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

Abstract: Image segmentation plays a crucial role in medical image analysis, aiding in tasks such as disease detection, diagnosis, and treatment planning. This review paper synthesizes recent advancements in image segmentation techniques, focusing on applications in medical imaging, particularly in the detection and analysis of brain tumors and skin cancer. Drawing from a selection of seminal papers spanning from 1997 to 2021, we explore various methodologies, including traditional approaches like k-means clustering and novel techniques such as deep convolutional neural networks (CNNs) with transfer learning........

Index Terms—Image Segmentation, Medical Imaging, Brain Tumor Detection, Deep Learning

[1] Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., & Süsstrunk, S. (2012). Slic Superpixels Compared To State-Of-The-Art Superpixel Methods. Ieee Transactions On Pattern Analysis And Machine Intelligence, 34(11), 2274–2282.
[2] Acharya, J., Gadhiya, S., & Raviya, K. (2013). Segmentation Techniques For Image Analysis: A Review. International Journal Of Computer Science And Management Research, 2(1), 1218–1221.

Abstract: This study outlines a comparative studies on Vulnerabilities Assessment tools in security systems, the Research deepen into network reconnaissance and vulnerability assessment methodologies within Windows environments. Its core aim is to increase comprehension and practical profinciency by outlining structured objectives about network tracerouting, host discovery, port and service identification, OS profiling, and vulnerability analysis. Within the dynamic circumstances of cyber threats, the research underscores the urgency of practical defense measures and the fundamental role of defensive identification and mitigation of vulnerabilities. It serves as a significant step towards providing individuals with essential cybersecurity expertise, addressed towards protecting network infrastructures against any potential exploits.

Keywords: Vulnerability Assessment, Network Reconnaissance, Vulnerability Scanning Tools, Practical Implementation.

[1] Kyriakos Kritikos, Kostas Magoutis, Manos Papoutsakis, Sotiris Ioannidis, "A Survey On Vulnerability Assessment Tools And Databases For Cloud-Based Web Applications," Elsevier.Com, [Online]. Available: Www.Elsevier.Com/Journals/Array/2590-0056/Open-Access-Journal.
[2] Dipali N Railkar, Shubhalaxmi Joshi "A Study On Vulnerability Scanning Tools For Network Security", February 2022.
[3] Rio Armando, Igagkom Agnam Melyantara, Rizma Elfariani, Desy Fitri Aulia Latuconsina, Muhammad Nasrullah "It Support Website Security Evaluation Using Vulnerability Assessment Tools", December 2022.
[4] Https://Www.Virtualbox.Org/
[5] Https://Www.Manageengine.Com/

Abstract: This paper proposes a machine learning-based ap- proach to predict churn in telecom systems, aiming to provide insights into future customer retention strategies. This research paper investigates the efficacy of three prominent machine learn- ing algorithms, XGBoost, Random Forest, and Decision Trees, in predicting churn within the telecom industry. Leveraging a rich dataset from a telecom company, this study compares the performance of these algorithms in terms of predictive accuracy and computational efficiency. Through comprehensive experimentation and evaluation, the paper sheds light on the strengths and limitations of each algorithm in churn prediction. The findings provide valuable insights for telecom companies aiming to optimize their customer retention strategies..

Keywords: Churn prediction, Telecom systems, Machine learning algorithms, XGBoost, Random Forest, Decision Trees, Comparative analysis, Customer retention, Predictive modeling, Churn Prediction.

[1] Dr. O. Rama Devi, Sai Krishna Pothini," Customer Churn Prediction Using Machine Learning: Subcription Renewal On Ott Platforms", Ieee Xplore Part Number: Cfp23bc3-Art; Isbn: 978-1-6654-5630-2, 978- 1-6654-5630-2/23/$31.00 2023 Ieee
[2] Qiuying Chen, Sang-Joon Lee," A Machine Learning Approach To Predict Customer Churn Of A Delivery Platform", 2023 International Conference On Artificial Intelligence In Information And Communi- Cation (Icaiic)—978-1-6654-5645-6/23/$31.00 2023 Ieee — Doi: 10.1109/Icaiic57133.2023.10067108
[3] Weijie Yu, Weinan Weng," Customer Churn Prediction Based On Machine Learning" 2022 4th International Conference On Artificial Intelligence And Advanced Manufacturing (Aiam), 978-1-6654-6399- 7/22/$31.00 C2022 Ieee
[4] Brandusoiu I, Toderean G, Ha B. Methods For Churn Prediction In The Prepaid Mobile Telecommunications Industry. In: International Confer- Ence On Communications. 2016. P. 97–100.
[5] Huang F, Zhu M, Yuan K, Deng Eo. Telco Churn Prediction With Big Data. In: Acm Sigmod International Conference On Management Of Data. 2015. P .607–18.

