arXiv subjects

Eiman Kanjo

Publications and source records attributed to Eiman Kanjo.

At least 19 recordsLinked to original sources

arXiv2026

Beyond Peak TOPS/W: A System-Level Perspective on Hybrid Digital, Analogue and Neuromorphic Computing

The digital revolution, which progressively replaced analogue methods with digital circuits, has entered a new phase as AI expands across cloud infrastructure, mobile networks, wearables and physical systems, including drones and robots. Digital computing remains the general-purpose foundation of this expansion: it supports heterogeneous, on-device and decentralised AI through programmable control, mature software and decades of accumulated engineering infrastructure. Yet as energy and data-movement constraints become more significant, that same foundation is increasingly being extended rather than replaced by selected analogue and physical principles that it can host, configure and verify. Photonic, in-memory and neuromorphic architectures offer routes to reducing data movement and accelerating matrix-intensive and event-driven processing, not as alternatives to digital infrastructure but as specialised engines operating within it. This paper argues that hybrid digital--analogue computing represents a credible pathway towards more energy-efficient AI systems: one in which physical substrates earn an expanding role only where they deliver a measurable system-level advantage, under digital orchestration that manages integration, uncertainty and fallback. It examines the architectural principles, workload suitability, energy accounting, software requirements, limitations and open challenges associated with this transition, and argues that future progress should be evaluated through deployed-system metrics rather than isolated peak tera operations per second per watt (TOPS/W) claims.

cs.AR↗

arXiv2026

Tiny Collaborative Inference for Occlusion-Robust Object Detection

Edge AI nodes for search and rescue are increasingly expected to run computer vision locally, yet ultra-low-end hardware imposes hard constraints on memory, compute, and inter-device communication. This work addresses occlusion-robust object detection on devices with less than 1 MB SRAM by combining an MCUNet backbone, a YOLOv2 detection head, and Lite quantisation. Two collaborative inference strategies are evaluated: feature-level fusion, concatenating intermediate feature maps, and decision-level fusion via Weighted Boxes Fusion (WBF). WBF outperforms feature-level fusion under all tested occlusion conditions, yielding gains of up to +0.2736 mAP in asymmetric scenarios. Extending fusion to three views improves accuracy further (up to +0.3827 mAP) at modest communication overhead (~1.3 KB per exchange). Hardware experiments progress from a host-assisted USB-relay baseline to a Wi-Fi peer-to-peer deployment on two Coral Dev Board Micro units, where WBF executes on-device with negligible communication energy relative to inference. In a 301.9 s autonomous session of 108 frames, fused output is produced on 61 frames versus 47 for a single board - a coverage gain of +29.8%. A decentralised federated learning feasibility note is included but not treated as a primary result, as performance remains limited under non-iid data. The results support decision-level fusion as a viable option for improving occlusion robustness in small-scale edge object detection, including host-free multi-board operation on ultra-low-end hardware.

cs.CV↗

arXiv2026

Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies

Deploying foundation models in embodied edge systems is fundamentally a systems problem, not just a problem of model compression. Real-time control must operate within strict size, weight, and power constraints, where memory traffic, compute latency, timing variability, and safety margins interact directly. The Deployment Gauntlet organizes these constraints into eight coupled barriers that determine whether embodied foundation models can run reliably in practice. Across representative edge workloads, autoregressive Vision-Language-Action policies are constrained primarily by memory bandwidth, whereas diffusion-based controllers are limited more by compute latency and sustained execution cost. Reliable deployment therefore depends on system-level co-design across memory, scheduling, communication, and model architecture, including decompositions that separate fast control from slower semantic reasoning.

cs.RO↗

arXiv2026

Node Learning: A Framework for Adaptive, Decentralised and Collaborative Network Edge AI

