Measuring and Improving the Efficiency of Python Code Generated by LLMs Using CoT Prompting and Fine-Tuning by Ramya Jonnala, Jeong Yang, Young Lee, Gongbo Liang, Zechun Cao

“…Furthermore, we investigated the impact of two distinct optimization strategies: Chain-of-Thought (CoT) prompting and model fine-tuning. …”
Get full text

Comparative Analysis of RF, SVR with Gaussian Kernel and LSTM for Predicting Loan Defaults by Konstantinos Kofidis, Cătălina Lucia Cocianu

“…The research acknowledges that both the LSTM and SVR models remain in the developmental stages, with ongoing initiatives aimed at refining these models through hyperparameter optimization and advanced architectural frameworks to enhance their predictive efficacy in practical applications.…”
Get full text

Explainable post hoc portfolio management financial policy of a Deep Reinforcement Learning agent. by Alejandra de-la-Rica-Escudero, Eduardo C Garrido-Merchán, María Coronado-Vaca

“…In this work, driven by the motivation of making DRL explainable, we developed a novel Explainable DRL (XDRL) approach for PM, integrating the Proximal Policy Optimization (PPO) DRL algorithm with the model agnostic explainable machine learning techniques of feature importance, SHAP and LIME to enhance transparency in prediction time. …”
Get full text

Conformal Segmentation in Industrial Surface Defect Detection with Statistical Guarantees by Cheng Shen, Yuewei Liu

“…Traditional defect detection methods predominantly rely on manual inspection, which suffers from low efficiency and high costs. Some machine learning algorithms and artificial intelligence models for defect detection, such as Convolutional Neural Networks (CNNs), present outstanding performance, but they are often data-dependent and cannot provide guarantees for new test samples. …”
Get full text

Target Tactical Intention Recognition in Multiaircraft Cooperative Air Combat by Meng Guanglei, Zhao Runnan, Wang Biao, Zhou Mingzhe, Wang Yu, Liang Xiao

“…The purpose of the employment of SVM is to avoid local optimization and reduce data dimension. Moreover, we use three models, i.e., dynamic Bayesian network (DBN), radar model, and threat assessment model to extract crucial information regarding maneuver occupancy, silent penetration, and attack tendency. …”
Get full text

Research on the High Stability of an Adaptive Controller Based on a Neural Network for an Electrolysis-Free-Capacitor Motor Drive System by Danyang Bao, Haorui Shen, Wenxiang Ding, Hao Yuan, Yingying Guo, Zhendong Song, Tao Gong

“…This study investigates the stable operation mechanism under intermittent working conditions by analyzing DC bus voltage transient characteristics. It optimizes control parameters for stable intermittent operations and establishes a neural network-based adaptive controller model. …”
Get full text

Intelligent Systems for Inorganic Nanomaterial Synthesis by Chang’en Han, Xinghua Dong, Wang Zhang, Xiaoxia Huang, Linji Gong, Chunjian Su

“…Case studies on quantum dots and gold nanoparticles demonstrate the enhanced efficiency of closed-loop synthesis systems and their machine learning-enabled autonomous optimization of process parameters. …”
Get full text

Performance evaluation of a diesel engine fuelled with waste plastic pyrolysis oil, 1-butanol, and CeO2 additives under varying injection pressures by K. Sunil Kumar, Sumathy Muniamuthu, T.M. Yunus Khan, Abdul Razak

“…Furthermore, advanced Machine Learning (ML) techniques are employed for modeling, enabling precise prediction and analysis of engine behavior under varying operating conditions. …”
Get full text

Detecting eavesdropping nodes in the power Internet of Things based on Kolmogorov-Arnold networks. by Rong Wang, Weibin Jiang, Yanjin Shen, Qiqing Yue, Kan-Lin Hsiung

“…To address the challenges of real-world power grid environments, this paper designs optimization strategies such as adaptive grid refinement and hierarchical sparsity regularization, further enhancing the model's robustness and interpretability. …”
Get full text

Traffic Incident Duration Prediction: A Systematic Review of Techniques by Artur Grigorev, Adriana-Simona Mihaita, Fang Chen

