Salar Faisal Noori

M.S.

Software Engineering

B.S

Computer Science

Assistant Lecturer

Cardiovascular Disease Prediction with Machine Learning

Cardiovascular disease (CVD) is determined as a life-threatening disease globally with a high mortality rate. Over a certain period, there are some commonly overwhelming health issues noted in various countries. The major issues that influence CVD are family history, gender, stress, age, high blood pressure, cholesterol, BMI, and unhealthy life activities. Based on all these issues, researchers intend to propose various approaches for earlier prediction. Moreover, the proposed model's prediction accuracy and its enhancements are owing to the life-threatening risks and inherent criticality of CVD. This work concentrates on modeling an efficient ensemble-based regressive neighborhood model (ERN) is proposed for the effectual CVD prediction model. Various performance metrics are evaluated and compared with various other approaches.

How to Make a Quiz for your students using Moodle Platform.

Peshmarga Hall

I Explain how to make a quiz and how to choose the questions like ... Essay, Multiple Choice, Short Answer, also how to reduce students cheating and etc. Using Moodle platform.

Quiz Sample in Moodle Platform

i have handled workshop on Moodle Paltform

Information Technology based on Industry 5.0 Human Place into IoT-and CPS-based Industrial Systems

Information technology is developing at a breakneck pace in anticipation of Industry 5.0, whereas art design is founded on inventiveness and creativity. The big data age has begun as a result of the revolutionary development of big data technology.The main trend is to promote resources, tools, and big data thinking. It is a significant manifestation of creative thought, which explores the connection between art and design and is closely related to art design. However, ignoring the social and human factors, they have up until now primarily been fueled by technological advancements. The connected innovations of Human-Cyber-Physical Systems are then outlined in this study, with a focus on their applications in Emotional Intelligence (EI). These primarily comprise system design, theoretical evaluation, methodology development, and application predictions. Future development and research directions for HCPS are based on the human-in-the-loop idea and digital transformation, both of which can significantly enhance the system's performance. In the end, an integrated and complete contemporary power grid is created by more robustly achieving the ideal system efficiency of EI with the help of HCPS. These study findings demonstrate the complementary nature of the design, art, and cultural and creative sectors

Multifaceted Interplay between Mobile Edge Computing based on Industry 5.0 in Transportation

A new technology called mobile edge computing, or MEC, is now acknowledged as a crucial 5G network enabler. The demand for computation-intensive mobile network applications—which call for greater storage, potent machines, and real-time responses—has increased significantly in recent years. Because they must support many services, including traffic monitoring or data sharing involving various aspects of vehicular traffic, transportation systems play a crucial part in this ecosystem. Furthermore, new resource-hungry applications like in-car entertainment and self-driving cars have been imagined, making the need for processing and storage resources one of the biggest problems facing transportation networks. With the advent of multi-access edge computing (MEC) technological advances, real-time, high-bandwidth, minimal latency access to radio network resources is intended to be made possible by bringing cloud computing capabilities to the edge of the wireless access network. With MEC's capacity to offer cloud computing and gateways capabilities at the network edge, IoT is recognized as a major application case for the technology. Because of its extensive mobility support and dense geographical spread, MEC will stimulate the development of a wide range of apps and services that require ultralow latencies and high quality of service. For this reason, MEC is a crucial enabler of Internet of Things services and applications that need immediate operation. At last, the globally ideal answer has been achieved. The suggested strategy is superior, as shown by the simulation results

Quantum Computing-Inspired Genetic Algorithm for Network Optimization in WSN

his study presents a pioneering Quantum Computing-Inspired Genetic Algorithm (QIGA) designed for the efficient optimization of Wireless Sensor Networks (WSN). Leveraging the principles of quantum computing, QIGA employs a unique approach to address the complex routing challenges in WSNs. The algorithm starts with the quantum encoding of candidate routes, utilizing quantum bits (qubits) to represent multiple routes simultaneously through principles like superposition and entanglement. Genetic operations, including crossover and mutation, are then applied in the quantum domain to explore diverse solution spaces. The quantum-encoded routes are subsequently decoded into classical routes, and their fitness is evaluated based on crucial WSN optimization criteria, such as energy efficiency, latency, and reliability. The study integrates quantum-inspired selection strategies to determine the next generation of routes, fostering adaptability and efficiency in the optimization process. Through iterative refinement, QIGA aims to converge towards optimal routing solutions for WSNs. The proposed algorithm showcases a quantum-inspired paradigm that holds promise for addressing the intricate challenges of network optimization in WSNs. The study contributes to the evolving landscape of quantum computing applications in networking and lays the foundation for future advancements in quantum-inspired algorithms tailored for practical implementation in WSN environments

