Survey of deep fake audio generation and detection techniques by ZENG Zhiping, ZHANG Xulong, QU Xiaoyang, XIAO Chunguang, WANG Jianzong

“…Subsequently, an in-depth analysis was conducted on both acoustic feature-based and end-to-end model-based fake audio detection strategies, delving into details such as deep acoustic feature detection, pre-trained neural network feature detection, end-to-end model optimization, generalization enhancement techniques, and the enhancement of real-time detection. …”
Get full text

Simultaneous Estimation of Wrist Joint Angle and Torque During Isokinetic Contraction Based on HD-sEMG by Mingjie Yan, Zhe Chen, Jianmin Li, Jinhua Li, Lizhi Pan

“…Six other decoding models were also used to continuously estimate the wrist joint angle and torque, including support vector machine (SVM), residual network (ResNet), long short-term memory (LSTM), transformer-based model (TBM), muscle synergy-based graph attention networks (MSGAT-LSTM), and spatio-temporal feature extraction network (STFEN). …”
Get full text

Patch-Based Deep-Learning Model With Limited Training Dataset for Liver Tumor Segmentation in Contrast-Enhanced Hepatic Computed Tomography by Yuqiao Yang, Muneyuki Sato, Ze Jin, Kenji Suzuki

“…We applied a multi-scale Hessian ellipsoid enhancer to extract multi-scale features of the liver tumor. We implemented a region-stratified sampling strategy to prevent overfitting in patch-based neural network training. …”
Get full text

Reliability analysis in curriculum development for social science education driven by machine learning by Rui Mao

“…The model was subsequently trained with sub-sample data containing 80% of the data while this part was further tested with 20% for verifying the generalizability and robustness of the model. Performance evaluation was conducted on the linear regression, random forest and artificial neural networks (ANN) through statistical metrics such as root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE). …”
Get full text

Artificial intelligence-generated images in skin cancer education: an experimental study by Jevan Cevik, Ishith Seth, Warren M Rozen

“…Generative adversarial networks, a branch of AI renowned for image-generation capabilities, particularly hold promise. …”
Get full text

Winter wheat mapping using unbalanced multi-source remote sensing data by Haofei Li, Xiaohui He, Mengjia Qiao, Haonan Sun, Jinlan Kong, Xijie Cheng, Panle Li, Jian Zhang, Renyi Liu, Jiandong Shang

“…Comprehensive evaluations on three datasets demonstrate that the proposed MS-JBM model surpasses existing multi-source spatio-temporal feature extraction models.…”
Get full text

Neuro-VGNB: Transfer Learning-Based Approach for Detecting Brain Stroke by Muhammad Usama Tanveer, Kashif Munir, Bharati Rathore, Abdulatif Alabdulatif, Rutvij H. Jhaveri, Maham Fatima

“…Our innovative approach, termed Neuro-VGNB, aims to leverage these advanced methodologies to improve classification accuracy significantly.To evaluate the effectiveness of our Neuro-VGNB model, we conducted comprehensive comparisons between traditional spatial features and the newly proposed transfer features. …”
Get full text

Expanding the clinical spectrum of 19p13.3 microduplication syndrome: a case report highlighting nephrotic syndrome and literature review by Wenjie Sun, Hong Yan, Mengxin Sun, Jie Wang, Kunxia Li

“…Relevant literature was reviewed using the search terms “19p13.3” and “19p13.3 microduplication syndrome” in the China Knowledge Network, Wanfang Database, Weipu Journal Service Platform, and PubMed (date range: database establishment to September 2023). …”
Get full text

Fast Anomaly Detection for Vision-Based Industrial Inspection Using Cascades of Null Subspace PCA Detectors by Muhammad Bilal, Muhammad Shehzad Hanif

“…In this study, we introduce a novel anomaly detection framework that leverages feature maps from a lightweight convolutional neural network (CNN) backbone, MobileNetV2, and cascaded detection to achieve notable accuracy as well as computational efficiency. …”
Get full text

Neural systems for processing social relationship information along two principal dimensions by Wonjun Kang, Minjae Kwon, Sue-Hyun Lee

“…Moreover, the first dimension is predominantly processed within a posterior cortical network centered around the posterior superior temporal sulcus (pSTS), while the second dimension is primarily processed within an anterior cortical network centered around the ventromedial prefrontal cortex (vmPFC). …”
Get full text

A Comparative Study of Deep Learning’s Performance Methods for News Article using Word Representations by Iman Saladin B. Azhar, Winda Kurnia Sari, Naretha Kawadha Pasemah Gumay

