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

Abstract: This work uses a dataset of 299 patient instances with 13 parameters from the UCI machine learning library to predict the optimal model and classifier for analyzing heart failure circumstances. Explanatory Data Analysis (EDA), which uses pre-processing, spread and location metrics, and visualization approaches to make sense of the data, is where the study starts. Using the original, unbalanced, and significant feature datasets, machine learning methods including Naïve Bayes, Logistic Regression, Support Vector Machine, Random Forest, K-nearest neighbor,........

Index Terms—Imbalanced data; Mann Whitney U; SMOTE; ADASYN; Chi-square; Random Forest

[1]. Davide Chicco & Giuseppe Jurman. (2020, February 3). Machine Learning Can Predict Survival Of Patients With Heart Failure From Serum Creatinine And Ejection Fraction Alone. BMC Medical Informatics And Decision Making, 20(1).
Doi:Https://Doi.Org/10.1186/S12911-020-1023-5
[2]. Https://Docs.Scipy.Org/Doc/Scipy/Reference/Generated/Scipy.Stats.Mannwhitneyu.Html#Scipy.Stats.Mannwhitneyu. (N.D.).
[3]. Https://Imbalanced-Learn.Org/Stable/References/Generated/Imblearn.Over_Sampling.ADASYN.Html. (N.D.).
[4]. Https://Scikit-Learn.Org/Stable/Modules/Preprocessing.Html#Preprocessing. (N.D.).
[5]. Opeyemi, A.-A. F. (2021, May 5). Using Ensemble Learning To Fix Imbalanced Data Set. International Journal Of Advances In Engineering And Management, 3( 2395-5252), 653-672. Doi:DOI: 10.35629/5252-0305653672

Abstract: Railway track faults pose a significant risk to train operations, leading to accidents and potential loss of life and resources. Manual inspection methods are time-consuming and prone to errors. To address this issue, a novel approach using a camera mounted on trains for real-time track fault detection is proposed. This system employs image processing techniques to analyze the camera data and identify any faults present on the tracks. The proposed approach leverages an innovative system where a webcam is strategically mounted on a toy train moving........

Index Terms—Arduino, Machine Learning, MATLAB, Webcam

[1] R.C. Gonzalez And R.E. Woods, Digital Image Processing, 4 Edition, Pearson, 2017
[2] N. Watson, Understanding Convolutional Neural Networks (Cnns), Infinite Skills, 2017
[3] "Introduction To Convolution Neural Network," Geeksforgeeks, Aug. 21, 2017. Https://Www.Geeksforgeeks.Org/Introduction- Convolution-Neural-Network/
[4] H. U. R. Siddiqui, A. A. Saleem, M. A. Raza, K. Zafar, K. Munir, And S. Dudley, "Iot Based Railway Track Faults Detection And Localization Using Acoustic Analysis," Ieee Access, Vol. 10, Pp. 106520–106533, 2022, Doi: Https://Doi.Org/10.1109/Access.2022.3210326.
[5] Y.-W. Lin, C.-C. Hsieh, W.-H. Huang, S.-L. Hsieh, And W.-H. Hung, "Railway Track Fasteners Fault Detection Using Deep Learning," 2019 Ieee Eurasia Conference On Iot, Communication And Engineering (Ecice), Oct. 2019, Doi: Https://Doi.Org/10.1109/Ecice47484.2019.8942769

Abstract: Image classification is termed as supervised learning problem: in which we define a set of target classes (objects to identify in images) and then train a model to recognize them using labelled example photos. Data Science deals with collecting large amounts of data and then analyse user behaviour. The information is used to draw conclusions, make plans, implement policies, and make better, data-driven decisions. There are........

