Today, online users will have an average of 25 password-protected accounts online, yet use, on average, 6.5 passwords. The excessive cognitive burden of remembering large amounts of passwords causes Password Fatigue. Therefore users tend to reuse passwords or recycle password patterns whenever prompted to change their passwords regularly. Researchers have created Adaptive Password Policies to prevent users from creating new passwords similar to previously created ones. However, this approach creates user frustration as it neglects users’ cognitive burden. This paper proposes a novel User-Centric Adaptive Password Policy (UCAPP) Framework for password creation and management that assigns users system-generated passwords based on a cognitive-behavioural agent-based model. The framework comprises a Password Policy Assignment Test (PassPAST), a Cognitive Burden Scale (CBS), a User Profiling Algorithm, and a Password Generator (PassGEN). The framework creates tailor-made password policies that maintain password memorability for users of different cognitive thresholds without sacrificing password strength and entropy. The framework successfully created 30-40% stronger passwords for Critical users and random (non-mnemonic) passwords for Typical users based on each individual’s cognitive password thresholds in a preliminary test.
{"title":"User-centric adaptive password policies to combat password fatigue","authors":"Y. Al-Slais, W. El-Medany","doi":"10.34028/iajit/19/1/7","DOIUrl":"https://doi.org/10.34028/iajit/19/1/7","url":null,"abstract":"Today, online users will have an average of 25 password-protected accounts online, yet use, on average, 6.5 passwords. The excessive cognitive burden of remembering large amounts of passwords causes Password Fatigue. Therefore users tend to reuse passwords or recycle password patterns whenever prompted to change their passwords regularly. Researchers have created Adaptive Password Policies to prevent users from creating new passwords similar to previously created ones. However, this approach creates user frustration as it neglects users’ cognitive burden. This paper proposes a novel User-Centric Adaptive Password Policy (UCAPP) Framework for password creation and management that assigns users system-generated passwords based on a cognitive-behavioural agent-based model. The framework comprises a Password Policy Assignment Test (PassPAST), a Cognitive Burden Scale (CBS), a User Profiling Algorithm, and a Password Generator (PassGEN). The framework creates tailor-made password policies that maintain password memorability for users of different cognitive thresholds without sacrificing password strength and entropy. The framework successfully created 30-40% stronger passwords for Critical users and random (non-mnemonic) passwords for Typical users based on each individual’s cognitive password thresholds in a preliminary test.","PeriodicalId":13624,"journal":{"name":"Int. Arab J. Inf. Technol.","volume":"8 1 1","pages":"55-62"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83426018","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Deep learning is one of the trending technologies in computer vision to identify and classify objects. Deep learning is a subset of Machine Learning and Artificial Intelligence. Detecting and classifying the object was a challenging task in traditional computer vision techniques, and now there are numerous deep learning Techniques scaled up to achieve this. The primary purpose of the research is to detect and segment the human hand wrist region using deep learning methods. This research is widespread to deep learning enthusiasts who needs to segment custom objects using instance segmentation. We demonstrated a segmented hand wrist using the Mask Regional Convolutional Neural Network (R-CNN) technique with an average accuracy of 99.73%. This work also compares the performance evaluation of baseline and custom Hand Wrist Mask R-CNN. The achieved validation class loss is 0.00866 training and 0.02736 validation; both the values are comparatively deficient compared with baseline Mask R-CNN.
{"title":"Deep Learning Based Hand Wrist Segmentation using Mask R-CNN","authors":"GokulaKrishnan Elumalai, M. Ganesan","doi":"10.34028/iajit/19/5/10","DOIUrl":"https://doi.org/10.34028/iajit/19/5/10","url":null,"abstract":"Deep learning is one of the trending technologies in computer vision to identify and classify objects. Deep learning is a subset of Machine Learning and Artificial Intelligence. Detecting and classifying the object was a challenging task in traditional computer vision techniques, and now there are numerous deep learning Techniques scaled up to achieve this. The primary purpose of the research is to detect and segment the human hand wrist region using deep learning methods. This research is widespread to deep learning enthusiasts who needs to segment custom objects using instance segmentation. We demonstrated a segmented hand wrist using the Mask Regional Convolutional Neural Network (R-CNN) technique with an average accuracy of 99.73%. This work also compares the performance evaluation of baseline and custom Hand Wrist Mask R-CNN. The achieved validation class loss is 0.00866 training and 0.02736 validation; both the values are comparatively deficient compared with baseline Mask R-CNN.","PeriodicalId":13624,"journal":{"name":"Int. Arab J. Inf. Technol.","volume":"47 1","pages":"785-792"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80896812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Chian Techapanupreeda, Ekarat Rattagan, W. Kurutach
In the last two decades, the term “electronic health (e-health) systems” were extensively mentioned in the healthcare industry with the aim of replacing paper usage and increasing productivity. Unfortunately, these systems are not still widely used by healthcare professionals and patients due to the concerns on security and accountability issues. In this article, we propose an accountability transaction protocol to overcome all security issues for implementing electronic health systems. To validate our proposed protocol, we used both Automated Validation of Internet Security Protocols and Applications (AVISPA) and Scyther as the tools to prove its soundness.
