International Journal of Artificial Intelligence

A Standard Deep Learning-Based Model That Integrates R3D-18 With RNN for Clip Classification and Transition Point Detection in Basketball Video Footages

2026-07-17T04:02:46+00:00

Research on basketball video clip analysis is rapidly emerging as a vital tool for coaching, player development, scouting, recruitment of coaches and players. Such analysis enhances post-game review, tactical planning, practice design, in-game adjustments, visual feedback and decision-making. However, many existing models lack robust architectures for transition detection, limiting their effectiveness. Additionally, high costs, limited customization, internet dependency and complex interfaces restrict widespread adoption of most models across professional and grassroots levels. To address these challenges, this paper implements a deep learning model with Python language. The model integrates Residual 3D Network with 18 layers (R3D-18) to capture spatial-temporal features, Convolutional neural networks (CNNs) to perform feature extraction and Recurrent Neural Network (RNN) to accomplish temporal modeling of offline basketball videos. Using entropy thresholding and top-k (i.e., top-10) accuracy metrics on four basketball datasets, the model performs clip-wise and video-level action classification with exceptional confidence, achieving 99.92% and 99.52% certainty that all the evaluative footages depict basketball videos. The model further detected no transitions in basketball_video1 and basketball_video3 while notable transitions appeared at clips 8 and 7 in basketball_video2 and basketball_video4, respectively corresponding to spikes in uncertainty likely caused by activity changes like switching from basketball to running. Average entropy scores of 4.787, 3.5341, 3.7912 and 3.1976 across datasets were reported, reflecting potentially elusive variations and uncertainties within clip-level predictions due to nuanced activity shifts despite strong overall classification confidence.

Capability-Specific Degradation Patterns in Quantized Small Language Models

2026-07-17T04:02:44+00:00

Post-training quantization is the default method for deploying small language models (one to four billion parameters) on consumer and edge hardware, yet its effect is usually summarized by a single aggregate accuracy score that can conceal severe failures in individual capabilities. This paper presents a capability-level analysis of four-bit quantization for seven open instruction-tuned small language models drawn from five architecture families: Qwen2.5, Llama-3.2, Gemma-2, Phi-3.5, and SmolLM2. Each model is evaluated at sixteen-bit floating point and at four-bit precision across six capabilities, namely factual knowledge, commonsense reasoning, mathematical reasoning, multilingual mathematical reasoning, code generation, and instruction following, yielding eighty-four controlled evaluations. Instead of reporting only mean accuracy, we construct a per-capability degradation map and test, using Kendall's rank correlation, whether capabilities degrade in a consistent order across architectures. The results show that degradation is strongly capability-specific: multilingual mathematical reasoning and code generation are the most fragile capabilities, with relative losses of up to fifty-seven percent, whereas commonsense reasoning is almost entirely preserved. However, the ordering of degradation is only weakly consistent across architectures, with a mean Kendall's tau of 0.29, indicating that the most and least fragile capabilities are shared but the overall ranking is architecture-dependent. Smaller models degrade more in magnitude. We conclude that small-model quantization should be evaluated per capability rather than in aggregate.

Fuzzy Logic for Heart Disease Prediction

2026-07-17T04:09:02+00:00

Cardiovascular disease remains one of the leading causes of mortality worldwide, emphasizing the importance of early and accurate risk prediction systems. This study proposes a web-based heart disease prediction system utilizing a fuzzy logic approach to effectively manage uncertainty and imprecision in clinical data. As illustrated in the system interface, the model incorporates five primary input parameters: blood pressure, blood sugar level, cholesterol level, body mass index (BMI), and family history. These parameters are transformed into linguistic variables through fuzzification and evaluated using a rule-based fuzzy inference system constructed from expert knowledge and recent research findings. The fuzzy logic framework enables flexible decision-making that closely resembles human reasoning, overcoming limitations of conventional threshold-based diagnostic methods. The system produces an interpretable heart disease risk classification, such as low or high risk, which is presented through an interactive web interface along with a prediction history feature. Based on a review of related studies published within the last five years, fuzzy logic and neuro-fuzzy models have shown strong performance, transparency, and suitability for clinical decision support. The proposed system demonstrates the practicality of integrating fuzzy logic into web applications to support early heart disease risk assessment and preventive healthcare.