مطالب مرتبط با کلیدواژه

deep learning


۱.

Improving Stock Return Forecasting by Deep Learning Algorithm(مقاله علمی وزارت علوم)

نویسنده:
منبع: Advances in Mathematical Finance and Application, Volume ۴, Issue ۳, Summer ۲۰۱۹ 1 - 13

کلیدواژه‌ها: deep learning historical average model nonlinear model gold price

حوزه های تخصصی:
تعداد بازدید : ۴۵۳ تعداد دانلود : ۲۶۰
Improving return forecasting is very important for both investors and researchers in financial markets. In this study we try to aim this object by two new methods. First, instead of using traditional variable, gold prices have been used as predictor and compare the results with Goyal's variables. Second, unlike previous researches new machine learning algorithm called Deep learning (DP) has been used to improve return forecasting and then compare the results with historical average methods as bench mark model and use Diebold and Mariano’s and West’s statistic (DMW) for statistical evaluation. Results indicate that the applied DP model has higher accuracy compared to historical average model. It also indicates that out of sample prediction improvement does not always depend on high input variables numbers. On the other hand when using gold price as input variables, it is possible to improve this forecasting capability. Result also indicate that gold price has better accuracy than Goyal's variable to predicting out of sample return.
۲.

Classification of Brain Tumor by Combination of Pre-Trained VGG16 CNN(مقاله علمی وزارت علوم)

نویسنده:
منبع: Journal of Information Technology Management , Volume ۱۲, Issue ۲, ۲۰۲۰ (Proceedings of The ۶'th International Conference on Communication Management and Information Technology (ICCMIT'۲۰)) 13 - 25

کلیدواژه‌ها: Brain tumor deep learning VGG16 CNN GLCM features

حوزه های تخصصی:
تعداد بازدید : ۴۱۱ تعداد دانلود : ۸۰
In recent years, brain tumors become the leading cause of death in the world. Detection and rapid classification of this tumor are very important and may indicate the likely diagnosis and treatment strategy. In this paper, we propose deep learning techniques based on the combinations of pre-trained VGG-16 CNNs to classify three types of brain tumors (i.e., meningioma, glioma, and pituitary tumor). The scope of this research is the use of gray level of co-occurrence matrix (GLCM) features images and the original images as inputs to CNNs. Two GLCM features images are used (contrast and energy image). Our experiments show that the original image with energy image as input has better distinguishing features than other input combinations; accuracy can achieve average of 96.5% which is higher than accuracy in state-of-the-art classifiers.
۳.

P-V-L Deep: A Big Data Analytics Solution for Now-casting in Monetary Policy(مقاله علمی وزارت علوم)

نویسنده:
منبع: Journal of Information Technology Management , Volume ۱۲, Issue ۴, ۲۰۲۰ 22 - 62

کلیدواژه‌ها: Big data analytics deep learning Now-casting Monetary policy

حوزه های تخصصی:
تعداد بازدید : ۴۵۳ تعداد دانلود : ۲۳۰
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 data aimed at reducing the risks of policy-making institution’s investment in the field of IT. The main scientific contribution of this article is presenting a new approach of policy-making for the now-casting of economic indicators in order to improve the performance of forecasting through the combination of deep nets and deep learning methods in the data and features representation. In this regard, a net under the title of P-V-L Deep: Predictive Variational Auto Encoders - Long Short-term Memory Deep Neural Network was designed in which the architecture of variational auto-encoder was used for unsupervised learning, data representation, and data reconstruction; moreover, long short-term memory was adopted in order to evaluate now-casting performance of deep nets in time-series of macro-econometric variations. Represented and reconstructed data in the generative network of variational auto-encoder to determine the performance of long-short-term memory in the forecasting of the economic indicators were compared to principal data of the net. The findings of the research argue that reconstructed data which are derived from variational auto-encoder embody shorter training time and outperform of prediction in long short-term memory compared to principal data.
۴.