Index Terms—Artificial Intelligence (AI); EDA; K-Nearest Neighbours; Decision Tree; SVM

[1]. Juan Mario Haut1, Mercedes Eugenia Paoletti1, Abel Paz-Gallardo2,Javier Plaza1 And Antonio Plaza1, "Cloud Implementation Of Logistic Regression For Hyperspectral Image Classification", 17th International Conference On Computational And Mathematical Methods In Science And Engineering, CMMSE 2017 4–8 July, 2017
[2]. Https://Blog.Dataiku.Com/2019/07/04/Fundamental-Steps-Data-Project-Success
[3]. Aritz Pe´Rez , Pedro Larran˜aga, In˜aki Inza, " Supervised Classification With Conditional Gaussian Networks: Increasing The Structure Complexity From Naive Bayes", International Journal Of Approximate Reasoning 43 (2006) 1–25.
[4]. Sancho Mccann And David G. Lowe, "Local Naive Bayes Nearest Neighbor For Image Classification", Technical Report TR-2011-11 University Of British Columbia, December 2, 2011.
[5]. Chun-Chieh Yang, Shiv O. Prasher, Peter Enright,Chandra Madramootoo, Magdalena Burgess,Pradeep K. Goel, Ian Callum,"Application Of Decision Tree Technology For Image Classification Using Remote Sensing Data", Agricultural Systems 76 (2003) 1101–1117, Accepted 15 May 2002

Abstract: Accurate and efficient barcode recognition is essential across various logistics, retail, and healthcare industries, as it enables automated tracking, inventory management, and quick transactions. Introducing deep learning techniques has considerably enhanced the accuracy and speed of barcode recognition systems. This paper explores using advanced object detection and decoding algorithms to improve barcode recognition. By employing the YOLO-v5 algorithm, which achieved a mean average precision of 97% at an intersection over the union threshold of 0.5 and 98% over thresholds from 0.5 to 0.95, the system accurately identifies barcode regions within large datasets. The Pyzbar library complements YOLO........

Index Terms—Deep Learning; Barcode recognition; YOLO-v5; Pyzbar.

[1] Ultralytics. "YOLOv5 Documentation." https://docs.ultralytics.com/yolov5/ (accessed June 13, 2024).
[2] P. Maske, K. Pardhi, S. Hatzade, R. Sharma, and S. Wazalwar, "Image Security Barrier (ISB): Hide valuable information in image using machine learning," in 2022 10th International Conference on Emerging Trends in Engineering and Technology-Signal and Information Processing (ICETET-SIP-22), 2022: IEEE, pp. 1-6.
[3] T. Kamnardsiri, P. Charoenkwan, C. Malang, and R. Wudhikarn, "1D Barcode Detection: Novel Benchmark Datasets and Comprehensive Comparison of Deep Convolutional Neural Network Approaches," Sensors, vol. 22, no. 22, p. 8788, 2022.
[4] Y. Xiao and Z. Ming, "1D Barcode Detection via Integrated Deep-Learning and Geometric Approach," Applied Sciences, vol. 9, no. 16, p. 3268, 2019. [Online]. Available: https://www.mdpi.com/2076-3417/9/16/3268.
[5] Y. Luo and J. Chen, "Two-Dimensional codes recognition algorithm based on Yolov5," Academic Journal of Computing & Information Science, vol. 5, no. 7, pp. 68-72, 2022.

Abstract: This paper proposes a system for detecting counterfeit products using blockchain technology. The system would involve two types of users: the official company responsible for registering products and the customers who want to ensure their purchases are genuine. The official company would register its products on the application, assigning them unique QR codes. When customers buy a product, they can simply scan the QR code using the application. The application would then verify the product's authenticity through the blockchain. The blockchain would store a record of all product registrations and transactions. This would make it very difficult for counterfeiters to create fake products or tamper with the data on the blockchain.
Keywords:— Blockchain, QR, Customer, Product, Authenticity

[1]. Y. Lu, Journal of Management Analytics 5, 1 (2018)
[2]. F.Casino, T.K. Dasaklis, C. Patsakis, Telematics Informatics 36, 55 (2019)
[3]. C. Shaik, Computer Science & Engineering: An International Journal (CSEIJ) 11 (2021)
[4]. M.A. Benatia, D. Baudry, A. Louis, Journal of Ambient Intelligence and Humanized Computing pp. 1–10 (2020)
[5]. M.A. Habib, M.B. Sardar, S. Jabbar, C.N. Faisal, N. Mahmood, M. Ahmad, Blockchainbased supply chain for the automation of transaction process: Case study-based validation, in 2020 International Conference on Engineering and Emerging Technologies (ICEET) (IEEE, 2020), pp. 1–7

