About the journal
Journal of Computer and Robotics (JCR) published by Qazvin Islamic Azad University (located in Iran) is scholarly open access, peer-reviewed, semi-annual journal. JCR publishes original theoretical and technical research papers as well as experimental ones for development in Computing, Automation, Robotics, and Electrical Engineering. The Journal targets many special issues on innovative topics and specific subjects and strives to bridge the gap between theoretical research and practical applications. The policy of peer review is of Double-blinded. The journal welcomes all research papers from all over the world. The editorial board members are from diverse countries of the world. The journal tries to expedite the review process of received papers. JCR is promised to publish papers that are of enough conformity with the stated aims & scope. JCR is continuously trying to improve its processes with the respect to the international standards of journals.
 |
 |
 |
| Conflict of interest | Copyright policy | Paper template |
Recent Articles
-
Open Access Article
1 - An Interval Type-2 Fuzzy-Markov Model for Prediction of Urban Air Pollution
Aref Safari Rahil Hosseini Mahdi MazinaniIssue 1 , Vol. 17 , Winter 2023Prediction is a very important problem that appears in many disciplines. Better weather forecasts can save lives in the event of a catastrophic hurricane; better financial forecasts can improve the return on an investment. The increasing rate of industrial development a MorePrediction is a very important problem that appears in many disciplines. Better weather forecasts can save lives in the event of a catastrophic hurricane; better financial forecasts can improve the return on an investment. The increasing rate of industrial development and urbanization, especially in developing countries, has led to increased levels of air pollution along with increased concern about air pollution effect on human health. This has taken about a diversity of strategies for air quality management, prediction and pollution control. Today’s applications of fuzzy systems are emerging in uncertain environments such as air quality assessments. A fuzzy system that accounts for all of the uncertainties that are present, namely, rule uncertainties due to training with noisy data and measurement uncertainties due to noisy measurements that are used during actual forecasting. The performance results on real data set show the superiority of the fuzzy-markov model in the prediction process with an average accuracy of 94.79% compared to other related works. These results are promising for early prediction of the natural disasters and prevention of its side effects Manuscript profile -
Open Access Article
2 - The Effect of using Virtual Reality Game on Health and Fitness
Seyed Amirhossein Mousavi Ehsan Tahami Majid Zare BidakiIssue 1 , Vol. 17 , Winter 2023During the corona days, the body's activities are very reduced due to the quarantine, and after that, many people still have little activity. Nearly two billion people in the world are overweight. In other words, more than 30% of the world's population is obese or overw MoreDuring the corona days, the body's activities are very reduced due to the quarantine, and after that, many people still have little activity. Nearly two billion people in the world are overweight. In other words, more than 30% of the world's population is obese or overweight. In this study, a solution for fitness and weight loss at home has been proposed. 2 groups participated in this study, the first group consisted of 20 people in a traditional way and the second group included 20 people under virtual reality, all of whom were undergraduate students, for 4 weeks and 3 sessions per week participated in this study and none of them had experience using virtual reality. The results show that fitness parameters include waist circumference, weight, BMI and the distance traveled in the Cooper test have improved. The motivation of people to continue this study was more in the virtual reality group than in the normal group. Manuscript profile -
Open Access Article
3 - A Novel Classification Method: A Hybrid Approach Based on Large Margin Nearest Neighbor Classifier
Alieh Ashoorzadeh Abbas Toloie Eshlaghy Mohammad Ali Afshar KazemiIssue 1 , Vol. 17 , Winter 2023Classification is the operation of dividing various data into multiple classes where they share quantitative and qualitative similarities. Classification has many use cases in engineering fields such as cloud computing, power distribution, and remote sensing. The accura MoreClassification is the operation of dividing various data into multiple classes where they share quantitative and qualitative similarities. Classification has many use cases in engineering fields such as cloud computing, power distribution, and remote sensing. The accuracy of many classification techniques such as k-nearest neighbor (k-NN) is highly dependent on the method used in the calculation of distances between samples. It is assumed that samples close to each other belong to the same class while samples that belong to different classes have a large distance between them. One of the popular distance calculation methods is the Mahalanobis distance. Many methods, including large margin nearest neighbor (LMNN), have been proposed to improve the performance of k-NN in recent years. Our proposed method aims to introduce a cost function to calculate data similarities while solving the local