Nam Pham

Nam Pham

Auto-generated profile, based on publicly available information

Nam Pham

Thai Nguyen University of Information and Communication Technology, Thainguyen, Vietnam

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

1 January 2010
Verified
Conference Paper
Closed access
NPNam Pham
Nam Pham
TATarek Abdelzaher
Tarek Abdelzaher
SNSuman Nath
Suman Nath
This paper derives fundamental bounds on privacy achievable in future human-centric cyber-physical systems, where time-series sensor data are shared among individuals to compute aggregate information of mutual interest. For example, individual GPS-trajectories may be shared to compute average traffic speed at different locations. An optimal trade-off is explored between individual user privacy, achieved by perturbing data prior to sharing, and the corresponding accuracy of computed aggregate information. The work is motivated by an emergent category of cyber-physical applications that involves large-scale interaction between humans, networked engineered artifacts, and the physical world. These applications are brought about by the proliferation of personal sensing devices of everyday use, leading to unprecedented opportunities for sensory data collection and sharing. The collection of sensory data from large numbers of participants offers privacy as a major new cyber-physical system challenge. In this paper, we propose a novel privacy measure, based on mutual information, and derive a perturbation algorithm, to apply prior to data sharing, that guarantees a least upper bound on the privacy measure. The new algorithm effectively hides individual user data by optimally perturbing the time-series using knowledge of only the mean and the covariance of the original data. We evaluate it using both synthetic data and collected real application data. The results show that the method significantly improves the trade-off between privacy and the accuracy of reconstruction of aggregate information from shared perturbed data.

27 March 2023
Verified
Conference Paper
Open access
CXCary Xiao
Cary Xiao
NPNam Pham
Nam Pham
EIErik Imel
Erik Imel
XLXiao Luo
Xiao Luo
Graph Attention Networks (GAT) have been extensively used to perform node-level classification on data that can be represented as a graph. However, few papers have investigated the effectiveness of using GAT on graph representations of patient similarity networks. This paper proposes Patient-GAT, a novel method to predict chronic health conditions by first integrating multi-modal data fusion to generate patient vector representations using imputed lab variables with other structured data. This data representation is then used to construct a patient network by measuring patient similarity, finally applying GAT to the patient network for disease prediction. We demonstrated our framework by predicting sarcopenia using real-world EHRs obtained from the Indiana Network for Patient Care. We evaluated the performance of our system by comparing it to other baseline models, showing that our model outperforms other methods. In addition, we studied the contribution of the temporal representation of the lab data and discussed the interpretability of this model by analyzing the attention coefficients of the trained Patient-GAT model. Our code can be found on Github1

11 October 2023 in IEEE Access
Verified
Journal Article
Open access
TPThanh-Nam Pham
Thanh-Nam Pham
TDTho Mai Duc
Tho Mai Duc
XPXuan-Kien Pham
Xuan-Kien Pham
This paper proposes constructing a smart parking service model based on the Internet of Things and Fog computing architecture. The weaknesses of previous parking service delivery systems are that they did not offer a complete set of end-to-end parking services, such as inaccurate information about parking in real-time, poor system storage and expansion capacity, and knowledge to assist the driver in successfully reaching the parking space at a minimum cost. Therefore, our system offers a complete set of parking assistance services, from when the driver searches and makes a reservation to navigation services that help the driver successfully park at the desired parking spot. To address the problems of storage and system expansion, we also implemented services based on the Internet of Things and Fog computing platforms. The simulation and experimental implementation results show that the services we designed significantly improve the performance of the existing parking system compared to the other systems. Real-time vehicles are handled quickly, significantly reducing driver costs and increasing profits for managers.

9 August 2021 in TNU Journal of Science and Technology
Verified
Journal Article
Closed access
PDF file
PNPhạm Thành Nam
Phạm Thành Nam
PKPhạm Xuân Kiên
Phạm Xuân Kiên
ĐCĐoàn Mạnh Cường
Đoàn Mạnh Cường
Hiện nay, bài toán ùn tắc giao thông và đỗ xe đang trở thành vấn đề lớn tại các thành phố đang phát triển tại Việt Nam. Xây dựng các bãi đỗ xe thông minh là một giải pháp tối ưu để giải quyết bài toán này dựa trên sự phát triển của khoa học công nghệ. Trong nghiên cứu này, chúng tôi đề xuất xây dựng thử nghiệm một mô hình hệ thống mạng lưới liên kết các bãi đỗ xe thông minh để giải quyết các yêu cầu đỗ xe của người dùng. Trong hệ thống này, các bãi đỗ xe được xây dựng dựa trên công nghệ Internet of Things (IoT) kết hợp với công nghệ lưu trữ đám mây để lưu trữ dữ liệu. Thông tin dữ liệu của các bãi đỗ như là chi phí đỗ xe, số lượng chỗ đỗ còn trống được định kỳ cập nhật trên hệ thống theo thời gian thực. Thông tin này được sử dụng như là các tham số để người dùng đưa ra các quyết định tối ưu trong việc tìm kiếm và đặt chỗ đỗ xe của mình. Chúng tôi đã triển khai thử nghiệm thành công hệ thống đỗ xe thông minh ra thực tế bao gồm phần cứng bãi đỗ, phần mềm người dùng để tìm kiếm và đặt chỗ, các chức năng dẫn đường trong hệ thống.