srinivaspublication
Not a member yet
667 research outputs found
Sort by
Classification of Breast Ultrasound Images: An Analysis Using Machine Intelligent Based Approach
No full textPurpose: Breast Cancer (BC) is considered as one of the most dangerous diseases, especially in women. The survivability of the patient is a challenging task if the breast cancer is in severe stage. It is very much essential for the early classification of breast ultrasound images (BUIs) into several categories such as benign (BN), malignant (MG) and normal (NL), etc. so that preventive measures can be taken accordingly at the earliest.
Approach: In this work, a machine intelligent (MI) based approach is proposed for the classification of BUIs into the BN, MG and NL types. The proposed approach is focused on the stacking (hybridization) of Logistic Regression (LRG), Support Vector Machine (SVMN), Random Forest (RFS) and Neural Network (NNT) methods to carry out such classification. The proposed method is compared with other machine learning (ML) based methods such as LRG, SVMN, RFS, NNT, Decision Tree (DTR), AdaBoost (ADB), Naïve Bayes (NBY), K-Nearest Neighbor (KNNH) and Stochastic Gradient Descent (SGDC) for performance analysis.
Result: The proposed method and other ML based methods have been implemented using Python based Orange 3.26.0. In this work, 750 TLDIs having 250 numbers of each type such as BN, MG and NL are taken from the Kaggle source. The performance of all the methods is assessed using the performance parameters such as classification accuracy (CA), F1, Precision (PR) and Recall (RC). From the results, it is found that the proposed method is capable of providing better classification results in terms of CA, F1, PR and RC as compared to other ML based methods such as LRG, SVMN, RFS, NNT, DTR, ADB, NBY, KNNH and SGD.
Originality: In this work, a MI based approach is proposed by focusing on the stacking of LRG, SVMN, RFS and NNT methods to carry out the classification of BUIs into several types such as BN, MG and NL. The proposed approach performs better in terms of CA, F1, PR and RC as compared to LRG, SVMN, RFS, NNT, DTR, ADB, NBY, KNNH and SGDC methods.
Paper Type: Conceptual Research
Blockchain Based Privacy and Security Across Cloud in Electric Vehicle Application for Sustainable Development in Industry, Innovation and Infrastructure
No full textPurpose: In this paper we utilise electric vehicle-based cloud edge (EVCE) computing, it is possible to integrate vehicle contexts in a seamless manner. With the increasing use of electric vehicles (EVs) in V2X, this is likely to become a trend. When it comes to information and energy exchanges, a hybrid cloud/edge computing system with EVs as a potential resource infrastructure presents considerable security challenges. In order to find context-aware vehicular applications, the viewpoints of information and energy interactions are taken into consideration. The use of distributed consensus has resulted in the creation of blockchain-inspired energy and data coins, which use the frequency of data contributions and the amount of energy contributions to demonstrate the proof of work for each coin. When it comes to protecting vehicle interactions, the industry, innovation, and infrastructure sectors of Envision2030 are confronted with a number of different security alternatives.
Design/Methodology/Approach: The EVCE computing for mobile cloud architecture to the electric vehicle acting as the edges across the network. The unutilised energy resources, and communication and computational resources of EVs are pooled together and used for other purposes. Mobile cloudlets for electric vehicles are created using VANETs and other interconnected services that gets connected together. When EVs are parked for extended periods of time in different locations, they form a cooperative network of services. Incorporating flexible connected EVs into traditional cloud infrastructures enables contact with remote service providers, local area networks (LANs), as well as other organisations, while operating in the cloud computing mode.
Findings/Result: The primary purpose of a blockchain application is to maintain a record of all of the transactions that have been made by the various members of the network. After the submitted transactions have been confirmed and arranged, a block is formed, and the outcomes of the transactions are put on the blockchain as transaction results.
Originality/Value: When it comes to transactions, HLF three-stage revolutionary design, dubbed execute-order-validate, is reliant on the preceding steps of the transaction to function properly. Because the actual throughput is close to 100%, a 100 TPS transmit rate is achievable and sustainable
Paper Type: Experimental Researc
Analysis of Significant Electrocardiogram (ECG/EKG) Variations in Psychological Stress
Get PDFPurpose: Mental stress and other psychosomatic disorders have been linked to an increased risk of sudden cardiac death in population studies. There hasn't been a thorough examination as to whether emotional or physical stresses might cause sporadic ventricular arrhythmias in vulnerable patients. An outsized and mounting body of discovery shed light on the fact that internal health is interrelated to risk factors for heart complaint before an opinion of an internal health complaint and through treatment. These things can arise both directly, through natural pathways, and laterally, through parlous health actions. People who are passing through clinical depression, anxiety disorders, common and general stress syndromes, and indeed post-traumatic stress disorder commonly known as PTSD over an absolute period of your occasion may observe definite physiological alterations in the body, similarly, as a highly enlarged cardiac reactivity such as augmented vital signs and elevated blood pressure, deducted or condensed blood inflow directly to the center, and heightened or highly raised amount of an organic chemical compound called cortisol. Over time, these physiologic processes may generate calcium particle depositions or buildup within the normal organic pathways. It may also manifest events of body metabolic dysfunction as well as cardiac conduction problems. Substantiation shows that many physiological and psychiatric/psychological diseases -similar to chronic clinical depression, psychological stress, and PTSD can appear after any cardiac event regardless of its severity.
