This paper explores the growing significance of remote healthcare methods in the post-pandemic world. While most current remote healthcare applications rely on video conferencing for patient-doctor communication, they fall short in providing comprehensive, personalised, and customised rehabilitation experiences for neurological patients. This paper presents the design and implementation of a web-based application that offers standard therapy demonstrations, schedules specific therapy sessions, guides patients through exercises in the absence of a doctor and evaluates their performance upon completing the therapy. The web application also features messaging and video conferencing functionalities for seamless doctor-patient communication. Furthermore, the application facilitates doctor-patient allocation, follow-up appointments, and the option to consult with additional healthcare professionals. With a focus on minimal entry barriers, the system is deployable for each patient, ensuring the secure storage of data entirely onboard.

Integrating transparency, interpretability, and accountability into the design of Artificial Intelligence (AI) tools for Ambient Assisted Living (AAL) enhances user trust and acceptance. Clear explanations of the AI system’s operations and decision-making process are vital, enabling users to comprehend the factors influencing predictions and recommendations. This paper introduces a novel explainable framework tailored for AAL, representing a structured approach to comprehensively understand feature importance in the decision-making process of machine learning models. The framework adopts a hierarchical approach, commencing with an overview of feature importance for the entire AAL system (Tier 0) and subsequently organising explanations into smaller subsets (Tiers 1, 2 and 3) based on user-defined measures, such as accuracy, activity types in AAL, and specific time periods. By facilitating metadata exploration and offering in-depth insights, the proposed framework augments model interpretability and user trust, ultimately empowering informed decision-making within AAL contexts.

Among numerous pattern recognition methods the neural network approach has been the subject of much research due to its ability to learn from a given collection of representative examples. This paper is concerned with the design of a Weightless Neural Network, which decomposes a given pattern into several sets of n points, termed n-tuples. Considerable research has shown that by optimising the input connection mapping of such n-tuple networks classification performance can be improved significantly. This paper investigates the hybridisation of Genetic Algorithm (GA) and Particle Swarm Optimisation (PSO) techniques in search of better connection maps to the N-tuples. Experiments were conducted to evaluate the proposed method by applying the trained classifier to recognise hand-printed digits from a widely used database compiled by U.S. National Institute of Standards and Technology (NIST).

Among numerous pattern recognition methods the neural network approach has been the subject of much research due to its ability to learn from a given collection of representative examples. This paper concerns with the optimization of a weightless neural network, which decomposes a given pattern into several sets of n points, termed n-tuples. A population-based stochastic optimization technique, known as Particle Swarm Optimization (PSO), has been used to select an optimal set of connectivity patterns to improve the recognition performance of such .n-tuple. classifiers. The original PSO was refined by combining it with a bio-inspired technique called the Self-Organized Criticality (SOC) to add diversity in the population for finding better solutions. The hybrid algorithms were adapted for the n-tuple system and the performance was measured in selecting better connectivity patterns. The aim was to improve the discriminating power of the classifier in recognizing handwritten characters by exploiting the criticality dispersion in the swarm population. This paper presents the implementation of the hybrid model in greater detail with the effect of criticality dispersion in finding better solutions.

The employment of field programmable gate arrays (FPGAs) to a robot controller is very attractive, since it allows for fast IC prototyping and low cost modifications. The speedup is achieved because of pipelining and dedicated functions in hardware that are customized to the problem. The self learning ability and the adaptive nature of an Artificial Neural Network (ANN) makes it a good candidate for the control structure of a robot's navigation. An evolutionary approach in designing robots can evolve the architecture of ANNs and yields automatic creation of the controller while the robot moves in task environments. The poster briefly describes the important hardware issues involved with the FPGA based design of an evolutionary robot controller for the collision free navigation of mobile robots.

This article describes an alternative hardware solution to be implemented on FPGAs (field programmable gate array) for collision free robot navigation. A RAM based artificial neural network (ANN) was considered as the heart of the controller due to the advantage of its ease of implementation in conventional hardware. The structure of the ANN was well suited to realize the experiments for evolutionary robotics (ER). The hardware implementation gives massive parallelism of neural networks and the FPGA allows fast IC prototyping and low cost modifications.