Guest Editorial: Deep Learning for Visual Information Analytics and Management(مقاله علمی وزارت علوم)

نویسنده:
منبع: Journal of Information Technology Management , Volume ۱۲, Special Issue: Deep Learning for Visual Information Analytics and Management., ۲۰۲۰ 1 - 2

کلیدواژه‌ها: deep learning Visual information Data analytics Watermarking

حوزه های تخصصی:
تعداد بازدید : ۱۹۳ تعداد دانلود : ۱۰۵
The special issue aims to cover the latest research topics in designing and deploying visual information analytics and management techniques using deep learning. It is intended to serve as a platform to researchers who want to present research in deep learning. The special issue focuses explicitly on deep learning and its application in visual computing and signal processing. It emphasizes on the extent to which Deep Learning can help specialists in understanding and analyzing complex images and signals. The field of Visual Information Analytics and Management is considered in its broadest sense and covers both digital and analog aspects. This involves development of techniques for image analysis, understanding and restoration. Deep learning techniques are effective for visual analytics. Deep learning is a fast growing area and is gaining impetus for application in various fields. Therefore, in this special issue, the objective is to publish articles related to deep learning in various problems of visual information analytics and management.
۵.

Long Short-Term Memory Approach for Coronavirus Disease Predicti(مقاله علمی وزارت علوم)

نویسنده:
منبع: Journal of Information Technology Management , Volume ۱۲, Special Issue: The Importance of Human Computer Interaction: Challenges, Methods and Applications., ۲۰۲۰ 11 - 21

کلیدواژه‌ها: deep learning LSTM Prediction COVID-19 Recurrent Neural Network (RNN)

حوزه های تخصصی:
تعداد بازدید : ۳۹۴ تعداد دانلود : ۳۳۳
Corona Virus (COVID-19) is a major problem among people, and it causes suffering worldwide. Yet, the traditional prediction models are not yet suitably efficient in catching the fundamental expertise as they cannot visualize the difficulty in the health's representation problem areas. This paper states prediction mechanism that uses a model of deep learning called Long Short-Term Memory (LSTM). We have carried this model out on corona virus dataset that obtained from the records of infections, deaths, and recovery cases across the world. Furthermore, producing a dataset which includes features of geographic regions (temperature and humidity) that have experienced severe virus outbreaks, risk factors, spatio-temporal analysis, and social behavior of people, a predictive model can be developed for areas where the virus is likely to spread. However, the outcomes of this study are justifiable to alert the authorities and the people to take precautions.
۶.

Automatic Chest CT Image Findings of Novel Coronavirus Pneumonia (COVID-19) Using U-Net Based Convolutional Neural Network(مقاله علمی وزارت علوم)

نویسنده:
منبع: Journal of Information Technology Management , Volume ۱۲, Special Issue: The Importance of Human Computer Interaction: Challenges, Methods and Applications., ۲۰۲۰ 22 - 35

کلیدواژه‌ها: COVID-19 CT imaging findings Segmentation deep learning Ground-glass opacities U-Net

حوزه های تخصصی:
تعداد بازدید : ۲۲۳ تعداد دانلود : ۱۷۱
The continuing outbreak of COVID-19 pneumonia is globally concerning. Timely detection of infection ensures prompt quarantine of patient which is crucial for preventing the rapid spread of this contagious disease and also supports the patient with necessary medication. Due to the high infection rate of COVID-19, our health management system needs an automatic diagnosis tool that equips the health workers to pay immediate attention to the needy person. Chest CT is an essential imaging technique for diagnosis and staging of 2019 novel coronavirus disease (COVID-19). The identification of COVID-19 CT findings assists health workers on further clinical evaluation, especially when the findings on CT scans are trivial, the person may be recommended for Reverse-transcription polymerase chain reaction (RT-PCR) tests. Literature reported that the ground-glass opacity (GGO) with or without consolidation are dominant CT findings in COVID-19 patients. In this paper, the U-Net based segmentation approach is proposed to automatically segment and analyze the GGO and consolidation findings in the chest CT scan. The performance of this system is evaluated by comparing the auto-segmented infection regions with the manually-outlines ones on 100 axial chests CT scans of around 40 COVID-19 patients from SIRM dataset. The proposed U-Net with pre-process approach yields specificity of 0.91 ± 0.09 and sensitivity of 0.87 ± 0.07 on segmenting GGO region and specificity of 0.81 ± 0.13 and sensitivity of 0.44 ± 0.17 on segmenting consolidation region. Also the experimental results confirmed that the automatic detection method identifies the CT finding with a precise opacification percentage from the chest CT image.
۷.

