2022 56th Annual Conference on Information Sciences and Systems (CISS)最新文献_第4页

Secure Integer Comparison Protocol For ML-based Disease Diagnosis In MHN With Energy Efficient Edge Computing 基于高效能边缘计算的MHN基于ml的疾病诊断安全整数比较协议

2022 56th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2022-03-09 DOI: 10.1109/CISS53076.2022.9751179

Sona Alex, Kirubai Dhanaraj, P. Deepthi

{"title":"Secure Integer Comparison Protocol For ML-based Disease Diagnosis In MHN With Energy Efficient Edge Computing","authors":"Sona Alex, Kirubai Dhanaraj, P. Deepthi","doi":"10.1109/CISS53076.2022.9751179","DOIUrl":"https://doi.org/10.1109/CISS53076.2022.9751179","url":null,"abstract":"The benefits that MHN offers to healthcare services are not fully garnered due to concerns on privacy and security of sensitive medical data. Severe constraints on battery capacity and computing resources at the edge devices of MHN impose restrictions in deploying strong secure systems. Medical data need to be stored, communicated, and processed securely in real-time. Homomorphic encryption help to perform linear operations securely on the encrypted data. More complicated operations like ML-based disease diagnosis require nonlinear operations such as integer comparison. Hence a secure multiparty computation over homomorphically encrypted data is required for secure integer comparison. However, comparison protocols available in the literature use energy-hungry public-key cryptosystems. This article presents the design of an energy-efficient additively homomorphic modified Rivest scheme (AHMRS) to support secure integer comparison protocol (SICP-AHMRS), which facilitates fast and energy-efficient ML-based disease diagnosis. The proposed SICP-AHMRS guarantees the privacy of the data being compared. The experiments using the Raspberry Pi 3B+ board show that the energy consumption, processing delay, and bandwidth efficiency of the proposed SICP-AHMRS are much better than those of the existing schemes.","PeriodicalId":305918,"journal":{"name":"2022 56th Annual Conference on Information Sciences and Systems (CISS)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134590428","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Learning and generalization of one-hidden-layer neural networks, going beyond standard Gaussian data 学习和泛化单隐层神经网络，超越标准高斯数据

2022 56th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2022-03-09 DOI: 10.1109/CISS53076.2022.9751184

Hongkang Li, Shuai Zhang, M. Wang

引用次数: 3

Fairness in Sensor Detection Systems 传感器检测系统中的公平性

2022 56th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2022-03-09 DOI: 10.1109/CISS53076.2022.9751155

Benedito J. B. Fonseca

引用次数: 1

On the Convergence of Hybrid Federated Learning with Server-Clients Collaborative Training 混合联邦学习与服务器-客户端协同训练的融合研究

2022 56th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2022-03-09 DOI: 10.1109/CISS53076.2022.9751161

Kun Yang, Cong Shen

{"title":"On the Convergence of Hybrid Federated Learning with Server-Clients Collaborative Training","authors":"Kun Yang, Cong Shen","doi":"10.1109/CISS53076.2022.9751161","DOIUrl":"https://doi.org/10.1109/CISS53076.2022.9751161","url":null,"abstract":"State-of-the-art federated learning (FL) paradigms utilize data collected and stored in massively distributed clients to train a global machine learning (ML) model, in which local datasets never leave the devices and the server performs simple model aggregation for better privacy protection. In reality, however, the parameter server often has access to certain (possibly small) amount of data, and it is computationally more powerful than the clients. This work focuses on analyzing the convergence behavior of hybrid federated learning that leverages the server dataset and its computation power for collaborative model training. Different from standard FL where stochastic gradient descent (SGD) is always computed in a parallel fashion across all clients, this architecture enjoys both parallel SGD at clients and sequential SGD at the server, by using the aggregated model from clients as a new starting point for server SGD. The main contribution of this work is the convergence rate upper bounds of this aggregate-then-advance hybrid FL design. In particular, when the local SGD keeps an $mathcal{O}(1/t)$ stepsize, the server SGD must adjust its stepsize to scale no slower than $mathcal{O}(1/t^{2})$ to strictly outperform local SGD with strongly convex loss functions. Numerical experiments are carried out using standard FL tasks, where the accuracy and convergence rate advantages over clients-only (FEDAVG) and server-only training are demonstrated.","PeriodicalId":305918,"journal":{"name":"2022 56th Annual Conference on Information Sciences and Systems (CISS)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125433066","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Multi-Designated Receiver Authentication-Codes with Information-Theoretic Security 具有信息安全的多指定接收方认证码

2022 56th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2022-03-09 DOI: 10.1109/CISS53076.2022.9751164

Takenobu Seito, Junji Shikata, Yohei Watanabe

引用次数: 0

Neural Language Modeling of Unstructured Clinical Notes for Automated Patient Phenotyping 非结构化临床记录的神经语言建模用于自动患者表型