Abstract: Background: The convergence of modern technology and supply chain operational dynamics has shaped the fabric of today's freight transportation practice and made the role of electric vehicles (EVs) profoundly significant in regular use in business operations. In addition to the expanding prevalence of EVs and charging infrastructures for medium and heavy-duty supply chain transport systems, it challenges the business community for deployment purposes. Moreover, these intelligent transport systems for modern supply chain organizations delve into the heart of a transformative realm, offering opportunities for academics and practitioners to explore the tools, strategies, methodologies, and training......

Keywords: Business Operation; Electronic Vehicles; Freight Transport; Supply Chain Management; Security Vulnerabilities; Security Solutions.

[1] Strauss. M. "Deployment Of EU Electric Vehicle Charging Station Too Slow, Auditors Say". Available Online: Https://Www.Reuters.Com/Article/Us-Eu-Autos-Electric-Charging/Deployment-Of-Eu-Electric-Vehicle-Charging-Stations-Too-Slow-Auditors-Say-Iduskbn2c023c/ (Accessed On 15 February 2024).
[2] Geotab. Electric Vehicle Trends In 2020: Top 6 Factors Impacting Fleet Electrification; Geotab: Oakville, ON, Canada, 2020.
[3] Zachary. S. "16 Countries Now Over 10% Plugin Vehicle Share, 6 Over 20%",
Https://Cleantechnica.Com/2021/09/05/16-Countries-Now-Over-10-Plugin-Vehicle-Share-6-Over-20/, 2021.
[4] Madhani A. And Krisher, T. "Biden Pushes Electric Vehicle Chargers As Energy Costs Spike,"
Https://Www:Usnews:Com/News/Business/Articles/2021-11-17/Biden-Pushes-Electric-Vehicle-Chargers-As-Energycosts-Spike, Nov. 2021.
[5] Gordon, P. "Netherlands Aims To Ban Conventionally-Fueled Vehicles By 2050," Https://Www:Smart-Energy:Com/Industry-Sectors/Electricvehicles/Netherlands-Aim-To-Ban-Conventionally-Fueled-Vehicles-By-2050/, Jan 2019

Abstract: The concept of using ocean models to predict person- ality traits based on machine learning (ML) and artificial intelli- gence (AI) is an emerging field in the intersection of psychology, computer science, and physics. The Ocean Model theory suggests that personality traits can be viewed as interconnected waves or patterns that ebb and flow over time, much like the ocean's tides. By analyzing these patterns and fluctuations using ML and AI algorithms, it may be possible to predict an individual's personality traits with a high degree of accuracy. This paper presents an overview of the Ocean Model theory, and its potential applications in personality assessment having two unique modules with a comparative study of algorithms, which can be used for streamlining the recruitment process.

Keywords: Machine learning, K Means Clustering, Logistic Regression.

[1] Allan Robey, Kashish Agarwal, Keval Joshi, Shalimali Joshi (2019).Per- sonality Prediction System through CV Analysis, IRJET vol 06 issue 02, e-ISSN-2395-0056, p-ISSN-2395-0072
[2] Devesh Agarwal, Mr. M. Karthikeyan(2022). PERSONALITY PREDIC- TION USING MACHINE LEARNING, IRJMETS Vol:04 /Issue:04/ April-2022, e-ISSN-2582-5208
[3] Atharva Kulkarni, TanujShankarwar, SiddharthThorat (2021). Personal- ity Prediction Via CV Analysis using Machine Learning, IJERT Sep 2021 Vol 10 Issue 09, ISSN – 2278-0181
[4] M. Kalghatgi, M Ramannavar, and Dr. N. S. Sidnal, "Neural Network approach to personality prediction based on the Big-Five Model" in IJIRAE, vol2 issue 8, August 2015, pp 56-63.
[5] J. Zubeda, M. Shaheen, G. Narsayya Godavari, and S. Naseem "Resume Ranking using NLP and Machine Learning", unpublished

Abstract: Integrating machine learning (ML) models into backend systems is increasingly vital for driving innovation across industries. This integration enhances user engagement, operational efficiency, and data-driven decision-making. Despite its benefits, challenges such as scalability and maintenance persist, requiring careful planning and expertise in software development and ML. This paper explores the landscape of integrating ML models into backend......

Keywords: Machine Learning Integration, Backend System Architecture, ML Deployment Challenges, Scalability of ML Models, Backend Frameworks

[1]. David, K. (2023). Incorporating Machine Learning Models Into Node.Js Backend Systems
Https://Medium.Com/@Kokodavidclaus/Incorporating-Machine-Learning-Models-Into-Node-Js-Backend-Systems-448394bb08cf.
[2]. Alwis, L. W. (2022). Integrating Machine Learning Models Into Your Mern App
[3]. Stack Overflow. (2020). How To Put Machine Learning Models Into Production [Stackoverflow.Blog].
[4]. Amazon Web Services. (2023). Integrating Machine Learning Models Into Your Java-Based Microservices [Aws.Amazon.Com]
[5]. Arif C., Michael C, And Bryce H. (2019). Global Ai Survey: Ai Proves Its Worth, But Few Scale Impact.Mckinsey Analytics, 2019.