optimum pitfall of LMNN and optimizing the cost function determining distances between instances. Although k-NN is an efficient classification technique that is simple to comprehend and use, it is costly to compute for large datasets and sensitive to outlier data. Another difficult feature of k-NN is that it can only measure distance in Euclidean space. The distance metric should ideally be modified to fit the specific needs of the application. Due to the disadvantages in k-NN and LMNN methods, to optimize the objective function to calculate distances for the test data and to improve classification accuracy, we initially use the genetic algorithm to reduce the range of the solution space and then by using the gradient descent the optimal values of parameters in the cost function is obtained. Our method is carried out on different benchmark datasets with varying numbers of attributes and the results are compared to k-NN and LMNN methods. Misclassification rate, precision, f1 score, and kappa score are calculated for different values of k, mutation rate, and crossover rate. Overall, our proposed method shows superior performance with an average accuracy rate of 87.81% which is the highest among all methods. The average precision, f1 score, and kappa score of our method are 0.8453, 0.8513, and 0.6976 respectively. Manuscript profile -
Open Access Article
4 - Identifying and Ranking the Criteria of Outsourcing Capabilities of Maintenance Activities and Analyzing the Profitability of Outsourcing Using Bayesian BWM
Hamid Esmaili Hossein Kaveh PishghadamIssue 1 , Vol. 17 , Winter 2023Outsourcing of corporate activities by suppliers has long been done in the oil and gas industry. Outsourcing is known as a tool to gain strategic advantages. Outsourcing maintenance is also a common practice in many industries, including producing chemicals, petroleum, MoreOutsourcing of corporate activities by suppliers has long been done in the oil and gas industry. Outsourcing is known as a tool to gain strategic advantages. Outsourcing maintenance is also a common practice in many industries, including producing chemicals, petroleum, petrochemicals, and medical equipment. However, this process involves many risks, with their extent and nature still unclear. There are strong reasons for outsourcing some of the most important economic concepts. Determining the effective indicators in this selection and the importance and priority of each of them has always been the subject of intense research. In this paper, we examined the effects of these variables and assessed their relationship with decision-making outsourcing maintenance at gas refineries. First, the effective variables were identified by reviewing the literature and based on experts’ opinions. Next, it was tried to prioritize the indicators identified from previous studies using the relatively new Bayesian Best-Worst method (BWM). The results are then compared using one of the most recent decision-making methods, i.e., the Ordinal Priority Approach. Comparing the results of these two models shows that in both models, the cost of technology modernization and upgrades, the cost of emergency repairs and production stops, the cost of depreciation of equipment and machinery, and the cost of major repairs are the top four significant criteria among all the examined ones. However, the first and second methods consider “cost of maintenance” and “cost of productivity” more significant, respectively. It is worth noting that other differences were also identified in this study. Manuscript profile -
Open Access Article
5 - Enhanced Self-Attention Model for Cross-Lingual Semantic Textual Similarity in SOV and SVO Languages: Persian and English Case Study
Ebrahim Ganjalipour Amir Hossein Refahi Sheikhani Sohrab Kordrostami Ali Asghar HosseinzadehIssue 1 , Vol. 17 , Winter 2023Semantic Textual Similarity (STS) is considered one of the subfields of natural language processing that has gained extensive research attention in recent years. Measuring the semantic similarity between words, phrases, paragraphs, and documents plays a significant role MoreSemantic Textual Similarity (STS) is considered one of the subfields of natural language processing that has gained extensive research attention in recent years. Measuring the semantic similarity between words, phrases, paragraphs, and documents plays a significant role in natural language processing and computational linguistics. Semantic Textual Similarity finds applications in plagiarism detection, machine translation, information retrieval, and similar areas. STS aims to develop computational methods that can capture the nuanced degrees of resemblance in meaning between words, phrases, sentences, paragraphs, or even entire documents which is a challenging task for languages with low digital resources. This task becomes intricate in languages with pronoun-dropping and Subject-Object-Verb (SOV) word order specifications, such as Persian, due to their distinctive syntactic structures. One of the most important aspects of linguistic diversity lies in word order variation within languages. Some languages adhere to Subject-Object-Verb (SOV) word order, while others follow Subject-Verb-Object (SVO) patterns. These structural disparities, compounded by factors like pronoun-dropping, render the task of measuring cross-lingual STS in such languages exceptionally intricate. In the context of low-resource languages like Persian, this study proposes a customized model based