Search for: deep-learning
Total 247 records
Standard SPECT myocardial perfusion estimation from half-time acquisitions using deep convolutional residual neural networks, Article Journal of Nuclear Cardiology ; 2020 ; AmirMozafari Sabet, K ; Arabi, H ; Pourkeshavarz, M ; Teimourian, B ; Ay, M. R ; Zaidi, H ; Sharif University of Technology
Introduction: The purpose of this work was to assess the feasibility of acquisition time reduction in MPI-SPECT imaging using deep leering techniques through two main approaches, namely reduction of the acquisition time per projection and reduction of the number of angular projections. Methods: SPECT imaging was performed using a fixed 90° angle dedicated dual-head cardiac SPECT camera. This study included a prospective cohort of 363 patients with various clinical indications (normal, ischemia, and infarct) referred for MPI-SPECT. For each patient, 32 projections for 20 seconds per projection were acquired using a step and shoot protocol from the right anterior oblique to the left posterior...
Article Journal of Information Technology Management ; Volume 12, Issue 4 , 2021 , Pages 22-62 ; 20085893 (ISSN) ; Kazemi, M. A ; Alborzi, M ; Azar, A ; Kermanshah, A ; Sharif University of Technology
University of Tehran 2021
The development of new technologies has confronted the entire domain of science and industry with issues of big data's scalability as well as its integration with the purpose of forecasting analytics in its life cycle. In predictive analytics, the forecast of near-future and recent past - or in other words, the now-casting - is the continuous study of real-time events and constantly updated where it considers eventuality. So, it is necessary to consider the highly data-driven technologies and to use new methods of analysis, like machine learning and visualization tools, with the ability of interaction and connection to different data resources with varieties of data regarding the type of big...
Sensitivity and generalized analytical sensitivity expressions for quantitative analysis using convolutional neural networks, Article Analytica Chimica Acta ; 2021 ; 00032670 (ISSN) ; Kirsanov, D ; Olivieri, A. C ; Parastar, H ; Sharif University of Technology
Elsevier B.V 2021
In recent years, convolutional neural networks and deep neural networks have been used extensively in various fields of analytical chemistry. The use of these models for calibration tasks has been highly effective; however, few reports have been published on their properties and characteristics of analytical figures of merit. Currently, most performance measures for these types of networks only incorporate some function of prediction error. While useful, these measures are incomplete and cannot be used as an objective comparison among different models. In this report, a new method for calculating the sensitivity of any type of neural network is proposed and studied on both simulated and real...
M.Sc. Thesis Sharif University of Technology ; Hemmatyar, Ali Mohammad Afshin
In the last few years, the most important problem to find a solution for the COVID-19 disease, and tests show that many factors are effective in the health and recovery of people with this disease. Therefore, scientists all over the world are looking to prevent the spread of this disease by identifying the effective factors in the recovery of corona patients and finding solutions for their health. The proposed algorithm is hybrid deep learning model CNN+GRU and appeal them to the laboratory test data from hospital. In this research, the goal is to be able to diagnose this disease in time with routine laboratory test, which consist of three main stages. In the first stage: initial...
M.Sc. Thesis Sharif University of Technology ; Soleymani Baghshah, Mahdieh
A predefined assumption in many learning algorithms is that the training and test data must be in thesame feature space and have the same distribution.However, this assumption may not hold in all of these algorithms and in the real world there might be difference between the source and the targer domian, whether in the feature space or the distribution. Moreover, there might be a few number of labled data of the target domain which causes difficulty in learning an accurate classifier. In such cases, transferring knowledge can be useful if can be done successfully and transfer learning was introduced for this purpose. Domain Adaptation is one of the transfer leaning problems that assume some...
M.Sc. Thesis Sharif University of Technology ; Soleimani, Mahdieh
Collaborative fltering (CF) is one of the best and widely employed approaches in Recommender systems (RS). This approach tries to fnd some latent features for users and items so it would predict user rates with these features. Early CF methods used matrix factorization to learn users and items latent features. But these methods face cold start as well as sparsity problem. Recent years methods employ side information along with rating matrix to learn users and items latent features. On the other hand, deep learning models show great potential for learning effective representations especially when auxiliary information is sparse. Due to this feature of deep learning, we use deep learning to...
M.Sc. Thesis Sharif University of Technology ; Ghaemmaghami, Shahrokh
Nowadays, using of digital cameras is streaming across the world dramatically. Application of these devices is very diverse. One of the most interesting application of those is face verification. For example, imagine your smartphone has an application which verifies faces in front of its front camera, if that face be your face (with variation from original) then application automatically unlocks your phone. Face verification systems are also deployed in airports to verify passport photos and in smart homes. One of the most regular problems in face verification is occlusion. When your face is occluded with natural or random changes we can say your face is occluded. All of the recent papers...
