iosr-JCE   Volume-27 ~ Issue-5 ~ Sep. - Oct. 2025

Abstract: The contemporary financial environment is marked with its rising complexity and speed due to a combination of globalization and technological inventions as well as the real-time information flow. Investors, financial institutions and risk managers need to have a way to guide them in determining price behavior in the short term; otherwise, they will not be able to develop appropriate trading strategies and avoid risks. Nevertheless, this is still one of the most challenging problems in the quantitative finance. The uncertainties of financial markets, which can be characterized by such aspects as the existence of significant volatility, non-stationarity, and non-linear relationships, are a well-known problem that makes question the effectiveness of traditional forecasting models. This has caused a continued argument and quest to stronger prediction models.

[1]. Box, G. E. P., & Jenkins, G. M. (1976). Time Series Analysis: Forecasting And Control. San Francisco: Holden-Day.
[2]. Chen, Y., Zhang, X., & Wu, X. (2015). Deep Learning For Financial Forecasting: A Review. Journal Of Financial Data Science, 1(2), 1-15.
[3]. Diebold, F. X., & Mariano, R. S. (1995). Comparing Predictive Accuracy. Journal Of Business & Economic Statistics, 13(3), 253-265.
[4]. Engle, R. F. (1982). Autoregressive Conditional Heteroscedasticity With Estimates Of The Variance Of United Kingdom Inflation. Econometrica: Journal Of The Econometric Society, 50(4), 987-1007.
[5]. Fischer, T., & Krauss, C. (2018). Deep Learning With Lstms For Financial Forecasting. Journal Of Economics And Business, 104, 39-51.

Abstract: Background: This project presents an “virtual reality in education: enhancing learning quality and skill acquisition in university settings” Designed to automate student attendance and monitor academic performance in virtual classroom environments like Zoom. The system efficiently tracks student presence during online sessions, automatically recording attendance. If a student fails to attend or exits the session prematurely, immediate notifications.......

Key Word: Deep Learning, Computer Vision, Human Activity Recognition

[1]. Sharma Et Al. (2019) – Real-Time Engagement Via Webcam And ML Used Webcam-Based Emotion, Eye, And Head Tracking To Predict Engagement; Limited To Basic Expressions.
[2]. Nair Et Al. (2023) – CNN-Based Emotion Detection In Virtual Classrooms Achieved High Accuracy In Nuanced Emotion Recognition, But Posed Real-Time And Privacy Challenges.
[3]. Abedi & Khan (2024) – Privacy-Aware Engagement With ST-GCN Utilized Facial Landmarks And Spatio-Temporal Models With Explainability; Performance Affected By Lighting.
[4]. Sen Sharma Et Al. (2022) – Gaze-Based Attention Monitoring Tool Monitored Student Gaze In Virtual Classes; Lacked Strong Evidence Linking Tool To Academic Improvement.
[5]. Multiple Authors (2022) – Temporal Facial Analysis For Engagement Combined CNN And LSTM For Tracking Engagement Over Time; Limited By Self-Reported Data And Compute Needs.

Abstract: The growing need for comprehensive user activity monitoring in security analysis, parental control, and employee supervision has led to the evolution of advanced keylogging systems. This article presents “System-Wide Keylogger and Device Report Generation,” a Python-based solution that seamlessly captures keystrokes and gathers detailed system diagnostics in real time. Leveraging the pynput library, the system logs all keyboard activity with contextual metadata, while also generating an extensive system report using platform and psutil, covering.......

Keywords: Keylogger, System Report, Python, pynput, psutil, Keystroke Monitoring, Device Information, Real-time Logging

[1]. Pykeylogger Developers, Pykeylogger – A Python-Based Keylogger, 2007. Https://Github.Com/Pykeylogger/Pykeylogger
[2]. A. Molina And X. Zhang, “Comparative Analysis Of Keylogging Tools And Ethical Implications,” Journal Of Information Security Research, Vol. 8, No. 3, Pp. 121–130, 2020.
[3]. R. Dhillon, P. Verma, And K. Singh, “Contextual Logging: Integrating Screen Capture With Keyloggers For Enhanced Forensic Analysis,” Cybersecurity Advances, Vol. 5, No. 1, Pp. 33–40, 2021.
[4]. M. Al-Maqtari, Y. Khan, And R. Malik, “Lightweight Surveillance With Python: Secure Remote Transmission Using SMTP,” International Journal Of Computer Applications, Vol. 179, No. 28, Pp. 45–49, 2018.
[5]. N. Chawla And R. Sharma, “Stealth-Based Activity Logging For Real-Time Monitoring,” Security And Privacy In Computing, Vol. 12, No. 4, Pp. 201–207, 2019