on linguistic properties. Leveraging pronoun-dropping and SOV word order specifications of Persian, we introduce an innovative enhancement: a novel weighted relative positional encoding integrated into the self-attention mechanism. Moreover, we enrich context representations by infusing co-occurrence information through pointwise mutual information (PMI) factors. This paper introduces a cross-lingual model for semantic similarity analysis between Persian and English texts, utilizing parallel corpora. The experiments show that our proposed model achieves better performance than other models. Ablation study also shows that our system can converge faster and is less prone to overfitting. The proposed model is evaluated on Persian-English and Persian-Persian STS-Benchmarks and achieved 88.29% and 91.65% Pearson correlation coefficients on monolingual and cross-lingual STS-B, respectively. Manuscript profile -
Open Access Article
6 - Prediction of Digital Governance in the Direction of Urban Smartness with Sustainability Approach (Case Study: Tehran)
Bahram Parvin Ali Shayan Alireza Poorebrahimi Reza RadfarIssue 1 , Vol. 17 , Winter 2023Objectives: In this research, the researchers seek to present a mechanism for digital governance foresight in the direction of urban smartness with a sustainability approach based on scenario writing in the city of Tehran.Tools and methods:The research method is mixed i MoreObjectives: In this research, the researchers seek to present a mechanism for digital governance foresight in the direction of urban smartness with a sustainability approach based on scenario writing in the city of Tehran.Tools and methods:The research method is mixed in terms of how to check the data; Because it uses both quantitative research strategies (in expert data) and qualitative method strategy (in interview content analysis). In terms of the nature of the data, the current research uses both quantitative and qualitative methods. This article is included in basic-applied research. Because the research is exploratory and its main purpose is to identify the environmental drivers related to the subject of the research, therefore the research is of a fundamental type; At the same time, its achievements are included as a benchmark for urban management, especially relevant organizations including the municipality, so it is also considered practical. The statistical population of the research includes elites, managers, and senior experts, whose opinions can be used in the field of digital governance and urban smartness with a sustainable approach.Finding :Based on the results, the first scenarios in the areas of intelligence, participation, transparency, structural arrangements, -integration, culture and stabilization of the best scenario and the sixth scenario, and to some extent scenario 5, the worst possible scenarios are the worst. The second to fourth scenarios are based on the least changes in the main factors and showed improvement in one factor and in one factor the regression was shown. Resulting :The results showed that capacity-building to create the right to access information, increase law-abiding, discipline urban management mechanisms, and strengthen internal platforms for networking and securing information in line with urban intelligence can be implemented through the implementation of digital governance requirements. Manuscript profile
Most Viewed Articles
-
Open Access Article
1 - Cryptographic Algorithms: A Review of the Literature, Weaknesses and Open Challenges
Yashar Salami Vahid Khajevand Esmaeil ZeinaliIssue 2 , Vol. 16 , Spring 2023Information security has become an important issue in the modern world due to its increasing popularity in Internet commerce and communication technologies such as the Internet of Things. Future media actors are considered a threat to security. Therefore, the need to us MoreInformation security has become an important issue in the modern world due to its increasing popularity in Internet commerce and communication technologies such as the Internet of Things. Future media actors are considered a threat to security. Therefore, the need to use different levels of information security in different fields is more needed. Advanced information security methods are vital to prevent this type of threat. Cryptography is a valuable and efficient component for the safe transfer or storage of information in the cyber world. Familiarity with all types of encryption models is an essential need for cybersecurity experts. This paper separates Cryptographic algorithms into symmetric (SYM) and asymmetric (ASYM) categories based on the type of cryptographic structure. SYM algorithms mostly use the Feistel network (FN) structure, Substitution-Permutation Network (SPN), and the ASYM algorithms follow the mathematical structures. Based on this, we examined different encryption methods in terms of performance and detailed comparison of key size, block size, and the number of rounds. In continuation of the weakness of each algorithm against attacks and open challenges in each category, to study more is provided. Manuscript profile -
Open Access Article
2 - An Improved Real-Time Noise Removal Method in Video StreamBased on Pipe-and-Filter Architecture