“…A good word representation is essential to address this challenge, and the word representation using GloVe is one of the popular methods that provides pre-trained word representations in high-dimensional vectors. This research evaluates the effectiveness of three deep learning techniques Convolutional Neural Network (CNN), Deep Neural Network (DNN), and Long Short-Term Memory (LSTM) for online news classification using 300-dimensional GloVe word representations. …”
Get full text

Myoepithelioma of the upper lip: A rare case report with a literature review of diagnostic approaches by Farid Ghadyani, Samira Behrad

Get full text

Well Performance from Numerical Methods to Machine Learning Approach: Applications in Multiple Fractured Shale Reservoirs by Kailei Liu, Boyue Xu, Changjea Kim, Jing Fu

“…Finally, the artificial neural network is used to determine the relationship between key factors and well production performance. …”
Get full text

SPECIALIZED MAPPING OF CRUSTAL FAULT ZONES. PART 2: MAIN STAGES AND PROSPECTS by K. Zh. Seminsky

“…There are three stages in the special mapping method (Fig. 3) as follows:Stage I: Preparation and analysis of previously published data on the regional fault structure (Fig. 1, А–Г), establishment of a networks of stations to conduct structural geological monitoring and mass measurements of joints, re­cord of rock data (Fig. 2, А), general state of the fault network (Fig. 1, Д–З), fracture density (Fig. 2, Б) and, if any, structures of the above-jointing level (Fig. 1, Е, З; Fig. 2, А).Stage II is aimed at processing of field data and includes activities in four groups (II.1–II.4) as follows: Group II.1: construction of circle diagrams, specification of characteristics of joint systems and their typical scatters (Fig. 4, А), identification of simple (generally tipple) paragenesises, and determination of dynamic settings of their formation (translocal rank) (Table 1), evaluation of densities and complexity of the joint networks, analysis of their spacial patterns within the site under mapping, and identification of the most intensively destructed zones in the rock massif (Fig. 2, Б–В). …”
Get full text

Assessment of Tumor Infiltrating Lymphocytes in Predicting Stereotactic Ablative Radiotherapy (SABR) Response in Unresectable Breast Cancer by Mateusz Bielecki, Khadijeh Saednia, Fang-I Lu, Shely Kagan, Danny Vesprini, Katarzyna J. Jerzak, Roberto Salgado, Raffi Karshafian, William T. Tran

“…Results: The KNN, SVM, and GNB models were implemented using clinical and graph features. Among the generated prediction models, the graph features showed higher predictive performances compared to the models containing clinical features alone. …”
Get full text

Exploring the heterogeneity of osteosarcoma cell characteristics and metabolic states and their association with clinical prognosis by Sen Qin, YaoFeng Hu, RuCui Deng, Zhe Wang

“…Various methods were utilized, such as differential expression analysis of genes, analysis of metabolic pathways, and weighted gene co-expression network analysis (WGCNA), to pinpoint crucial genes. …”
Get full text

Automatic Blob Detection Method for Cancerous Lesions in Unsupervised Breast Histology Images by Vincent Majanga, Ernest Mnkandla, Zenghui Wang, Donatien Koulla Moulla

“…Finally, a deep learning recurrent neural network (RNN) model automatically detects and extracts cancerous lesions and their edges from the histology images via the blob detection method. …”
Get full text

Active Contours Connected Component Analysis Segmentation Method of Cancerous Lesions in Unsupervised Breast Histology Images by Vincent Majanga, Ernest Mnkandla, Zenghui Wang, Donatien Koulla Moulla

“…This segmentation method is evaluated on an unsupervised, augmented human breast cancer histology dataset of 15,179 images. …”
Get full text

Mapping sewage treatment plants for wastewater reclamation and reuse in industrial parks of Peninsular Malaysia: A path towards water security by Nur Hairunnisa Rafaai, Khai Ern Lee, Noor Zarina Mohd Nazir, Ainul Rasyidah Ab Rahim, Thian Lai Goh, Mazlin Mokhtar, Wan Abd Rahim Wan Abdullah, Huzaini Husain, Raja Baharudin Raja Mamat

Get full text

Ethnic Architectural Heritage Identification Using Low-Altitude UAV Remote Sensing and Improved Deep Learning Algorithms by Ting Luo, Xiaoqiong Sun, Weiquan Zhao, Wei Li, Linjiang Yin, Dongdong Xie

“…Finally, an attention mechanism SE module is introduced to improve the DeepLabV3+ network model structure and achieve superior ethnic building recognition results. …”
Get full text