Recognizing and localizing chicken behaviors in videos based on spatiotemporal feature learning by Yilei Hu, Jinyang Xu, Zhichao Gou, Di Cui

“…This limitation highlights the insufficient temporal resolution of video-based behavior recognition models. This study presents a chicken behavior recognition and localization model, CBLFormer, which is based on spatiotemporal feature learning. …”
Get full text

Memory-Efficient Batching for Time Series Transformer Training: A Systematic Evaluation by Phanwadee Sinthong, Nam Nguyen, Vijay Ekambaram, Arindam Jati, Jayant Kalagnanam, Peeravit Koad

“…We evaluate our proposed batching framework systematically using peak GPU memory consumption and epoch runtime as efficiency metrics across varying batch sizes, sequence lengths, feature dimensions, and model architectures. Results show consistent memory savings, averaging 90% and runtime improvements of up to 33% across multiple transformer-based models (Informer, Autoformer, Transformer, and PatchTST) and a linear baseline (DLinear) without compromising model accuracy. …”
Get full text

Optimisation-Based Feature Selection for Regression Neural Networks Towards Explainability by Georgios I. Liapis, Sophia Tsoka, Lazaros G. Papageorgiou

Get full text

Facial Feature Recognition with Multi-task Learning and Attention-based Enhancements by M. Rohani, H. Farsi, S. Mohamadzadeh

“…Second, we present an enhanced attention mechanism that guides the model to prioritize features that contribute to more robust FFR. This mechanism is trained on the diverse and challenging images of UTKFace and is capable of identifying subtle and discriminative features in faces for more accurate gender, race, and age recognition. …”
Get full text

Physically Based Dimensionless Features for Pluvial Flood Mapping With Machine Learning by Mark S. Bartlett, Jared VanBlitterswyk, Martha Farella, Jinshu Li, Curtis Smith, Anthony J. Parolari, Lalitha Krishnamoorthy, Assaad Mrad

Get full text

Spoofing speech detection algorithm based on joint feature and random forest by Jiaqi YU, Zhihua JIAN, Jia XU, Lin YOU, Yunlu WANG, Chao WU

“…In order to describe the characteristic information of the speech signal more comprehensively and improve the detection rate of camouflage, a spoofing speech detection method based on the combination of uniform local binary pattern texture feature and constant Q cepstrum coefficient acoustic feature was proposed, which used random forest as the classifier model.The texture feature vector in the speech signal spectrogram was extracted by using the uniform local binary mode, and the joint feature was formed with the constant Q cepstrum coefficient.Then, the obtained joint feature vector was used to train the random forest classifier, so as to realize the camouflage speech detection.In the experiment, the performances of several spoofing detection systems constructed by other feature parameters and the support vector machine classifier model were compared, and the results show that the proposed speech spoofing detection system combined with the joint feature and the random forest model has the best performance.…”
Get full text

Spoofing speech detection algorithm based on joint feature and random forest by Jiaqi YU, Zhihua JIAN, Jia XU, Lin YOU, Yunlu WANG, Chao WU

“…In order to describe the characteristic information of the speech signal more comprehensively and improve the detection rate of camouflage, a spoofing speech detection method based on the combination of uniform local binary pattern texture feature and constant Q cepstrum coefficient acoustic feature was proposed, which used random forest as the classifier model.The texture feature vector in the speech signal spectrogram was extracted by using the uniform local binary mode, and the joint feature was formed with the constant Q cepstrum coefficient.Then, the obtained joint feature vector was used to train the random forest classifier, so as to realize the camouflage speech detection.In the experiment, the performances of several spoofing detection systems constructed by other feature parameters and the support vector machine classifier model were compared, and the results show that the proposed speech spoofing detection system combined with the joint feature and the random forest model has the best performance.…”
Get full text

Vehicle trajectory prediction based on spatio-temporal Transformer feature fusion by ZHAO Wenhong, WANG Wei, WAN Zilu

“…The proposed model was trained and validated on the publicly available NGSIM dataset. …”
Get full text

A robust covariate‐invariant gait recognition based on pose features by Anubha Parashar, Apoorva Parashar, Rajveer Singh Shekhawat

“…This study proposes an approach based on pose features to attempt gait recognition of people with an overcoat, carrying objects, or other covariates. …”
Get full text

Adversarial detection based on feature invariant in license plate recognition systems by ZHU Xiaoyu, TANG Peng, ZHANG Haochen, QIU Weidong, HUANG Zheng

Get full text

Detection of Road Rage in Vehicle Drivers Based on Speech Feature Fusion by Xiaofeng Feng, Chenhui Liu, Ying Chen

“…These features are first analysed, and each feature selected for fusion is determined preliminarily based on experience. …”
Get full text

A Linguistic Features-Based Approach for the Functional Analysis of Disinformation in Spanish by Eduardo Puraivan, Fabian Riquelme, Rene Venegas

Get full text

A Multi-Time-Frequency Feature Fusion Approach for Marine Mammal Sound Recognition by Xiangxu Meng, Xin Liu, Yinan Xu, Yujing Wu, Hang Li, Kye-Won Kim, Suya Liu, Yihu Xu

“…This paper proposes an Evaluation-Adaptive Weighted Multi-Head Fusion Network that integrates CQT and STFT features via a dual-branch ResNet architecture. The model enhances intra-branch features using channel attention and adaptive weighting of each branch based on its validation accuracy during training. …”
Get full text

Features of socio-psychological adaptation of young people with emotional disorders to the conditions of professional education by Olga V. Kalashnikova

Get full text

Performance Evaluation of Artificial Neural Network Methods Based on Block Machine Learning Classification by Raya Hamdy, Mohammed Younis

“…This study proposes a block-by-block (5x5 chunks) segmentation method for semantic segmentation, which involves image dissection, feature extraction, and model training based on specific color and textural properties. …”
Get full text

Enhancing Object Detection in Underground Mines: UCM-Net and Self-Supervised Pre-Training by Faguo Zhou, Junchao Zou, Rong Xue, Miao Yu, Xin Wang, Wenhui Xue, Shuyu Yao

“…Building upon this foundation, we propose UCM-Net, a detection model based on the YOLO architecture. Furthermore, a self-supervised pre-training method is introduced to generate mine-specific pre-trained weights, providing the model with more semantic features. …”
Get full text

Possibility to increase the speeds of express and high-speed trains by turnouts and connecting tracks by A. M. Brzhezovskiy, B. E. Glyuzberg, M. I. Titarenko, I. E. Il’In, V. S. Viktorov, V. N. Tulushev

Get full text

E-LEARNING TRAINING USING EDMODO BASED ON TEACHERS OF SMK NU UNGARAN by Subiyanto Subiyanto, Iin Supriyati, Nisaun Markamah

Get full text

Fault Diagnosis of Gearbox Bearings of High-speed Train Based on the SVD-MOMEDA by Dan ZHU, Yanchen SU, Chunguang YAN

“…Aiming at problems of high-speed train gearbox bearing fault signals being difficult to detect under strong noise background, and the problem that the multipoint optimal minimum entropy deconvolution adjusted(MOMEDA) method was affected by the order of filter and the period of impulse signal, an improved MOMEDA method for bearing fault diagnosis based on singular value decomposition(SVD) was proposed. …”
Get full text

Research on license plate recognition based on graphically supervised signal-assisted training by Dianwei Chi, Zehao Jia, Lizhen Liu

“…An auxiliary training branch is added, utilizing these graphical signals to guide the model in learning improved image features. …”
Get full text