Vahid Fazel Asl Babak Karasfi Behrooz Masoumi Mohamadreza KeyvanporIssue 1 , Vol. 14 , Winter 2021Automated analysis of video scenes requires the separation of moving objects from the background environment, which could not separate moving items from the background in the presence of noise. This paper presents a method to solve this challenge; this method uses the D MoreAutomated analysis of video scenes requires the separation of moving objects from the background environment, which could not separate moving items from the background in the presence of noise. This paper presents a method to solve this challenge; this method uses the Directshow framework based on the pipe-and-filter architecture. This framework trace in three ways. In the first step, the values of the MSE, SNR, and PSNR criteria calculate. In this step, the results of the error criteria are compared with applying salt and pepper and Gaussian noise to images and then applying median, Gaussian, and Directshow filters. In the second step, the processing time for each method check in case of using median, Gaussian, and Directshow filter, and it will result that the used method in the article has high performance for real-time computing. In the third step, error criteria of foreground image check in the presence or absence of the Directshow filter. In the pipe-and-filter architecture, because filters can work asynchronously; as a result, it can boost the frame rate process, and the Directshow framework based on the pipe-and-filter architecture will remove the existing noise in the video at high speed. The results show that the used method is far superior to existing methods, and the calculated values for the MSE error criteria and the processing time decrease significantly. Using the Directshow, there are high values for the SNR and PSNR criteria, which indicate high-quality image restoration. By removing noise in the images, you could also separate moving objects from the background appropriately. Manuscript profile -
Open Access Article
3 - An Interval Type-2 Fuzzy-Markov Model for Prediction of Urban Air Pollution
Aref Safari Rahil Hosseini Mahdi MazinaniIssue 1 , Vol. 17 , Winter 2023Prediction is a very important problem that appears in many disciplines. Better weather forecasts can save lives in the event of a catastrophic hurricane; better financial forecasts can improve the return on an investment. The increasing rate of industrial development a MorePrediction is a very important problem that appears in many disciplines. Better weather forecasts can save lives in the event of a catastrophic hurricane; better financial forecasts can improve the return on an investment. The increasing rate of industrial development and urbanization, especially in developing countries, has led to increased levels of air pollution along with increased concern about air pollution effect on human health. This has taken about a diversity of strategies for air quality management, prediction and pollution control. Today’s applications of fuzzy systems are emerging in uncertain environments such as air quality assessments. A fuzzy system that accounts for all of the uncertainties that are present, namely, rule uncertainties due to training with noisy data and measurement uncertainties due to noisy measurements that are used during actual forecasting. The performance results on real data set show the superiority of the fuzzy-markov model in the prediction process with an average accuracy of 94.79% compared to other related works. These results are promising for early prediction of the natural disasters and prevention of its side effects Manuscript profile -
Open Access Article
4 - Determining COVID-19 Tweet Check-Worthiness: Based On Deep Learning Approach
hosniyeh safiarian Mohammad Jafar Tarokh MohammadAli Afshar KazemiIssue 1 , Vol. 16 , Winter 2023When, we consider the ubiquity of Facebook, twitter, LinkedIn, it is easy to understand how social media is woven into the fabric of our day-to-day activities. It is a suitable tool to find information about news , events , and different Issues. After corona virus outbr MoreWhen, we consider the ubiquity of Facebook, twitter, LinkedIn, it is easy to understand how social media is woven into the fabric of our day-to-day activities. It is a suitable tool to find information about news , events , and different Issues. After corona virus outbreak, it is inspired users to understand pandemic news, mortality statistics and vaccination news. According to evidence, the diffusion of pandemic news on social medium has increased from 2020 and user face a ton of COVID19 messages. The purpose of this paper is to determine the check-worthiness of news about COVID-19 to identify and priorities news that need fact-checking. We proposed a method that is called CVMD. We extracted the feature of content. We use the deep learning approach for prediction it means that we model this problem with a binary classification problem. Our proposed method is evaluated by different measures on twitter dataset and the results show that CVMD method has a high accuracy in prediction rather than other methods. Manuscript profile -
Open Access Article
5 - Prediction of Digital Governance in the Direction of Urban Smartness with Sustainability Approach (Case Study: Tehran)
