Loading...
Search for: database
0.011 seconds
Total 197 records

    DONE: Distributed approximate newton-type method for federated edge learning

    , Article IEEE Transactions on Parallel and Distributed Systems ; Volume 33, Issue 11 , 2022 , Pages 2648-2660 ; 10459219 (ISSN) Dinh, C. T ; Tran, N. H ; Nguyen, T. D ; Bao, W ; Balef, A. R ; Zhou, B. B ; Zomaya, A. Y ; Sharif University of Technology
    IEEE Computer Society  2022
    Abstract
    There is growing interest in applying distributed machine learning to edge computing, forming federated edge learning. Federated edge learning faces non-i.i.d. and heterogeneous data, and the communication between edge workers, possibly through distant locations and with unstable wireless networks, is more costly than their local computational overhead. In this work, we propose ${{sf DONE}}$DONE, a distributed approximate Newton-type algorithm with fast convergence rate for communication-efficient federated edge learning. First, with strongly convex and smooth loss functions, ${{sf DONE}}$DONE approximates the Newton direction in a distributed manner using the classical Richardson iteration... 

    BIM and machine learning in seismic damage prediction for non-structural exterior infill walls

    , Article Automation in Construction ; Volume 139 , 2022 ; 09265805 (ISSN) Mousavi, M ; TohidiFar, A ; Alvanchi, A ; Sharif University of Technology
    Elsevier B.V  2022
    Abstract
    Despite the seismic vulnerability of non-structural Exterior Infill Walls (EIWs), their resilient design has received minimal attention. This study addresses the issue by proposing a novel framework for predicting possible damage states of EIWs. The framework benefits from an automated combination of Building Information Modeling as a visualized 3D database of the building's components and the Machine Learning classification as the prediction engine. The framework's applicability is studied in a Proof of Concept example of the exterior walls of the buildings damaged in the 2017 earthquake in Kermanshah, Iran. The Extremely Randomized Trees classifier produced the best results for predicting... 

    Pan-cancer analysis of microRNA expression profiles highlights microRNAs enriched in normal body cells as effective suppressors of multiple tumor types: A study based on TCGA database

    , Article PLoS ONE ; Volume 17, Issue 4 April , 2022 ; 19326203 (ISSN) Moradi, S ; Kamal, A ; Es, H. A ; Farhadi, F ; Ebrahimi, M ; Chitsaz, H ; Sharifi Zarchi, A ; Baharvand, H ; Sharif University of Technology
    Public Library of Science  2022
    Abstract
    Background MicroRNAs (miRNAs) are frequently deregulated in various types of cancer. While antisense oligonucleotides are used to block oncomiRs, delivery of tumour-suppressive miRNAs holds great potential as a potent anti-cancer strategy. Here, we aim to determine, and functionally analyse, miRNAs that are lowly expressed in various types of tumour but abundantly expressed in multiple normal tissues. Methods The miRNA sequencing data of 14 cancer types were downloaded from the TCGA dataset. Significant differences in miRNA expression between tumor and normal samples were calculated using limma package (R programming). An adjusted p value < 0.05 was used to compare normal versus tumor miRNA... 

    MaxHiC: A robust background correction model to identify biologically relevant chromatin interactions in Hi-C and capture Hi-C experiments

    , Article PLoS Computational Biology ; Volume 18, Issue 6 , 2022 ; 1553734X (ISSN) Alinejad Rokny, H ; Modegh, R. G ; Rabiee, H. R ; Sarbandi, E. R ; Rezaie, N ; Tam, K. T ; Forrest, A. R. R ; Sharif University of Technology
    Public Library of Science  2022
    Abstract
    Hi-C is a genome-wide chromosome conformation capture technology that detects interactions between pairs of genomic regions and exploits higher order chromatin structures. Conceptually Hi-C data counts interaction frequencies between every position in the genome and every other position. Biologically functional interactions are expected to occur more frequently than transient background and artefactual interactions. To identify biologically relevant interactions, several background models that take biases such as distance, GC content and mappability into account have been proposed. Here we introduce MaxHiC, a background correction tool that deals with these complex biases and robustly... 