{"title":"A transaction security accountability protocol for electronic health systems","authors":"Chian Techapanupreeda, Ekarat Rattagan, W. Kurutach","doi":"10.34028/iajit/19/3/1","DOIUrl":"https://doi.org/10.34028/iajit/19/3/1","url":null,"abstract":"In the last two decades, the term “electronic health (e-health) systems” were extensively mentioned in the healthcare industry with the aim of replacing paper usage and increasing productivity. Unfortunately, these systems are not still widely used by healthcare professionals and patients due to the concerns on security and accountability issues. In this article, we propose an accountability transaction protocol to overcome all security issues for implementing electronic health systems. To validate our proposed protocol, we used both Automated Validation of Internet Security Protocols and Applications (AVISPA) and Scyther as the tools to prove its soundness.","PeriodicalId":13624,"journal":{"name":"Int. Arab J. Inf. Technol.","volume":"2014 1","pages":"289-297"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82742561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The human voice speech includes essentially paralinguistic information used in many applications for voice recognition. Classifying speakers according to their age-group has been considered as a valuable tool in various applications, as issuing different levels of permission for different age-groups. In the presented research, an automatic system to classify speaker age-group without depending on the text is proposed. The Fundamental Frequency (F0), Jitter, Shimmer, and Spectral Sub-Band Centroids (SSCs) are used as a feature, while the Probabilistic Neural Network (PNN) is utilized as a classifier for the purpose of classifying the speaker utterances into eight age-groups. Experiments are carried out on VoxCeleb1 dataset to demonstrate the proposed system's performance, which is considered as the first effort of its kind. The suggested system has an overall accuracy of roughly 90.25%, and the findings reveal that it is clearly superior to a variety of base-classifiers in terms of overall accuracy.
{"title":"VoxCeleb1: speaker age-group classification using probabilistic neural network","authors":"A. A. Badr, A. Abdul-Hassan","doi":"10.34028/iajit/19/6/2","DOIUrl":"https://doi.org/10.34028/iajit/19/6/2","url":null,"abstract":"The human voice speech includes essentially paralinguistic information used in many applications for voice recognition. Classifying speakers according to their age-group has been considered as a valuable tool in various applications, as issuing different levels of permission for different age-groups. In the presented research, an automatic system to classify speaker age-group without depending on the text is proposed. The Fundamental Frequency (F0), Jitter, Shimmer, and Spectral Sub-Band Centroids (SSCs) are used as a feature, while the Probabilistic Neural Network (PNN) is utilized as a classifier for the purpose of classifying the speaker utterances into eight age-groups. Experiments are carried out on VoxCeleb1 dataset to demonstrate the proposed system's performance, which is considered as the first effort of its kind. The suggested system has an overall accuracy of roughly 90.25%, and the findings reveal that it is clearly superior to a variety of base-classifiers in terms of overall accuracy.","PeriodicalId":13624,"journal":{"name":"Int. Arab J. Inf. Technol.","volume":"216 1","pages":"854-860"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90483511","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ensemble classification is an actively researched paradigm that has received much attention due to increasing real-world applications. The crucial issue of ensemble learning is to construct a pool of base classifiers with accuracy and diversity. In this paper, unlike conventional data-streams oriented ensemble methods, we propose a novel Measure via both Accuracy and Diversity (MAD) instead of one of them to supervise ensemble learning. Based on MAD, a novel online ensemble method called Accuracy and Diversity weighted Ensemble (ADE) effectively handles concept drift in data streams. ADE mainly uses the following three steps to construct a concept-drift oriented ensemble: for the current data window, 1) a new base classifier is constructed based on the current concept when drift detect, 2) MAD is used to measure the performance of ensemble members, and 3) a newly built classifier replaces the worst base classifier. If the newly constructed classifier is the worst one, the replacement has not occurred. Comparing with the state-of-art algorithms, ADE exceeds the current best-related algorithm by 2.38% in average classification accuracy. Experimental results show that the proposed method can effectively adapt to different types of drifts.
