Hanieh Hashemi
YOU?
Author Swipe
View article: Smart University of Medical Sciences Virtual Summer Semester from the Perspective of Its Stakeholders: A Multi-methods Cross-sectional Study
Smart University of Medical Sciences Virtual Summer Semester from the Perspective of Its Stakeholders: A Multi-methods Cross-sectional Study Open
Background: In medical education, determining the strengths, weaknesses, desirability, and success of training courses from the perspective of its stakeholders is of particular importance because it can be the basis for subsequent decision…
View article: Differentially Private Heavy Hitter Detection using Federated Analytics
Differentially Private Heavy Hitter Detection using Federated Analytics Open
In this work, we study practical heuristics to improve the performance of prefix-tree based algorithms for differentially private heavy hitter detection. Our model assumes each user has multiple data points and the goal is to learn as many…
View article: Design, Development and Evaluation of an Application based on Clinical Decision Support Systems (CDSS) for Over-The-Counter (OTC) Therapy: An Educational Interventions in Community Pharmacists.
Design, Development and Evaluation of an Application based on Clinical Decision Support Systems (CDSS) for Over-The-Counter (OTC) Therapy: An Educational Interventions in Community Pharmacists. Open
The OTC therapy application developed in this study will help Persian-speaking pharmacists to increase their knowledge and pharmaceutical skills.
View article: Data Leakage via Access Patterns of Sparse Features in Deep Learning-based Recommendation Systems
Data Leakage via Access Patterns of Sparse Features in Deep Learning-based Recommendation Systems Open
Online personalized recommendation services are generally hosted in the cloud where users query the cloud-based model to receive recommended input such as merchandise of interest or news feed. State-of-the-art recommendation models rely on…
View article: Prediction of students’ performance in a national medical exam using machine learning techniques
Prediction of students’ performance in a national medical exam using machine learning techniques Open
Predicting student academic performance in educational information systems becomes one of the major concerns in improving the quality of academic institutions. Educational data mining can identify the settings that characterize students’ b…
View article: DarKnight: An Accelerated Framework for Privacy and Integrity Preserving Deep Learning Using Trusted Hardware
DarKnight: An Accelerated Framework for Privacy and Integrity Preserving Deep Learning Using Trusted Hardware Open
Privacy and security-related concerns are growing as machine learning reaches diverse application domains. The data holders want to train or infer with private data while exploiting accelerators, such as GPUs, that are hosted in the cloud.…
View article: Using logistic regression and point-biserial correlation, an investigation of pedestrian violations and their opportunities to cross at signalized intersections
Using logistic regression and point-biserial correlation, an investigation of pedestrian violations and their opportunities to cross at signalized intersections Open
Intersection's safety and efficiency are affected by pedestrian offences. As a result, it's critical to recognize and prioritize the factors that influence pedestrian violations. Three intersections with commercial, medical, and educationa…
View article: Discovering Rules from a National Exam Repository: A Use Case for Data Analysis from Iranian Medical Schools Entry Exam
Discovering Rules from a National Exam Repository: A Use Case for Data Analysis from Iranian Medical Schools Entry Exam Open
Many methods have been studied to analyze and interpret patterns and relationships that are embedded in the database to discover new knowledge in educational systems. Association rule mining is a type of data mining that identifies relatio…
View article: Adaptive Verifiable Coded Computing: Towards Fast, Secure and Private Distributed Machine Learning
Adaptive Verifiable Coded Computing: Towards Fast, Secure and Private Distributed Machine Learning Open
Stragglers, Byzantine workers, and data privacy are the main bottlenecks in distributed cloud computing. Some prior works proposed coded computing strategies to jointly address all three challenges. They require either a large number of wo…
View article: Contributing Factors in Pedestrians Waiting Time at Signalized Intersections Using Survival Analysis
Contributing Factors in Pedestrians Waiting Time at Signalized Intersections Using Survival Analysis Open
Recognizing elements that determine pedestrian waiting time is important when designing intersection implications in order to reduce violations and their repercussions.The goal of this study is to investigate these influencing elements.To …
View article: Attribute Inference Attack of Speech Emotion Recognition in Federated Learning Settings
Attribute Inference Attack of Speech Emotion Recognition in Federated Learning Settings Open
Speech emotion recognition (SER) processes speech signals to detect and characterize expressed perceived emotions. Many SER application systems often acquire and transmit speech data collected at the client-side to remote cloud platforms f…
View article: DarKnight: An Accelerated Framework for Privacy and Integrity Preserving Deep Learning Using Trusted Hardware
DarKnight: An Accelerated Framework for Privacy and Integrity Preserving Deep Learning Using Trusted Hardware Open
Privacy and security-related concerns are growing as machine learning reaches diverse application domains. The data holders want to train or infer with private data while exploiting accelerators, such as GPUs, that are hosted in the cloud.…
View article: Verifiable Coded Computing: Towards Fast, Secure and Private Distributed Machine Learning.