An Efficient Privacy-preserving Deep Learning Scheme for Medical Image Analysis(مقاله علمی وزارت علوم)

نویسنده:
منبع: Journal of Information Technology Management , Volume ۱۲, Special Issue: The Importance of Human Computer Interaction: Challenges, Methods and Applications., ۲۰۲۰ 50 - 67

کلیدواژه‌ها: deep learning Data privacy Image privacy Medical image analysis Data morphing

حوزه های تخصصی:
تعداد بازدید : ۱۶۹ تعداد دانلود : ۷۲
In recent privacy has emerged as one of the major concerns of deep learning, since it requires huge amount of personal data. Medical Image Analysis is one of the prominent areas where sensitive data are shared to a third party service provider. In this paper, a secure deep learning scheme called Metamorphosed Learning (MpLe) is proposed to protect the privacy of images in medical image analysis. An augmented convolutional layer and image morphing are two main components of MpLe scheme. Data providers morph the images without privacy information using image morphing component. The human unrecognizable image is then delivered to the service providers who then apply deep learning algorithms on morphed data using augmented convolution layer without any performance penalty. MpLe provides sturdy security and privacy with optimal computational overhead. The proposed scheme is experimented using VGG-16 network on CIFAR dataset. The performance of MpLe is compared with similar works such as GAZELLE and MiniONN and found that the MpLe attracts very less computational and data transmission overhead. MpLe is also analyzed for various adversarial attack and realized that the success rate is as low as . The efficiency of the proposed scheme is proved through experimental and performance analysis.
۸.

Feature Selection and Hyper-parameter Tuning Technique using Neural Network for Stock Market Prediction(مقاله علمی وزارت علوم)

نویسنده:
منبع: Journal of Information Technology Management , Volume ۱۲, Special Issue: The Importance of Human Computer Interaction: Challenges, Methods and Applications., ۲۰۲۰ 89 - 108

کلیدواژه‌ها: Neural Network Stock market prediction Numerai NMR deep learning

حوزه های تخصصی:
تعداد بازدید : ۲۴۵ تعداد دانلود : ۳۹۶
The conjecture of stock exchange is the demonstration of attempting to decide the forecast estimation of a particular sector or the market, or the market as a whole. Every stock every investor needs to foresee the future evaluation of stocks, so a predicted forecast of a stock’s future cost could return enormous benefit. To increase the accuracy of the Conjecture of stock Exchange with daily changes in the market value is a bottleneck task. The existing stock market prediction focused on forecasting the regular stock market by using various machine learning algorithms and in-depth methodologies. The proposed work we have implemented describes the new NN model with the help of different learning techniques like hyperparameter tuning which includes batch normalization and fitting it with the help of random-search-cv. The prediction of the Stock exchange is an active area for research and completion in Numerai. The Numerai is the most robust data science competition for stock market prediction. Numerai provides weekly new datasets to mold the most exceptional prediction model. The dataset has 310 features, and the entries are more than 100000 per week. Our proposed new neural network model gives accuracy is closely 86%. The critical point, it isn’t easy with our proposed model with existing models because we are training and testing the proposed model with a new unlabeled dataset every week. Our ultimate aim for participating in Numerai competition is to suggest a neural network methodology to forecast the stock exchange independent of datasets with reasonable accuracy.
۹.

