Jun Shen

ORCID: 0000-0002-9403-7140
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Service-Oriented Architecture and Web Services
  • Cloud Computing and Resource Management
  • Online Learning and Analytics
  • IoT and Edge/Fog Computing
  • Business Process Modeling and Analysis
  • Semantic Web and Ontologies
  • Traffic Prediction and Management Techniques
  • Cloud Data Security Solutions
  • Recommender Systems and Techniques
  • Cryptography and Data Security
  • Blockchain Technology Applications and Security
  • Privacy-Preserving Technologies in Data
  • Neural Networks and Applications
  • Energy Load and Power Forecasting
  • Innovative Teaching and Learning Methods
  • Bioinformatics and Genomic Networks
  • Topic Modeling
  • Big Data and Business Intelligence
  • Semiconductor Quantum Structures and Devices
  • Distributed and Parallel Computing Systems
  • Image and Signal Denoising Methods
  • Network Security and Intrusion Detection
  • Advanced Software Engineering Methodologies
  • Phase Equilibria and Thermodynamics
  • Software System Performance and Reliability

University of Wollongong
2016-2025

University of California, Los Angeles
2024-2025

Hebei University
2005-2025

Shanghai University of Traditional Chinese Medicine
2024

Shanghai Guanghua Hospital of Integrated Traditional Chinese and Western Medicine
2023-2024

Hubei University of Medicine
2024

Jinan University
2017-2024

Shanghai University of Engineering Science
2021-2024

Chongqing Institute of Green and Intelligent Technology
2013-2024

Beijing Institute of Technology
2021-2024

10.1016/1049-9652(92)90060-b article EN CVGIP Graphical Models and Image Processing 1992-03-01

With the rapid development of cloud computing, storage has been accepted by an increasing number organizations and individuals, therein serving as a convenient on-demand outsourcing application. However, upon losing local control data, it becomes urgent need for users to verify whether service providers have stored their data securely. Hence, many researchers devoted themselves design auditing protocols directed at outsourced data. In this paper, we propose efficient public protocol with...

10.1109/tifs.2017.2705620 article EN IEEE Transactions on Information Forensics and Security 2017-05-18

With recent advances in mobile learning (m-learning), it is becoming possible for activities to occur everywhere. The learner model presented our earlier work was partitioned into smaller elements the form of profiles, which collectively represent entire process. This paper presents an Adaptive Neuro-Fuzzy Inference System (ANFIS) delivering adapted content learners. ANFIS designed using trial and error based on various experiments. study conducted illustrate that effective with hybrid...

10.1109/tlt.2011.36 article EN other-oa IEEE Transactions on Learning Technologies 2011-12-13

10.1016/j.future.2016.11.033 article EN publisher-specific-oa Future Generation Computer Systems 2016-12-08

In recent years, machine learning-based cyber intrusion detection methods have gained increasing popularity. The number and complexity of new attacks continue to rise; therefore, effective intelligent solutions are necessary. Unsupervised learning techniques particularly appealing systems since they can detect known unknown types as well zero-day attacks. the current paper, we present an unsupervised anomaly method, which combines Sub-Space Clustering (SSC) One Class Support Vector Machine...

10.26599/tst.2019.9010051 article EN Tsinghua Science & Technology 2020-07-24

10.1016/j.pmcj.2017.03.013 article EN publisher-specific-oa Pervasive and Mobile Computing 2017-04-02

The Corona Virus Disease 2019 has a great impact on public health and psychology. People stay at home for long time rarely go out. With the improvement of epidemic situation, people began to different places check in. To maintain mental health, it is necessary propose point-of-interest (POI) prediction model which can mine users' interests. However, current techniques suffer from lower precision during practical value poor, due sparse data check-in. Faced with this challenge, we an...

10.1002/int.22710 article EN International Journal of Intelligent Systems 2021-10-01

Cyber attacks and intrusions have become the major obstacles to adoption of Industrial Internet Things (IIoT) in critical industries. Imbalanced data distribution is a common problem IIoT environments that negatively influence machine learning-based intrusion detection systems (IDSs). To address this issue, we introduce EvolCostDeep, hybrid model stacked autoencoders (SAE) convolutional neural networks (CNNs) with new cost-dependent loss function. The function aims optimize model's...

10.1109/jiot.2022.3188224 article EN IEEE Internet of Things Journal 2022-07-04

Development of potent and broad-spectrum antimicrobial peptides (AMPs) could help overcome the resistance crisis. We develop a peptide language-based deep generative framework (deepAMP) for identifying potent, AMPs. Using deepAMP to reduce enhance membrane-disrupting abilities AMPs, we identify, synthesize, experimentally test 18 T1-AMP (Tier 1) 11 T2-AMP 2) candidates in two-round design by employing cross-optimization-validation. More than 90% designed AMPs show better inhibition...

10.1038/s41467-024-51933-2 article EN cc-by-nc-nd Nature Communications 2024-08-30

The metaverse, along with its various Web 3.0 sub-domains, represents a ground-breaking extension of the physical and digital worlds. In this emerging landscape, real virtual worlds are being integrated in ways that facilitate interaction create immersive experiences. This transformation has significant implications for diverse fields, particularly reshaping both online traditional education methods. By analyzing 417 comprehensive white papers released 2022 2023 from leading consulting firms...

10.1109/tlt.2024.3385505 article EN IEEE Transactions on Learning Technologies 2024-01-01

A structure based on a bipolar transport/emitting layer is proposed and implemented for making organic light-emitting diodes. Compared to the conventional heterojunction diodes, more than factor of six improvement in device reliability (a projected operating lifetime 70 000 h) achieved structure. The significant attributed elimination heterointerface present devices which greatly affects reliability.

10.1063/1.124309 article EN Applied Physics Letters 1999-07-12

10.1016/0031-3203(91)90048-a article EN Pattern Recognition 1991-01-01

Radio frequency identification (RFID) is expected to become pervasive and ubiquitous, as it can be embedded into everyday items smart labels. A typical scenario of exploiting RFID supply chain. The based chain management yields convenience, efficiency productivity gains. However, systems create new risks security privacy. We briefly present the current solutions approach then proposed, which exploits randomized read access control thus prevents hostile tracking man-in-the-middle attack. In...

10.1109/cec-east.2004.14 article EN IEEE International Conference on E-Commerce Technology for Dynamic E-Business 2005-03-21

Mobile learning in massive open online course (MOOC) evidently differs from its traditional ways as it relies more on collaborations and becomes fragmented. We present a cloud-based virtual environment (VLE) which can organize learners into better teamwork context customize micro resources order to meet personal demands real time. Particularly, smart was built by newly designed Software Service (SaaS), namely Micro Learning (MLaaS). It aims provide adaptive contents well path identifications...

10.1109/tsc.2015.2473854 article EN IEEE Transactions on Services Computing 2015-08-27
Coming Soon ...