A Dual-Branch Fusion Model for Deepfake Detection Using Video Frames and Microexpression Features by Georgios Petmezas, Vazgken Vanian, Manuel Pastor Rufete, Eleana E. I. Almaloglou, Dimitris Zarpalas

“…In this paper, we propose a novel approach to deepfake detection by combining video frame analysis with facial microexpression features. …”
Get full text

BEVCorner: Enhancing Bird’s-Eye View Object Detection with Monocular Features via Depth Fusion by Jesslyn Nathania, Qiyuan Liu, Zhiheng Li, Liming Liu, Yipeng Gao

Get full text

Early Detection of ITSC Faults in PMSMs Using Transformer Model and Transient Time-Frequency Features by Ádám Zsuga, Adrienn Dineva

“…Existing diagnostic approaches, including motor current signature analysis (MCSA) and wavelet-based methods, are primarily designed for steady-state conditions and rely on manual feature selection, limiting their applicability in real-time embedded systems. …”
Get full text

Leveraging spatial dependencies and multi-scale features for automated knee injury detection on MRI diagnosis by Jianhua Sun, Ye Cao, Ying Zhou, Baoqiao Qi

“…BackgroundThe application of deep learning techniques in medical image analysis has shown great potential in assisting clinical diagnosis. …”
Get full text

Echoes From the Void: Detecting DNS Tunneling With Blackhole Features in Encrypted Scenarios With High Accuracy by Wafa S. Alorainy

“…A five-fold cross-validation with a random forest classifier achieved 99.9% classification accuracy, a 99.9% F1 score, and 100% precision and recall. Feature importance analysis indicates that blackhole-related features contribute to the detection query-to-blackhole ratios (Gini importance of 0.35) and inter-blackhole intervals (0.20), which help focus on stealthy tunneling behavior. …”
Get full text

Utility of FET-PET in detecting high-grade gliomas presenting with equivocal MR imaging features by Ameya D. Puranik, Mathew Boon, Nilendu Purandare, Venkatesh Rangarajan, Tejpal Gupta, Aliasgar Moiyadi, Prakash Shetty, Epari Sridhar, Archi Agrawal, Indraja Dev, Sneha Shah

Get full text

On-line Identification Method of Pantograph Anomaly Based on Feature Analysis by WANG Junping, MAO Huihua, SHEN Yunbo, LI Miaocheng, CHEN Xin'an

“…Therefore, this paper proposes an on-line recognition method based on feature analysis and independent of the number of fault samples. …”
Get full text

Incremental Adversarial Learning for Polymorphic Attack Detection by Ulya Sabeel, Shahram Shah Heydari, Khalil El-Khatib, Khalid Elgazzar

Get full text

Temporal Community Detection and Analysis with Network Embeddings by Limengzi Yuan, Xuanming Zhang, Yuxian Ke, Zhexuan Lu, Xiaoming Li, Changzheng Liu

“…In order to understand their dynamic characteristics, it is essential to investigate temporal community detection (TCD), which poses significant challenges compared to static network analysis. …”
Get full text

ENHANCING NETWORK INTRUSION DETECTION USING MACHINE LEARNING AND META-MODELLING FOR IMPROVED CYBER SECURITY PERFORMANCE by Sunita, Pankaj Verma, Nitika, Jaspreet Kaur, Vijay Rana

Subjects: Get full text

Video Anomaly Detection Methods: a Survey by WU Peichen, YUAN Lining, GUO Fang, LIU Zhao

“…By comparing the network architectures of different models, this paper summarizes the test datasets, use cases, advantages, and limitations of various abnormal behavior detection models. Furthermore, it compares and evaluates models using benchmark datasets and common evaluation standards such as frame-level and pixel-level standards, and conducts intra-class comparisons based on performance results, followed by analysis of the outcomes. …”
Get full text

Environmental Factors in Structural Health Monitoring—Analysis and Removal of Effects from Resonance Frequencies by Rims Janeliukstis, Lasma Ratnika, Liga Gaile, Sandris Rucevskis

“…Secondly, the selection of only a handful of the most informative resonance frequency features not only reduces the feature space, but also increases the classification performance, albeit with a trade-off between false alarms and missed damage detection. …”
Get full text

Analysis of super-long and sparse feature in pseudo-random sequence based on similarity by Chun-jie CAO, Jing-zhang SUN, Zhi-qiang ZHANG, Long-juan WANG, Meng-xing HUANG