Real Time Object Detection using CNN based Single Shot Detector Model(مقاله علمی وزارت علوم)

نویسنده:
منبع: Journal of Information Technology Management , Volume ۱۳, Issue ۱, ۲۰۲۱ 62 - 80

کلیدواژه‌ها: Object Detection deep learning CNN SSD Tensor Flow OpenCV

حوزه های تخصصی:
تعداد بازدید : ۳۲۹ تعداد دانلود : ۱۸۱
Object Detection has been one of the areas of interest of research community for over years and has made significant advances in its journey so far. There is a tremendous scope in the applications that would benefit with more innovations in the domain of object detection. Rapid growth in the field of machine learning has complemented the efforts in this area and in the recent times, research community has contributed a lot in real time object detection. In the current work, authors have implemented real time object detection and have made efforts to improve the accuracy of the detection mechanism. In the current research, we have used ssd_v2_inception_coco model as Single Shot Detection models deliver significantly better results. A dataset of more than 100 raw images is used for training and then xml files are generated using labellimg. Tensor flow records generated are passed through training pipelines using the proposed model. OpenCV captures real-time images and CNN performs convolution operations on images. The real time object detection delivers an accuracy of 92.7%, which is an improvement over some of the existing models already proposed earlier. Model detects hundreds of objects simultaneously. In the proposed model, accuracy of object detection significantly improvises over existing methodologies in practice. There is a substantial dataset to evaluate the accuracy of proposed model. The model may be readily useful for object detection applications including parking lots, human identification, and inventory management.
۱۰.

Comparative Analysis on Hybrid Content & Context-basedimage Retrieval System(مقاله علمی وزارت علوم)

نویسنده:
منبع: Journal of Information Technology Management , Volume ۱۳, Special Issue: Big Data Analytics and Management in Internet of Things, ۲۰۲۱ 133 - 142

کلیدواژه‌ها: CBIR Content Context Machine Learning deep learning

حوزه های تخصصی:
تعداد بازدید : ۱۵۹ تعداد دانلود : ۱۴۹
Learning effective segment depictions and resemblance measures are fundamental to the recuperation execution of a substance based picture recuperation (CBIR) structure. Regardless of wide research tries for a significant long time, it stays one of the most testing open gives that broadly impedes the achievements of real-world CBIR structures. The key test has been credited to the extraordinary "semantic hole" subject that happens between low-level photo pixels got by technologies and raised close semantic thoughts saw by a human. Among various techniques, AI has been successfully analyzed as a possible course to interface the semantic gap in the whole deal. Impelled by late triumphs of significant learning techniques for PC vision and various applications, in this paper, we try to address an open issue: if significant learning is a longing for spreading over the semantic gap in CBIR and how much updates in CBIR endeavors can be cultivated by exploring the front line significant learning methodology for learning feature depictions and likeness measures. Specifically, we explore a structure of significant learning with application to CBIR assignments with a wide game plan of definite examinations by investigating front line significant learning methodologies for CBIR endeavors under moved settings. From our exploratory examinations, we find some encouraging results and compress some huge bits of information for upcoming research.
۱۱.

Comparative Analysis on Hybrid Content & Context-basedimage Retrieval System(مقاله علمی وزارت علوم)

نویسنده:
منبع: Journal of Information Technology Management , Volume ۱۳, Special Issue: Role of ICT in Advancing Business and Management, ۲۰۲۱ 133 - 142

کلیدواژه‌ها: CBIR Content Context Machine Learning deep learning

حوزه های تخصصی:
تعداد بازدید : ۲۸۴ تعداد دانلود : ۲۲۸
Learning effective segment depictions and resemblance measures are fundamental to the recuperation execution of a substance based picture recuperation (CBIR) structure. Regardless of wide research tries for a significant long time, it stays one of the most testing open gives that broadly impedes the achievements of real-world CBIR structures. The key test has been credited to the extraordinary "semantic hole" subject that happens between low-level photo pixels got by technologies and raised close semantic thoughts saw by a human. Among various techniques, AI has been successfully analyzed as a possible course to interface the semantic gap in the whole deal. Impelled by late triumphs of significant learning techniques for PC vision and various applications, in this paper, we try to address an open issue: if significant learning is a longing for spreading over the semantic gap in CBIR and how much updates in CBIR endeavors can be cultivated by exploring the front line significant learning methodology for learning feature depictions and likeness measures. Specifically, we explore a structure of significant learning with application to CBIR assignments with a wide game plan of definite examinations by investigating front line significant learning methodologies for CBIR endeavors under moved settings. From our exploratory examinations, we find some encouraging results and compress some huge bits of information for upcoming research.
۱۲.

