Assam Don Bosco University Journals
Not a member yet
795 research outputs found
Sort by
Automated Multimodal Fusion with PDE Preprocessing and Learnable Convolutional Pools
Get PDFThis research paper introduces a novel automated multimodal and Multifocus fusion framework tailored formedical imaging applications. The proposed approach leverages advanced deep learning techniques, incorporating PartialDifferential Equation (PDE) preprocessing and learnable convolutional pools. The algorithm accommodates diversemedical modalities, such as MRI, CT, visual, infrared, and multi-focus images. Through modality-specific preprocessing,modified convolutional layers, and adaptive pooling, the model intelligently fuses information from various sources,enhancing the overall imaging quality. Experimental evaluations demonstrate the effectiveness of the proposed method ingenerating high-quality multimodal medical images, showcasing its potential for improving diagnostic accuracy and clinicaldecision-making
Design And Analysis Of Hanger Irrigation System
Get PDFThis study aimed to evaluate the effectiveness of a newly designed hanger irrigation system in providing consistent water supply for agriculture. Irrigation is a vital component of agriculture, and efforts have been made to increase the irrigated area through surface irrigation projects and groundwater resources. Agriculture plays a critical role in India's economic development, as around 70% of the population relies on it for their livelihoods and essential needs. However, the growing population has led to water scarcity, which poses a significant challenge to the farming sector. Therefore, there is a need to discover alternative irrigation systems that are durable and affordable. To minimize labor costs and ensure uniform water usage, the hanger irrigation system was designed using SolidWorks software, and Finite Element Analysis was employed to enhance vibrational sustainability and reduce deformation in the model. The structure was built using structural steel and bamboo fiber as materials, and vibration analysis was conducted with the ANSYS 19 software to ensure stability. Static analysis was also performed using different materials to improve the system's load-bearing capacity, and cost comparisons were made between bamboo and steel models. The results of the modal and static analyses of different materials were discussed to arrive at a conclusion.Overall, the study highlights the importance of effective water management during irrigation to achieve maximum crop productivity and meet the country's food production goals. The hanger irrigation system has the potential to provide a consistent water supply while minimizing labor costs, making it a viable alternative irrigation system for agriculture
A Performance Analysis and Design of Skewed Intersection at Vivekanand Tiraha (Vidisha) : A Case Study
Get PDFABSTRACT:The increasing traffic volume at Vivekananda Tiraha has increased many problems like congestion ,increasing conflict points, roadside parking hindering traffic movement, oversized vehicles , etc. In order to solve these problems in an efficient and appropriate manner a traffic management system should be designed at the intersection. A performance study of skewed intersections at Vivekananda Tiraha is done to regulate the flow of traffic in a channelized manner. To solve this either a Rotary for a traffic signal can be designed at an intersection.Rotary requires bulging of the weaving area to provide yielding of vehicles coming from Vidisha. It also requires widening of approach from Bhopal end in order to counter problem of skewness, as vehicles coming from Bhopal are not able to see the complete weaving area and tends to move straightwards towards Vidisha.Widening also required for construction of splitter island on undivided Bhopal leg. Thus rotary of proper dimension cannot be constructed due to lack of space at the junction .Thus the best choice we have is installation of a traffic signal with proper markings at each approach .For achieving this objective PCU count has been worked out using traffic control room cameras installed at the intersection. Keywords: Skewed Intersection,Widening,Roadside parking , Conflict Point
Exploring investment prospects in green securities and specialized investments for a greener future
Get PDFWith each passing day, the world is becoming more environmentally conscious. In this changing perspective, investors are also increasingly seeking investment opportunities that prioritize sustainability whether the investment option is in company securities or projects. Green investing, which focuses on companies and assets committed towards the conservation of natural resources is increasingly becoming more popular. This article explores specialized green securities and investment opportunities like green index funds, green mutual funds, green bonds, and green exchange-traded funds (ETFs). It also discusses the challenges of defining and measuring green investments, and the drivers of such investments. It examines the concept of sustainable investing, and environmental, social, and corporate governance (ESG) factors, and how these are impacting the investment landscape. The article hopes to provide readers with an understanding of green securities and specialized investments, and how such investors can contribute to a greener future by focusing on the same.Keywords: Green securities, Specialized investments, Sustainable investing, Environmental, social, and governance (ESG), Socially responsible investing (SRI), Greenwashing
A Study on Sentiment Analysis for Low-Resource Language with Emphasis on Khasi Language
Get PDFSentiment Analysis is an NLP task of finding the opinion and classifies the opinionexpressed in a text according to its polarity (e.g., positive, negative or neutral).Low resource sentiment analysis refers to the task of performing sentimentanalysis on text data with limited annotated data available. This is a commonscenario in many real-world applications, where annotating large amounts oftext data can be time-consuming, expensive, or even impossible. To overcomethis challenge, various methods have been proposed to perform sentiment analysiswith limited annotated data, such as transfer learning, multi-task learning,unsupervised learning, and active learning. In this paper, we look into worksdone on low-resource language sentiment analysis, compare the approaches nothese papers and compiling the success, challenges and pending issues on them.This paper gives an outline of how sentiment analysis is performed and presentsa set of prerequisite before applying sentiment analysis on Khasi Text
Recent advancements in cancer diagnosis using machine learning techniques: a systematic review of decades of research, comparisons, and problems