M.Sc. Thesis Sharif University of Technology ; Rahimi Tabar, Mohammad Reza
A complex system consists of a large number of subsystems that interact with each other and with the environment. These systems have collective behaviors that may are desired and undesired. Learning, intelligence and epilepsy are examples of desirable and undesirable collective behaviors. Control of these systems arises when they are out of the desired state or one wants to avoid approaching the system to its undesired state. For control of complex systems, we need external functions that apply to specific subsystems. These functions can be obtained from the numerical solution of Hamilton-Jacobi-Bellman equation. The Hamilton-Jacobi-Bellman equation is nonlinear and must be solved at very...
Article Future Generation Computer Systems ; 2016 ; 0167739X (ISSN) ; Kuhad, P ; Yassine, A ; Pouladzadeh, P ; Shirmohammadi, S ; Shirehjini, A. A. N ; Sharif University of Technology
Mobile e-health applications provide users and healthcare practitioners with an insightful way to check users/patients' status and monitor their daily calorie intake. Mobile e-health applications provide users and healthcare practitioners with an insightful way to check users/patients' status and monitor their daily activities. This paper proposes a cloud-based mobile e-health calorie system that can classify food objects in the plate and further compute the overall calorie of each food object with high accuracy. The novelty in our system is that we are not only offloading heavy computational functions of the system to the cloud, but also employing an intelligent cloud-broker mechanism to...
M.Sc. Thesis Sharif University of Technology ; Sameti, Hossein ; Bokaei, Mohammad Hadi
News plays a very important role in stock market trading. Nowadays news from a different part of the world and about different fields can be accessed easily, and for a successful trade, it is necessary to analyze accurately and use this big data and information as soon as possible. For this reason, this thesis tries to present and study models based on Deep Learning networks and Natural Language Processing for financial news analysis and predicting stock indices movement. This research takes advantage of a language model for learning and representing news text, and beside this language model it uses deep learning networks at multiple levels to extract proper features from each news in a day...
M.Sc. Thesis Sharif University of Technology ; Vosoughi Vahdat, Bijan ; Mohammadzadeh, Narjesolhoda
Computers, laptops, tablets and even cell phones are capable of recording, producing, storing and sharing videos. With the increasing availability of movies and more and easier access to them, the need for understanding videos has increased. Due to the limited human ability in analyzing videos, there is an increasing demand for intelligent systems to analyze videos and recognize the actions in them.Action recognition is the classification of the action performed by the individual in the video, and there are different types of action recognition depending on the nature of the data and the way it will be processed. Vision-based human action recognition is affected by several challenges due to...
M.Sc. Thesis Sharif University of Technology ; Marvasti, Farrokh ; Ghaemmaghami, Shahrokh
Pitch frequency is one of the most important attributes of speech, which has been found to be quite challenging in noisy conditions. In this paper, we propose a pitch detection method based on separation of the low pitch from high pitch signals, depending on the pitch frequency below or over 200Hz, respectively, using a deep convolutional neural network. The pitch frequency is initially estimated, employing a conventional pitch detection method. From this initial estimation and using a deep convolutional neural network which determines the signals type (high-pitch or low-pitch), the pitch candidates are derived. To choose the true pitch values, we use three features in addition to soft...
M.Sc. Thesis Sharif University of Technology ; Heydarnoori, Abbas
Software requirements are changing continuously and hence during software evolution and maintenance, source codes changes are being committed in the software repositories. Reading source codes to understand the changes is a very time consuming and tedious activity. Commit messages contain information about code changes that let developers be aware of the essence of the changes without reading the source codes. Unfortunately, due to the pressure of deadlines and lack of time, developers neglect to write these messages. Commit messages can speed up the process of software understanding for developers and also play an important role in software documentation. Therefore, an automated method for...
M.Sc. Thesis Sharif University of Technology ; Manzuri, Mohammad Taghi
Visual Question Answering (VQA) deep-learning systems tend to capture superficial statistical correlations in the training data because of strong language priors and fail to generalize to test data with a significantly different question-answer(QA) distribution. To address this issue, we introduce a Visually Directed Question Encoder to replace the commonly used RNNs in base models. our method uses visual features alongside word embeddings of question words to encode each word. As a result, the model is forced to look at the visual information relevant to each word and it no longer produces answers based on just the question itself. We evaluate our approach on the VQA generalization task...