Bahram Parvin Ali Shayan Alireza Poorebrahimi Reza RadfarIssue 1 , Vol. 17 , Winter 2023Objectives: In this research, the researchers seek to present a mechanism for digital governance foresight in the direction of urban smartness with a sustainability approach based on scenario writing in the city of Tehran.Tools and methods:The research method is mixed i MoreObjectives: In this research, the researchers seek to present a mechanism for digital governance foresight in the direction of urban smartness with a sustainability approach based on scenario writing in the city of Tehran.Tools and methods:The research method is mixed in terms of how to check the data; Because it uses both quantitative research strategies (in expert data) and qualitative method strategy (in interview content analysis). In terms of the nature of the data, the current research uses both quantitative and qualitative methods. This article is included in basic-applied research. Because the research is exploratory and its main purpose is to identify the environmental drivers related to the subject of the research, therefore the research is of a fundamental type; At the same time, its achievements are included as a benchmark for urban management, especially relevant organizations including the municipality, so it is also considered practical. The statistical population of the research includes elites, managers, and senior experts, whose opinions can be used in the field of digital governance and urban smartness with a sustainable approach.Finding :Based on the results, the first scenarios in the areas of intelligence, participation, transparency, structural arrangements, -integration, culture and stabilization of the best scenario and the sixth scenario, and to some extent scenario 5, the worst possible scenarios are the worst. The second to fourth scenarios are based on the least changes in the main factors and showed improvement in one factor and in one factor the regression was shown. Resulting :The results showed that capacity-building to create the right to access information, increase law-abiding, discipline urban management mechanisms, and strengthen internal platforms for networking and securing information in line with urban intelligence can be implemented through the implementation of digital governance requirements. Manuscript profile -
Open Access Article
6 - Green Reverse Supply Chain on the Way of Optimization: A Case of Dairy Sector
zeinab zarrat dakheli parast hassan haleh soroush avakh darestani hamzeh amin tahmasbiIssue 1 , Vol. 16 , Winter 2023The achievement of chain greening objectives, besides costs minimization, can be realized when both reverse and forward flows are taken into account in the design of the supply chain network. It is possible to decrease the chain costs and have a greener chain by means o MoreThe achievement of chain greening objectives, besides costs minimization, can be realized when both reverse and forward flows are taken into account in the design of the supply chain network. It is possible to decrease the chain costs and have a greener chain by means of different strategies like vehicular routing, hub location, inventory management, and simultaneous pickup and delivery. The development of green reverse supply chains and the practice of the above-mentioned strategies are becoming increasing important with the appearance of perishable product chains. Considering the mentioned points, the current study attempts to design a green reverse supply chain network for the purpose of distributing dairy items such as yogurt drink where the strategy of simultaneous pickup and delivery under uncertainty is taken into consideration. This model focuses on the simultaneous costs reduction and also decrease of lost demands and presents a fuzzy solution for solving the bi-objective model. Manuscript profile -
Open Access Article
7 - A New Approach to Improve Tracking Performance of Moving Objects with Partial Occlusion.
Zahra Sahraei Amir Masoud Eftekhari MoghadamIssue 1 , Vol. 12 , Winter 2019< p>Tracking objects in video images has attracted much attention by machine vision and image processing researchers in recent years. Due to the importance of the subject, this paper presents a method for improving object tracking tasks with partial occlusion, whi More< p>Tracking objects in video images has attracted much attention by machine vision and image processing researchers in recent years. Due to the importance of the subject, this paper presents a method for improving object tracking tasks with partial occlusion, which increases the efficiency of tracking. The proposed approach first performs a pre-processing and extracts the tracking targets from the image. Then the salient feature points are extracted from the targets that are moving objects. In the next step, the particle filter is used for tracking. The final steps are modifying points and updates. A new approach is used to determine the speed of the feature points because the speed of some points can be out of range and this causes errors in tracking especially when there is occlusion. The location of the new points is corrected and updated using the threshold values in modifying the process as needed. The experiments performed on the video sequence of PETS2000 database show that the precision and recall of the proposed approach are higher than other compared approaches. Manuscript profile -
Open Access Article
8 - A Novel Classification Method: A Hybrid Approach Based on Large Margin Nearest Neighbor Classifier
