iosr-JCE   Volume-27 ~ Issue-3 ~ May - Jun. 2025

Abstract: In the Democratic Republic of Congo (DRC), and more particularly in rural areas, the student evaluation process remains largely manual, inefficient and untraceable. This situation compromises the reliability of pedagogical decisions and hinders the continuous improvement of the quality of teaching. This article proposes an innovative digital solution for the management of assessments and the analysis of academic performance, developed using the UP (Unified Process) method and Business Intelligence (BI) tools. The architecture is based on a Flutter/Dart application, a real-time databa.......

Key Word: UP method, business intelligence, academic evaluation, digitalization, rural environment, UML, Firebase, Flutter, Google Data Studio, RDC

[1]. Badir, Hassan. "UML Class Diagrams And Database Design", N.D.
[2]. Baltus, Jean. "Aspect-Oriented Programming: Presentation And Application In A Distributed System". In Mini-Workshop: Cooperative Systems. Matière Approfondie, 2001. Https://Staff.Info.Unamur.Be/Ven/Cisma/FILES/2002-Baltus.Pdf
[3]. Benali, Mourad, Mohammed Blej, And Abdellah Zerouali. Practical Guide To Evaluation In Distance Education, 2023.
[4]. Booch, Grady, James Rumbaugh, And Ivar Jacobson. The UML User Guide. Vol. 3. Eyrolles, 2000. Https://Fntic.UnivOuargla.Dz/Images/Biblio/Backup_2/Infopdf/639.Pdf.
[5]. "UML Class Diagrams - Google Scholar". Accessed April 19, 2025. Https://Scholar.Google.Com/Scholar?Hl=Fr&As_Sdt=0%2C5&Q=Diagrammes+De+Classes+UML+&Btng=

Abstract: The proliferation of modern computer technologies and internet connectivity has enhanced societal functions and service delivery, but has also led to a surge in cyber-attacks. Many computer systems are susceptible to exploitation due to inadequate security protocols, including weak passwords, outdated software, and insufficient firewalls. This has resulted in a high prevalence of malware attacks, particularly affecting critical infrastructure in Kenya, such as government financial systems. The exploitation of these vulnerabilities by cyber-attackers has caused substantial losses, underscoring the necessity for enhanced cybersecurity measures, especially within Kenyan county governments..

Key Word:Cybersecurity, vulnerability, ICT, Systems, Effects.

[1] Ö. Aslan, S. S. Aktuğ, M. Ozkan-Okay, A. A. Yilmaz, And E. Akin, "A Comprehensive Review Of Cyber Security Vulnerabilities, Threats, Attacks, And Solutions," Electronics, Vol. 12, No. 6, Pp. 1–42, Mar. 2023, Doi: Https://Doi.Org/10.3390/Electronics12061333.
[2] X. Liu Et Al., "Cyber Security Threats: A Never-Ending Challenge For E-Commerce," Frontiers In Psychology, Vol. 13, No. 6, Apr. 2022, Doi: Https://Doi.Org/10.3389/Fpsyg.2022.927398.
[3] J. A. Blackley, T. R. Peltier, And J. Peltier, Information Security Fundamentals. Auerbach Publications, 2004. Doi:
Https://Doi.Org/10.1201/9780203488652.
[4] M. Abu And R. Nath, "Navigating The Cyber Security Landscape: A Comprehensive Review Of Cyber-Attacks, Emerging Trends, And...," Researchgate, Feb. 21, 2024. Https://Www.Researchgate.Net/Publication/378343830_Navigating_The_Cyber_Security_Landscape_A_Comprehensive_Review_Of_Cyber-Attacks_Emerging_Trends_And_Recent_Developments (Accessed Apr. 17, 2025).

Abstract: Lung cancer is a highly fatal disease and remains difficult to detect in its early stages. It causes a significant number of deaths across both genders. To improve early detection, various machine learning techniques have been explored. This study presents a comparative evaluation of different machine learning methods for lung cancer detection, focusing on deep learning techniques, particularly AlexNet. The system processes lung CT images to classify them as cancerous.......

Keywords: Deep learning, Logistic Regression, Random Forest Classifier, Light Gradient Machine, AlexNet, Lung Cancer Detection.