Abstract: Through the use of computer vision techniques, then Automated Attendance System utilizing Image Processing project seeks to streamline then current attendance-taking procedure. The system takes a picture and uses image processing algorithms to automatically register people's attendance in a variety of venues, including meetings, events, and classes. By using facial recognition technology, the systems records attendance without requiring manual entry, which lowers the possibility of human error. The system makes sure that attendance is managed accurately and efficiency by using sophisticated image processing algorithms. This increases the overall productivity and dependability of the attendance tracking process. This project improves time management and overall administrative work efficiency in a variety of ways by automating monitoring system.

Keywords: Image Processor Algorithms, python, CNN.

[1] Vaibhav V. Mainkar, Murlidhar Shriram Samant, Dhanashri Vishnu Patil, Priyanka Arun Pednekar, Harshad Vijay Shinde "Attendance Monitoring System Using Image Processing" International Journal Of Information And Computing Science, Volume 2, Issue 2 February 2018, Issn No: 09972-1347.
[2] Aziza Ahmedi, Dr Suvarna Nandyal "An Automatic Attendance System Using Image Processing" The International Journal Of Engineering And Science (Ijes), Volume 4, Issue 19 October 2015, Issn(E): 2319-1813, Issn(P): 2319-1805.
[3] Soundarya S, Ashwini P, Rucha W, Gaurav K "A Review Pape R On Attendance Management System Using Face Recognition" International Journal Of Creative Research Thoughts (Ijcrt), Volume 9, Issue 11 November 2021, Issn: 2320-2882.
[4] Serign Modou Bah, Fang Ming "An Improved Face Recognition Algorithm And Its Application In Attendance Management System" Elsevier, Issue 26 December 2019, Issn: 2590-0056.
[5] Md Massod Ahmad, Sahaj Putra, Kaushik Dev, Saleem Khan Mulla "Multiple Face Recognition Using Matlab For Attendance Management" International Research Journal Of Engineering And Technology (Irjet), Volume 7, Issue 04 April 2020, E-Issn: 2395-0056, P-Issn: 2395-0072.

Abstract: Intrusion detection is one of the important ap- plications of Wireless Sensor Networks (WSNs).Prior research indicated that the barrier coverage method combined with Mobile Sensor Networks (MSNs) can enhance the effectiveness of intrusion detection by mitigating coverage holes commonly appeared in stationary WSNs. However, the trajectories of moving sensors and moving intruders have not been investigated thoroughly, where the impact between two adjacent moving sensors and between a moving sensor and a moving intruder are still under- determined. In order to address these open problems, in this paper, we firstly discuss the virtual potential field between sensors as well as between sensors and intruders. We then propose to formulate the mobility pattern.....

Index Terms—Mobile sensor networks, intrusion detection.

.....

Abstract: Background: The study present a cryptographic secure engineered intrusion prevention architecture for wireless sensor networks, aiming to extend the network's lifetime through lightweight, secure data routing amongst the network's mobile nodes. The objectives of the study are to; conduct a systematic review of security solutions to address potential attacks on wireless sensor networks; and to propose an algorithm that combines energy-aware routing and secure transmission using clustering along with cryptography....

Keywords: clustering, digital envelopes, digital signature, intrusion prevention, Public Key Infrastructure, secure data routing, secure transmission

[1] Haque, M. M., Et Al. "An Asymmetric Key-Based Security Architecture For Wireless Sensor Networks." Ksii Transactions On Internet And Information Systems 2, No. 5 (2008): 265–279.
[2] Hu, Y.-C., D. B. Johnson, And A. Perrig. "Sead: Secure Efficient Distance Vector Routing For Mobile Wireless Ad Hoc Networks." Ad Hoc Networks 1, No. 1 (2003): 175–192.
[3] Zhang, K., C. Wang, And C. Wang. "A Secure Routing Protocol For Cluster-Based Wireless Sensor Networks Using Group Key Management." In 2008 4th International Conference On Wireless Communications, Networking And Mobile Computing. Ieee, 2008.
[4] Mohaisen, A., Et Al. "On The Insecurity Of Asymmetric Key-Based Architecture In Wireless Sensor Networks." Ksii Transactions On Internet And Information Systems 3, No. 4 (2009): 376–384.
[5] Hamza, R., Et Al. "A Privacy-Preserving Cryptosystem For Iot Ehealthcare." Information Sciences 527 (2020): 493-510..