Capsule Network Regression Using Information Measures: An Application in Bitcoin Market(مقاله علمی وزارت علوم)

نویسنده:
منبع: Advances in Mathematical Finance and Application, Volume ۷, Issue ۱, Winter ۲۰۲۲ 37-48

کلیدواژه‌ها: deep learning Financial Market Prediction

حوزه های تخصصی:
تعداد بازدید : ۳۲۹ تعداد دانلود : ۱۶۴
Predicting financial markets has always been one of the most challenging issues, attracting the attention of many investors and researchers. In this regard, deep learning methods have been used a lot recently. Due to the desired results, such networks are always in development and progress. One of the networks that is being implemented in various fields is capsule network. The first time the classification capsule network was introduced, it was able to attract a lot of attention with its success on MNIST data 1 . In such networks, as in the other ones, the parameters are obtained by minimizing a loss function. In this paper, we first change the classification capsule network to a regression capsule network by modifying the last layer of the network. Then we use different information measures such as Kullnack-Leibler, Lin-Wang and Triangular information measures as a loss function, and compare their results with wellknown models including Artificial Neural Network (ANN), Convolutional Network (CNN) and Long Short-Term Memory (LSTM) as well as common used loss functions such as Mean Square Error (MSE) and Mean Absolute Percentage Error (MAPE). Using appropriate accuracy metrics, it is shown that the capsule network using triangular information measure is well able to predict the price of bitcoin for the medium and long term period including 10, 90 and 180 days.
۱۳.

Analysis of Stock Market Manipulation using Generative Adversarial Nets and Denoising Auto-Encode Models(مقاله علمی وزارت علوم)

نویسنده:
منبع: Advances in Mathematical Finance and Application, Volume ۷, Issue ۱, Winter ۲۰۲۲ 149-167

کلیدواژه‌ها: Anomaly Detection deep learning Generative Adversarial Net (GAN) Stock Manipulation Detection

حوزه های تخصصی:
تعداد بازدید : ۶۷۰ تعداد دانلود : ۲۶۱
Market manipulation remains the biggest concern of investors in today’s securities market. The development of technologies and complex trading algorithms seems to facilitate stock market manipulation and make it inevitable for regulators to use Deep Learning models to prevent manipulation. In this research, a Denoising GAN-based model has been designed. The proposed model (GAN-DAE4) consists of a three-layer encoder along with a 2-dimension encoder as the discriminator and a three-layer decoder as the generator. First, using statistical methods such as sequence, skewness, and kurtosis tests and some unsupervised learning methods such as Contextual Anomaly Detection (CAD) and some visual and graphical methods, the manipulated stocks have been detected in the Tehran Stock Exchange from 2015 to 2020; then GAN-DAE4 and some supervised deep learning models have been applied to the prepared data set. The results show that GAN-DAE4 outperformed other deep learning models (with F2-measure 73.71%) such as Decision Tree (C4.5), Random Forest, Neural Network, and Logistic Regression.
۱۴.

A Data Envelopment Analysis Model to Provide a Dynamic Accounting Information System for Measuring the Financial Effectiveness of Management Accounting System(مقاله علمی وزارت علوم)

نویسنده:
منبع: Advances in Mathematical Finance and Application, Volume ۷, Issue ۱, Winter ۲۰۲۲ 169-186

کلیدواژه‌ها: deep learning Financial Market Prediction

حوزه های تخصصی:
تعداد بازدید : ۲۶۸ تعداد دانلود : ۲۱۵
The secret to achieving your organization's goals in complex and challenging environments is to make the right managerial and rational decisions. In this regard, the accounting information system as one of the sources of information for the decision of managers is of particular importance. Therefore, in order to achieve these goals, it is necessary to have an accounting information system with dynamic capabilities. The dynamic capability of the accounting information system (hidden variable) was measured by the observed variables of flexibility, continuous evaluation, continuous investment and system variability. Therefore, based on this argument, the aim of the present study is to provide a dynamic capability model of the accounting system based on the financial effectiveness of the management accounting system. Data envelopment analysis is a well-known methodology that is applied to evaluate the selected firms based on the most important features. The results of analysis of the proposed method on 86 companies listed on the Tehran Stock Exchange and analysis and analysis of data by structural equation modeling show that the dynamic capability of the accounting information system consists of (flexibility, continuous evaluation, continuous investment and system variability). The result indicate that the management accounting system is effective.
۱۵.

