IoT Assistive Technology for People with Disabilities
Soulease: A Mind-Refreshing Application for Mental Well-Being
AI-Powered Weather System with Disaster Prediction
AI Driven Animal Farming and Livestock Management System
Advances in AI for Automatic Sign Language Recognition: A Comparative Study of Machine Learning Approaches
Design and Evaluation of Parallel Processing Techniques for 3D Liver Segmentation and Volume Rendering
Ensuring Software Quality in Engineering Environments
New 3D Face Matching Technique for an Automatic 3D Model Based Face Recognition System
Algorithmic Cost Modeling: Statistical Software Engineering Approach
Prevention of DDoS and SQL Injection Attack By Prepared Statement and IP Blocking
Software Architecture plays a vital role in the success or failure of software systems. Architecture understandability is a very important factor for managing and improving the system architecture. In this work, understandability of software architectures at the component-level will be explored. This study examines software structural properties of size, coupling, stability, and complexity against the effort spent by a developer to study a component. Number of software design metrics have been explored in the same context in the literature before, however, this work would explore a different combination of design metrics. A case study has been adopted from the literature that used an open source software system, which comprises of seven components. Analyses of Correlation, Collinearity, and Multivariate regression have been performed. The results of the statistical analyses indicate a correlation between most of the metrics used and the required effort needed to understand a component.
Medical Image Processing exploits the use of signal processing concept when applied to medical images. The medical images may be X-rays, Computed Tomographic (CT) images, or Mammograms. This paper gives an overview of image processing for the application areas of medical science that covers the concepts of Computer-Aided Diagnosis (CAD) system used in medical images and diagnosis system for segmentation, detection, and classification of cancer stages by post-processing the medical images. Medical Image Processing has brilliant research scope in understanding physical, mathematical, and engineering avenues of medical image uses in various disease diagnosis methods. This enables to “see” inside the human body to diagnose the disease and monitor treatment; an overview of recent developments in the field of medical imaging along with prominent challenges that radiologists and physicians come across while scanning, interpretation, and diagnosis processes. A practical approach and experimental results in some cases of segmentation with a review of a specific algorithm for medical image processing or analysis, along with the concept of CAD system and its evaluation criteria are discussed.
As and when the conventional analytical and empirical approaches fail to optimize a given system, we need to look for alternatives. The emerging trend is to get inspiration from nature to handle such complex situations and systems. Traditionally, the gradient based optimization techniques are used for finding an optimal solution to a given problem. However, due to the inability of these techniques in terms of handling multi-variable multi-constrained complex systems, the nature inspired evolutionary algorithms (population based search algorithms) have been developed over the past few years. This paper focuses on nature- or bio-inspired evolutionary computation technique called Differential Evolution (DE) (an improved version of Generic Algorithm), its working principle, and demonstration with a numerical example using step-by-step procedure. Various DE strategies are discussed and applied to many engineering and management problems. DE is extended to multi-objective optimization problems as Multi-Objective Differential Evolution (MODE) and its variants, that can handle the limitations of traditional optimization techniques in addressing complex engineering problems in terms of constraints, objectives, etc. are demonstrated. The working principles of these Evolutionary Algorithms are demonstrated with examples and industrial applications.
Heart Diseases have been the leading cause of death for decades. The proportion of deaths caused by heart disease is nearly 25% per year around the world. Therefore, there is a need for new potential strategies to reduce the risk factors of Cardiovascular disease (CVD). The objective of the research is, linking heart health and owning a pet, as holding a pet is probably associated with a lower risk of heart disease for those without a history of heart problems, and with the greater survival rates among heart disease patients. For the risk factors, medical dataset that has attributes such as age, sex, chest pain type, cholesterol level, blood pressure, blood sugar, heart rate, obesity and hereditary are collected. Finally, the review of the available data suggests that, owning a pet likely reduces the risk of developing heart disease or worsening it. The research is implemented in WEKA tool, using Association rule along with the Apriori algorithm.
Tracking of humans in video streams is important for many applications. For tracking purposes, many algorithms have come up in the recent years. The most prominent one among all of them is Gaussian Mixture Model (GMM). This algorithm is basically employed for tracking the objects in the Video scene. Later, the algorithm has been modified for the purpose of tracking humans. GMM uses only single rectangular template for tracking an object. In order to track humans specifically, the template has been divided into four regions. The top region is for the head and the remaining regions are for the chest, waist and legs respectively. All the regions are of rectangle shape. Connection has been established among all the regions assuming that all four regions will move at a time for humans. There is only 10% horizontal variation allowed between the regions. The proposed algorithm could handle both partial occlusion and full occlusion. The new algorithm is compared with the tracking system of GMM algorithm. The precision, recall, false alarm per frame, false negatives, false positives and mostly lost are compared with the existing GMM. The time taken for processing a single frame is reduced by using new algorithm when compared with the existing algorithm. Performance metrics show that the Weighted Running Window Background (WRWB) Model Based GMM algorithm out performs when compared with GMM algorithm in terms of time taking.
