A5100697050- Advanced Malware Detection Techniques
- Network Security and Intrusion Detection
- Digital Media Forensic Detection
- Complex Network Analysis Techniques
- Medical Image Segmentation Techniques
- Cryptography and Data Security
- Text and Document Classification Technologies
- Spam and Phishing Detection
- Advanced Manufacturing and Logistics Optimization
- Robotic Path Planning Algorithms
- Data Visualization and Analytics
- Topic Modeling
- Optimization and Search Problems
- Advanced Neural Network Applications
- Digital and Cyber Forensics
- Adversarial Robustness in Machine Learning
- Recommender Systems and Techniques
- Functional Brain Connectivity Studies
- Blockchain Technology Applications and Security
- Machine Learning in Healthcare
- Imbalanced Data Classification Techniques
- Advanced Bandit Algorithms Research
- Security and Verification in Computing
- Mobile Crowdsensing and Crowdsourcing
- Web Applications and Data Management
Shanghai Jiao Tong University
2025
Chongqing University
2024
Yunnan University
2024
Beijing Graphene Institute
2023
BGI Research
2023
Institute of Information Engineering
2016-2023
Chinese Academy of Sciences
2003-2023
University of Chinese Academy of Sciences
2019-2023
BGI Group (China)
2023
Shenzhen University
2021
Recommender systems have to deal with the cold start problem as new users and/or items are always present. Rating elicitation is a common approach for handling start. However, there still lacks principled model guiding how select most useful ratings. In this paper, we propose identify representative and using representative-based matrix factorization. Not only do show that selected representatives superior other competing methods in terms of achieving good balance between coverage diversity,...
Since its introduction, IoT (Internet of Things) has enjoyed vigorous support from governments and research institutions around the world, remarkable achievements have been obtained. The perception layer plays an important role as a link between real world; security become bottleneck restricting further development IoT. is self-organizing network system consisting various resource-constrained sensor nodes through wireless communication. Accordingly, costly encryption mechanism cannot be...
In the era of knowledge economy, talents are core resources to promote economic and social development, university teachers as executor higher education, development management human is particularly important. At present, with popularization education deepening market system, many colleges universities faced problem insufficient quantity quality teachers, which not only affects but also restricts long-term universities. Therefore, it great theoretical practical significance study resource...
Deep Learning has established itself to be a common occurrence in the business lexicon. The unprecedented success of deep learning recent years can attributed to: an abundance data, availability gargantuan compute capabilities offered by GPUs, and adoption open-source philosophy researchers industry. neural networks decomposed into series different operators. MIOpen, AMD's primitives library for provides highly optimized implementations such operators, shielding from internal implementation...
PDF malware remains as a major hacking technique. To distinguish malicious PDFs from massive files poses challenge to forensic investigation. Machine learning has become mainstream technology for document detection either help analysts in investigation or prevent system being attacked. However, adversarial attacks against classifiers have emerged. Crafted example based on precision manipulation may be easily misclassified. This threat many detectors machine techniques. Various analysis...
Recently, word enhancement has become very popular for Chinese Named Entity Recognition (NER), reducing segmentation errors and increasing the semantic boundary information of words. However, these methods tend to ignore relationship before after sentence integrating lexical information. Therefore, regularity length not been fully explored in various word-character fusion methods. In this work, we propose a Lexicon-Attention Data-Augmentation (LADA) method NER. We discuss challenges using...
Due to the ever increasing attacks using malicious documents, detection of such documents has become a serious and urgent research issue. In past decade, attracted significant attentions, many methods have been proposed, including conventional static methods, dynamic methods. However, both two categories limitations under either obfuscated or run-time conditions, can not achieve satisfactory performance for behaviors. this work, we firstly present new descriptive structure our targeted...
In this paper, a coding framework VIP-ICT-Codec is introduced. Our method based on the VTM (Versatile Video Coding Test Model). First, we propose color space conversion from RGB to YUV domain by using PCA-like operation. A for PCA mean calculation proposed de-correlate residual components of channels. Besides, correlation UV compensated considering that they share same tree in VVC. We also learn mapping alleviate over-filtered and under-filtered problem specific images. Finally, regard rate...
Clustering techniques have been applied to neuroscience data analysis for decades. New algorithms keep being developed and address different problems. However, when it comes the applications of clustering, is often hard select appropriate algorithm evaluate quality clustering results due unknown ground truth. It also case that conclusions might be biased based on only one specific because each has its own assumption structure data, which not same as real data. In this paper, we explore...
Data-driven landscape across finance, government, and healthcare, the continuous generation of information demands robust solutions for secure storage, efficient dissemination, fine-grained access control. Blockchain technology emerges as a significant tool, offering decentralized storage while upholding tenets data security accessibility. However, on-chain off-chain strategies are still confronted with issues such untrusted absence ownership, limited control policy clients, deficiency in...
Motivation: Understanding the impact of cortical vascular architecture on spatiotemporal features hemodynamic responses. Goal(s): Automatic extraction realistic vasculature models from microscopy data, and simulation changes across extracted network. Approach: We present a pipeline that utilizes graph theory for extracting representing it as graph. Simulations were performed using graphs by converting connectivity matrix into dynamic system modeled RC circuits. Results: two used them to...
Abstract Three-dimensional Spatial Transcriptomics has revolutionized our understanding of tissue regionalization, organogenesis, and development. However, to reconstruct single sections back their in situ three-dimensional morphology, existing approaches either only adopt gene expression information guide reconstruction or overlook shape correction against experiment-induced section distortions. This leads significant discrepancies between results the actual vivo locations cells, imposing...
As the most widely used solution for intelligent manufacturing, Distributed Numerical Control (DNC) system faces with various novel attack opportunities caused by increasing connection to industrial ethernet and external interfaces. Attackers can easily fabricate packets between machine tools Machine Data Collection (MDC) server. This may threaten not only processing tasks production logic but also physical safety business efficiency. Intrusion Detection System (IDS) is seen as a promising...
In the paper, we modelling for information theft Trojan based on Stochastic Game Nets (SGN), a novel method which good at multirole game problem described, and has been applied in many fields of networks with interactive behaviors. Combination SGN practical problem, present an algorithm solving equilibrium strategy to computer model SGN. Finally analyse our research paper some indicators, such as probability successful average time theft. The results can also offer consultations user.
The collection and identification of digital evidence is an essential procedure in file forensics, which contains manual retrieval, traditional hash techniques query by keywords etc. For the vulnerability electronic documents, it easy to be changed or tampered with. So looking for files similar with target becomes important forensic. However, forensic system usually based on searching just scan entire files, both lack high enough speed accuracy support nowadays tasks. Considering fuzzy...