The expansion of AI toward the edge increasingly exposes the cost and fragility of cen- tralised intelligence. Data transmission, latency, energy consumption, and dependence on large data centres create bottlenecks that scale poorly across heterogeneous, mobile, and resource-constrained environments. In this paper, we introduce Node Learning, a decen- tralised learning paradigm in which intelligence resides at individual edge nodes and expands through selective peer interaction. Nodes learn continuously from local data, maintain their own model state, and exchange learned knowledge opportunistically when collaboration is beneficial. Learning propagates through overlap and diffusion rather than global synchro- nisation or central aggregation. It unifies autonomous and cooperative behaviour within a single abstraction and accommodates heterogeneity in data, hardware, objectives, and connectivity. This concept paper develops the conceptual foundations of this paradigm, contrasts it with existing decentralised approaches, and examines implications for communi- cation, hardware, trust, and governance. Node Learning does not discard existing paradigms, but places them within a broader decentralised perspective

cs.AI↗

arXiv2025

Transformer Redesign for Late Fusion of Audio-Text Features on Ultra-Low-Power Edge Hardware

Deploying emotion recognition systems in real-world environments where devices must be small, low-power, and private remains a significant challenge. This is especially relevant for applications such as tension monitoring, conflict de-escalation, and responsive wearables, where cloud-based solutions are impractical. Multimodal emotion recognition has advanced through deep learning, but most systems remain unsuitable for deployment on ultra-constrained edge devices. Prior work typically relies on powerful hardware, lacks real-time performance, or uses unimodal input. This paper addresses that gap by presenting a hardware-aware emotion recognition system that combines acoustic and linguistic features using a late-fusion architecture optimised for Edge TPU. The design integrates a quantised transformer-based acoustic model with frozen keyword embeddings from a DSResNet-SE network, enabling real-time inference within a 1.8MB memory budget and 21-23ms latency. The pipeline ensures spectrogram alignment between training and deployment using MicroFrontend and MLTK. Evaluation on re-recorded, segmented IEMOCAP samples captured through the Coral Dev Board Micro microphone shows a 6.3% macro F1 improvement over unimodal baselines. This work demonstrates that accurate, real-time multimodal emotion inference is achievable on microcontroller-class edge platforms through task-specific fusion and hardware-guided model design.

cs.SD↗

arXiv2025

TrajAware: Graph Cross-Attention and Trajectory-Aware for Generalisable VANETs under Partial Observations

Vehicular ad hoc networks (VANETs) are a crucial component of intelligent transportation systems; however, routing remains challenging due to dynamic topologies, incomplete observations, and the limited resources of edge devices. Existing reinforcement learning (RL) approaches often assume fixed graph structures and require retraining when network conditions change, making them unsuitable for deployment on constrained hardware. We present TrajAware, an RL-based framework designed for edge AI deployment in VANETs. TrajAware integrates three components: (i) action space pruning, which reduces redundant neighbour options while preserving two-hop reachability, alleviating the curse of dimensionality; (ii) graph cross-attention, which maps pruned neighbours to the global graph context, producing features that generalise across diverse network sizes; and (iii) trajectory-aware prediction, which uses historical routes and junction information to estimate real-time positions under partial observations. We evaluate TrajAware in the open-source SUMO simulator using real-world city maps with a leave-one-city-out setup. Results show that TrajAware achieves near-shortest paths and high delivery ratios while maintaining efficiency suitable for constrained edge devices, outperforming state-of-the-art baselines in both full and partial observation scenarios.

cs.LG↗

arXiv2025

A Multicore and Edge TPU-Accelerated Multimodal TinyML System for Livestock Behavior Recognition

The advancement of technology has revolutionized the agricultural industry, transitioning it from labor-intensive farming practices to automated, AI-powered management systems. In recent years, more intelligent livestock monitoring solutions have been proposed to enhance farming efficiency and productivity. This work presents a novel approach to animal activity recognition and movement tracking, leveraging tiny machine learning (TinyML) techniques, wireless communication framework, and microcontroller platforms to develop an efficient, cost-effective livestock sensing system. It collects and fuses accelerometer data and vision inputs to build a multimodal network for three tasks: image classification, object detection, and behavior recognition. The system is deployed and evaluated on commercial microcontrollers for real-time inference using embedded applications, demonstrating up to 270$\times$ model size reduction, less than 80ms response latency, and on-par performance comparable to existing methods. The incorporation of the wireless communication technique allows for seamless data transmission between devices, benefiting use cases in remote locations with poor Internet connectivity. This work delivers a robust, scalable IoT-edge livestock monitoring solution adaptable to diverse farming needs, offering flexibility for future extensions.

cs.CV↗

arXiv2025

A Hybrid Edge Classifier: Combining TinyML-Optimised CNN with RRAM-CMOS ACAM for Energy-Efficient Inference