    Location Privacy Preservation for Secondary Users in a Database-Driven Cognitive Radio Network

    , Article ISeCure ; Volume 14, Issue 2 , 2022 , Pages 215-227 ; 20082045 (ISSN) Salami, Z ; Ahmadian Attari, M ; Aref, M. R ; Jannati, H ; Sharif University of Technology
    Iranian Society of Cryptology  2022
    Abstract
    Since their introduction, Cognitive Radio Networks (CRN), as a new solution to the problem of spectrum scarcity, have received great attention from the research society. An important field in database-driven CRN studies is pivoted on their security issues. A critical issue in this context is user’s location privacy, which is potentially under serious threat. The query process by secondary users (SU) from the database is one of the points where the problem rises. In this paper, we propose a Privacy-Preserving Query Process (PPQP), accordingly. This method lets SUs deal in the process of spectrum query without sacrificing their location information. Analytical assessment of PPQP’s privacy... 

    Towards more secure constructions of adjustable join schemes

    , Article IEEE Transactions on Dependable and Secure Computing ; Volume 19, Issue 2 , 2022 , Pages 1078-1089 ; 15455971 (ISSN) Khazaei, S ; Rafiee, M ; Sharif University of Technology
    Institute of Electrical and Electronics Engineers Inc  2022
    Abstract
    An adjustable join (AdjoinAdjoin) scheme [4] is a symmetric-key primitive that enables a user to securely outsource his database to a server, and later to issue join queries for a pair of columns. When queries are extended to a list of columns, the 3Partition3Partition security of Adjoin schemes [8] does not capture the expected security. To address this deficiency, we introduce the syntax and security notion of multi-adjustable join (M-AdjoinM-Adjoin) schemes. We propose a new security notion for this purpose, which we refer to as M3PartitionM3Partition. The 3Partition3Partition security of AdjoinAdjoin extends to the M3PartitionM3Partition security of M-AdjoinM-Adjoin in a straightforward... 

    Security of multi-adjustable join schemes: separations and implications

    , Article IEEE Transactions on Dependable and Secure Computing ; Volume 19, Issue 4 , 2022 , Pages 2535-2545 ; 15455971 (ISSN) Rafiee, M ; Khazaei, S ; Sharif University of Technology
    Institute of Electrical and Electronics Engineers Inc  2022
    Abstract
    Database management systems (DBMS) are one of cloud services with major applications in industry and business. In the use of such services, since the cloud service provider cannot be entrusted with the plain data, the databases are typically encrypted prior to outsourcing. One of the most challenging issues in designing these services is supporting SQL join queries on the encrypted database. The multi-adjustable join scheme (M-Adjoin) [Khazaei-Rafiee 2020], an extension of Adjoin [Popa-Zeldovich 2012 and Mironov-Segev-Shahaf 2017], is a symmetric-key primitive that supports the join queries for a list of column labels on an encrypted database. In previous works, the following security... 

    Distributed detection and mitigation of biasing attacks over multi-agent networks

    , Article IEEE Transactions on Network Science and Engineering ; Volume 8, Issue 4 , 2021 , Pages 3465-3477 ; 23274697 (ISSN) Doostmohammadian, M ; Zarrabi, H ; Rabiee, H. R ; Khan, U. A ; Charalambous, T ; Sharif University of Technology
    IEEE Computer Society  2021
    Abstract
    This paper proposes a distributed attack detection and mitigation technique based on distributed estimation over a multi-agent network, where the agents take partial system measurements susceptible to (possible) biasing attacks. In particular, we assume that the system is not locally observable via the measurements in the direct neighborhood of any agent. First, for performance analysis in the attack-free case, we show that the proposed distributed estimation is unbiased with bounded mean-square deviation in steady-state. Then, we propose a residual-based strategy to locally detect possible attacks at agents. In contrast to the deterministic thresholds in the literature assuming an upper... 

