A Virtual Power Plant (VPP) is a network of distributed power generating units, flexible consumers, and storage systems. VPP balances the load on grid by allocating generated different linked units during periods peak load. Demand-side energy equipment, such as Electric Vehicles (EVs) mobile robots, can also balance supply-demand when effectively deployed. However, fluctuation various makes supply challenging goal. Moreover, communication security between aggregator end facilities critical...

Neuromorphic computing systems are an emerging field that takes its inspiration from the biological neural architectures and computations inside mammalian nervous system. The spiking networks (SNNs) mimic real by conveying information through communication of short pulses between neurons. Since each neuron in these is connected to thousands others, high bandwidth required. Moreover, since spike times used encode SNN, very low latency also necessary. On other hand, combination Two-dimensional...

Neuromorphic systems have shown improvements over the years, leveraging Spiking neural networks (SNN) event-driven nature to demonstrate low power consumption. As neuromorphic require high integration form a functional silicon brain-like, moving 3D integrated circuits (3D-ICs) with three-dimensional network on chip (3D-NoC) interconnect is suitable approach that allows scalable design, shorter connections, and lower However, highly dense also encounter reliability issue where single point of...

With the increasing demand for computing machines that more closely model biological brain, field of neuro-inspired has progressed to exploration Spiking Neural Networks (SNN), and best challenges conventional Von Neumann architecture, several hardware-based (neuromorphic) chips have been designed. A neuromorphic chip is based on spiking neurons process input information only when they receive spike signals. Given a sparsely-distributed train, power consumption such event-driven hardware...

Almost every larger city in Europe has ambitious smart projects. This is particularly true for Hamburg, a Hanseatic the north of Germany. Hamburg smartest Germany according to Federal Association Information Technology. Although there are no megacities European Union (the largest Berlin with 3.7 million inhabitants), increasing urbanization apparent and produces problems be solved. At same time rural depopulation creates conjugated problems.One category these mobility. Mobility can regarded...

Neuromorphic computing uses spiking neuron network models to solve machine learning problems in a more energy-efficient way when compared conventional artificial neural networks.However, mapping the various components neuromorphic hardware is not trivial realize desired model for an actual simulation.Moreover, neurons and synapses could be affected by noise due external interference or random actions of other (i.e., neurons), which eventually lead unreliable results.This work proposes...

Application-specific architectures with multiple processing cores integrated a three-dimensional Network-on-Chip (NoC) concept can exploit the parallelism inherent within spiking and non-spiking neural networks to provide low latency high-bandwidth communication. One of critical components in these NoC-based is on-chip routing scheme, which allows data be communicated between also off-chip transported cores. In this work, we present low-latency tree-based multicast spike for scalable...

Autonomous Driving has recently become a research trend and efficient autonomous driving system is difficult to achieve due safety concerns, Applying traffic light recognition one of the factors prevent accidents that occur as result violation. To realize safe system, we propose in this work design optimization detection based on deep neural network. We designed lightweight convolution network with parameters less than 10000 implemented software. achieved 98.3% inference accuracy 2.5 fps...

COVID-19 is currently on the rage all over world and has become a pandemic. To efficiently handle it, accurate diagnosis prompt reporting are essential. The AI-Enabled Real-time Biomedical System (AIRBiS) research project aims to develop system that handles using chest X-ray images. divided into UI, network, software hardware. This work focuses hardware, which uses CNN technology create model determines presence of pneumonia. designed an FPGA speed up diagnostic results. increases...

Despite the advancement of prosthetic hands, many conventional products are difficult to control and have limited capabilities. Even though these limitations being pushed by state-of-the-art commercial hand products, they often expensive due high cost production. Therefore, in Adaptive Neuroprosthesis Arm (NeuroSys) project, we aim develop a low-cost with functionalities that let users perform various gestures accurate grasp. This paper mainly focuses on sEMG signal recognition for prototype...

The use of robotic arms in various fields human endeavor has increased over the years, and with recent advancements artificial intelligence enabled by deep learning, they are increasingly being employed medical applications like assistive robots for paralyzed patients neurological disorders, welfare elderly, prosthesis amputees. However, robot tailored towards such resource-constrained. As a result, learning conventional neural network (ANN) which is often run on GPU high computational...

The success of deep learning in extending the frontiers artificial intelligence has accelerated application AI-enabled systems addressing various challenges different fields. In healthcare, is deployed on edge computing platforms to address security and latency challenges, even though these are often resource-constrained. Deep based conventional neural networks, which computationally complex, require high power, have low energy efficiency, making them unsuitable for platforms. Since also...

recent years, robots have been introduced in most factories. However, manual work still continues to be done some places where giant cannot installed. In particular, traditional Japanese crafts are by hand, and people that engage such called craftsmen. Generally, artisans need years of training become experts right away. One the problems these face is lack successors. To address this challenge, paper proposes a raspberry pi hardware based control method for prosthetic hand using gestures...

Neuromorphic computing tries to model in hardware the biological brain which is adept at operating a rapid, real-time, parallel, low power, adaptive and fault-tolerant manner within volume of 2 liters. Leveraging event driven nature Spiking Neural Network (SNN), neuromorphic systems have been able demonstrate power consumption by gating sections network not an any point time. However, further exploration this field towards building edge application friendly agents efficient scalable with...