Research on anomaly detection algorithm based on sparse variational autoencoder using spike and slab prior by Huahua CHEN, Zhe CHEN

“…Anomaly detection remains to be an essential and extensive research branch in data mining due to its widespread use in a wide range of applications.It helps researchers to obtain vital information and make better decisions about data by detecting abnormal data.Considering that sparse coding can get more powerful features and improve the performance of other tasks, an anomaly detection model based on sparse variational autoencoder was proposed.Firstly, the discrete mixed modelspike and slab distribution was used as the prior of variational autoencoder, simulated the sparsity of the space where the hidden variables were located, and obtained the sparse representation of data characteristics.Secondly, combined with the deep support vector network, the feature space was compressed, and the optimal hypersphere was found to discriminate normal data and abnormal data.And then, the abnormal fraction of the data was measured by the Euclidean distance from the data feature to the center of the hypersphere, and then the abnormal detection was carried out.Finally, the algorithm was evaluated on the benchmark datasets MNIST and Fashion-MNIST, and the experimental results show that the proposed algorithm achieves better effects than the state-of-the-art methods.…”
Get full text

Research on anomaly detection algorithm based on sparse variational autoencoder using spike and slab prior by Huahua CHEN, Zhe CHEN

“…Anomaly detection remains to be an essential and extensive research branch in data mining due to its widespread use in a wide range of applications.It helps researchers to obtain vital information and make better decisions about data by detecting abnormal data.Considering that sparse coding can get more powerful features and improve the performance of other tasks, an anomaly detection model based on sparse variational autoencoder was proposed.Firstly, the discrete mixed modelspike and slab distribution was used as the prior of variational autoencoder, simulated the sparsity of the space where the hidden variables were located, and obtained the sparse representation of data characteristics.Secondly, combined with the deep support vector network, the feature space was compressed, and the optimal hypersphere was found to discriminate normal data and abnormal data.And then, the abnormal fraction of the data was measured by the Euclidean distance from the data feature to the center of the hypersphere, and then the abnormal detection was carried out.Finally, the algorithm was evaluated on the benchmark datasets MNIST and Fashion-MNIST, and the experimental results show that the proposed algorithm achieves better effects than the state-of-the-art methods.…”
Get full text

International Natural Uranium Price Prediction Based on TF-CNN-BiLSTM Model by YANG Jingzhe, XUE Xiaogang

“…To address these challenges, this study proposed a novel TF-CNN-BiLSTM model, which synergistically combines the self-attention mechanism of Transformer, the local feature extraction capability of convolutional neural network (CNN), and the bidirectional temporal dependency modeling of bidirectional long short-term memory (BiLSTM). …”

GC4MRec: Generative-Contrastive for Multimodal Recommendation by Lei Wang, Yingjie Li, Heran Wang, Jun Li

“…On the one hand, we design a bilateral information flow module using two graph convolutional networks (GCNs). This module captures modal features from two distinct perspectives—standard and generatively augmented—to extract latent preferences. …”
Get full text

ASLDetect: Arabic sign language detection using ResNet and U-Net like component by Naif Alasmari, Sultan Asiri

Get full text

Small Object Tracking in LiDAR Point Clouds: Learning the Target-Awareness Prototype and Fine-Grained Search Region by Shengjing Tian, Yinan Han, Xiantong Zhao, Xiuping Liu

“…To this end, we propose a deep neural network framework that trains a Siamese network for feature extraction and innovatively incorporates two pivotal modules: the target-awareness prototype mining (TAPM) module and the regional grid subdivision (RGS) module. …”
Get full text

Probabilistic forecasting of renewable energy and electricity demand using Graph-based Denoising Diffusion Probabilistic Model by Amir Miraki, Pekka Parviainen, Reza Arghandeh

Get full text

Artificial intelligence in suicide prevention: Utilizing deep learning approach for early detection by Vikas Gaur, Gaurav Maggu, Khushboo Bairwa, Suprakash Chaudhury, Sana Dhamija, Tahoora Ali

“…Aim: Our primary objective was to construct an artificial intelligence (AI) model employing an artificial neural network (ANN) architecture to predict students at risk of suicidal tendencies. …”
Get full text

An EMG-Based GRU Model for Estimating Foot Pressure to Support Active Ankle Orthosis Development by Praveen Nuwantha Gunaratne, Hiroki Tamura