Get PDFCancer is a non-communicable disease that spreads throughout the body through uncontrolled cell growth. The malignant cell grows into a tumor, which weakens the immune system and disrupts other biological processes. The most frequent types of cancer are breast, lung, and cervical cancer. Several screening methods are available to detect the presence of cancer at various stages. Misdiagnosis can occur in some circumstances owing to human mistakes or incorrect data interpretation, resulting in the loss of human lives. To address these issues, this research study proposes an effective machine learning-based review and diagnosis technique backed by intelligence learning models. Artificial intelligence-based feature selection and classification techniques are used to detect cancer at an earlier stage, improve prediction accuracy, and save lives. In this research study, breast, cervical, and lung cancer datasets from the University of California, Irvine repository was used in these experimental investigations. To train and validate the optimal features minimized by the proposed system, the authors used supervised machine learning approaches. There could be numerous features that may contribute to the occurrence of cancer, it is difficult to pinpoint the specific environmental and other diagnostic features that contribute to it, but it still plays a role in determining cancer occurrence. We can achieve our goal of estimating the probability of cancer occurrences by using machine learning algorithms and frequent diagnostic data. Cancer data sets contain a variety of patient information features, but not all of them are useful in cancer prognosis. In such cases, a feature selection approach plays a crucial role in identifying the relevant feature set. In this research, we compare the effects of feature selection approaches on the accuracy provided by existing machine learning algorithms. We investigated the following machine learning methods for this purpose: Logistic Regression(LR), Naive Bayes(NB), Random Forest(RF), Hoeffding Tree(HT), and Multi-Layer Perceptron(MLP). Information Gain(IF), Gain Ratio(GR), Relief-F(R-F), and One-R(OR) were all evaluated as feature selection strategies.The training and performance models are validated using various accuracy matrices such as accuracy, sensitivity, specificity, f-measure, kappa score, and area under the ROC curve(AUC) using the 10-fold cross-validation approach. The accuracy of the proposed framework was 100%, 100%, and 91.30% on breast, cervical, and lung cancer datasets, respectively. Furthermore, this approach may serve as a versatile tool for extracting patterns from several clinical trials for various forms of cancer conditions
Attitude Towards SIP: An Empirical Examination
Get PDFThe purpose of this study is to examine the attitude of individuals towards systematic investment plans. The study attempted to understand how personality traits of individuals affect their attitude towards the selected investment category. The study also assessed the impact of investment strategy, investment attitude, investment priority and risk capacity affected attitude towards SIP. The findings of the study revealed that openness to experience has an impact on attitudes towards SIP. Whereas investment attitude, agreeableness, conscientiousness, extraversion, emotional stability, risk capacity, and investment priority do not have any impact on attitude towards SIP.Keywords: systematic investment plans, mutual funds, personality traits, risk capacit
Exploring the relationship between Academic Motivation and Achievement: A study of University Students in North-East India
Get PDFThe relationship between academic motivation and academic achievement among university students in North-East India are investigated in this study. This study examines the factors that influence academic motivation, namely intrinsic motivation (Knowledge, Accomplishment, and Stimulation) extrinsic motivation (Introjected regulation, External regulation, and Identified regulation) and “Amotivation” using Vallerand et al. (1992) Academic Motivation Scale as a guide. 462 university students representing a range of academic fields were surveyed to collect the necessary data for the study. Grade point averages, or GPAs, are used to quantify academic success and used as a parameter to judge academic achievement. Descriptive analysis indicated that primary source of motivation for female university students are intrinsic whereas for male it was external. However, there were no significant differences in their motivation and achievements. GPA’s showed positive correlation with all the constructs of academic motivation. The only factor that could significantly predict GPAs were “Amotivation” and intrinsic motivation for accomplishment according to multiple regression analysis.Keywords: Academic Motivation, Academic Achievement, Academic Motivation Scale, “Amotivation”, Intrinsic motivation, extrinsic motivation, North-East India
Applications of Chatbots & AI Image Generators
Get PDFThis research digs into the domain of testing and evaluating chatbots and im-age-generation AI bots which are wide-ranging applications. While these AI systems hold promise in enhancing user experience and operational efficiency, their deployment necessitates rigorous inspection. Chatbots are integral to customer service and demand precision and reliability. Image-generation AI focuses on output quality. To ensure its responsible use, vigorous testing and evaluation are necessary. The research will evaluate the current state of chat-bots and AI image generators, revealing gaps in outcomes and ethical considerations. This study contributes to the responsible and effective deployment of chatbots and image-generation AI bots, to pave the way for their continued integration into our daily lives and businesses
Evaluation of Best Mobile Phone in India using Entropy based TOPSIS, EDAS and CODAS as MCDM methods
Get PDFManufacturers frequently release new mobile phone models with improved features and technical characteristics to keep up with consumers’ changing preferences. This illustrates a classic instance of multi-criteria decision making (MCDM) considering the difficulty of selecting a product with numerous selection criteria and numerous possibilities. To assist customers in making decisions, the major goal of this study is to rank the mobile phone among several viable possibilities. Ten alternate models (under Rs.30, 000 category) from various manufacturers have been chosen based on a website (Gadgets360.com) listing in July 2023 under the heading, ‘Best mobile phones under 30000 in India’. Seven prominent characteristics that serve as distinguishing criteria are picked for ranking purposes. To eliminate any subjective ideas, the weights to these criteria are calculated using the Entropy approach to be applied to MCDM algorithms, namely TOPSIS, EDAS and CODAS to rank these mobile phones. The ranking was effectively attained, and the Spearman Correlation analysis revealed a strong positive correlation between the procedures and the outcomes.Keywords: MCDM, Mobile Phone Ranking, TOPSIS, EDAS, CODAS