    The knowledge map of energy security

    , Article Energy Reports ; Volume 7 , 2021 , Pages 3570-3589 ; 23524847 (ISSN) Nasr Esfahani, A ; Bagheri Moghaddam, N ; Maleki, A ; Nazemi, A ; Sharif University of Technology
    Elsevier Ltd  2021
    Abstract
    Much efforts have been made in the area of energy security in recent years, but due to its wide scope, it is necessary to review relevant knowledge activities and to analyze the state of knowledge of the field of energy security measurement. The purpose of this article is to present a comprehensive map of knowledge in the field of energy security. For this reason, many documents and articles have been collected during the period 2002–2019 using 7 large and reputable scientific databases as well as 53 different journals, 90% white Q1 quality. There is employed meta-synthesis, scientometrics and network analysis. In the initial survey stage where 1290 articles were found, after analyzing the... 

    COVID-19 diagnosis using capsule network and fuzzy c -means and mayfly optimization algorithm

    , Article BioMed Research International ; Volume 2021 , 2021 ; 23146133 (ISSN) Farki, A ; Salekshahrezaee, Z ; Mohammadi Tofigh, A ; Ghanavati, R ; Arandian, B ; Chapnevis, A ; Sharif University of Technology
    Hindawi Limited  2021
    Abstract
    The COVID-19 epidemic is spreading day by day. Early diagnosis of this disease is essential to provide effective preventive and therapeutic measures. This process can be used by a computer-aided methodology to improve accuracy. In this study, a new and optimal method has been utilized for the diagnosis of COVID-19. Here, a method based on fuzzy C-ordered means (FCOM) along with an improved version of the enhanced capsule network (ECN) has been proposed for this purpose. The proposed ECN method is improved based on mayfly optimization (MFO) algorithm. The suggested technique is then implemented on the chest X-ray COVID-19 images from publicly available datasets. Simulation results are... 

    Evaluation and optimization of distributed machine learning techniques for internet of things

    , Article IEEE Transactions on Computers ; 2021 ; 00189340 (ISSN) Gao, Y ; Kim, M ; Thapa, C ; Abuadbba, S ; Zhang, Z ; Camtepe, S ; Kim, H ; Nepal, S ; Sharif University of Technology
    IEEE Computer Society  2021
    Abstract
    Federated learning (FL) and split learning (SL) are state-of-the-art distributed machine learning techniques to enable machine learning without accessing raw data on clients or end devices. However, their comparative training performance under real-world resource-restricted Internet of Things (IoT) device settings, e.g., Raspberry Pi, remains barely studied, which, to our knowledge, have not yet been evaluated and compared, rendering inconvenient reference for practitioner. This work firstly provides empirical comparisons of FL and SL in real-world IoT settings regarding learning performance and on-device execution overhead. Our analyses demonstrate that the learning performance of SL is... 

    Semi-supervised parallel shared encoders for speech emotion recognition

    , Article Digital Signal Processing: A Review Journal ; Volume 118 , 2021 ; 10512004 (ISSN) Pourebrahim, Y ; Razzazi, F ; Sameti, H ; Sharif University of Technology
    Elsevier Inc  2021
    Abstract
    Supervised speech emotion recognition requires a large number of labeled samples that limit its use in practice. Due to easy access to unlabeled samples, a new semi-supervised method based on auto-encoders is proposed in this paper for speech emotion recognition. The proposed method performed the classification operation by extracting the information contained in unlabeled samples and combining it with the information in labeled samples. In addition, it employed maximum mean discrepancy cost function to reduce the distribution difference when the labeled and unlabeled samples were gathered from different datasets. Experimental results obtained on different emotional speech datasets... 