In recent years, the development of smart edge computing systems to process information locally is on the rise. Many near-sensor machine learning (ML) approaches have been implemented to introduce accurate and energy efficient template matching operations in resource-constrained edge sensing systems, such as wearables. To introduce novel solutions that can be viable for extreme edge cases, hybrid solutions combining conventional and emerging technologies have started to be proposed. Deep Neural Networks (DNN) optimised for edge application alongside new approaches of computing (both device and architecture -wise) could be a strong candidate in implementing edge ML solutions that aim at competitive accuracy classification while using a fraction of the power of conventional ML solutions. In this work, we are proposing a hybrid software-hardware edge classifier aimed at the extreme edge near-sensor systems. The classifier consists of two parts: (i) an optimised digital tinyML network, working as a front-end feature extractor, and (ii) a back-end RRAM-CMOS analogue content addressable memory (ACAM), working as a final stage template matching system. The combined hybrid system exhibits a competitive trade-off in accuracy versus energy metric with $E_{front-end}$ = $96.23 nJ$ and $E_{back-end}$ = $1.45 nJ$ for each classification operation compared with 78.06$μ$J for the original teacher model, representing a 792-fold reduction, making it a viable solution for extreme edge applications.

cs.LG↗

arXiv2025

Decentralised Resource Sharing in TinyML: Wireless Bilayer Gossip Parallel SGD for Collaborative Learning

With the growing computational capabilities of microcontroller units (MCUs), edge devices can now support machine learning models. However, deploying decentralised federated learning (DFL) on such devices presents key challenges, including intermittent connectivity, limited communication range, and dynamic network topologies. This paper proposes a novel framework, bilayer Gossip Decentralised Parallel Stochastic Gradient Descent (GD PSGD), designed to address these issues in resource-constrained environments. The framework incorporates a hierarchical communication structure using Distributed Kmeans (DKmeans) clustering for geographic grouping and a gossip protocol for efficient model aggregation across two layers: intra-cluster and inter-cluster. We evaluate the framework's performance against the Centralised Federated Learning (CFL) baseline using the MCUNet model on the CIFAR-10 dataset under IID and Non-IID conditions. Results demonstrate that the proposed method achieves comparable accuracy to CFL on IID datasets, requiring only 1.8 additional rounds for convergence. On Non-IID datasets, the accuracy loss remains under 8\% for moderate data imbalance. These findings highlight the framework's potential to support scalable and privacy-preserving learning on edge devices with minimal performance trade-offs.

cs.LG↗

arXiv2022

DeepSafety:Multi-level Audio-Text Feature Extraction and Fusion Approach for Violence Detection in Conversations

Natural Language Processing has recently made understanding human interaction easier, leading to improved sentimental analysis and behaviour prediction. However, the choice of words and vocal cues in conversations presents an underexplored rich source of natural language data for personal safety and crime prevention. When accompanied by audio analysis, it makes it possible to understand the context of a conversation, including the level of tension or rift between people. Building on existing work, we introduce a new information fusion approach that extracts and fuses multi-level features including verbal, vocal, and text as heterogeneous sources of information to detect the extent of violent behaviours in conversations. Our multilevel multimodel fusion framework integrates four types of information from raw audio signals including embeddings generated from both BERT and Bi-long short-term memory (LSTM) models along with the output of 2D CNN applied to Mel-frequency Cepstrum (MFCC) as well as the output of audio Time-Domain dense layer. The embeddings are then passed to three-layer FC networks, which serve as a concatenated step. Our experimental setup revealed that the combination of the multi-level features from different modalities achieves better performance than using a single one with F1 Score=0.85. We expect that the findings derived from our method provides new approaches for violence detection in conversations.

cs.CY↗

arXiv2021

DigitalExposome: Quantifying the Urban Environment Influence on Wellbeing based on Real-Time Multi-Sensor Fusion and Deep Belief Network

