iosr-JCE   Volume-26 ~ Issue-3 ~ May - Jun. 2024

Abstract: Matching research supervisors with suitable schol- ars is paramount for cultivating effective academic partnerships. Nevertheless, conventional techniques frequently lack efficacy and depend on subjective evaluations. The present study advocates for a machine-learning strategy to automatize and enhance this matching procedure. By utilizing a variety of data sources such as publications, research interests, and expertise, sophisticated algo- rithms like collaborative filtering and natural language process- ing are employed. Our integrated computational........

Index Terms—Machine Learning, Artificial Intelligence, Re- search Platform, Academic Research

...

Abstract: This investigation undertakes a robust quantitative approach, centering on the utilization of the Support Vector Machine (SVM) classification algorithm to accurately predict the health risk levels of pregnant women. By employing SVM, renowned for its efficacy in classification tasks, the study aims to provide a reliable means of forecasting disease risks among expectant mothers. The initial dataset exhibited a modest accuracy rate of 60%, which saw a significant improvement to 79% after undergoing meticulous preprocessing procedures. These preprocessing....

Keywords:Support Vector Machine, Pregnant Women Health Risk, Predictive Modeling

[1] Wanriko, S., Hnoohom, N., Wongpatikaseree, K., Jitpattanakul, A., & Musigavong, O. (2021, March). Risk Assessment Of Pregnancy-Induced Hypertension Using A Machine Learning Approach. In 2021 Joint International Conference On Digital Arts, Media And Technology With Ecti Northern Section Conference On Electrical, Electronics, Computer, And Telecommunication Engineering (Pp. 233-237). Ieee.(Doi: 10.1109/Ectidamtncon51128.2021.9425764).
[2] Hossain, M. I., Habib, M. J., Saleheen, A. A. S., Kamruzzaman, M., Rahman, A., Roy, S., ... & Rukon, M. R. (2022). Performance Evaluation Of Machine Learning Algorithm For Classification Of Unintended Pregnancy Among Married Women In Bangladesh. Journal Of Healthcare Engineering, 2022. (Doi: 10.1155/2022/1460908).
[3] Chelsea, M. Y., & Rosa, P. H. P. (2024). Classification Of Delivery Type Of Pregnant Women Using Support Vector Machine. In E3s Web Of Conferences (Vol. 475, P. 02015). Edp Sciences. (Doi:Https://Doi.Org/10.1051/E3sconf/202447502015).
[4] Javed, F., Gilani, S. O., Latif, S., Waris, A., Jamil, M., & Waqas, A. (2021). Predicting Risk Of Antenatal Depression And Anxiety Using Multi-Layer Perceptrons And Support Vector Machines. Journal Of Personalized Medicine, 11(3), 199. (Doi:
Https://Doi.Org/10.3390/Jpm11030199).
[5] Mou, A. D., Barman, Z., Hasan, M., Miah, R., Hafsa, J. M., Das Trisha, A., & Ali, N. (2021). Prevalence Of Preeclampsia And The Associated Risk Factors Among Pregnant Women In Bangladesh. Scientific Reports, 11(1), 21339.(Doi:
Https://Doi.Org/10.1038/S41598-021-00839-W).

Abstract: Image generation has advanced significantly as a result of the generative adversarial networks' (GANs) quick development. Still, the growing realism of generated images as demonstrated by models like StyleGAN and BigGAN, raises concerns regarding national security, social stability, and personal privacy. Through our analysis, we've identified the perceptual degradation issue in existing attack methods when directly applied to these advanced GAN-generated images. Consequently, Considering visual perception, we have created a novel adversarial assault strategy specifically designed for image anti-forensics, especially in the altered color domain. Despite its simplicity.....

Keywords: Generative Adversarial Networks ,Object Detection, Detection Capabilities, BigGAN, DCGAN, Convolutional Neural Network (CNN)

...

Abstract: Large companies frequently employ two well-liked software development approaches: Scrum and XP (Extreme Programming). Enhancing teamwork, output, and the caliber of software outputs are the goals of both frameworks. This study contrasts and compares Scrum with XP in major enterprises, emphasizing important queries and factors to take into account before using either methodology. According to the statistics, scrum is the methodology most commonly employed in major firms. Whether to embrace XP or Scrum depends on the particular needs and needs and context of an organization, and each has pros and cons. Certain success factors have been established in the context of both approaches.

Keywords: Scrum, Extreme programming, large, organizations, adoption, success

...

Abstract: Digital transformation represents a major challenge for the financial sector in Africa, offering both growth opportunities and significant challenges. This study focuses on analyzing the specific challenges faced by African financial institutions during their transition to digital, based on an in-depth case study of the Caisse Populaire d'Épargne et de Crédit de Guinée (CPECG) - Yètè Mali. By examining the experiences and practices of this institution, the study aims to identify the most common obstacles and the strategies adopted to overcome them, thereby providing valuable insights for other actors in the financial sector in Africa.