Get full text

GRE²-MDCL: Graph Representation Embedding Enhanced via Multidimensional Contrastive Learning by Quanjun Li, Weixuan Li, Xiya Zheng, Junhua Zhou, Wenming Zhong, Xuhang Chen, Chao Long

“…However, most graph neural network models require extensive labelled data, limiting their practical applicability. …”
Get full text

Deep fusion of incomplete multi-omic data for molecular mechanism of Alzheimer’s disease by Linhui Xie, Yash Raj, Mingzhao Tong, Kwangsik Nho, Paul Salama, Andrew J. Saykin, Shiaofen Fang, Jingwen Yan

“…In addition, TransFuse yielded a subset of multi-omics features forming functional disease network modules, providing valuable insights into underlying molecular mechanism. …”
Get full text

Similarities and differences between dog–human and human–human relationships by Borbála Turcsán, Dorottya Júlia Ujfalussy, Andrea Kerepesi, Ádám Miklósi, Enikő Kubinyi

“…This may stem from the fact that the dog-human relationship features a more asymmetric power dynamic than human relationships – i.e., owners have full control over the dog’s life. …”
Get full text

A Generalized GNN-Transformer-Based Radio Link Failure Prediction Framework in 5G RAN by Kazi Hasan, Khaleda Papry, Thomas Trappenberg, Israat Haque

“…This paper fills the gap by proposing GenTrap, a novel RLF prediction framework that introduces a Graph Neural Network (GNN)-based learnable weather effect aggregation module and employs state-of-the-art time series transformer as the temporal feature extractor for radio link failure prediction. …”
Get full text

Near-Infrared Hyperspectral Target Tracking Based on Background Information and Spectral Position Prediction by Li Wu, Mengyuan Wang, Weixiang Zhong, Kunpeng Huang, Wenhao Jiang, Jia Li, Dong Zhao

“…This module effectively reduces the computational complexity of feature extraction by capsule networks and improves tracking stability. …”
Get full text

OA-MEN: a fusion deep learning approach for enhanced accuracy in knee osteoarthritis detection and classification using X-Ray imaging by Xiaolu Ren, Xiaolu Ren, Lingxuan Hou, Shan Liu, Peng Wu, Siming Liang, Haitian Fu, Chengquan Li, Ting Li, Yongjing Cheng

“…This approach ensures enhanced extraction of semantic information without losing the advantages of large feature maps provided by high image resolution in lower layers of the network. …”
Get full text

Berberine alleviates atherosclerosis by modulating autophagy and inflammation through the RAGE-NF-κB pathway by Peng Zhang, Meiying Jin, Lei Zhang, Yanjun Cui, Xiaokang Dong, Jie Yang, Jiayu Zhang, Haopeng Wu

“…IntroductionLipid accumulation and foam cell formation are significant features that expedite the progression of atherosclerosis (AS). …”
Get full text

Predictive Modeling of soil salinity integrating remote sensing and soil variables: An ensembled deep learning approach by Sana Arshad, Jamil Hasan Kazmi, Endre Harsányi, Farheen Nazli, Waseem Hassan, Saima Shaikh, Main Al-Dalahmeh, Safwan Mohammed

“…Initially, Recursive Feature Elimination was implemented as a feature-selection method to select the most effective predictors. …”
Get full text

AI-enhanced automation of building energy optimization using a hybrid stacked model and genetic algorithms: Experiments with seven machine learning techniques and a deep neural net... by Mohammad H. Mehraban, Samad ME Sepasgozar, Alireza Ghomimoghadam, Behrouz Zafari

“…This model was trained and validated using simulation data from selected areas of London. It was further evaluated on unseen data from diverse UK cities without retraining, confirming its predictive power across varying climatic conditions. …”
Get full text

Social Media Based Topic Modeling for Smart Campus: A Deep Topical Correlation Analysis Method by Jun Peng, Yiyi Zhou, Xiaoshuai Sun, Jinsong Su, Rongrong Ji

“…In particular, bidirectional recurrent neural networks and convolutional neural networks are used to learn deep textual and visual features, respectively. …”
Get full text

COMMUNICATIVE AND PRAGMATIC PARAMETERS OF THE BLOG AS A GENRE OF PERSONAL INTERNET COMMUNICATION (BASED ON TEXTS BY LYUDMILA LINNYK ON THE WEBSITE “GALICIAN CORRESPONDENT”) by Nataliia Ya. Ivanyshyn

“…The purpose of the study is to reveal the communicative and pragmatic features of a blog as a specific genre of Internet communication. …”
Get full text