2022 56th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2022-03-09 DOI: 10.1109/CISS53076.2022.9751198

Akshara Prabhakar, S. Shidharth, Sowmya S Kamath

{"title":"Neural Language Modeling of Unstructured Clinical Notes for Automated Patient Phenotyping","authors":"Akshara Prabhakar, S. Shidharth, Sowmya S Kamath","doi":"10.1109/CISS53076.2022.9751198","DOIUrl":"https://doi.org/10.1109/CISS53076.2022.9751198","url":null,"abstract":"The availability of huge volume and variety of healthcare data provides a wide scope for designing cutting-edge clinical decision support systems (CDSS) that can improve the quality of patient care. Identifying patients suffering from certain conditions/symptoms, commonly referred to as phenotyping, is a fundamental problem that can be addressed using the rich health-related data collected for generation of Electronic Health Records (EHRs). Phenotyping forms the foundation for translational research, effectiveness studies, and is used for analyzing population health using regularly collected EHR data. Also, determining if a patient has a particular medical condition is crucial for secondary analysis, such as in critical care situations to predict potential drug interactions and adverse events. In this paper, we consider all categories of unstructured clinical notes of patients, typically stored as part of EHRs in the raw form. The standard MIMIC-III dataset is considered for benchmark experiments for patient phenotyping. Experiments revealed that our proposed models outperformed state-of-the art works built on vanilla BERT & ClinicalBERT models on the patient cohort considered, measured in terms of standard multi-label classification metrics like AUROC score (improvement by 6%), F1-score (by 4%), and Hamming Loss (by 17%) when we considered only patient discharge summaries and radiology notes. Further experiments with other note categories showed that using discharge summaries and physician notes yields significant improvements on the entire dataset giving 0.8 AUROC score, 0.72 F1 score, 0.09 Hamming loss.","PeriodicalId":305918,"journal":{"name":"2022 56th Annual Conference on Information Sciences and Systems (CISS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131229434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Policy Gradient for Ratio Optimization: A Case Study 比率优化的策略梯度:一个案例研究

2022 56th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2022-03-09 DOI: 10.1109/CISS53076.2022.9751163

Wesley A. Suttle, Alec Koppel, Ji Liu

引用次数: 0

Doubly Pessimistic Algorithms for Strictly Safe Off-Policy Optimization 严格安全脱策略优化的双悲观算法

2022 56th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2022-03-09 DOI: 10.1109/CISS53076.2022.9751158

Sanae Amani, Lin F. Yang

{"title":"Doubly Pessimistic Algorithms for Strictly Safe Off-Policy Optimization","authors":"Sanae Amani, Lin F. Yang","doi":"10.1109/CISS53076.2022.9751158","DOIUrl":"https://doi.org/10.1109/CISS53076.2022.9751158","url":null,"abstract":"We study offline reinforcement learning (RL) in the presence of safety requirements: from a dataset collected a priori and without direct access to the true environment, learn an optimal policy that is guaranteed to respect the safety constraints. We address this problem by modeling the safety requirement as an unknown cost function of states and actions, whose expected value with respect to the policy must fall below a certain threshold. We then present an algorithm in the context of finite-horizon Markov decision processes (MDPs), termed Safe-DPVI that performs in a doubly pessimistic manner when 1) it constructs a conservative set of safe policies; and 2) when it selects a good policy from that conservative set. Without assuming the sufficient coverage of the dataset or any structure for the underlying MDPs, we establish a data-dependent upper bound on the suboptimality gap of the safe policy Safe-DPVI returns. We then specialize our results to linear MDPs with appropriate assumptions on dataset being well-explored. Both data-dependent and specialized bounds nearly match that of state-of-the-art unsafe offline RL algorithms, with an additional multiplicative factor $frac{Sigma_{h=1}^{H}alpha_{h}}{H}$, where αh characterizes the safety constraint at time-step $h$. We further present numerical simulations that corroborate our theoretical findings. A full version referred to as technical report of this paper is accessible at: https://offline-rl-neurips.github.io/2021/pdf/21.pdf","PeriodicalId":305918,"journal":{"name":"2022 56th Annual Conference on Information Sciences and Systems (CISS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116154572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Design and Implementation of a Steganography-based System that Provides Protection for Breast Cancer Patient's Data 基于隐写术的乳腺癌患者数据保护系统的设计与实现

2022 56th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2022-03-09 DOI: 10.1109/CISS53076.2022.9751183

Sewar Khalifeh, Jude Georgi, Shatha Shakhatreh

引用次数: 1

Interpretable Hierarchical Bayesian Modeling of Cell-Type Distributions in COVID-19 Disease COVID-19疾病中细胞类型分布的可解释层次贝叶斯模型

2022 56th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2022-03-09 DOI: 10.1109/CISS53076.2022.9751177

Sarah Parsons, Nathan P. Whitener, Sapana Bhandari, Natalia Khuri

引用次数: 0