Keywords: Digital transformation, financial sector, Africa, CPECG-Yètè Mali, challenges, opportunities, case study.

...

Abstract: The agriculture sector plays a key role in the economic development of India. The task of fruit grading is vital in the agricultural industry because there is a great demand for high-quality fruits in the market. However, fruit grading by humans is inefficient, labor-intensive, and prone to error. The automated grading system not only speeds up the time of processing but also minimizes errors. The fruit grading system is a method used to categorize fruits based on various factors such as size, shape, color, texture, and overall quality. This system ensures.....

Keywords: Fruit Grading, Computer vision, Frontend and Backend, Machine Learning, CSS, HTML, Python, Fruit cate- gory, Database, Grading, Agriculture, Distributors, Packaging.

...

Abstract: Large companies frequently employ two well-liked software development approaches: Scrum and XP (Extreme Programming). Enhancing teamwork, output, and the caliber of software outputs are the goals of both frameworks. This study contrasts and compares Scrum with XP in major enterprises, emphasizing important queries and factors to take into account before using either methodology. According to the statistics, scrum is the methodology most commonly employed in major firms. Whether to embrace XP or Scrum depends on the particular needs and needs and context of an organization, and each has pros and cons. Certain success factors have been established in the context of both approaches

Keywords: Scrum, Extreme programming, large, organizations, adoption, success.

...

Abstract: In today's world, a precise method for predicting cardiac disease is essential with emotionally supportive system. To determine if a patient has a cardiac illness or is in a normal condition, data mining techniques are frequently used. In this work, a prediction model for forecasting cardiac diseases is suggested using the Naive Bayes (NB) and Random Forest algorithms. Extensive testing on a large-scale coronary health dataset validates the model's better performance compared to current methods, which is primarily reflected in enhanced prediction accuracy.

Key Word: Data Mining, Naive Bayes, Random Forest

...

Abstract: Malayalam is a low resource language spoken by the people of Kerala, a state of southern India. There is a rapid advancement in the ASR since the last few years due to the emerging of advanced machine learning techniques and tools. Being a regional language Malayalam speech recognition still faces major challenges like lack of annotated speech corpus and language models. This paper discusses major research works and language modeling methods in the area of Automatic Speech Recognition of Malayalam language.
Background: The purpose of the paper is to review recent advancements in Automatic Speech Recognition of Malayalam......

Keywords: Automatic Speech Recognition; Malayalam Language Model; Generative model; Discriminative model; End to End Model.

[1] Rashmi C R ,Review Of Algorithms And Applications In Speech Recognition System, International Journal Of Computer Science And Information Technologies, Vol. 5 , No.4 , Pp. 5258-5262, 2014.
[2] A Review On Speech Recognition Technique, International Journal Of Computer Applications, Vol 10, No.3, Pp. 16-24. 2010.
[3] Mohamed Hashim Changrampadi, A. Shahina, M. Badri Narayanan, A. Nayeemulla Khan, End-To-End Speech Recognition Of Tamil Language, Intelligent Automation & Soft Computing,Vol. 32, No.2, Pp. 1309-1323,2022.
[4] Manohar K, Jayan A R And Rajan R,Mlphon: A Multifunctional Grapheme-Phoneme Conversion Tool Using Finite State Transducers. Ieee Access, Vol.10, Pp. 97555–97575,2022.
[5] "Sharika - Malayalam Speech Recognition System", Shyam.K, Icist, 2007.

Abstract: Deep learning, a powerful tool for learning, has evolved significantly due to the development of recurrent neural networks and perceptrons. However, optimal training requires overcoming challenges such as data preparation, optimization schemes, regularization processes, and hardware acceleration. Academics are now exploring methods to apply transfer learning, a contemporary deep learning technique, to the analysis of structured data in healthcare and finance. Ethical issues such as privacy and data bias are being addressed through self-supervised and federated learning. Hybrid models combining deep learning with other artificial intelligence techniques,.....

Keywords: Deep Learning Models, GEN AI, Deep Fake video detection and CNN

[1]. Andrews, E. L. (2019). How fake news spreads like a real virus | Stanford School of Engineering. Stanford ENGINEERING.
[2]. Apuke, O. D., & Omar, B. (2020). Fake news and COVID-19: modelling the predictors of fake news sharing among social media users. In Telematics and Informatics.
[3]. Durall, R., Keuper, M., Pfreundt, F. J., & Keuper, J. (2020). Unmasking DeepFakes with Simple Features. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. [4]. Kumar, S., Singh, S., & Kumar, J. (2019, January). Gender classification using machine learning with multi-feature method. In 2019 IEEE 9th Annual Computing and Communication Workshop and Conference (CCWC) (pp. 0648-0653). IEEE.
[5]. Prasadi Peddi and Dr. Akash Saxena (2015), The Adoption of a Big Data and Extensive Multi-Labled Gradient Boosting System for Student Activity Analysis, International Journal of All Research Education and Scientific Methods (IJARESM), ISSN: 2455-6211, Volume 3, Issue 7, pp:68-73