{"title":"Ensemble based on accuracy and diversity weighting for evolving data streams","authors":"Yange Sun, Han Shao, Bencai Zhang","doi":"10.34028/iajit/19/1/11","DOIUrl":"https://doi.org/10.34028/iajit/19/1/11","url":null,"abstract":"Ensemble classification is an actively researched paradigm that has received much attention due to increasing real-world applications. The crucial issue of ensemble learning is to construct a pool of base classifiers with accuracy and diversity. In this paper, unlike conventional data-streams oriented ensemble methods, we propose a novel Measure via both Accuracy and Diversity (MAD) instead of one of them to supervise ensemble learning. Based on MAD, a novel online ensemble method called Accuracy and Diversity weighted Ensemble (ADE) effectively handles concept drift in data streams. ADE mainly uses the following three steps to construct a concept-drift oriented ensemble: for the current data window, 1) a new base classifier is constructed based on the current concept when drift detect, 2) MAD is used to measure the performance of ensemble members, and 3) a newly built classifier replaces the worst base classifier. If the newly constructed classifier is the worst one, the replacement has not occurred. Comparing with the state-of-art algorithms, ADE exceeds the current best-related algorithm by 2.38% in average classification accuracy. Experimental results show that the proposed method can effectively adapt to different types of drifts.","PeriodicalId":13624,"journal":{"name":"Int. Arab J. Inf. Technol.","volume":"15 1","pages":"90-96"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87814783","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Voice User Interfaces (VUIs) are increasingly popular owing to improvements in automatic speech recognition. However, the understanding of user interaction with VUIs, particularly Arabic VUIs, remains limited. Hence, this research compared user performance, learnability, and satisfaction when using voice and keyboard-and-mouse input modalities for text creation on Arabic user interfaces. A Voice-enabled Email Interface (VEI) and a Traditional Email Interface (TEI) were developed. Forty participants attempted pre-prepared and self-generated message creation tasks using voice on the VEI, and the keyboard-and-mouse modal on the TEI. The results showed that participants were faster (by 1.76 to 2.67 minutes) in pre-prepared message creation using voice than using the keyboard and mouse. Participants were also faster (by 1.72 to 2.49 minutes) in self-generated message creation using voice than using the keyboard and mouse. Although the learning curves were more efficient with the VEI, more participants were satisfied with the TEI. With the VEI, participants reported problems, such as misrecognitions and misspellings, but were satisfied about the visibility of possible executable commands and about the overall accuracy of voice recognition.
{"title":"Voice versus keyboard and mouse for text creation on arabic user interfaces","authors":"K. Majrashi","doi":"10.34028/iajit/19/1/15","DOIUrl":"https://doi.org/10.34028/iajit/19/1/15","url":null,"abstract":"Voice User Interfaces (VUIs) are increasingly popular owing to improvements in automatic speech recognition. However, the understanding of user interaction with VUIs, particularly Arabic VUIs, remains limited. Hence, this research compared user performance, learnability, and satisfaction when using voice and keyboard-and-mouse input modalities for text creation on Arabic user interfaces. A Voice-enabled Email Interface (VEI) and a Traditional Email Interface (TEI) were developed. Forty participants attempted pre-prepared and self-generated message creation tasks using voice on the VEI, and the keyboard-and-mouse modal on the TEI. The results showed that participants were faster (by 1.76 to 2.67 minutes) in pre-prepared message creation using voice than using the keyboard and mouse. Participants were also faster (by 1.72 to 2.49 minutes) in self-generated message creation using voice than using the keyboard and mouse. Although the learning curves were more efficient with the VEI, more participants were satisfied with the TEI. With the VEI, participants reported problems, such as misrecognitions and misspellings, but were satisfied about the visibility of possible executable commands and about the overall accuracy of voice recognition.","PeriodicalId":13624,"journal":{"name":"Int. Arab J. Inf. Technol.","volume":"63 1","pages":"132-142"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86878805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This Approach comprises of methods to produce novel and efficient methods to implement search of data objects in various applications. It is based on the best match search to implement proximity or best match search over complex or more than one data source. In particular with the availability of very large numeric data set in the present day scenario. The proposed approach which is based on the Arithmetic measures or distance measures called as the predominant Mean based algorithm. It is implemented on the longest common prefix of data object that shows how it can be used to generate various clusters through combining or grouping of data, as it takes O(log n) computational time. And further the approach is based on the process of measuring the distance which is suitable for a hierarchy tree property for proving the classification is needed one for storing or accessing or retrieving the information as required. The results obtained illustrates overall error detection rates in generating the clusters and searching the key value for Denial of Service (DOS) attack 5.15%, Probe attack 3.87%, U2R attack 8.11% and R2L attack 11.14%. as these error detection rates denotes that our proposed algorithm generates less error rates than existing linkage methods.