A Grouping Hotel Recommender System Based on Deep Learning and Sentiment Analysis(مقاله علمی وزارت علوم)

نویسنده:
منبع: Journal of Information Technology Management , Volume ۱۱, Issue ۲, ۲۰۱۹ 59 - 78

کلیدواژه‌ها: Grouping recommender systems Sentiment Analysis deep learning Singular Value Decomposition (SVD)

حوزه های تخصصی:
تعداد بازدید : ۲۹۶ تعداد دانلود : ۱۳۳
Recommender systems are important tools for users to identify their preferred items and for businesses to improve their products and services. In recent years, the use of online services for selection and reservation of hotels have witnessed a booming growth. Customer’ reviews have replaced the word of mouth marketing, but searching hotels based on user priorities is more time-consuming. This study is aimed at designing a recommender system based on the explicit and implicit preferences of the customers in order to increase prediction’s accuracy. In this study, we have combined sentiment analysis with the Collaborative Filtering (CF) based on deep learning for user groups in order to increase system accuracy. The proposed system uses Natural Language Processing (NLP) and supervised classification approach to analyze sentiments and extract implicit features. In order to design the recommender system, the Singular Value Decomposition (SVD) was used to improve scalability. The results show that our proposed method improves CF performance.
۱۶.

Simulate Congestion Prediction in a Wireless Network Using the LSTM Deep Learning Model(مقاله علمی وزارت علوم)

نویسنده:
منبع: Journal of Information Technology Management , Volume ۱۱, Issue ۴, ۲۰۱۹ 70 - 79

کلیدواژه‌ها: AP Android Congestion deep learning LSTM Wireless networks

حوزه های تخصصی:
تعداد بازدید : ۲۳۳ تعداد دانلود : ۸۹
Achieved wireless networks since its beginning the prevalent wide due to the increasing wireless devices represented by smart phones and laptop, and the proliferation of networks coincides with the high speed and ease of use of the Internet and enjoy the delivery of various data such as video clips and games. Here's the show the congestion problem arises and represent   aim of the research is to avoid congestion at APs to wireless networks by adding a control before congestion occurs. A wireless connection was made using the Android system, and congestion was predicted based on the analysis of wireless communication packages around the access point using the LSTM deep learning model. The results show that if the amount of information in the input data is large, a more accurate prediction can be made.
۱۷.

Deep-Learning-CNN for Detecting Covered Faces with Niqab(مقاله علمی وزارت علوم)

نویسنده:
منبع: Journal of Information Technology Management , Volume ۱۴, ۵th International Conference of Reliable Information and Communication Technology (IRICT ۲۰۲۰), ۲۰۲۲ 114 - 123

کلیدواژه‌ها: Face-detection Object-detection Computer Vison deep learning Artificial Intelligence Convolutional Neural Network

حوزه های تخصصی:
تعداد بازدید : ۲۵۴ تعداد دانلود : ۱۳۸
Detecting occluded faces is a non-trivial problem for face detection in computer vision. This challenge becomes more difficult when the occlusion covers majority of the face. Despite the high performance of current state-of-the-art face detection algorithms, the detection of occluded and covered faces is an unsolved problem and is still worthy of study. In this paper, a deep-learning-face-detection model Niqab-Face-Detector is proposed along with context-based labeling technique for detecting unconstrained veiled faces such as faces covered with niqab. An experimental test was conducted to evaluate the performances of the proposed model using the Niqab-Face dataset. The experiment showed encouraging results and improved accuracy compared with state-of-the-art face detection algorithms
۱۸.