    Private set operations over encrypted cloud dataset and applications

    , Article Computer Journal ; Volume 64, Issue 8 , 2021 , Pages 1145-1162 ; 00104620 (ISSN) Rafiee, M ; Khazaei, S ; Sharif University of Technology
    Oxford University Press  2021
    Abstract
    We introduce the notion of private set operations (PSO) as a symmetric-key primitive in the cloud scenario, where a client securely outsources his dataset to a cloud service provider and later privately issues queries in the form of common set operations. We define a syntax and security notion for PSO and propose a general construction that satisfies it. There are two main ingredients to our PSO scheme: an adjustable join (Adjoin) scheme (MIT-CSAIL-TR-2012-006 (2012) Cryptographic treatment of CryptDB's adjustable join. http://people.csail.mit.edu/nickolai/papers/popa-join-tr.pdf) and a tuple set (TSet) scheme (Cash, D., Jarecki, S., Jutla, C. S., Krawczyk, H., Rosu, M.-C., and Steiner, M.... 

    The effect of magnesium supplementation on anthropometric indices: A systematic review and dose-response meta-analysis of clinical trials

    , Article British Journal of Nutrition ; Volume 125, Issue 6 , 2021 , Pages 644-656 ; 00071145 (ISSN) Rafiee, M ; Ghavami, A ; Rashidian, A ; Hadi, A ; Askari, G ; Sharif University of Technology
    Cambridge University Press  2021
    Abstract
    Abstract The aim of this study was to determine the effects of Mg supplementation on anthropometric indices consisting of body weight, waist circumference (WC), BMI and body fat percentage. In this systematic review and dose-response meta-analysis, we searched PubMed, Cochrane Library, Scopus, Web of Science and Google Scholar from databases inception up to February 2020 for relevant randomised controlled trials. Quality of evidence was evaluated using the Cochrane Collaboration Tool. All the outcomes of this meta-analysis were pooled using the random effect model. Analysis of dose-response for Mg dosage was carried out using a fractional polynomial model. The systematic review and... 

    Security of multi-adjustable join schemes: separations and implications

    , Article IEEE Transactions on Dependable and Secure Computing ; 2021 ; 15455971 (ISSN) Rafiee, M ; Khazaei, S ; Sharif University of Technology
    Institute of Electrical and Electronics Engineers Inc  2021
    Abstract
    Database management systems (DBMS) are one of cloud services with major applications in industry and business. In the use of such services, since the cloud service provider cannot be entrusted with the plain data, the databases are typically encrypted prior to outsourcing. One of the most challenging issues in designing these services is supporting SQL join queries on the encrypted database. The multi-adjustable join scheme (M-Adjoin) [Khazaei-Rafiee 2020], an extension of Adjoin [Popa-Zeldovich 2012 and Mironov-Segev-Shahaf 2017], is a symmetric-key primitive that supports the join queries for a list of column labels on an encrypted database. In previous works, the following security... 

    Gelatin-based functional films integrated with grapefruit seed extract and TiO2 for active food packaging applications

    , Article Food Hydrocolloids ; Volume 112 , 2021 ; 0268005X (ISSN) Riahi, Z ; Priyadarshi, R ; Rhim, J. W ; Bagheri, R ; Sharif University of Technology
    Elsevier B.V  2021
    Abstract
    Gelatin-based functional films were prepared by the addition of grapefruit seed extract (GSE, 5 wt% based on gelatin) and various amounts of TiO2 (0.5, 1.0, 3.0, and 5.0 wt% based on gelatin). TiO2 was evenly dispersed in the gelatin film, but the film surface roughness was increased as the concentration of TiO2 increased. The mechanical strength and water contact angle (WCA) of the composite film were the highest, while the water vapor permeability (WVP) was the lowest when 0.5 wt% TiO2 was used. The addition of GSE slightly reduced the UV light transmittance, but the addition of TiO2 almost completely prevented the UV light transmission. The addition of GSE and TiO2 did not significantly... 