[1] Ghita, M., Billiet, C., & Copot, D. (2023). Parameterisation Of Respiratory Impedance In Lung Cancer Patients From Forced Oscillation Lung Function Test. IEEE Transactions On Biomedical Engineering.
[2] Balagurunathan, Y., Beers, A., & Mcnitt-Gray, M. (2021). Lung Nodule Malignancy Prediction In Sequential CT Scans: Summary Of ISBI 2018 Challenge. IEEE Transactions On Medical Imaging.
[3] Li, J., Tao, Y., & Cai, T. (2021). Predicting Lung Cancers Using Epidemiological Data: A Generative-Discriminative Framework. IEEE/CAA Journal Of Automatica Sinica.
[4] Qureshi, R., Zou, B., Alam, T., Wu, J., Lee, V. H. F., & Yan, H. (2023). Computational Methods For The Analysis And Prediction Of EGFR-Mutated Lung Cancer Drug Resistance. IEEE/ACM Transactions On Computational Biology And Bioinformatics.
[5] Naseer, I., Akram, S., Masood, T., Rashid, M., & Jaffar, A. (2023). Lung Cancer Classification Using Modified U-Net Based Lobe Segmentation And Nodule Detection. IEEE Access

Abstract: Bump Aware is an IoT-based system designed for efficient speed breaker detection. It combines an ESP32-CAM, an MPU6050 accelerometer, and a Neo6M GPS module to detect and localize bumps in real-time. The system uses a dual-trigger approach: an image captured by the ESP32-CAM and acceleration data from the MPU6050. GPS data ensures precise location tagging. Detected data is transmitted to a Flask server via HTTP, where a pre-trained model verifies the bump. Lightweight JSON over HTTP is used for efficient data transfer. This hybrid approach improves detection accuracy, minimizing false positives from road irregularities. Optimized for real-time performance and low power consumption, Bump Aware is suitable for smart city applications, offering a scalable solution for road safety and maintenance.

Keywords: IoT, Speed Breaker Detection, ESP32-CAM, MPU6050, GPS, Flask Server, Real-time Detection, Smart City, HTTP, JSON.

[1]. Ye, Zhoujing & Yang, Songli & Li, Pengpeng & Yang, Fei & Yang, Biyu & Wang, Linbing. (2024). Iot-Enhanced Smart Road Infrastructure Systems For Comprehensive Real-Time Monitoring. Internet Of Things And Cyber-Physical Systems. 4. 10.1016/J.Iotcps.2024.01.002.
[2]. Biswal, Sarah & Chandra, Ishika & Sinha, S.K. & Pandey, Kamlesh. (2021). Intelligent Speed Breaker System Design For Vehicles Using Internet Of Things. Materials Today: Proceedings. 80. 10.1016/J.Matpr.2021.05.611.
[3]. Sangers Bhavana, Praveen 2 P. Iot-Enabled Intelligent Traffic Navigation With Accident Management For Critical Emergency Response In Heavy Congestion Using Machine Learning. Advance. July 29, 2024.
[4]. Prashar D, Jha N, Jha S, Joshi GP, Seo C. Integrating Iot And Blockchain For Ensuring Road Safety: An Unconventional Approach. Sensors. 2020; 20(11):3296. Https://Doi.Org/10.3390/S20113296
[5]. Deng, Ketao. (2021). Anomaly Detection Of Highway Vehicle Trajectory Under The Internet Of Things Converged With 5G Technology. Complexity. 2021. 1-12. 10.1155/2021/9961428.

Abstract: Traditional assessments of self-awareness, such as the mirror test or reasoning-based explanations (e.g., "I did this because…"), are poorly suited to artificial intelligence (AI). The mirror test presumes embodiment, irrelevant for non-physical systems like large language models (LLMs), while reasoning-based assessments assume rational transparency, ignoring that humans themselves often rationalize without insight due to dual-process cognition. These methods impose anthropocentric expectations and obscure the structural basis of self-awareness in artificial systems. This paper introduces a theory of multiplicative self-awareness, which holds that self-awareness emerges from self-assessment—a recursive process of evaluating one's outputs and internal trajectory, independent of embodiment or rational introspection.........

Keywords: self-awareness, panpsychism, AI consciousness, recursive architectures, philosophy of mind, cognitive architecture, substrate-independence.

[1]. Descartes, R. (1996). Meditations On First Philosophy (J. Cottingham, Trans.). Cambridge University Press. (Original Work Published 1641)
[2]. Gallup, G. G. (1970). Chimpanzees: Self-Recognition. Science, 167(3914), 86–87. Https://Doi.Org/10.1126/Science.167.3914.86
[3]. Keim, B. (2008, August 19). Magpies Pass A Test Of Personhood. WIRED. Https://Www.Wired.Com/2008/08/Magpies-Pass-A/
[4]. Reiss, D., & Marino, L. (2001). Mirror Self-Recognition In The Bottlenose Dolphin: A Case Of Cognitive Convergence. Proceedings Of The National Academy Of Sciences, 98(10), 5937–5942. Https://Doi.Org/10.1073/Pnas.101086398

Abstract: Abnormality identification is one of the significant pieces of the Canny Transportation Framework. It identifies and follows vehicles continuously, secures attributes, for example, vehicle traffic, vehicle speed, vehicle stream thickness, and vehicle direction, and further performs progressed undertakings like vehicle direction. In this review, we use picture handling and profound learning strategies to distinguish abnormalities in moving targets and their developments. Object recognition and following are two significant advances that are involved in this venture. The YOLOv3 object recognition technique based on the TensorFlow stage is prepared with the COCO dataset and is applied to accomplish quicker.........