Abstract: Introduction: Neonatal bacterial infection (NBI) is a public health problem. The high mortality associated with this disease and the difficulties of diagnosis increase the need to study biomarkers to enable rapid management of infected neonates. The aim of this study was to evaluate the performance of procalcitonin, interleukin-6 and C-reactive protein in the diagnosis of neonatal bacterial infection at Brazzaville University Hospital. Patients, Materials and Methods: This was a cross-sectional analytical study conducted in the Neonatology, Bacteriology and Biochemistry departments of the Brazzaville University Hospital Centre between April and September 2023. The study population consisted of 118 neonates........
Keywords:— Biomarkers, diagnosis, neonatal bacterial infection

[1]. Jeanne Garric, Soizic Morin, Françoise vincent-Hubert (2010). Les biomarqueurs en écotoxicologie : définition, intérêt, limite, usage. Sciences eaux et territoires;1: 2-19
[2]. 2. Mohammad Yousef Memar, Naser Alizadeh, Mojtaba Varshochi, and Hossein Samadi Kafil (2017). Immunologic biomarkers for diagnostic of Early-Onset Neonatal Sepsis, The Journal of Maternal-Fetal & Neonatal Medicine ; 32(1) : 143-153 DOI: 10.1080/14767058.2017.1366984
[3]. Oscar Marchetti, James Owen Robinson et Thierry Calandra (2005). Utilité de la procalcitonine dans le diagnostic et le suivi des infections chez les patients neutroniques fébriles. Rev med suisse.1:878-86
[4]. Toshio Tanaka, Masashi Narazaki, and Tadamitsu Kishimoto (2014). IL-6 in Inflammation, Immunity, and Disease. Cold Spring Harb Perspect Biol ; 6(10): a016295. doi: 10.1101/cshperspect.a016295
[5]. G. Ekouya Bowassa , E.N. Ontsira-Ngoyi, A.R. Okoko , H.G. Kimpolo Tsiba, A.P.G. Oko. Moyen, A. Mbika Cardorelle, N. Ngakengni, B.C. Yoyo, G.M. Moyen(2015).Bacteriology of early neonatal infection in Brazzaville (Congo) ; Archives de Pédiatrie ; 22(10) : 1099-1101

Abstract: The integration of Artificial Intelligence (AI) has revolutionized the cybersecurity space, presenting a compelling blend of significant benefits and noteworthy challenges. AI applications, such as anomaly detection, intrusion prevention systems, malware analysis, and automated security patching, have demonstrably enhanced security measures. These advancements lead to increased efficiency, improved threat detection accuracy, and faster response times. Case studies substantiate AI's capability to fortify defenses, as demonstrably evidenced in the reviewed examples. However, alongside these advantages, AI introduces new vulnerabilities. These vulnerabilities include potential biases within algorithms, susceptibility to adversarial attacks designed to manipulate AI systems, and the possibility of malicious actors leveraging AI to launch sophisticated cyberattacks. Ethical concerns, particularly around autonomous AI weapons, highlight the need for stringent regulations and transparent development.........
Keywords:— AI, cybersecurity, threat detection, efficiency, bias, adversarial attacks, transparency, explainable AI (XAI), human-AI collaboration, self-learning systems.

[1]. AI Now Institute. (2018). AI Now Report 2018. Retrieved from [AI Now Institute](https://ainowinstitute.org/AI_Now_2018_Report.pdf).
[2]. Angwin, J., Larson, J., Mattu, S., & Kirchner, L. (2016). Machine Bias. ProPublica. Retrieved from https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing
[3]. Brundage, M., Avin, S., Clark, J., Toner, H., Eckersley, P., Garfinkel, B., ... & Amodei, D. (2018). The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation. arXiv preprint arXiv:1802.07228.[https://arxiv.org/abs/1802.07228](https://arxiv.org/abs/1802.07228).
[4]. Buolamwini, J., & Gebru, T. (2018). Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification. Proceedings of the Conference on Fairness, Accountability, and Transparency 77-91. Retrieved from [ACM Digital Library](https://dl.acm.org/doi/10.1145/3287560.3287572).
[5]. Calo, R. (2017). Artificial Intelligence Policy: A Primer and Roadmap. University of California, Davis Law Review, 51, 399-435. (https://lawreview.law.ucdavis.edu/issues/51/2/Articles/51-2_Calo.pdf).