Speaker verification method based on deep information divergence maximization by Chen CHEN, Yafeng RONG, Chaoqun JI, Deyun CHEN, Yongjun HE

“…To solve the problem that the nonlinear relationship between speaker representations cannot be accurately captured in speaker verification, an objective function based on depth information divergence maximization was proposed.It could implicitly represent the nonlinear relationship between speaker representations by calculating the similarity between their distributions.Under the supervision of the optimization goal of maximizing the statistical correlation, the deep neural network was optimized towards the direction that the within-class data was more compact and the between-class data were far away from each other, and finally the discrimination of deep speaker representation space could be effectively improved.Experimental results show that compared with other deep learning methods, the relative EER of the proposed method is reduced by 15.80% at most, which significantly improves the system performance.…”
Get full text

Dual-granularity lightweight model for vulnerability code slicing method assessment by Bing ZHANG, Zheng WEN, Yuxuan ZHAO, Ning WANG, Jiadong REN

“…Aiming at the problems existing in the assessment of existing vulnerability code slicing method, such as incomplete extraction of slicing information, high model complexity and poor generalization ability, and no feedback in the evaluation process, a dual-granularity lightweight vulnerability code slicing evaluation (VCSE) model was proposed.Aiming at the code snippet, a lightweight fusion model of TF-IDF and N-gram was constructed, which bypassed the OOV problem efficiently, and the semantic and statistical features of code slices were extracted based on the double granularity of words and characters.A heterogeneous integrated classifier with high accuracy and generalization performance was designed for vulnerability prediction and analysis.The experimental results show that the evaluation effect of lightweight VCSE is obviously better than that of the current widely used deep learning model.…”
Get full text

Intelligent adaptive edge systems：exploration and open issues by Xu WANG, Nanxi CHEN, Roujia ZHANG

“…Edge intelligence has emerged as a promising trend of the new generation of Internet of things.Edge computing devices are widely distributed, with various diverse end devices and services, delay sensitive, and serve mobile terminals.Therefore, the edge system needs to provide flexible, diverse, reconfigurable and scalable services.From the application fields of adaptive edge computing, the application requirements of intelligent adaptive edge systems were explored, the existing adaptive edge systems and their basic framework were analyzed and summarized, and the application of artificial intelligence technologies was discussed, such as deep learning and reinforcement learning.Then, how to design a special intelligent algorithm in specific application fields was introduced.Finally, the research status and future challenges in this field were discussed.…”
Get full text

Survey of video behavior recognition by Huilan LUO, Chanjuan WANG, Fei LU

“…Behavior recognition is developing rapidly,and a number of behavior recognition algorithms based on deep network automatic learning features have been proposed.The deep learning method requires a large number of data to train,and requires higher computer storage and computing power.After a brief review of the current popular behavior recognition method based on deep network,it focused on the traditional behavior recognition methods.Traditional behavior recognition methods usually followed the processes of video feature extraction,modeling of features and classification.Following the basic process,the recognition process was overviewed according to the following steps,feature sampling,feature descriptors,feature processing,descriptor aggregation and vector coding.At the same time,the benchmark data set commonly used for evaluating the algorithm performance was also summarized.…”
Get full text

Intelligent Planning Framework for Star-Walk Mission Based on Multimodal Observation Requirements Information by Guangxi ZHU, Gang WANG, Chao ZHANG, Yingte CHAI, Wei FU, Zhengqiang GUO

“…Combined with the current requirement and research for rapid intelligent planning of star-walk observation mission, and a framework based on multimodal observation requirements such as voice and text was designed.The framework aimed to satisfied the requirements and focued on breaking through three key issues for future emergency rescue applications: multimodal requirement interpretation, full-elements resource coordination and complex emergency missions planning, and to open the automatic link between observation requirement, resource planning and mission planning by making full use of deep learning methods.On these bases, the framework had the ability to provided rapid remote sensing observation information with a specified time and made full play to the comprehensive eff ectiveness of remote sensing information resources.…”
Get full text

Artificial Intelligence - Blessing or Curse in Dentistry? - A Systematic Review by Y Greeshma Vani, Suma B. Chalapathy, Pallavi Pandey, Shailendra K. Sahu, A Ramesh, Jayashree Sajjanar

“…The search was conducted using the terms “Artificial Intelligence,” “Dentistry,” “Machine learning,” “Deep learning,” and “Diagnostic System.” Out of 607 publications analyzed from 2010 to 2024, only 13 were selected for inclusion based on their relevance and publication year. …”
Get full text

SMART TRAFFIC SIGNAL CONTROL SYSTEM FOR TWO INTER-DEPENDENT INTERSECTIONS IN AKURE, NIGERIA by AJIBESIN SAMSON, PONNLE AKINLOLU, OYEDEPO OLUGBENGA

“…The system developed in this work uses deep learning and computer vision techniques to estimate the density of traffic and uses this information to adaptively switch traffic signals based on the traffic density estimated. …”
Get full text

Survey on adversarial attacks and defenses for object detection by Xinxin WANG, Jing CHEN, Kun HE, Zijun ZHANG, Ruiying DU, Qiao LI, Jisi SHE