In this paper, we define the term 'DigitalExposome' as a conceptual framework that takes us closer towards understanding the relationship between environment, personal characteristics, behaviour and wellbeing using multimodel mobile sensing technology. Specifically, we simultaneously collected (for the first time) multi-sensor data including urban environmental factors (e.g. air pollution including: PM1, PM2.5, PM10, Oxidised, Reduced, NH3 and Noise, People Count in the vicinity), body reaction (physiological reactions including: EDA, HR, HRV, Body Temperature, BVP and movement) and individuals' perceived responses (e.g. self-reported valence) in urban settings. Our users followed a pre-specified urban path and collected the data using a comprehensive sensing edge devices. The data is instantly fused, time-stamped and geo-tagged at the point of collection. A range of multivariate statistical analysis techniques have been applied including Principle Component Analysis, Regression and spatial visualisations to unravel the relationship between the variables. Results showed that EDA and Heart Rate Variability HRV are noticeably impacted by the level of Particulate Matters (PM) in the environment well with the environmental variables. Furthermore, we adopted Deep Belief Network to extract features from the multimodel data feed which outperformed Convolutional Neural Network and achieved up to (a=80.8%, σ=0.001) accuracy.

cs.LG↗

arXiv2021

The Rise of Technology in Crime Prevention: Opportunities, Challenges and Practitioners Perspectives

Criminal activity is a prevalent issue in contemporary culture and society, with most nations facing unacceptable levels of crime. Technological innovation has been one of the main driving forces leading to the continuous improvement of crime control and crime prevention strategies (e.g. GPS tracking and tagging, video surveillance, etc.). Given this, it is a moral obligation for the research community to consider how the contemporary technological developments (i.e. Internet of Things (IoT), Machine Learning, Edge Computing)might help reduce crime worldwide. In line with this, this paper provides a discussion of how a sample of contemporary hardware and software-based technologies might help further reduce criminal actions. After a thorough analysis of a wide array of technologies and a number of workshops with organisations of interest, we believe that the adoption of novel technologies by vulnerable individuals, victim support organisations and law enforcement can help reduce the occurrence of criminal activity.

cs.CY↗

arXiv2020

Combining Deep Transfer Learning with Signal-image Encoding for Multi-Modal Mental Wellbeing Classification

The quantification of emotional states is an important step to understanding wellbeing. Time series data from multiple modalities such as physiological and motion sensor data have proven to be integral for measuring and quantifying emotions. Monitoring emotional trajectories over long periods of time inherits some critical limitations in relation to the size of the training data. This shortcoming may hinder the development of reliable and accurate machine learning models. To address this problem, this paper proposes a framework to tackle the limitation in performing emotional state recognition on multiple multimodal datasets: 1) encoding multivariate time series data into coloured images; 2) leveraging pre-trained object recognition models to apply a Transfer Learning (TL) approach using the images from step 1; 3) utilising a 1D Convolutional Neural Network (CNN) to perform emotion classification from physiological data; 4) concatenating the pre-trained TL model with the 1D CNN. Furthermore, the possibility of performing TL to infer stress from physiological data is explored by initially training a 1D CNN using a large physical activity dataset and then applying the learned knowledge to the target dataset. We demonstrate that model performance when inferring real-world wellbeing rated on a 5-point Likert scale can be enhanced using our framework, resulting in up to 98.5% accuracy, outperforming a conventional CNN by 4.5%. Subject-independent models using the same approach resulted in an average of 72.3% accuracy (SD 0.038). The proposed CNN-TL-based methodology may overcome problems with small training datasets, thus improving on the performance of conventional deep learning methods.

cs.CV↗

arXiv2020

Beyond Mobile Apps: A Survey of Technologies for Mental Well-being

Mental health problems are on the rise globally and strain national health systems worldwide. Mental disorders are closely associated with fear of stigma, structural barriers such as financial burden, and lack of available services and resources which often prohibit the delivery of frequent clinical advice and monitoring. Technologies for mental well-being exhibit a range of attractive properties, which facilitate the delivery of state-of-the-art clinical monitoring. This review article provides an overview of traditional techniques followed by their technological alternatives, sensing devices, behaviour changing tools, and feedback interfaces. The challenges presented by these technologies are then discussed with data collection, privacy, and battery life being some of the key issues which need to be carefully considered for the successful deployment of mental health toolkits. Finally, the opportunities this growing research area presents are discussed including the use of portable tangible interfaces combining sensing and feedback technologies. Capitalising on the data these ubiquitous devices can record, state of the art machine learning algorithms can lead to the development of robust clinical decision support tools towards diagnosis and improvement of mental well-being delivery in real-time.