CoReHAR: A Hybrid Deep Network for Video Action Recognition(مقاله علمی وزارت علوم)

نویسنده:
منبع: International Journal of Web Research, Volume ۳, Issue ۱,Spring-Summer ۲۰۲۰ 1 - 10
تعداد بازدید : ۲۴۱ تعداد دانلود : ۱۲۴
Automating the processing of videos in applications such as surveillance, sport commentary and activity detection, human-machine interaction, and health/disability care is crucial to their correct functioning. In such video processing tasks, recognition of various human actions is a pivotal component for the correct understanding of videos and making decisions upon it. Accurately recognizing human actions is a complex process, demanding high computing capabilities and intelligent algorithms. Several factors, such as object occlusion, camera movement, and background clutter, further challenge the task and its accuracy, essentially leaving deep learning approaches the only viable option for properly detecting human actions in videos. In this study, we propose CoReHAR, a novel Human Action Recognition method that employs both deep Convolutional and Recurrent neural networks on raw video frames. Using the pre-trained ResNet152 CNN, deep features are initially extracted from video frames. The sequential information of the frames is then learned using DB-LSTM RNN. Multiple stacked layers in forward and backward passes of the DB-LSTM provide increased network depth for higher accuracy. A number of techniques are also applied to improve CoReHAR’s processing speed on heterogeneous GPU-enabled systems. The proposed method is evaluated using PyTorch, and is compared to the state-of-the-art methods, showing a considerable efficiency increase, with nearly 95% recognition accuracy measured as an average over all splits of the challenging UCF101 dataset.
۱۹.

Multimodal Sentiment Analysis of Social Media Posts Using Deep Neural Networks(مقاله علمی وزارت علوم)

نویسنده:
منبع: International Journal of Web Research, Volume ۴, Issue ۱,Spring-Summer ۲۰۲۱ 1 - 9
تعداد بازدید : ۲۶۲ تعداد دانلود : ۱۵۶
With the fast growth of social media, they have become the most important platform for posting multimodal content generated by users. Much of the data on social networks such as Instagram and Telegram is multimodal data. With the aim of analyzing such multimodal data in social networks, multimodal sentiment analysis has become one of the most significant subjects for researchers in the field of emotion recognition and data mining. Although multimodal sentiment analysis of social media data for English language has been addressed in several researches recently, few studies addressed the problem for the Persian language which is the official language of more than 120 million of people around the word. In this study, a multimodal deep learning model is proposed to address this problem. The proposed method utilizes a bi-directional long short-term memory (bi-LSTM) for processing text posts and a VGG16 convolutional network for analyzing images. A new dataset of Instagram and Telegram posts, MPerSocial, containing 1000 pairs of images and Persian comments is introduced in the current study and used for evaluating the proposed method. The results of experiments show that using the fusion of textual and image modalities improves sentiment polarity detection accuracy by 20% and 8% compared with the scenario in which image and text modalities in isolation. Also, the performance of the proposed model is better than three similar deep and four traditional machine learning models. All codes and dataset used in the current study are publicly available at GitHub.  
۲۰.

A Deep Learning Approach for Diagnosis Chest Diseases(مقاله علمی وزارت علوم)

نویسنده:
منبع: International Journal of Web Research, Volume ۴, Issue ۱,Spring-Summer ۲۰۲۱ 10 - 17
تعداد بازدید : ۳۴۴ تعداد دانلود : ۱۶۴
The human chest contains vital organs such as the heart, lungs, and other organs. Chest radiology is one of the best and least costly methods to diagnose chest diseases. In this study, proposed a new method to diagnose 14 main diseases of the chest such as (cardiomegaly, emphysema, effusion, hernia, nodule, pneumothorax, atelectasis, pleural - thickening, mass, edema, integration, penetration, fibrosis, pneumonia) using the neural network and deep learning to increase accuracy, sensitivity, and specificity. The proposed method is implemented in the form of a web application and is available as a decision-making system for physicians to diagnose chest diseases.The results of the simulation on the sample dataset showed that the diagnosis of chest diseases was 98.93%, indicating the high efficiency of the new method. Finally, the proposed method was compared with other deep learning architectures such as densenet121, vgg16, exception architecture on the same dataset, which showed a 5% higher accuracy than them.