Alieh Ashoorzadeh Abbas Toloie Eshlaghy Mohammad Ali Afshar KazemiIssue 1 , Vol. 17 , Winter 2023Classification is the operation of dividing various data into multiple classes where they share quantitative and qualitative similarities. Classification has many use cases in engineering fields such as cloud computing, power distribution, and remote sensing. The accura MoreClassification is the operation of dividing various data into multiple classes where they share quantitative and qualitative similarities. Classification has many use cases in engineering fields such as cloud computing, power distribution, and remote sensing. The accuracy of many classification techniques such as k-nearest neighbor (k-NN) is highly dependent on the method used in the calculation of distances between samples. It is assumed that samples close to each other belong to the same class while samples that belong to different classes have a large distance between them. One of the popular distance calculation methods is the Mahalanobis distance. Many methods, including large margin nearest neighbor (LMNN), have been proposed to improve the performance of k-NN in recent years. Our proposed method aims to introduce a cost function to calculate data similarities while solving the local optimum pitfall of LMNN and optimizing the cost function determining distances between instances. Although k-NN is an efficient classification technique that is simple to comprehend and use, it is costly to compute for large datasets and sensitive to outlier data. Another difficult feature of k-NN is that it can only measure distance in Euclidean space. The distance metric should ideally be modified to fit the specific needs of the application. Due to the disadvantages in k-NN and LMNN methods, to optimize the objective function to calculate distances for the test data and to improve classification accuracy, we initially use the genetic algorithm to reduce the range of the solution space and then by using the gradient descent the optimal values of parameters in the cost function is obtained. Our method is carried out on different benchmark datasets with varying numbers of attributes and the results are compared to k-NN and LMNN methods. Misclassification rate, precision, f1 score, and kappa score are calculated for different values of k, mutation rate, and crossover rate. Overall, our proposed method shows superior performance with an average accuracy rate of 87.81% which is the highest among all methods. The average precision, f1 score, and kappa score of our method are 0.8453, 0.8513, and 0.6976 respectively. Manuscript profile -
Open Access Article
9 - The Effect of using Virtual Reality Game on Health and Fitness
Seyed Amirhossein Mousavi Ehsan Tahami Majid Zare BidakiIssue 1 , Vol. 17 , Winter 2023During the corona days, the body's activities are very reduced due to the quarantine, and after that, many people still have little activity. Nearly two billion people in the world are overweight. In other words, more than 30% of the world's population is obese or overw MoreDuring the corona days, the body's activities are very reduced due to the quarantine, and after that, many people still have little activity. Nearly two billion people in the world are overweight. In other words, more than 30% of the world's population is obese or overweight. In this study, a solution for fitness and weight loss at home has been proposed. 2 groups participated in this study, the first group consisted of 20 people in a traditional way and the second group included 20 people under virtual reality, all of whom were undergraduate students, for 4 weeks and 3 sessions per week participated in this study and none of them had experience using virtual reality. The results show that fitness parameters include waist circumference, weight, BMI and the distance traveled in the Cooper test have improved. The motivation of people to continue this study was more in the virtual reality group than in the normal group. Manuscript profile -
Open Access Article
10 - A Novel Eye Gaze Estimation Method Using Ant Colony Optimizer
Mina Etehadi AbariIssue 1 , Vol. 12 , Winter 2019This paper addresses the eye gaze estimation problem in low-resolution images, using the low-cost camera in order to eliminate problems caused by infrared high-resolution imaging such as needing an expensive camera, complex setup, special light sources, and being limite MoreThis paper addresses the eye gaze estimation problem in low-resolution images, using the low-cost camera in order to eliminate problems caused by infrared high-resolution imaging such as needing an expensive camera, complex setup, special light sources, and being limited in lab research environments. In the proposed method, the human face is detected with Ant Colony Optimization (ACO) algorithm, and then the Kirsch compass mask is utilized to detect the position of humans’ eyes. For iris detection, a novel strategy based on ACO algorithm, which has been rarely used before, is applied. The pupil is recognized by morphological processing. Finally, the extracted features, obtained from the radius and position of the irises of the pupils, are given to the Support Vector Machine (SVM) classifier to detect the gaze pointing. In order to receive assurance of the reliability and superiority of the newly designed ACO algorithm, some other metaheuristic algorithms such as (GA, PSO, and BBO) are implemented and evaluated. Additionally, a novel dataset, comprising 700 images gazing at seven different major orientations, is created in this research. The extensive experiments are performed on three various datasets, including Eye-Chimera with 92.55% accuracy, BIOID dataset with 96% accuracy, and the newly constructed dataset with 90.71% accuracy. The suggested method outperformed the state of the art gaze estimation methods in terms of the robustness and accuracy. Manuscript profile