cs.CY↗

arXiv2020

TangToys: Smart Toys that can Communicate and Improve Children's Wellbeing

Children can find it challenging to communicate their emotions especially when experiencing mental health challenges. Technological solutions may help children communicate digitally and receive support from one another as advances in networking and sensors enable the real-time transmission of physical interactions. In this work, we pursue the design of multiple tangible user interfaces designed for children containing multiple sensors and feedback actuators. Bluetooth is used to provide communication between Tangible Toys (TangToys) enabling peer to peer support groups to be developed and allowing feedback to be issued whenever other children are nearby. TangToys can provide a non-intrusive means for children to communicate their wellbeing through play.

cs.HC↗

arXiv2020

Sensor Data and the City: Urban Visualisation and Aggregation of Well-Being Data

The growth of mobile sensor technologies have made it possible for city councils to understand peoples' behaviour in urban spaces which could help to reduce stress around the city. We present a quantitative approach to convey a collective sense of urban places. The data was collected at a high level of granularity, navigating the space around a highly popular urban environment. We capture people's behaviour by leveraging continuous multi-model sensor data from environmental and physiological sensors. The data is also tagged with self-report, location coordinates as well as the duration in different environments. The approach leverages an exploratory data visualisation along with geometrical and spatial data analysis algorithms, allowing spatial and temporal comparisons of data clusters in relation to people's behaviour. Deriving and quantifying such meaning allows us to observe how mobile sensing unveils the emotional characteristics of places from such crowd-contributed content.

cs.HC↗

arXiv2020

LabelSens: Enabling Real-time Sensor Data Labelling at the point of Collection on Edge Computing

In recent years, machine learning has developed rapidly, enabling the development of applications with high levels of recognition accuracy relating to the use of speech and images. However, other types of data to which these models can be applied have not yet been explored as thoroughly. Labelling is an indispensable stage of data pre-processing that can be particularly challenging, especially when applied to single or multi-model real-time sensor data collection approaches. Currently, real-time sensor data labelling is an unwieldy process, with a limited range of tools available and poor performance characteristics, which can lead to the performance of the machine learning models being compromised. In this paper, we introduce new techniques for labelling at the point of collection coupled with a pilot study and a systematic performance comparison of two popular types of deep neural networks running on five custom built devices and a comparative mobile app (68.5-89% accuracy within-device GRU model, 92.8% highest LSTM model accuracy). These devices are designed to enable real-time labelling with various buttons, slide potentiometer and force sensors. This exploratory work illustrates several key features that inform the design of data collection tools that can help researchers select and apply appropriate labelling techniques to their work. We also identify common bottlenecks in each architecture and provide field tested guidelines to assist in building adaptive, high-performance edge solutions.

cs.LG↗

arXiv2020

A Modified Epidemiological Model to Understand the Uneven Impact of COVID-19 on Vulnerable Individuals and the Approaches Required to Help them Emerge from Lockdown

COVID-19 has shown a relatively low mortality rate in young healthy individuals, with the majority of this group being asymptomatic or having mild symptoms, while the severity of the disease among individuals with underlying health conditions has caused signiffcant mortality rates worldwide. Understanding these differences in mortality amongst different sectors of society and modelling this will enable the different levels of risk and vulnerabilities to be determined to enable strategies exit the lockdown. However, epidemiological models do not account for the variability encountered in the severity of the SARS-CoV-2 disease across different population groups. To overcome this limitation, it is proposed that a modiffed SEIR model, namely SEIR-v, through which the population is separated into two groups regarding their vulnerability to SARS-CoV-2 is applied. This enables the analysis of the spread of the epidemic when different contention measures are applied to different groups in society regarding their vulnerability to the disease. A Monte Carlo simulation indicates a large number of deaths could be avoided by slightly decreasing the exposure of vulnerable groups to the disease. From this modelling a number of mechanisms can be proposed to limit the exposure of vulnerable individuals to the disease in order to reduce the mortality rate among this group. One option could be the provision of a wristband to vulnerable people and those without a contact-tracing app. By combining very dense contact tracing data from smartphone apps and wristband signals with information about infection status and symptoms, vulnerable people can be protected and kept safer. Widespread utilisation would extend the protection further beyond these high risk groups.

physics.soc-ph↗