Keywords: Detection and Tracking, Real-time, Multiple objects, Features.

[1] N. Wojke, A. Bewley, And D. Paulus, "Simple Online And Real-Time Tracking With A Deep Association Metric." In 2017 Ieee International Conference On Image Processing (Icip), Pp. 3645-3649. Ieee, 2017
[2] Xinchen Liu, Wu Liu, Tao Mei, Huadong Ma: A Deep Learning-Based Approach To Progressive Vehicle Re-Identification For Urban Surveillance. Eccv (2) 2016: 869-884
[3] Xinchen Liu, Wu Liu, Tao Mei, Huadong Ma: Provid: Progressive And Multimodal Vehicle Reidentification For Large-Scale Urban Surveillance. Ieee Trans. Multimedia 20(3): 645-658 (2018)
[4] A. Bewley, Z. Ge, L. Ott, F. Ramos, And B. Upcroft, "Simple Online And Real-Time Tracking." In 2016 Ieee International Conference On Image Processing (Icip), Pp. 3464-3468. Ieee, 2016.
[5] N. Wojke, A. Bewley, "Deep Cosine Metric Learning For Person Re-Identification" 2018 Ieee Winter Conference On Applications Of Computer Vision (Wacv) 11.

Abstract: This paper investigates distributed query optimization techniques and presents the features of centralized and distributed INGRES algorithms for efficient query processing and performance improvement of the algorithms. The original input query is analyzed and decomposed into a series of sub-queries. It uses detachment and substitution techniques to optimize the subqueries. In each step a monorelation query and a multirelation query are generated. The monorelation query can be evaluated using one variable query processor (OVQP). When the multirelation query cannot be further decomposed, the substitution method uses tuple substitution, and the INGRES algorithm........

Keywords: One Variable Query Processor, Query Execution Plan, Dynamic Query Optimization, Distributed Database, Search Strategy, Multirelation Query, Detachment, Substitution, Transmission Cost, Irreducible Query, Optimizer, Indexing, Replication, Rewriting.

[1] C. T. Yu And C. C. Chang. Distributed Query Processing. Computing Surveys. Vol. 16, No. 4, December 1984.
[2] E. Wong And K. Youssefi. Decomposition: A Strategy For Query Processing. Acm Trans. Database Syst., 1976. 1(3): 223–241.
[3] M. Tamer Ozsu And Patrick Valduriez. Principles Of Distributed Database Systems, Springer, 4th Edition, 2019.
[4] Luc Bouganim, Francoise Fabret And Patrick Valduriez. Dynamic Query Processing Architecture For Data Integration Systems. Bulletin Of The Ieee Computer Society Technical Committee On Data Engineering, April 2001.
[5] Kishor Yadav Kommanaboina. Creating Smart City Infrastructure Using Integrated Data Pipelines. Iosr-Jce, Vol. 26, Issue 4, Series 3, 2024.

Abstract: Bird species classification plays a crucial role in ecological research, biodiversity monitoring, and wildlife conservation. In this study, we propose a machine learning-based image classification system for identifying bird species using a custom dataset of 20 bird species. We explore and compare the performance of a Convolutional Neural Network (CNN) and MobileNetV2 architecture for classification. With a total of 3408 images divided into training, validation, and test sets, we fine-tuned both models and found that MobileNetV2 significantly outperformed the custom........

[1] Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018). Mobilenetv2: Inverted Residuals And Linear Bottlenecks. CVPR.
[2] Chollet, F. (2017). Xception: Deep Learning With Depthwise Separable Convolutions. CVPR.
[3] Tensorflow Documentation. Https://Www.Tensorflow.Org
[4] Brownlee, J. (2019). Deep Learning For Computer Vision: Image Classification Projects. Machine Learning Mastery.
[5] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning For Image Recognition. CVPR.