Objective: The focal objective of this article is to identify psychological stress, its influence on cardiac problems such as cardiac arrhythmia, and its symptomatic manifestations on an electrocardiogram. Apart from that, this paper also focuses on the area of how ECG changes due to psychological distress. Another objective of this paper is to provide vivid information about psychological stress and its link with acute and chronic cardiac pathologies. Laymen should know the fact that the mind and the body are linked with each other and if the mind is distressed for a long time will affect the health condition of the physical body also.
Design/Methodology/Approach: To build the paper, mostly secondary information has been used from various sources such as clinical literature, journals, websites, etc. Primary information has also been used to increase the accuracy and reliability of the paper. Primary data have been taken from neuropsychologists, cardiologists, clinical psychopathologists, and behavioral medicine specialists. Based on all these databases, systematic and scientific clinical analysis of information has been done to avoid any mistakes and errors.
Findings/Result: In people with ICDs, stress and physical exercise might cause ventricular rhythm abnormalities. Future studies into medicines that prevent these stimuli' responses might reduce ventricular arrhythmias and upsets in some of these patients. People with type A personalities should try to control or adjust their innate personality and character to reduce the vulnerability to develop any kind of cardiac arrhythmia or any other cardiac pathologies. All ECG variations and arrhythmias are not related to psychological stress rather it needs differential diagnosis to rule out any other underlying problems. A thorough differential investigation is suggested to rule out whether the cardiac problem is due to psychological stress or not.
Originality and value: A comprehensive analysis and interpretation have been made to cover the concerned topic of study and make information more reliable and valid. A new initiative is taken to provide information about the mind and heart link.
Paper Type: Secondary clinical report analysis/interpretive paper 
Lockdown: The Most Effective Preventive Measurement of Corona Virus Pandemic Disease through Social Distancing
No full textPurpose: The lifestyle of people throughout the world has been affected exceptionally due to the severity of COVID-19 pandemic disease. Different steps to prevent this pandemic disease have been taken to protect the entire nation by the government of the affected countries. Several research works are going on to forecast on the different cases of the disease like new affected cases, new death cases. But the researchers have not worked for the Stringency Index on which transmission of the virus mostly depends till now.
Objective: Decision of maintaining strict lockdown and partial lockdown are the most effective preventive measure to resist this pandemic disease by breaking the cycle of transmission through social distancing.
Methodology: In our proposed work we have introduced the reality. Data from various sources on this disease for most affected countries like India have been collected by the authors. They have started an experiment on that data and ultimately have prepared a mathematical model to correlate between basic reproduction rate and the stringency index.
Results: The authors have calculated average new infected cases, maximum new infected cases and minimum new infected cases which are highly associated with the stringency index. Average death cases, maximum death cases, and minimum death cases are also been calculated as these are also associated with the stringency index.
Conclusion: Depending on the result of experiment of our work government of India as well as World Health Organization can take a decision for maintaining an effective lockdown to protect the entire nation from this deadlier disease
Development of Fashionable Products through Online Retailing: A Case Study on Amazon and Flipkart
No full textPurpose: The internet has concise the world bringing global community to very close. It helps to communicate information in a cheaper, quicker, and simpler form. At present era, the internet enables fashion businesses to reach out to each and every corner of the world without making significant investments. Fashion companies might have their own website to promote and sell their products or they can also exhibit their products on e-commerce and social networking platforms, drawing a larger number of buyers. Fashion houses can use online media to sell their items all over the world at a low cost. The main purpose of this study is to see the development of fashion products through online retailing. The author mainly considered Amazon and Flipkart for the study.
Methodology: This qualitative research is based on secondary data. Secondary data is gathered from the research papers published in reputable journals, newspapers, articles. Financial information was collected from the annual reports of Amazon and Flipkart and also census reports.