Verifiable Coded Computing: Towards Fast, Secure and Private Distributed Machine Learning. Open
Stragglers, Byzantine workers, and data privacy are the main bottlenecks in distributed cloud computing. Several prior works proposed coded computing strategies to jointly address all three challenges. They require either a large number of…
View article: Adaptive Verifiable Coded Computing: Towards Fast, Secure and Private Distributed Machine Learning
Adaptive Verifiable Coded Computing: Towards Fast, Secure and Private Distributed Machine Learning Open
Stragglers, Byzantine workers, and data privacy are the main bottlenecks in distributed cloud computing. Some prior works proposed coded computing strategies to jointly address all three challenges. They require either a large number of wo…
View article: Opportunities and Challenges of Online Take-Home Exams in Medical Education
Opportunities and Challenges of Online Take-Home Exams in Medical Education Open
Context: Student assessment is an essential part of higher education. Many different technology-based assessment methods have been formed with the increasing development of IT and its introduction into the education system. Online take-hom…
View article: Byzantine-Robust and Privacy-Preserving Framework for FedML
Byzantine-Robust and Privacy-Preserving Framework for FedML Open
Federated learning has emerged as a popular paradigm for collaboratively training a model from data distributed among a set of clients. This learning setting presents, among others, two unique challenges: how to protect privacy of the clie…
View article: Privacy and Integrity Preserving Training Using Trusted Hardware
Privacy and Integrity Preserving Training Using Trusted Hardware Open
Privacy and security-related concerns are growing as machine learning reaches diverse application domains. The data holders want to train with private data while exploiting accelerators, such as GPUs, that are hosted in the cloud. However,…
View article: Secure and Fault Tolerant Decentralized Learning
Secure and Fault Tolerant Decentralized Learning Open
Federated learning (FL) is a promising paradigm for training a global model over data distributed across multiple data owners without centralizing clients' raw data. However, sharing of local model updates can also reveal information of cl…
View article: Byzantine-Resilient Federated Learning with Heterogeneous Data Distribution
Byzantine-Resilient Federated Learning with Heterogeneous Data Distribution Open
For mitigating Byzantine behaviors in federated learning (FL), most state-of-the-art approaches, such as Bulyan, tend to leverage the similarity of updates from the benign clients. However, in many practical FL scenarios, data is non-IID a…
View article: DarKnight: A Data Privacy Scheme for Training and Inference of Deep Neural Networks
DarKnight: A Data Privacy Scheme for Training and Inference of Deep Neural Networks Open
Protecting the privacy of input data is of growing importance as machine learning methods reach new application domains. In this paper, we provide a unified training and inference framework for large DNNs while protecting input privacy and…
View article: PartitionedVC: Partitioned External Memory Graph Analytics Framework for\n SSDs
PartitionedVC: Partitioned External Memory Graph Analytics Framework for\n SSDs Open
Graph analytics are at the heart of a broad range of applications such as\ndrug discovery, page ranking, and recommendation systems. When graph size\nexceeds memory size, out-of-core graph processing is needed. For the widely\nused externa…
View article: PartitionedVC: Partitioned External Memory Graph Analytics Framework for SSDs
PartitionedVC: Partitioned External Memory Graph Analytics Framework for SSDs Open
Graph analytics are at the heart of a broad range of applications such as drug discovery, page ranking, and recommendation systems. When graph size exceeds memory size, out-of-core graph processing is needed. For the widely used external m…