Comparative performance analysis of end-to-end ASR models on Indo-Aryan and Dravidian languages within India’s linguistic landscape by Palash Jain, Anirban Bhowmick

“…Using four transformer-based pre-trained models—Wav2Vec2.0-base, XLSR-53, W2V2-BERT, and Whisper small—the analysis explores their adaptability to these languages’ linguistic features, with word error rate (WER) and character error rate (CER) serving as evaluation metrics. …”
Get full text

Integrative analysis of gene expression and DNA methylation through one‐class logistic regression machine learning identifies stemness features in medulloblastoma by Hao Lian, Yi‐Peng Han, Yu‐Chao Zhang, Yang Zhao, Shan Yan, Qi‐Feng Li, Bao‐Cheng Wang, Jia‐Jia Wang, Wei Meng, Jian Yang, Qin‐Hua Wang, Wei‐Wei Mao, Jie Ma

Get full text

Multi-scale feature fusion and feature calibration with edge information enhancement for remote sensing object detection by Lihua Yang, Yi Gu, Hao Feng

“…Abstract Vision Transformer-based detectors have achieved remarkable success in the field of object detection, but the application of these models to high-resolution remote sensing imagery faces challenges in computational costs and performance bottlenecks due to the increased computational complexity required to process high-resolution imagery, especially when capturing fine-grained edge features. …”
Get full text

Optimizing ML models for cybercrime detection: balancing performance, energy consumption, and carbon footprint through multi-objective optimization by Romil Rawat

“…Abstract This study aims to enhance computational performance while minimizing environmental impact in AI (Artificial Intelligence) and ML (Machine Learning) applications, especially in cybersecurity, by developing energy-efficient models using a multi-objective optimization approach. …”
Get full text

DA-YOLOv7: A Deep Learning-Driven High-Performance Underwater Sonar Image Target Recognition Model by Zhe Chen, Guohao Xie, Xiaofang Deng, Jie Peng, Hongbing Qiu

“…New modules such as the Omni-Directional Convolution Channel Prior Convolutional Attention Efficient Layer Aggregation Network (OA-ELAN), Spatial Pyramid Pooling Channel Shuffling and Pixel-level Convolution Bilat-eral-branch Transformer (SPPCSPCBiFormer), and Ghost-Shuffle Convolution Enhanced Layer Aggregation Network-High performance (G-ELAN-H) are central to its design, which reduce the computational burden and enhance the accuracy in detecting small targets and capturing local features and crucial information. …”
Get full text

Evaluating the impact of hyperparameters on the performance of 1D CNN model for nutritional profiling of underutilized crops using NIRS data by Simardeep Kaur, Naseeb Singh, Amit Kumar, Philanim W S, Veerendra Kumar Verma, Amit Kumar Patil, Rakesh Bhardwaj, Amritbir Riar

“…Our results show that increasing the number of convolutional layers improved the model's predictive power by enhancing feature extraction; however, beyond a certain limit, performance declined due to overfitting. …”
Get full text

EcoDetect-YOLOv2: A High-Performance Model for Multi-Scale Waste Detection in Complex Surveillance Environments by Jing Su, Ruihan Chen, Mingzhi Li, Shenlin Liu, Guobao Xu, Zanhong Zheng

Get full text

The impact of relevant versus irrelevant media multitasking on academic performance during online learning: a serial of mediating models by Lifang Fan, Chen Pan, Xuejun Bai, Shiyi Li, Shiyi Li, Shiyi Li

“…The participants completed an online survey, which incorporated the Academically Relevant Media Multitasking Questionnaire (AR-MMQ), the Academically Irrelevant Media Multitasking Questionnaire (AIR-MMQ), the Self-regulation Strategies Scale (SRS), the Flow Experience Scale (FL), and the Academic Performance Scale (AP). After conducting bivariate correlation analysis, the sequential mediation pathways were examined using structural equation modeling.ResultsThe findings revealed that: (1) Academically relevant media multitasking exhibited significant positive correlations with self-regulation strategies, flow experience, and academic performance. …”
Get full text