    Numerical-probabilistic modeling of the liquefaction-induced free fields settlement

    , Article Soil Dynamics and Earthquake Engineering ; Volume 149 , 2021 ; 02677261 (ISSN) Sadeghi, H ; Pak, A ; Pakzad, A ; Ayoubi, P ; Sharif University of Technology
    Elsevier Ltd  2021
    Abstract
    Liquefaction is a phenomenon through which saturated sandy soil loses its shear strength and turns into a liquefied state. One of the most detrimental consequences of liquefaction is the reconsolidation volumetric settlements after the earthquakes, which is due to the dissipation of excess pore pressure caused by earthquakes. Severe floods can follow these settlements in free fields such as grounds close to the sea or rivers. Several researchers studied this phenomenon using data obtained from experiments in the lab or observations in the fields. Previous works were mainly based on a limited number of experimental observations and considered loadings and boundary conditions that were... 

    Stacked hourglass network with a multi-level attention mechanism: where to Look for intervertebral disc labeling

    , Article 12th International Workshop on Machine Learning in Medical Imaging, MLMI 2021, held in conjunction with 24th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2021, 27 September 2021 through 27 September 2021 ; Volume 12966 LNCS , 2021 , Pages 406-415 ; 03029743 (ISSN); 9783030875886 (ISBN) Azad, R ; Rouhier, L ; Cohen Adad, J ; Sharif University of Technology
    Springer Science and Business Media Deutschland GmbH  2021
    Abstract
    Labeling vertebral discs from MRI scans is important for the proper diagnosis of spinal related diseases, including multiple sclerosis, amyotrophic lateral sclerosis, degenerative cervical myelopathy and cancer. Automatic labeling of the vertebral discs in MRI data is a difficult task because of the similarity between discs and bone area, the variability in the geometry of the spine and surrounding tissues across individuals, and the variability across scans (manufacturers, pulse sequence, image contrast, resolution and artefacts). In previous studies, vertebral disc labeling is often done after a disc detection step and mostly fails when the localization algorithm misses discs or has false... 

    CANCERSIGN: a user-friendly and robust tool for identification and classification of mutational signatures and patterns in cancer genomes

    , Article Scientific Reports ; Volume 10, Issue 1 , 2020 Bayati, M ; Rabiee, H. R ; Mehrbod, M ; Vafaee, F ; Ebrahimi, D ; Forrest, A. R. R ; Alinejad Rokny, H ; Sharif University of Technology
    Nature Research  2020
    Abstract
    Analysis of cancer mutational signatures have been instrumental in identification of responsible endogenous and exogenous molecular processes in cancer. The quantitative approach used to deconvolute mutational signatures is becoming an integral part of cancer research. Therefore, development of a stand-alone tool with a user-friendly interface for analysis of cancer mutational signatures is necessary. In this manuscript we introduce CANCERSIGN, which enables users to identify 3-mer and 5-mer mutational signatures within whole genome, whole exome or pooled samples. Additionally, this tool enables users to perform clustering on tumor samples based on the proportion of mutational signatures in... 

    A hybrid deep model for automatic arrhythmia classification based on LSTM recurrent networks

    , Article 15th IEEE International Symposium on Medical Measurements and Applications, MeMeA 2020, 1 June 2020 through 3 June 2020 ; 2020 Bitarafan, A ; Amini, A ; Baghshah, M. S ; Khodajou Chokami, H ; Sharif University of Technology
    Institute of Electrical and Electronics Engineers Inc  2020
    Abstract
    Electrocardiogram (ECG) recording of electrical heart activities has a vital diagnostic role in heart diseases. We propose to tackle the problem of arrhythmia detection from ECG signals totally by a deep model that does not need any hand-designed feature or heuristic segmentation (e.g., ad-hoc R-peak detection). In this work, we first segment ECG signals by detecting R-peaks automatically via a convolutional network, including dilated convolutions and residual connections. Next, all beats are aligned around their R-peaks as the most informative section of the heartbeat in detecting arrhythmia. After that, a deep learning model, including both dilated convolution layers and a Long-Short Term...