Search
6 articles for “Mean Absolute Error (MAE)”
-
Harnessing Machine Learning for Stock Movement Prediction: A Review of Current Approaches
Abstract: Stock price prediction is a crucial task in financial analysis, aiding investors and traders in making informed decisions. This study investigates the use of deep learning methods, particularly Long Short-Term Memory (LSTM) networks, for predicting stock prices based on historical market data. The dataset, sourced from Yahoo Finance, consists of time-series stock price data, which is preprocessed, feature-engineered, and visualized to improve prediction accuracy. The model's performance is assessed using …
Published in Journal of Advances in Shell Programming · Vol. 12, Issue 2, 2025 · pp. 29–40 Read article
-
Machine Learning Approach to Predict the Performability and Emissions of Diesel Engine Fueled with Doped Biodiesel Blend
Abstract: Enhancing the performability and emission characteristics of diesel engines has been a difficult task in light of growing concerns about global warming and other negative effects, as diesel accounts for 70% of global energy demand. In this study, engine performance and exhaust emissions for various fuel blends were thoroughly evaluated using machine learning techniques to predict engine emission and performance behavior. We focused on biodiesel blend and nanoparticle additive concentration …
Published in International Journal of Mechanical Dynamics and Systems Analysis · Vol. 3, Issue 1, 2025 · pp. 1–12 Read article
-
Integrative Machine Learning Approaches for Predicting the Rheological Behaviour of Soft Magnetorheological Elastomers
Abstract: Magnetorheological Elastomers (MREs) are advanced composite materials known for their ability to alter mechanical properties under external magnetic fields, making them highly valuable in adaptive damping systems, vibration control, and smart devices. The accurate prediction of rheological behavior in soft MREs remains a significant challenge due to the complex interplay between material composition and magnetic fields. To address this challenge, this study employs a multi-pronged approach that integrates traditional material …
Published in Journal of Polymer & Composites · Vol. 13, Issue 1, 2025 · pp. 1083–1096 Read article
-
Application of Artificial intelligence in Single Point Incremental Forming for Surface Roughness Prediction
Abstract: The sheet metal forming industries always try to find an emerging trend to form sheet-metal in a cost-effective manner. In this regard, a forming technique is trending termed as single point incremental forming (SPIF) in which a simple forming tool having hemispherical end rod is moving and simultaneously deforming the clamped metal sheet according to predetermined toolpath command and forms a complete shape. The achievement of required surface quality is …
Published in Journal of Polymer & Composites · Vol. 12, Issue 1, 2024 · pp. 237–246 Read article
-
Artificial Neural Network Based Prediction of Impact Loads and Thickness in CFRP and GFRP Composite Laminates
Abstract: Recent technological advancements, particularly the integration of neural networks, have facilitated a predictive approach to complex engineering problems, especially those involving composite materials with directional properties. The scarcity of literature on predicting impact damage using experimental and ultrasonic flaw detection data motivated this study. Experimental assessment of impact damage on carbon fiber/epoxy (CFRP) and glass fiber/epoxy (GFRP) composites was conducted using low-velocity drop weight impact testing. Damage assessment employed an …
Published in International Journal of Fracture Mechanics and Damage Science · Vol. 2, Issue 1, 2024 · pp. 34–45 Read article
-
SpecForesight: A Predictive Analytics Pipeline for Laptop Price Forecasting
Abstract: This paper frames laptop pricing as a supervised predictive analytics problem, transforming product specifications into feature-rich signals to forecast price with calibrated regression models and operational guardrails against drift. A structured pipeline ingests tabular listings, performs data cleaning, and engineers domain-informed features (e.g., central processing unit (CPU) family and clocks, graphics processing unit (GPU) tiering, memory/storage density, display, and touch capabilities), followed by encoding and normalization to optimize model learnability. …
Published in Journal of Computer Technology & Applications · Vol. 17, Issue 1, 2026 · pp. 61–71 Read article