Findings: The major findings of the study are: Male customer expressed a greater desire to purchase fashionable products, there is a healthy competition between both Amazon and Flipkart, Celebrities are being used by Amazon and Flipkart to promote their fashionable products, Flipkart's Recommendation module and Amazon's Stylist assist users to discover more and more fashion and other products similar to the ones they've looked at. It has one of the greatest conversions and contributes significantly to the company's revenue and units.
Practical Implication: This study will be helpful to know the different fashionable products offering by the Amazon and Flipkart companies and marketing channels using by these two companies to market their fashion products.
Paper Type: Company Case Stud
Conveyor Belt Speed Control Through CAN BUS in CoppeliaSim using Arduino Mega2560
Get PDFPurpose: CAN Bus is a robust way to communicate inter-device Communication. Primarily it is used in the vehicle. But now, it is also used in various industrial automation fields. Among different branded robots, they use CAN-bus to control the robot movement. When the new researchers integrate the can bus into their project, they need to spend time running and handling the device through the CAN bus. This research work is basically for those trying to integrate the CAN bus into their project in a short period. Here, we briefly describe the CAN bus protocol first, then go through a practical experiment to better understand it. In our experiment, we feed the Analog value as a speed profile through the CAN bus to the CoppeliaSim virtual environment to see the speed variation of the simulated conveyor belt upon rotating the potentiometer. The complete project code and demo video are available on Github. The interested researcher can download and experiment on it.
Design/Methodology/Approach: This research work demonstrates how to exchange data through CAN bus between a virtual and a natural environment. We created a virtual environment using the CoppeliasSim robot simulator. Inside the simulator, we add a conveyor belt. Using c#, we created a bridge application that translates the data between the simulator and the natural environment outside it. We used two Arduino Mega 2560 boards and two MCP2515 based TJA1050 popular CAN driver modules. The CoppeliaSim requests data to the remote master through the bridge application and CAN bus. The remote master reads the analog value and sends it back to the simulator through the local master. CoppeliaSim changes its conveyor belt speed by parsing the data and converting it to the speed value.
Findings/Result: We can find some concepts and procedures to control the virtual elements from the external world through the CAN bus. We can convert any environmental analog parameter into digital form and display it locally or remotely inside the simulator. We can build the digital twins used to process monitoring in the industrial automation field following this experiment.
Originality/Value: Most CAN bus-related documents lack a practical approach or an accumulation of workable summaries. We demonstrate the CAN bus differently in this research work. This paper is an entirely practical-oriented demonstration. This is the unique approach to controlling the virtual element from the real world through the CAN bus. The new researcher can get helpful references to integrate the CAN bus into their project.
Paper Type: Experimental-based Research
A Decentralised Research Article Publishing and Archiving System
No full textBackground/Purpose: Research papers provide the path for the expansion of knowledge, allowing for the emergence of new information and the avoidance of duplication of previous research effort. Researchers use their paper to convey their findings to the rest of the world. However, owing to problems such as processing fees from journals, an inefficient review procedure, a lengthy processing time, and the closure of journals, the research community has encountered a major hurdle. In order to overcome this issue, we propose in this study a system known as the Open Platform for Research Article Sharing (OPRAS), which would allow the author to publish his or her paper utilizing a peer-to-peer (P2P) architecture.
Objective: To get an understanding of the research article publication process and the issues it faces, in order to propose OPRAS, a new system that will employ a peer-to-peer architecture to share research articles.
Design/Methodology/Approach: Data from websites, research papers, and other sources are collected, analysed and presented using ABCD analysis.
Findings/Results: With the help of research articles that are published in journals, researchers can tell the world about their work. But authors can't publish their findings because of different problems, which makes it hard for society to learn new things. In this paper, a method for a new system called Open Platform for Research Article Sharing (OPRAS) utilizing the P2P architecture was put forward after looking at the different steps and problems that come up when publishing an article.
Originality/Value: A new system has been presented based on the relevance of research articles and an understanding of the problems in publishing research papers, which will attract the attention of the research community and lead to additional improvements in the proposed technique.
Paper Type: Research Paper
Causes and Effects of Design Change of Construction Projects
No full textPurpose: Design is the mother of all construction as it is not only technical but also strategic process for competitiveness. In last decade, enormous bridge projects have been designed in Nepal but not all of them have been implemented. The causes of bridge design changes, and their effects on projects in terms of cost and time schedule is found to be complex and are influenced by numerous interrelated factors. This research focuses on the causes, effects and impacts of design change/reviews in bridge projects designed and constructed under Bridge Branch, Department of Roads (DoR).
Design/Methodology/Approach: Five case studies were taken along with schedule questionnaire to contrast the causes, effects and impacts identified from questionnaire survey. The data obtained from the questionnaire were analyzed using the Relative Importance Index (RII) for finding the importance of each causes, effects, and impacts.