“…In response to recent developments in adversarial attacks and defenses for object detection, relevant terms and concepts associated with object detection and adversarial learning were first introduced.Subsequently, according to the evolution process of the methods, a comprehensive retrospective analysis was conducted on the research achievements in the realm of adversarial attacks and defense methods for object detection.Particularly, attack methods and defense strategies were categorized based on the attacker knowledge and the deep learning lifecycle.Furthermore, an in-depth analysis and discussion of the characteristics and relationships among different approaches were provided.Lastly, considering the strengths and limitations of existing research, the imminent challenges and directions were summarized for further exploration in adversarial attack and defense of object detection.…”
Get full text

Neuroeducation meets virtual reality: theoretical analysis and implications for didactic design by Terrenghi Ilaria, Garavaglia Andrea

“…Taking into account the latest research in neuroscience, we want to explore the potential of using immersive virtual environments to facilitate deep learning in educational contexts that invoke the value of experience, imitation and repetition. …”
Get full text

APPLYING THE AUTOENCODER MODEL FOR URL PHISHING DETECTION by Dang Thi Mai

“…This paper proposes an improved two-stage deep learning model using an Autoencoder network for phishing URL detection. …”
Get full text

Brief communication: Training of AI-based nowcasting models for rainfall early warning should take into account user requirements by G. Ayzel, M. Heistermann

“…<p>In the field of precipitation nowcasting, deep learning (DL) has emerged as an alternative to conventional tracking and extrapolation techniques. …”
Get full text

Research on university email analysis based on SVM-RFE and Transformer-TBAM by LI Zhen, LI Zhichao, CHEN Lin

“…By mining and analyzing email text data from universities, it can help faculty members better understand students’opinions and suggestions, and improve management efficiency. At present, deep learning methods are the main approach for text sentiment analysis, but existing methods have not fully utilized the features in Chinese text. …”
Get full text

WmFall: WiFi-based multistage fall detection with channel state information by Xu Yang, Fangyuan Xiong, Yuan Shao, Qiang Niu

“…Considering that falling and sitting are very similar to each other, a special method is designed for distinguishing them with deep learning algorithm. Finally, the fall detection system is evaluated in a laboratory, which has 89% detection precision with false alarm rate of 8% on the average.…”
Get full text

Research on Pneumothorax Classification Model of DenseNet Based on Multilayer Network Optimization by Hongliang Huang, Qike Wang, Lidong Wang

“…Then, the binary cross-entropy loss function and accuracy evaluation function iteratively evaluated the effectiveness of the deep learning model and conducted multiple experiments. …”
Get full text

Model Analysis of Environmental and Economic Impacts of a Microgrid Based on the Optimization Method by Pengxiao Ji

“…Moreover, considering the environmental benefits of the microgrid two-level economic dispatch model, this paper constructs an intelligent analysis model and uses the deep learning algorithm as the system learning algorithm to improve the system data processing capability. …”
Get full text

Prediction of reduced left ventricular ejection fraction using atrial fibrillation or flutter electrocardiograms: A machine-learning study by Soonil Kwon, SooMin Chung, So-Ryoung Lee, Kwangsoo Kim, Junmo Kim, Dahyeon Baek, Hyun-Lim Yang, Eue-Keun Choi, Seil Oh

“…This study aimed to investigate deep-learning approaches to predict reduced LVEF (<50%) in patients with AF/AFL ECGs and easily obtainable clinical information. …”
Get full text

Probabilistic prediction of aero engine remaining useful life based on Bayesian graph attention transformer by Yanyan HU, Yating BAI

“…However, traditional deep learning methods often only analyze temporal data correlations, overlooking the complex non-Euclidian spatial relationship between multiple sensor data. …”
Get full text

The role of Artificial Intelligence in detecting breast lesions using ultrasound by Daria Ziemińska, Karina Motolko, Rafał Burczyk, Konrad Duszyński, Elżbieta Tokarczyk, Martyna Michalska, Adam Łabuda

“…Machine learning (ML) and deep learning (DL) drive advances, with DL's CNNs leading in image analysis. …”
Get full text

First-in-Men Online Adaptive Robotic Stereotactic Body Radiation Therapy: Toward Ultrahypofractionation for High-Risk Prostate Cancer Patients by Victor J. Brand, MD, Maaike T.W. Milder, PhD, Miranda E.M.C. Christianen, MD, PhD, Kim C. de Vries, MD, Mischa S. Hoogeman, PhD, Luca Incrocci, MD, PhD, Femke E. Froklage, MD, PhD

“…Preclinical validation involved comparing deep learning–based auto-contouring with deformable or rigid contour propagation in terms of subsequent editing time. …”
Get full text

Classification of Aortic Stenosis Patients via ECG-Independent Multi-Site Measurements of Cardiac-Induced Accelerations and Angular Velocities at the Skin Level by Chiara Romano, Emanuele Maiorana, Annunziata Nusca, Simone Circhetta, Sergio Silvestri, Schena Emiliano, Gian Paolo Ussia, Carlo Massaroni

“…Then, binary classification was performed through three machine learning and three deep learning methods, considering SCG, GCG, and their combination. …”
Get full text