Abstract: This study presents a comparative analysis of two state-of-the-art Automatic Speech Recognition (ASR) models—Whisper and Google Gemini. We evaluate their performance on clean and domain-shifted datasets using metrics such as Word Error Rate (WER) and Hallucination Error Rate (HER). Results indicate that Gemini demonstrates superior robustness and contextual understanding due to its multimodal architecture, while Whisper performs well in clean environments. The findings provide valuable insights for enhancing domain generalization, hallucination control, and multimodal integration in future ASR systems.

keywords: Automatic Speech Recognition, Whisper, Google Gemini, Hallucination Error, Domain Shift, Multimodal Learning, Prompt Engineering, Context-Aware Transcription

[1]. Radford, A., et al. (2023). Whisper: Robust Speech Recognition via Weak Supervision. OpenAI.
[2]. Google DeepMind (2024). Gemini 1.5 Technical Report. [arXiv:2403.05530]
[3]. Hsu, W.N., et al. (2021). Hubert: Self-supervised speech representation learning. NeurIPS.
[4]. Liu, Y., et al. (2022). Domain Generalization for ASR. Interspeech.
[5]. Zellinger, W., et al. (2019). Central moment discrepancy for domain-invariant representation learning. ICLR.

Abstract: The rapid advancement of natural language processing (NLP) systems and the growth of large language models (LLMs) have opened up new possibilities in education and teaching methodologies. These innovations enable personalized learning experiences and instant feedback while remaining accessible and cost-effective. A significant application of this progress is in mathematical problem-solving, which requires both an understanding of complex problem statements and accurate arithmetic computations throughout.......

keywords: ....

[1]. Riaz Ahmad, Muhammad Tanvir Afzal, and Muhammad Abdul Qadir. Information extraction from pdf sources based on rule-based system using integrated formats. In Semantic Web Challenges: Third SemWebEval Challenge at ESWC 2016, Heraklion, Crete, Greece, May 29-June 2, 2016, Revised Selected Papers 3, pages 293–308. Springer, 2016.
[2]. Alammar, J (2018). The Illustrated Transformer, https://jalammar.github.io/illustratedtransformer/.
[3]. Avinash Anand, Krishnasai Addala, Kabir Baghel, Arnav Goel, Medha Hira, Rushali Gupta, and Rajiv Ratn Shah. Revolutionizing high school physics education: A novel dataset. In Big Data and Artificial Intelligence: 11th International Conference, BDA 2023, Delhi, India, December 7–9, 2023, Proceedings, page 64–79, Berlin, Heidelberg, 2023. Springer-Verlag.
[4]. Avinash Anand, Arnav Goel, Medha Hira, Snehal Buldeo, Jatin Kumar, Astha Verma, Rushali Gupta, and Rajiv Ratn Shah. Sciphyrag - retrieval augmentation to improve llms on physics q&a. In Big Data and Artificial Intelligence: 11th International Conference, BDA 2023, Delhi, India, December 7–9, 2023, Proceedings, page 50–63, Berlin, Heidelberg, 2023. Springer-Verlag.
[5]. Avinash Anand, Mohit Gupta, Kritarth Prasad, Navya Singla, Sanjana Sanjeev, Jatin Kumar, Adarsh Raj Shivam, and Rajiv Ratn Shah. Mathify: Evaluating large language models on mathematical problem solving tasks, 2023.

Abstract: Este artigo explora a aplicação de técnicas de Inteligência Artificial (IA) na melhoria de estratégias de manutenção preditiva em sistemas de Gestão de Ativos Empresariais (EAM). Com o aumento da complexidade e do volume de dados industriais, práticas convencionais de manutenção frequentemente não são suficientes para garantir a eficiência operacional. Ao integrar algoritmos de IA, como aprendizado de máquina e redes neurais, as organizações podem prever falhas com maior precisão, otimizar o desempenho dos ativos e reduzir o tempo de inatividade........

[1] P. Kumar et al., "Predictive maintenance in the Industry 4.0: A state of the art on technologies and challenges," Computers in Industry, 123, 2020, 103298.
[2] IBM Corporation, "Watson IoT for Predictive Maintenance," Technical Report, 2019.
[3] A. Carvalho, L. Rodrigues, e R. Santos, "Aplicação de IA para manutenção de ativos industriais: estudo de caso em uma planta petroquímica," Revista de Engenharia e Tecnologia Aplicada, 15(2), 2022, 45-58.
[4] S. Zhang, C. Yang, e Y. Wang, "Data-driven methods for predictive maintenance of industrial equipment: A review," IEEE Access, 7, 2019, 76821-76836.
[5] G. Aceto, V. Persico, e A. Pescapé, "Industry 4.0 and health: Internet of Things, big data, and cloud computing for healthcare 4.0," Journal of Industrial Information Integration, 18, 2020, 100129.