“…Future research directions proposed include the following: (1) development of data fusion models that integrate heterogeneous datasets of incident reports for enhanced predictive modeling; (2) utilization of natural language processing (NLP) to extract contextual information from textual incident reports; and (3) implementation of advanced ML pipelines that incorporate anomaly detection, hyperparameter optimization, and sophisticated feature selection techniques. …”
Get full text

Research of the Combined Trajectory Planning of Descartes Space and Joint Space by Lai Xiao, Liu Yong, Luo Wenguo, Dai Yanxia, Zeng Han

“…Comparing with the experimental results,the movement trend tend to be consistent,the part of the curve have subtle difference and need further optimization but the method has very important significance for machine operation.…”
Get full text

The use of artificial intelligence in stereotactic ablative body radiotherapy for hepatocellular carcinoma by Atsuto Katano

“…Clinical studies have demonstrated notable benefits, such as a reduction in contouring time and improved dosimetric quality using machine learning–based optimization algorithms. However, critical limitations persist. …”
Get full text

A Comprehensive Investigation of Fraud Detection Behavior in Federated Learning by Sun Rui

“…The comparison involves three machine learning models - Artificial Neural Networks (ANN), Random Forest (RF), and Convolutional Neural Networks (CNN) - to assess their efficacy in the FL context. …”
Get full text

Evaluation method of e-government audit information based on big data analysis by Jingui He, Hansi Ya

“…To address these challenges, this paper proposes a big data-driven evaluation and prediction model for e-government audit information. The proposed method is built on a Hadoop-based distributed computing platform, which supports heterogeneous data integration and efficient parallel processing. …”
Get full text

Road Event Detection and Classification Algorithm Using Vibration and Acceleration Data by Abiel Aguilar-González, Alejandro Medina Santiago

“…Road event detection is critical for tasks such as monitoring, anomaly detection, and optimization. Traditional approaches often require complex feature engineering or the use of machine learning models, which can be computationally intensive, especially when dealing with real-time data from high-frequency vibration and acceleration sensors. …”
Get full text

Lightweight Deep Learning for sEMG-Based Fingers Position Classification and Embedded System Deployment by Victor H. Benitez, Jesus Pacheco, Guillermo Cuamea-Cruz

“…This feature highlights its potential for real-time applications in prosthetics, robotics, and human-computer interaction. Although further optimization is needed for better generalization to unseen data, this study emphasizes the significance of developing deployable algorithms that excel beyond simulation environments focusing on enhancing model robustness and validating its real-time performance through hardware-based implementations. …”
Get full text

Music genre classification with parallel convolutional neural networks and capuchin search algorithm by Yuxin Zhang, Teng Li

“…Preprocessing the original signals, feature description utilizing DWT, MFCC, and STFT signal matrices, CNN model optimization to extract signal features, and music genre identification based on combined features make up the four main components of the technique. …”
Get full text

Experimental Study on Evaluation of Organization Collaboration in Prefabricated Building Construction by Dingjing Bao, Yuan Chen, Shuai Wan, Jinlai Lian, Ying Lei, Kaizhe Chen

“…Moreover, the BO-XGBoost model was compared with the random forest, support vector machine, and logistic regression prediction models. …”
Get full text

Lavender hydrosol analysis using UV spectroscopy data and partial least squares regression by Sára Preiner, Bálint Levente Tarcsay, Dóra Pethő, Norbert Miskolczi

“…The composition data obtained allowed for the calculation of changes within the quantities of different EO components in the samples.The partial least squares regression technique (PLS) was utilized to establish a connection between changes in the composition of the hydrosol and the changes in the UV–Vis spectra. After optimization the established PLS model showed an R2 score above 0.95 for the prediction of hydrosol composition changes during cross-validation. …”
Get full text

Indoor Positioning System based on SSA-ELM Neural Network for Visible Light by JIA Kejun, NIU Zhen, YU Kai, ZHANG Zhicong, PENG Duo, CAO Minghua

“…【Objective】The Extreme Learning Machine (ELM) neural network algorithm in the traditional indoor Visible Light Positioning (VLP) system suffers from unstable convergence and a tendency to get stuck in local optimal states, resulting in decreased positioning accuracy. …”
Get full text