6 November 2020 in IEEE Transactions on Knowledge and Data Engineering
Detecting anomalous objects from given data has a broad range of real-world applications. Although there is a rich number of outlier detection algorithms, most of them involve hidden assumptions and restrictions. This paper proposes a novel, yet effective outlier learning algorithm that is based on decomposing the full attributes space into different combinations of subspaces, in which the 3D-vectors, representing the data points per 3D-subspace, are rotated about the geometric median, using Rodrigues rotation formula, to construct the overall outlying score. The proposed approach is parameter-free, requires no distribution assumptions and easy to implement. Extensive experimental study and comparison are conducted on both synthetic and real-world datasets with six popular outlier detection algorithms, each from different category. The comparison is evaluated based on the precision @s, average precision, rank power, AUC ROC and time complexity metrics. The results show that the performance of the proposed method is competitive and promising.
2 June 2023 in IEEE Access
The smart textile and wearables sector is looking towards advancing technologies to meet both industry, consumer and new emerging innovative textile application demands, within a fast paced textile industry. In parallel, inspiration based on the biological neural workings of the human brain is driving the next generation of Artificial Intelligence (AI). AI inspired hardware (neuromorphic computing) and software modules mimicking the processing capabilities and properties of neural networks and the human nervous system are taking shape. The textile sector needs to actively look at such emerging and new technologies taking inspiration from their workings and processing methods in order to stimulate new and innovative embedded intelligence advancements in the e-textile world. This emerging next generation of AI is rapidly gaining interest across varying industries (textile, medical, automotive, aerospace, military). It brings the promise of new innovative applications enabled by low size, weight and processing power technologies. Such properties meet the need for enhanced performing integrated circuits (IC’s) and complex machine learning algorithms. How such properties can inspire and drive advancements within the e-textiles sector needs to be considered. This paper will provide an insight into AI advancements in the e-textiles domain before focusing specifically on the future vision and direction around the potential application of neuromorphic computing and spiking neural network inspired AI technologies within the textile sector. We investigate the core architectural elements of artificial neural networks, neuromorphic computing (2D and 3D structures) and how such neuroscience inspired technologies could impact and inspire change and new research developments within the e-textile sector.
24 February 2020 in IEEE Transactions on Nanobioscience
With the advancement of synthetic biology, several new tools have been conceptualized over the years as alternative treatments for current medical procedures. This work we investigate how synthetically engineered neurons can operate as digital logic gates that can be used towards bio-computing inside the brain and its impact on epileptic seizure-like behaviour. We quantify the accuracy of logic gates under high firing rates amid a network of neurons and by how much it can smooth out uncontrolled neuronal firings. To test the efficacy of our method, simulations composed of computational models of neurons connected in a structure that represents a logic gate are performed. Our simulations demonstrate the accuracy of performing the correct logic operation, and how specific properties such as the firing rate can play an important role in the accuracy. As part of the analysis, the mean squared error is used to quantify the quality of our proposed model and predict the accurate operation of a gate based on different sampling frequencies. As an application, the logic gates were used to smooth out epileptic seizure-like activity in a biological neuronal network, where the results demonstrated the effectiveness of reducing its mean firing rate. Our proposed system has the potential to be used in future approaches to treating neurological conditions in the brain.
5 August 2024 in IEEE Access
Autism is a developmental condition that affects motor skill development. There is a lack of comprehensive research exploring the potential benefits of extended reality (XR) technologies, including virtual reality (VR) and augmented reality (AR), for improving motor skills in autistic children. This systematic literature review (SLR) addresses this research gap by investigating XR-based interventions targeting motor skill development in autistic children. The SLR analysed 15 primary studies published between 2012 and 2024, examining the use of VR and AR to improve motor skill development in autistic children. The interventions ranged from one session to 12 weeks, lasting 12 to 45 minutes, and targeted various body movements. XR platforms and devices used included VR headsets, motion capture systems, and exercise bikes. Recurrent neural networks, dynamic difficulty adjustment, and behaviour trees were employed to enhance intervention dynamics and extract valuable insights from collected data. The results suggest that using XR interventions has significant potential to improve physical activity levels and motor skills development among autistic children. However, the research designs varied, with only one study including their intervention framework’s generalisation and maintenance phases. This study offers an encouraging avenue for future research and intervention design in this field.
26 September 2022 in IEEE Sensors Journal
SBSasitharan Balasubramaniam
Sasitharan Balasubramaniam
+1
Advances in artificial intelligence(AI) is an enabler for innovative wearable on-garment edge driven AI intelligence. Such AI technologies are leveraging bio-inspired methods to develop spiking neural networks (SNN) that mimic the workings of the human brain to produce higher performance edge based processing capabilities. Such advancements are driving the development and emergence of neuromorphic computing with SNN architectural designs. Taking inspiration from these this paper proposes and demonstrates a wearable μBrain multi-layer SNN smart garment, with an event-driven artificial SNN embedded into the garments fabric. The fabric based multilayer SNN is interchangeable and scalable through its fabric hidden layer and fabric patch design and can be interconnected with textile based analogue monitoring sensors. The prototype was tested to check the functionality of the individual and collective nodes of the SNN as well as evaluating the wearable μBrain for fault tolerance scenarios (ripping and fraying) proving the prototype remained intact following the disconnection of fabric node Patch 5 and 8. Two application demonstrators were identified and tested. The first application focused on the detection of touch sensation on a forearm using the wearable μBrain, here real world use cases were checked against the expected output. Fluctuations were encountered when voltage output readings were above and below the set threshold level of 2.3Volts. The second application interfaced the wearable μBrain to live neurons to demonstrate how textile pressure sensors on the surface can lead to stimulation of neurons, when validated we observed an 11 second timeframe where the brain slice was stimulated.
12 April 2023 in IEEE Sensors Journal
The next generation of etextiles foresees an era of smart wearable garments where embedded seamless intelligence provides the ability to sense, process and perform. Core to this vision is embedded textile functionality enabling dynamic configuration. In this paper we detail a methodology, design and implementation of a dynamic field programmable logic-driven fabric soft exosuit. Dynamic field programmability allows the soft exosuit to alter its functionality and adapt to specific exercise programs depending on the wearers need. The dynamic field programmability is enabled through motion based control arm movements of the soft exosuit triggering momentary sensors embedded in the fabric exosuit at specific joint placement points ( right arm: wrist, elbow ).The embedded circuitry in the fabric exosuit is implemented using a layered and interchangeable approach. This includes logic gate patches ( AND,OR,NOT ) and a layered textile interconnection panel. This modular and interchangeable design enhances the soft exosuits flexibility and adaptability. A truth table aligning to a rehabilitation healthcare use case was utilised. Tests were completed validating the field programmability of the soft exosuit and its capability to switch between its embedded logic driven circuitry and its operational and functionality options controlled by motion movement of the wearers right arm ( elbow and wrist ). Iterative exercise movement and acceleration based tests were completed to validate the functionality of the field programmable logic driven fabric exosuit. We demonstrate a working soft exosuit prototype with motion controlled operational functionality that can be applied to rehabilitation applications.