Fluidized Bed Dryer with food processing Application Using Exploratory Data Analysis

The Fluidized bed, a multi-phase innovation, makes a difference in useful contact in the midst of them, consequently, it is broadly utilized within the drying of vegetables, drug store businesses, chemical exchange, metallurgy, oil and in generating warm control. In fluidized bed forms, the strong and gas collaboration and responses in the midst of chemicals create sufficient factors which ought to be overseen, making the method exceptionally convoluted. Subsequently, to expect and assess diverse forms fluidized bed modeling and simulation are utilized all around. The prime intent of this think isn't as it were to conclude, but too to analyze and hone diverse parameters like Speed, discuss Temperature and Volume stream rateto accomplish the ideal drying rate in a fluidized bed dryer. A warming weapon with unstable temperatures is utilized to warm the air from the discuss blower, which encompasses an arrangement to switch between seven diverse speeds of discuss. The volume stream rate of the blower is consistent, i.e. 3.3 m3/min. The temperature of the discuss information (at both the entrance and exit of the drying chamber) is compared by employing a bland K-type thermocouple with 2 tests on an advanced show. What comes about, particularly the greatest drying rate is at that point approved to get the ideal values of the discuss speed, temperature, weight drop along the drying chamber and amount of dryable. The optimization of the specified parameters will be done utilizing one of the different optimization procedures accessible

Systematic Review on Multiply and Accumulate Unit (MAC) Architectures and Comparison with Various Multipliers

The basic architecture of digital signal processing and digital image processing systems is the Multiply and Accumulate (Mac) architecture. Digital signal processing applications require Mac hardware with high speed and lowpower consumption as the main functions of DSPs, such as filtering and conversion, are used continuously. Macs also have applications for hardware and software. Floating-point arithmetic using the Mac architecture is more accurate but consumes more power and more silicon space. ieee-754 is a floating point algorithm that improves accuracy on Mac devices. In this systematic review, we are discussing various Mac architectures and their comparison with various multipliers

A framework enhancement method of deep web data extraction

The solutions suggested for data extraction issue depends on the HTML DOM trees and response pages’ tags being analyzed. Although these solutions can achieve excellent outcomes, they are strongly dependent on HTML specifics. Therefore, to solve this issue this paper proposes a framework of two stages, for proficiently disclosure profound web data. The primary organizes, the proposed system performs “normal crawling” to get significant pages related to the user’s text query. To choose up significant web pages, a strategy is proposed based on the moved forward weighting work (ITF-IDF) is received by the crawler. In the second stage, “data region extraction “is performed to obtain data records. The proposed data extractor exploits the visual features of blocks to extract visual blocks. The strategy is proposed to cluster the visual blocks in a comparable format based on format tree and appearance likeness. Within the cluster with the most elevated weight, the visual blocks are chosen to be extricated as information records. The test comes about the outline that the system proposed is superior to past information extraction works.

Multi-perspective scaling convolutional neural networks for high-resolution MRI brain image segmentation

The occurrence of defect over the soft tissues and nervous system is gradually increasing where Magnetic Resonance Imaging (MRI) is the most preferred method for performing the examination. The brain tumor MR image segmentation performs functionalities like image reconstruction of affected (diseased tissues) and qualitative analysis of infected and normal tissues. The image segmentation accuracy with the physician’s perspective relies over the shape, size, and location of lesions tissues, appropriate diagnostic strategies, and disease determination. The outcomes of this investigation rely over Multi-Perspective Scaling Convolutional Neural Networks (MPS-CNN) model for segmenting brain tumors more effectually and accurately. The multi-scale inputs are given to the proposed CNN model to overcome the necessity to select the appropriate input scale based on the tumor size, neighborhood tumor analysis based on scaled images, and adoption towards various tumor sizes. Therefore, the segmentation accuracy can be increased based on the input multi-scale brain tumor images. Also, the faster segmentation with multi-scaling process accelerates the speed of ensuring real-time segmentation process. This scaling process can effectively segment the brain images in the MRI which enhances the generalization process. It is utilized for predicting the brain lesion tissue of MRI. The simulation is carried out in MATLAB environment. The anticipated MPS-CNN is compared with prevailing approaches like CNN, FCN, U-Net, SegNet, Deep V3, and Deep FCN. And the MPS-CNN shows better trade-off in contrary to other approaches.