“…Similarity analysis of pseudo-random sequence in wireless communication networks is a research hotspot problem in the domain of information warfare.Based on the difficulties in super-long sequence,extremely sparse feature,and futilities in engineering application for real-time processing exist in similarity analysis of sequence in wireless net-work,a method of similarity analysis of sequence in a certain margin of misacceptance probability was proposed.Firstly,the similarity probability distribution of real-random sequence was theoretically analyzed.Secondly,according to the standard of NIST SP 800-22,the randomness of pseudo-bitstream was analyzed and the validity of pseudo-bitstream was judged.Finally,similarity was analyzed and verified by combining super-long pseudo-random sequence in real wireless communication networks.The results indicate that the lower bound of similarity value is 0.62 when misacceptance prob-ability uncertainty at about 1%.Above conclusion is considerable importance from the significance and theoretical values in network security domains,such as protocol analysis,traffic analysis,intrusion detection and others.…”
Get full text

Clinical features and prognostic analysis of AKI in the internal medicine departments by XUE Xian, TANG Xiao-jing, ZHANG Di, SHEN Ai-wen, MEI Chang-lin

“…Objective To explore the clinical features of patients with acute kidney injury(AKI)in the internal medicine departments.Methods The kidney function indexes of the internal medicine patients were collected in Shanghai Changzheng Hospital from 2011 to 2012.According to the AKI diagnostic criteria of KDIGO in 2012,we screened out the AKI patients who met the criteria.By retrospectively studying their clinical data,we analyzed and summarized their clinical characteristics and the factors affecting the prognosis.Results From January 2011 to December 2012,there were a total of 33 332 cases of internal medicine patients in our hospital and 245 of them met the criteria of AKI.The incidence of AKI was 0.74%in internal medicine departments while the detection rate of AKI was 35.92%.The proportions of patients with AKI stage 1 to 3 were 42.45%,20.41% and 37.14%,respectively.Among all the internal medicine departments,patients in the department of nephrology accounted for 33.47%,followed by the department of cardiology(20.00%),gastroenterology(11.84%)and infectious disease(10.61%).The incidence of AKI from high to low was infection disease department(1.70%),nephrology department(1.37%),and cardiology department(1.11%).Of all the hospitalized patients with AKI,71.84% discharged with a better health condition and the kidney function discovered in only 34.69% of the discharged patients;28.16% died or gave up treatment.The most common departments with high fatality rate were the department of infectious disease(21.74%),gastroenterology and cardiology.Infection was the main cause of the AKI in internal medicine departments.Logistic regression analysis showed that higher AKI stage,more AKI risk factors,combination with liver disease or tumor were risk factors for death and giving up treatment,while chronic kidney disease was the protective factor.ConclusionsAKI is common in internal medicine system,with a high mortality rate and a higher recognition rate than perioperative AKI.Except for the department of nephrology,cardiology,departments of infectious disease and gastroenterology have heavy burden of AKI.The advanced stage of AKI,more risk factors,and comorbidities such as liver disease or tumor were associated with poor prognosis.…”
Get full text

Clinical Features and Genetic Analysis of Drug-resistant Epilepsy in Children by ZUO Ranran, SUN Suzhen

“…Methods A retrospective analysis of 95 children with DRE who were hospitalized in Hebei Children's Hospital from 2020 to 2022. …”
Get full text

Statistical Analysis of Haralick Texture Features to Discriminate Lung Abnormalities by Nourhan Zayed, Heba A. Elnemr

Get full text

Large-scale candidate gene analysis of HDL particle features. by Bernhard M Kaess, Maciej Tomaszewski, Peter S Braund, Klaus Stark, Suzanne Rafelt, Marcus Fischer, Robert Hardwick, Christopher P Nelson, Radoslaw Debiec, Fritz Huber, Werner Kremer, Hans Robert Kalbitzer, Lynda M Rose, Daniel I Chasman, Jemma Hopewell, Robert Clarke, Paul R Burton, Martin D Tobin, Christian Hengstenberg, Nilesh J Samani

Get full text

Automatic detection of non-convulsive seizures: A reduced complexity approach by Tazeem Fatma, Omar Farooq, Yusuf U. Khan, Manjari Tripathi, Priyanka Sharma

“…With the use of only one feature, all of the seizures under test were detected correctly, and hence the median sensitivity and specificity of 100% and 99.21% were achieved respectively.…”
Get full text

2D Animal Skeletons Keypoint Detection: Research Progress and Future Trends by Pengfei Ma, Ronghua Gao, Qifeng Li, Qinyang Yu, Rong Wang, Chengrong Lai, Weiwei Huang, Peng Hao, Zhaoyang Wang, Xuwen Li

“…The paper not only summarizes different model algorithms, datasets, and evaluation metrics related to animal keypoint detection but also integrates various application scenarios, highlighting distinct features under different focal points. …”
Get full text

Unsupervised Spectral-Spatial Feature Selection-Based Camouflaged Object Detection Using VNIR Hyperspectral Camera by Sungho Kim

“…This letter proposes a fully autonomous feature selection and camouflaged object detection method based on the online analysis of spectral and spatial features. …”
Get full text