A5087247680- Data Management and Algorithms
- Machine Learning and ELM
- Advanced Database Systems and Queries
- Brain Tumor Detection and Classification
- Energy Efficient Wireless Sensor Networks
- Blockchain Technology Applications and Security
- Functional Brain Connectivity Studies
- Graph Theory and Algorithms
- EEG and Brain-Computer Interfaces
- Bioinformatics and Genomic Networks
- Radiomics and Machine Learning in Medical Imaging
- Complex Network Analysis Techniques
- Gene Regulatory Network Analysis
- Caching and Content Delivery
- Gene expression and cancer classification
- Geographic Information Systems Studies
- Cloud Computing and Resource Management
- Cloud Data Security Solutions
- AI in cancer detection
- Advanced Memory and Neural Computing
- Mental Health Research Topics
- Data Stream Mining Techniques
- Neural dynamics and brain function
- Advanced Image Processing Techniques
- Opportunistic and Delay-Tolerant Networks
Northeastern University
2016-2025
Universidad del Noreste
2024
Neusoft (China)
2023
Beijing Institute of Big Data Research
2018-2023
Ministry of Education of the People's Republic of China
2010-2013
Northeastern University
2008
A computer-aided diagnosis (CAD) system based on mammograms enables early breast cancer detection, diagnosis, and treatment. However, the accuracy of existing CAD systems remains unsatisfactory. This paper explores a method feature fusion with convolutional neural network (CNN) deep features. First, we propose mass detection CNN features unsupervised extreme learning machine (ELM) clustering. Second, build set fusing features, morphological texture density Third, an ELM classifier is...
As uncertainty is the inherent character of sensing data, processing and optimization techniques for Probabilistic Skyline (PS) in wireless sensor networks (WSNs) are investigated. It can be proved that PS not decomposable after analyzing its properties, so in-network aggregation cannot used directly to improve performance. In this paper, an efficient algorithm, called Distributed Processing (DPPS) query WSNs, proposed. The algorithm divides data into candidate (CD), irrelevant (ID),...
COVID-19 virus is raging across the planet. In countries where epidemic under control, main mode of transmission through transport imported refrigerated food from areas. Blockchain a great way for government to trace every piece food. However, high-performance requirements blockchain system nodes limit its wide application. Several sharding-based systems have been proposed solve this limitation. Which blocks should be saved by in new problem. To problem, optimized data storage method paper....
Reverse skyline query plays an important role in many sensing applications, such as environmental monitoring, habitat and battlefield monitoring. Due to the limited power supplies of wireless sensor nodes, existing centralized approaches, which do not consider energy efficiency, cannot be directly applied distributed environment. In this paper, we investigate how process reverse queries efficiently networks. Initially, theoretically analyzed properties proposed a skyband-based approach...
Sleep staging is an indispensable indicator for measuring sleep quality and evaluating disorders. Deep learning methods have been successfully applied to automatic (ASS) based on EEG signals, achieving significant progress. However, previous studies limited extracting local features of signals while neglecting the importance global features. To solve this problem, we propose a novel ASS model named LGSleepNet, which consists asymmetric Siamese neural network (ASNN), adaptive orthogonal...
Interoperable Blockchain Database (IBD) can enable users to execute transactions for sharing data stored in various blockchains maintained by different organizations or communities a transparent manner. However, compared traditional distributed databases, IBD hardly provide high-level security and scalability, which are caused many factors, such as system architecture, consensus protocol, interactive pattern. Among them, the protocol is most critical factor, since credibility of nodes inside...
<i>A representative skyline</i> contains <inline-formula><tex-math notation="LaTeX">$k$ </tex-math></inline-formula> skyline points that can represent its corresponding full skyline. The existing measuring criteria of <inline-formula> <tex-math notation="LaTeX">$k$</tex-math></inline-formula> skylines are specifically designed for static data, and they cannot effectively handle streaming data. In this paper, we focus on the problem calculating over data streams. First, propose a new...