Findings/Result: The design change was found to be done mostly in the foundation of the bridges. Sometime the redesign was done for change in scope and location of the bridge due mostly due to social and political interference and interest rather than value engineering. The Consultant was the main origin agent for design changes of bridge projects as they were the most responsible for the detail survey, soil investigation and design and estimate of the bridge whereas the client found to be second origin agent for design change due to lack of required data, change of plans or scope. The major causes for the bridge design change were Non-complaint design with site requirement, Errors in design, Differing site conditions, unforeseen problems and Inadequate working details. The top three common effects of design changes are time overrun, cost overrun and requirement of additional specialist/equipment/personnel.
Originality/Value: It is basic research. This study helps in motivating and creating awareness among the design professionals working in design review which will create the influence to overcome issue of design change strategically.
Paper Type: Ex-Post Facto Researc
Planning Assessment of Transport System: A Case from Nepal
No full textPurpose: Road infrastructure is considered as “the infrastructure for infrastructure”. Planning assessment of the transport system is done for assessing and planning the present road and transport infrastructures and facilities within the municipality and the surrounding local bodies. The research aims to analyse the planning of the transport system of Devchuli Municipality for recommending pragmatic solution of transport problems.
Design/Methodology/Approach: Devchuli Municipality is located in Nawalparasi East district of Gandaki Province in Nepal. Municipality is divided into 17 wards, covers 112.72 km2 area. Municipality is populated with different castes and religions with population of 49,637. It consists of 12025 households with population density of 440 persons per sq.km and 4.13 people per household. Data were collected using Official document, Key informant interview, Field Survey, and observation and analyzed using Content, Origin and Destination (OD) Survey, Road Inventory Survey, Classified Vehicle Count Survey, Public Transport and Services Study.
Findings/Result: Municipal Transport Master Plan (MTMP) started with the setup of Municipal Road Coordination Committee (MRCC) and the collection of demand and inventory of road within the municipality. Road inventory survey was done and the length of the roads collected is about 339.67 km (without SRN) From the sample data it is found that nearly 11% of the mode of transportation is shared by active road users hence footpath is proposed on the roads. Visionary city development and Indicative Development Potential Plan is studied with which the existing and potential market center/service centers (key growth centers) and the areas having various development potentials such as agro-based industries, high value cash crops and tourism.
This study also formulated the road hierarchy for the various roads namely Class A, B, C and D. Class C and D basically deals with access while Class A and B basically deal with mobility and accessibility to higher services. Total cost for the required interventions proposed is calculated based on the rates of ToR for 5 years and was found to be approximately 794 million rupees.
Originality/Value: It is action research. This study helps to develop a Visionary city development plan for Pragmatic solutions for issues of transport.
Paper Type: Ex-Post Facto Researc
A Literature Review and Research Agenda on Explainable Artificial Intelligence (XAI)
Get PDFPurpose: When Artificial Intelligence is penetrating every walk of our affairs and business, we face enormous challenges and opportunities to adopt this revolution. Machine learning models are used to make the important decisions in critical areas such as medical diagnosis, financial transactions. We need to know how they make decisions to trust the systems powered by these models. However, there are challenges in this area of explaining predictions or decisions made by machine learning model. Ensembles like Random Forest, Deep learning algorithms make the matter worst in terms of explaining the outcomes of decision even though these models produce more accurate results. We cannot accept the black box nature of AI models as we encounter the consequences of those decisions. In this paper, we would like to open this Pandora box and review the current challenges and opportunities to explain the decisions or outcome of AI model. There has been lot of debate on this topic with headlines as Explainable Artificial Intelligence (XAI), Interpreting ML models, Explainable ML models etc. This paper does the literature review of latest findings and surveys published in various reputed journals and publications. Towards the end, we try to bring some open research agenda in these findings and future directions.
Methodology: The literature survey on the chosen topic has been exhaustively covered to include fundamental concepts of the research topic. Journals from multiple secondary data sources such as books and research papers published in various reputable publications which are relevant for the work were chosen in the methodology.
Findings/Result: While there are no single approaches currently solve the explainable ML model challenges, some model algorithms such as Decision Trees, KNN algorithm provides built in interpretations. However there is no common approach and they cannot be used in all the problems. Developing model specific interpretations will be complex and difficult for the user to make them adopt. Model specific explanations may lead to multiple explanations on same predictions which will lead to ambiguity of the outcome. In this paper, we have conceptualized a common approach to build explainable models that may fulfill current challenges of XAI.
Originality: After the literature review, the knowledge gathered in the form of findings were used to model a theoretical framework for the research topic. Then concerted effort was made to develop a conceptual model to support the future research work.
Paper Type: Literature Review