for 8000 activity episodes, the proposed SSL approach consumes at most 20 KB of CPU memory space, while providing a maximum accuracy of 90% and 100% classification rates. Full article

In an era dominated by Internet of Things (IoT) devices, software-as-a-service (SaaS) platforms, and rapid advances in cloud and edge computing, the demand for efficient and lightweight models suitable for resource-constrained devices such as data processing units (DPUs) has surged. Traditional deep learning models, such as convolutional neural networks (CNNs), pose significant computational and memory challenges, limiting their use in resource-constrained environments. Echo State Networks (ESNs), based on reservoir computing principles, offer a promising alternative with reduced computational complexity and shorter training times. This study explores the applicability of ESN-based architectures in image classification and weather forecasting tasks, using benchmarks such as the MNIST, FashionMnist, and CloudCast datasets. Through comprehensive evaluations, the Multi-Reservoir ESN (MRESN) architecture emerges as a standout performer, demonstrating its potential for deployment on DPUs or home stations. In exploiting the dynamic adaptability of MRESN to changing input signals, such as weather forecasts, continuous on-device training becomes feasible, eliminating the need for static pre-trained models. Our results highlight the importance of lightweight models such as MRESN in cloud and edge computing applications where efficiency and sustainability are paramount. This study contributes to the advancement of efficient computing practices by providing novel insights into the performance and versatility of MRESN architectures. By facilitating the adoption of lightweight models in resource-constrained environments, our research provides a viable alternative for improved efficiency and scalability in modern computing paradigms. Full article

Large Language Models achieve state of art performances on a broad variety of Natural Language Processing tasks. In the pervasive IoT era, their deployment on edge devices is more compelling than ever. However, their gigantic model footprint has hindered on-device learning applications which enable AI models to continuously learn and adapt to changes over time. Back-propagation, in use by the majority of deep learning frameworks, is computationally intensive and requires storing intermediate activations into memory to cope with the model’s weights update. Recently, “Forward-only algorithms” have been proposed since they are biologically plausible alternatives. By applying more “forward” passes, this class of algorithms can achieve memory reductions with respect to more naive forward-only approaches and by removing the need to store intermediate activations. This comes at the expense of increased computational complexity. This paper considered three Large Language Model: DistilBERT, GPT-3 Small and AlexaTM. It investigated quantitatively any improvements about memory usage and computational complexity brought by known approaches named PEPITA and MEMPEPITA with respect to backpropagation. For low number of tokens in context, and depending on the model, PEPITA increases marginally or reduces substantially arithmetic operations. On the other hand, for large number of tokens in context, PEPITA reduces computational complexity by 30% to 50%. MEMPEPITA increases PEPITA’s complexity by one third. About memory, PEPITA and backpropagation, require a comparable amount of memory to store activations, while MEMPEPITA reduces it by 50% to 94% with the benefits being more evident for architectures with a long sequence of blocks. In various real case scenarios, MEMPEPITA’s memory reduction was essential for meeting the tight memory requirements of 128 MB equipped edge consumer devices, which are commonly available as smartphone and industrial application multi processors. Full article

In the context of TinyML, many research efforts have been devoted to designing forward topologies to support On-Device Learning. Reaching this target would bring numerous advantages, including reductions in latency and computational complexity, stronger privacy, data safety and robustness to adversarial attacks, higher resilience against concept drift, etc. However, On-Device Learning on resource constrained devices poses severe limitations to computational power and memory. Therefore, deploying Neural Networks on tiny devices appears to be prohibitive, since their backpropagation-based training is too memory demanding for their embedded assets. Using Extreme Learning Machines based on Convolutional Neural Networks might be feasible and very convenient, especially for Feature Extraction tasks. However, it requires searching for a randomly initialized topology that achieves results as good as those achieved by the backpropagated model. This work proposes a novel approach for automatically composing an Extreme Convolutional Feature Extractor, based on Neural Architecture Search and Bayesian Optimization. It was applied to the CIFAR-10 and MNIST datasets for evaluation. Two search spaces have been defined, as well as a search strategy that has been tested with two surrogate models, Gaussian Process and Random Forest. A performance estimation strategy was defined, keeping the feature set computed by the MLCommons-Tiny benchmark ResNet as a reference model. In as few as 1200 search iterations, the proposed strategy was able to achieve a topology whose extracted features scored a mean square error equal to 0.64 compared to the reference set. Further improvements are required, with a target of at least one order of magnitude decrease in mean square error for improved classification accuracy. The code is made available via GitHub to allow for the reproducibility of the results reported in this paper. Full article

This study explores the integration of Wide Field Optical Coherence Tomography (WF-OCT) with an AI-driven clinical decision support system, with the goal of enhancing productivity and decision making in breast cancer surgery margin assessment. A computationally efficient convolutional neural network (CNN)-based binary classifier is developed using 585 WF-OCT margin scans from 151 subjects. The CNN model swiftly identifies suspicious areas within margins with an on-device inference time of approximately 10 ms for a 420 × 2400 image. In independent testing on 155 pathology-confirmed margins, including 31 positive margins from 29 patients, the classifier achieved an AUROC of 0.976, a sensitivity of 0.93, and a specificity of 0.98. At the margin level, the deep learning model accurately identified 96.8% of pathology-positive margins. These results highlight the clinical viability of AI-enhanced margin visualization using WF-OCT in breast cancer surgery and its potential to decrease reoperation rates due to residual tumors. Full article

Human activity recognition (HAR) using wearable sensors enables continuous monitoring for healthcare applications. However, the conventional centralised training of deep learning models on sensor data poses challenges related to privacy, communication costs, and on-device efficiency. This paper proposes a federated learning framework integrating spiking neural networks (SNNs) with long short-term memory (LSTM) networks for energy-efficient and privacy-preserving HAR. The hybrid spiking-LSTM (S-LSTM) model synergistically combines the event-driven efficiency of SNNs and the sequence modelling capability of LSTMs. The model is trained using surrogate gradient learning and backpropagation through time, enabling fully supervised end-to-end learning. Extensive evaluations of two public datasets demonstrate that the proposed approach outperforms LSTM, CNN, and S-CNN models in accuracy and energy efficiency. For instance, the proposed S-LSTM achieved an accuracy of 97.36% and 89.69% for indoor and outdoor scenarios, respectively. Furthermore, the results also showed a significant improvement in energy efficiency of 32.30%, compared to simple LSTM. Additionally, we highlight the significance of personalisation in HAR, where fine-tuning with local data enhances model accuracy by up to 9% for individual users. Full article