Predicting Hit Songs Using Audio and Visual Features by Cheng-Yuan Lee, Yi-Ning Tu

“…Random forest performed the best, with an accuracy of 82%. Average accuracy increased by 9% in all models when using audio and visual features together. …”
Get full text

Predicting Index Trend Using Hybrid Neural Networks with a Focus on Multi-Scale Temporal Feature Extraction in the Tehran Stock Exchange by Mohammad Osoolian, Ali Nikmaram, Mahdi Karimi

“…Moreover, to further enhance the performance and resilience of the model, sophisticated feature engineering methodologies are implemented to optimize its overall functionality. …”
Get full text

Improved classification algorithm for hyperspectral remote sensing images based on the hybrid spectral network model by Lv Deguo

Get full text

The Recognition of Protein Methylation Sites Based on CNN and Bi-LSTM Models by MA Chizhuo, ZHOU Wenjing, LEI Zhichao, WANG Chuzheng

“…Compared with other methods, the model has better performance.…”
Get full text

Experimental and Analytical Study on the Flexural Performance of Layered ECC–Concrete Composite Beams by Chong Gui, Jinlong Ji, Chongfa Xu, Zhihua Li, Xuan Guo

“…Building on these results, a theoretical model was formulated to predict the moment-deflection responses of ECC-concrete composite beams incorporating steel bars. …”
Get full text

Explaining the Earnings Management Prediction Model Using the Hybrid of Machine Learning Methods by Hassan Hassani, Esfandiar Malekian Kallehbasti, Yahya Kamyabi

“…The results show that the performance of accrual-based earnings management forecasting methods based on the relief-based feature selection model is better than the feature selection model based on principal component analysis. …”
Get full text

Assessment model of ozone pollution based on SHAP-IPSO-CNN and its application by Xiaolei Zhou, Xingyue Wang, Ruifeng Guo

“…Finally, the IPSO algorithm is combined with SHAP analysis to dynamically adjust the training features to optimize the performance of the CNN model. …”
Get full text

A model for shale gas well production prediction based on improved artificial neural network by LIN Hun, SUN Xinyi, SONG Xixiang, MENG Chun, XIONG Wenxin, HUANG Junhe, LIU Hongbo, LIU Cheng

Get full text

A Spoofing Speech Detection Method Combining Multi-Scale Features and Cross-Layer Information by Hongyan Yuan, Linjuan Zhang, Baoning Niu, Xianrong Zheng

“…Pre-trained self-supervised speech models can extract general acoustic features, providing feature inputs for various speech downstream tasks. …”
Get full text

License Plate Recognition Under the Dual Challenges of Sand and Light: Dataset Construction and Model Optimization by Zihao Wang, Yining Yang, Panxiong Yang, Xiaoge Zhang, Jiaming Li, Yanling Sun, Li Ma, Dong Cui

“…By introducing Batch Normalization (BN) layers, the model achieves greater training stability and generalization in complex environments. …”
Get full text

Detection of Hepatocellular Carcinoma Using Optimized miRNA Combinations and Interpretable Machine Learning Models by Zhengwu Long, Lisheng Zhang

“…Three interpretability techniques—permutation feature importance, Partial Dependence Plots (PDP), and Shapley Additive Explanations (SHAP)—were integrated into the pipeline to enhance model transparency. …”
Get full text

Comparative analysis and application of rockburst prediction model based on secretary bird optimization algorithm by Tengjie Yang, Tengjie Yang, Xinqiang Gao, Xinqiang Gao, Lichuan Wang, Yongqing Xue, Haobo Fan, Zhengguo Zhu, Zhengguo Zhu, Jingbo Zhao, Beiyi Dong, Beiyi Dong

“…However, current research often faces certain challenges related to the feature selection of prediction indices and poor model optimization performance. …”
Get full text