The stand-alone solar photovoltaic (PV) systems are a convenient way to provide the electricity for people far from electric grid or who want power without any dependence on utility grid, run their usual activities either at homes businesses. size of these vary according available radiations and different load conditions. Therefore, this paper takes an organized approach regarding designing systems. For purpose, detailed guidelines technical considerations needed in design process PV system...

With growing security threats, many online and offine frameworks have been proposed for anomaly detection in video sequences. However, existing techniques are either computationally very expensive or lack desirable accuracy. This research work proposes a novel particle filtering based framework which detects frames with anomalous activities upon the posterior probability of sequence. The method also regions frames. We propose prediction measurement models to accurately detect Novel model...

This paper considers the problem of multiple human target tracking in a sequence video data. A solution is proposed which able to deal with challenges varying number targets, interactions, and when every gives rise measurements. The developed novel algorithm comprises variational Bayesian clustering combined social force model, integrated within particle filter an enhanced prediction step. It performs measurement-to-target association by automatically detecting measurement relevance....

This work presents a flexible VLSI architecture to compute the N ‐point DCT. Since HEVC supports different block sizes for computation of DCT, that is, 4 × up 32 32, design support them helps reducing area overhead hardware implementations. The proposed in this is partially folded save and get speed large video sequences sizes. relies on decomposition DCT matrices into sparse submatrices order reduce multiplications. Finally, multiplications are completely eliminated using lifting scheme....

Source separation algorithms that utilize only audio data can perform poorly if multiple sources or reverberation are present. In this paper we therefore propose a video-aided model-based source algorithm for two-channel reverberant recording in which the assumed static. By exploiting cues from video, first localize individual speech enclosure and then estimate their directions. The interaural spatial cues, phase difference level difference, as well mixing vectors probabilistically modeled....

This paper considers the problem of anomaly detection in an outdoor environment where surveillance cameras are usually installed to monitor activities general public. A novel solution is proposed which combines audio and visual data automatically detect abnormal activities. The algorithm makes use both features anomalous scenes. Visual such as optical flow technique combined with particle swam optimization social force model used, whereas, acoustic as, energy, zero crossing rate, volume,...

We propose to perform wearable sensors-based human physical activity recognition. This is further extended an Internet-of-Things (IoT) platform which based on a web-based application that integrates sensors, smartphones, and To this end, smartphone collects the data from sensors sends it server for processing recognition of activity. collect novel set 13 activities performed both indoor outdoor. The participants are genders where their number per varies. During these activities, measure...

The advancements in Edge computing have paved the way for deep learning real-time systems. One of beneficiaries is an adaptive traffic control system that responds to observations by governing signal phase and timings. Reinforcement Learning (RL) extensively utilized literature order decrease congestion a road network. However, most previous works leverage centralized cloud-based RL due computational complexity underlying neural networks (DNN). Therefore, persistent challenge towards...

Automatic detection and recognition of traffic signs is a topic research for various applications like driver assistance, inventory management autonomous driving. Poorly maintained degrade by losing their colors or some part weird due to aging hence making the task more challenging. The problem mainly related developing world has gained less attention in literature on automatic sign recognition. To handle degradation issue, we present novel flexible Gaussian mixture model based technique...

The micro-hydro based interconnected power system performance in terms of stability is generally affected by the dynamic characteristic its components during and after when it subjected to physical disturbances such as quick change electric load, occurrence fault etc. These sometimes cause large variations frequency, voltage, flows other constraints; thereby, invoking actions processes, controls, protections that are incompletely inappropriately modeled conventional studies. Thus, complete...

This paper presents a novel sound event detection (SED) system for rare events occurring in an open environment. Wavelet multiresolution analysis (MRA) is used to decompose the input audio clip of 30 seconds into five levels. denoising then applied on third and fifth levels MRA filter out background. Significant transitions, which may represent onset event, are estimated these two by combining peak-finding algorithm with K-medoids clustering algorithm. The small portions one-second duration,...

This paper presents the simple and low-cost design of an automatic power factor correction (APFC) system for single phase domestic loads. The proposed uses TRIACs to switch capacitor banks in order correct inductive are more effective than electro-mechanical relays hit high-performance benchmarks. switching is controlled by Arduino board. programmed non-stop monitor calculate connecting load sensing signal from CT, PT Zero Cross Detectors (ZCDs), keep above reference value (0.9)...

Traffic sign detection and recognition has been a topic of research for at least the last two decades. Efforts are being made to reliably detect candidate traffic signs in natural uncontrolled environment recognize their contents. For detection, large proportion relevant literature disc usses color based segmentation by either sticking predefined space (e.g., RGB, HSI, YCbCr etc.) or make use empirically selected subset eigen achieve partially data dependent segmentation. Since, input RGB...

This paper discusses a convex Economic Load Dispatch (ELD) problem for 3-Generator 5-Bus system subjected to equality and inequality constraints. The solution this is found by modelling Particle Swarm Optimization (PSO), Gravitational Search Algorithm (GSA), hybrid of (in short PSO-GSA) discretely in MATLAB. core idea behind the combination PSO with GSA develop an algorithm which utilizes local search ability global simultaneously, thus making quick robust nature. Further, simulation results...

This research paper proposes a single camera based depth estimation technique. The proposed technique takes images of walls in room and detects objects interest cluttered environment. Having detected different the calculates their areas. Based on training data polynomial curve fitting approach estimates distance from objects. For real world object one can determine fixed equation which then be used to find any random distance. is efficient effectively applied indoor navigation or motion...

The world is facing the challenge of effectively exploiting and utilizing renewable energy resources, not only to meet increasing demand, but also preserve reduce depletion fossil fuels lessen amount CO2 emissions in our atmosphere. Among different forms energies, micro hydro power plants (MHPPs) are intensifying as a major source today they do encounter problems population displacement being extremely benign environment. But, still operate stand-alone mode supply electricity local rural...

In computer networks, vertices represent hosts or servers, and edges as the connecting medium between them. localization, some special (resolving sets) are selected to locate position of all in a network. If an arbitrary vertex stopped working still remain resolving set, then chosen set is called fault‐tolerant set. The least number such sets metric dimension Because variety applications different areas sciences, many generalizations were proposed, fault tolerant one this paper, we computed...

We perform image-based denomination recognition of the Pakistani currency notes. There are a total seven different denominations in current series Apart from color and texture, these notes differ one another mainly due to their aspect ratios. Our aim is exploit this single feature attain an that invariant most common image variations found images. Among others, notable caused by difference positions in-plane orientations While proposed methods for only focus on attaining higher rates, our...

The analysis of human sperm as part infertility investigations or assisted conception treatments is a labor intensive process reliant upon the skill observer and such prone to error. Therefore, there need develop automated systems that can adequately assess concentration, motility morphology live sperm. This paper presents an algorithm for analyzing motile Techniques eliminating background, segmentation cells template matching techniques are used analyze in two stages: first stage eliminates...