Výsledky vyhledávání - "Elaheh Baharlouei"

Akademický článek

Machine Learning, Deep Learning, and Data Preprocessing Techniques for Detecting, Predicting, and Monitoring Stress and Stress-Related Mental Disorders: Scoping Review

Autor: Moein Razavi, Samira Ziyadidegan, Ahmadreza Mahmoudzadeh, Saber Kazeminasab, Elaheh Baharlouei, Vahid Janfaza, Reza Jahromi, Farzan Sasangohar

Publikováno v: JMIR Mental Health, Vol 11, p e53714 (2024)

BackgroundMental stress and its consequent mental health disorders (MDs) constitute a significant public health issue. With the advent of machine learning (ML), there is potential to harness computational techniques for better understanding and addre

Externí odkaz: https://doaj.org/article/2c30b4ec934f4338b128909c33d7c5c3

Zobrazit plný text záznamu

High Accuracy Matrix Computations on Neural Engines: A Study of QR Factorization and its Applications

Autor: Elaheh Baharlouei, Shaoshuai Zhang, Panruo Wu

Publikováno v: HPDC

Fueled by the surge of ever expanding successful applications of deep neural networks and the great computational power demanded, modern computer processors and accelerators are beginning to offer half precision floating point arithmetic support, and

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::c9d379ca01b71f5f1d7d211d781fcd74
https://doi.org/10.1145/3369583.3392685

Zobrazit plný text záznamu

Hybrid history-based test, utilizing a probabilistic approach to reduce test time

Autor: Hossein Sabaghian-Bidgoli, Elaheh Baharlouei, Vahid Janfaza

Publikováno v: EWDTS

This paper presents a hybrid history-based test generation mechanism that intermittently applies partial-test vectors to reduce test application time. Test generation is done by looking into the results of the circuit under test that are used later a

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::f5848d9693c988e961a83b9031e9b998
https://doi.org/10.1109/ewdts.2017.8110140

Zobrazit plný text záznamu

A new fault-tolerant deadlock-free fully adaptive routing in NOC

Autor: Vahid Janfaza, Elaheh Baharlouei

Publikováno v: EWDTS

Future applications will require processors with many cores communicating through a regular interconnection network. As the semiconductor industry advances to the deep sub-micron and nano technology points, the on-chip components are more prone to th

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::d7be0c48c0443268dacccfb3b2be20f2
https://doi.org/10.1109/ewdts.2017.8110139

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání