https://cis.temple.edu/~wu/research/publications/Publication_files/10_bare_jrnl_compsoc.pdf
1.1 Motivation and Challenges Service provisioning and updating refers to the decision-making process of the locations of services within a specific edge computing network to balance the interests of service providers and consumers to achieve the greatest eficiency possible [7]. Numerous mobile devices and sensors in edge networks need to interface with services and exchange data in real-time ...
https://cis.temple.edu/~latecki/Papers/Quan_DRBANET_ICIP_2022.pdf
ABSTRACT Due to the powerful ability to encode image details and semantics, many lightweight dual-resolution networks have been proposed in recent years. However, most of them ignore the benefit of boundary information. This paper introduces a lightweight dual-resolution network, called DRBANet, aim-ing to refine semantic segmentation results with the aid of boundary information. DRBANet also ...
https://cis.temple.edu/~tug29203/19spring-5617/lectures/ch3-3.pdf
Lecture 6 – Chapter 3 TCP flow and congestion control CIS 5617, Fall 2019 Anduo Wang Based on Slides created by JFK/KWR
https://cis.temple.edu/~jiewu/research/publications/Publication_files/WENJUNJIANG2021TWeb.pdf
In online systems, including e-commerce platforms, many users resort to the reviews or comments generated by previous consumers for decision making, while their time is limited to deal with many reviews. Therefore, a review summary, which contains all important features in user-generated reviews, is expected. In this paper, we study “how to generate a comprehensive review summary from a ...
https://cis.temple.edu/~latecki/Papers/PAMI_Jan2013.pdf
Affinity Learning with Diffusion on Tensor Product Graph Xingwei Yang, Lakshman Prasad, and Longin Jan Latecki, Senior Member, IEEE
https://cis.temple.edu/~apal/nfmi_comnet.pdf
Near Field Magnetic Induction (NFMI) based communication is an emerging technology that promises several advantages over the traditional radio frequency (RF) communication including low energy use, ability to work reliably in a variety of difficult propagation media (e.g., water, non-ferromagnetic metals, underground, tissue media of fresh produce & meats, etc.), and low leakage possibility ...
https://cis.temple.edu/~latecki/Papers/BaiPAMI2019.pdf
Abstract—Diffusion process has advanced object retrieval greatly as it can capture the underlying manifold structure. Recent studies have experimentally demonstrated that tensor product diffusion can better reveal the intrinsic relationship between objects than other variants. However, the principle remains unclear, i.e., what kind of manifold structure is captured. In this paper, we propose ...
https://scholarshare.temple.edu/bitstreams/1c1f1a6d-0f34-4234-8b39-41d9eeb397f0/download
of machine learning (ML) versus a traditional statistical model in predicting dental caries in
https://cis.temple.edu/~wu/research/publications/Publication_files/J-CT-2024-Balancing%20Privacy%20and%20Accuracy%20using%20Siginificant%20Gradient%20Protection%20in%20Federated%20Learning.pdf
Abstract—Previous state-of-the-art studies have demonstrated that adversaries can access sensitive user data by membership inference attacks (MIAs) in Federated Learning (FL). Intro-ducing differential privacy (DP) into the FL framework is an effective way to enhance the privacy of FL. Nevertheless, in differentially private federated learning (DP-FL), local gradients become excessively ...
https://sites.temple.edu/pdames/files/2019/03/ChungEtAlTRO2018.pdf
Abstract—The use of aerial swarms to solve real-world prob-lems has been increasing steadily, accompanied by falling prices and improving performance of communication, sensing, and pro-cessing hardware. The commoditization of hardware has reduced unit costs, thereby lowering the barriers to entry to the field of aerial swarm robotics. A key enabling technology for swarms is the family of ...