M.Sc. Thesis Sharif University of Technology ; Ghaemmaghami, Shahrokh ; Eghlidos, Taraneh
DeepFake is a type of forgery that uses deep learning algorithms to make changes to audio and video content that the audience is unable to detect. Nowadays, due to the threats posed by the use of DeepFake to move people's faces in video, researchers' attention has been drawn to designing methods to detect this type of forgery. Detection methods are usually classified into two types. The first case is the extraction of features to detect forgery distortions, for example, the extraction of facial orientations to detect inconsistencies. The second case is the use of deep learning networks for feature extraction and classification, of which the EfficientNet network is an example. Despite the...
M.Sc. Thesis Sharif University of Technology ; Behroozi, Hamid ; Amini, Arash
Polar codes have received much attention to the extent that they are selected as a channel coding scheme in the 5G standard. The successive cancellation list (SCL) decoder suffers from high decoding Latency and limited Throughput due to its sequential decoding nature. Another polar decoding approach is the iterative belief propagation (BP) decoder which is inherently parallel and allows for better Decoding Latency and Throughput. However, its main drawback is an error-correction performance loss compared to the CRC-aided successive cancellation list (CA-SCL) decoder. From previous works, the CRC-aided belief propagation list (CA-BPL) decoder that benefits from the parallel structure of the...
M.Sc. Thesis Sharif University of Technology ; Akhavan Niaki, Taghi
In the era of artificial intelligence, achieving high accuracy in machine learning models is crucial for their practical applications. This thesis presents a novel approach to improve the accuracy of machine learning models by learning to defer to a team of human experts. The primary goal of this work is to build upon and extend previous research, proposing a model that outperforms existing models in the literature. Inspired by the "Mixture of Experts" framework, we introduce a neural network-based allocation system responsible for assigning cases to each member of the team, which consists of a machine learning model and multiple human experts. The allocation system intelligently determines...
Article 12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017, 30 May 2017 through 3 June 2017 ; 2017 , Pages 476-483 ; 9781509040230 (ISBN) ; Clapes, A ; Bellantonio, M ; Escalante, H. J ; Ponce Lopez, V ; Baro, X ; Guyon, I ; Kasaei, S ; Escalera, S ; Sharif University of Technology
Institute of Electrical and Electronics Engineers Inc 2017
The interest in action and gesture recognition has grown considerably in the last years. In this paper, we present a survey on current deep learning methodologies for action and gesture recognition in image sequences. We introduce a taxonomy that summarizes important aspects of deep learning for approaching both tasks. We review the details of the proposed architectures, fusion strategies, main datasets, and competitions. We summarize and discuss the main works proposed so far with particular interest on how they treat the temporal dimension of data, discussing their main features and identify opportunities and challenges for future research. © 2017 IEEE
Article Proceedings - 2018 IEEE Winter Conference on Applications of Computer Vision Workshops, WACVW 2018 ; Volume 2018-January , 2018 , Pages 28-36 ; 9781538651889 (ISBN) ; Bonderup, M. B ; Asadi Aghbolaghi, M ; Avots, E ; Nasrollahi, K ; Escalera, S ; Kasaei, S ; Moeslund, T. B ; Anbarjafari, G ; Sharif University of Technology
Institute of Electrical and Electronics Engineers Inc 2018
Automatic access control systems (ACS) based on the human biometrics or physical tokens are widely employed in public and private areas. Yet these systems, in their conventional forms, are restricted to active interaction from the users. In scenarios where users are not cooperating with the system, these systems are challenged. Failure in cooperation with the biometric systems might be intentional or because the users are incapable of handling the interaction procedure with the biometric system or simply forget to cooperate with it, due to for example, illness like dementia. This work introduces a challenging bimodal database, including face and hand information of the users when they...
Article 15th IEEE International Conference on Semantic Computing, ICSC 2021, 27 January 2021 through 29 January 2021 ; 2021 , Pages 370-373 ; 9781728188997 (ISBN) ; Monajem, M ; Christlein, V ; Heinrich, P ; Nicolaou, A ; Naderi Boldaji, H ; Lotfinia, M ; Evert, S ; Sharif University of Technology
Institute of Electrical and Electronics Engineers Inc 2021
Twitter sentiment analysis, which often focuses on predicting the polarity of tweets, has attracted increasing attention over the last years, in particular with the rise of deep learning (DL). In this paper, we propose a new task: predicting the predominant sentiment among (first-order) replies to a given tweet. Therefore, we created RETwEET, a large dataset of tweets and replies manually annotated with sentiment labels. As a strong baseline, we propose a two-stage DL-based method: first, we create automatically labeled training data by applying a standard sentiment classifier to tweet replies and aggregating its predictions for each original tweet; our rationale is that individual errors...