{"title":"A Novel Binary Search Tree Method to Find an Item Using Scaling","authors":"Praveen Pappula","doi":"10.34028/iajit/19/5/2","DOIUrl":"https://doi.org/10.34028/iajit/19/5/2","url":null,"abstract":"This Approach comprises of methods to produce novel and efficient methods to implement search of data objects in various applications. It is based on the best match search to implement proximity or best match search over complex or more than one data source. In particular with the availability of very large numeric data set in the present day scenario. The proposed approach which is based on the Arithmetic measures or distance measures called as the predominant Mean based algorithm. It is implemented on the longest common prefix of data object that shows how it can be used to generate various clusters through combining or grouping of data, as it takes O(log n) computational time. And further the approach is based on the process of measuring the distance which is suitable for a hierarchy tree property for proving the classification is needed one for storing or accessing or retrieving the information as required. The results obtained illustrates overall error detection rates in generating the clusters and searching the key value for Denial of Service (DOS) attack 5.15%, Probe attack 3.87%, U2R attack 8.11% and R2L attack 11.14%. as these error detection rates denotes that our proposed algorithm generates less error rates than existing linkage methods.","PeriodicalId":13624,"journal":{"name":"Int. Arab J. Inf. Technol.","volume":"90 1","pages":"713-720"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83921861","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
N. Matar, Tirad AlMalahmeh, Bilal I. Sowan, Saheer Al-Jaghoub, Wasef Mater
The adoption of new technologies in Jordanian Universities related to cloud services, shows differences in practices between faculty and staff members. Resistance to adoption may accrue by faculty and staff members who are accustomed and favoring old practices. A questionnaire was developed based on the Unified Theory of Acceptance and Use of Technology (UTAUT) model to identify factors that affect behavioral intentions that lead to the use of mobile cloud computing during the covid-19 pandemic, taking into consideration Work-type as the mediating factor. Five Jordanian Universities participated in this study, with a total response of 153 faculty and staff members. The conceptual proposed model was tested to ensure the fitness of the structural model for providing correct estimations. The collected sample was subjected to confirmatory factor analysis to ensure construct, convergent and discriminant validity. The results came positive in terms of composite reliability as they were above 0.70, for Average Variance Extracted (AVE) it came more than 0.05and Cronbach alpha exceeded 0.70. The results revealed the fitness of the proposed model to measure differences in behavioral intentions towards adopting mobile cloud services between faculty members and employees. Moreover, the results showed that work type had some interesting moderating impact on the tested relationships. Moreover, the results showed that there is a high Behavioral Intention (BI) between faculty and staff to use mobile cloud services and solutions within their workplace. In addition, the results showed some inequalities of the behavioral intention toward the adoption of mobile cloud services in Jordanian Universities between the two groups. These results call the university administration to clarify these factors for user groups to obtain a better judgment on investment and future practices for using new technologies.
{"title":"A multi-group structural equation modeling for assessing behavioral intention of using mobile cloud computing-the case of jordanian universities during the covid19 pandemic","authors":"N. Matar, Tirad AlMalahmeh, Bilal I. Sowan, Saheer Al-Jaghoub, Wasef Mater","doi":"10.34028/iajit/19/2/7","DOIUrl":"https://doi.org/10.34028/iajit/19/2/7","url":null,"abstract":"The adoption of new technologies in Jordanian Universities related to cloud services, shows differences in practices between faculty and staff members. Resistance to adoption may accrue by faculty and staff members who are accustomed and favoring old practices. A questionnaire was developed based on the Unified Theory of Acceptance and Use of Technology (UTAUT) model to identify factors that affect behavioral intentions that lead to the use of mobile cloud computing during the covid-19 pandemic, taking into consideration Work-type as the mediating factor. Five Jordanian Universities participated in this study, with a total response of 153 faculty and staff members. The conceptual proposed model was tested to ensure the fitness of the structural model for providing correct estimations. The collected sample was subjected to confirmatory factor analysis to ensure construct, convergent and discriminant validity. The results came positive in terms of composite reliability as they were above 0.70, for Average Variance Extracted (AVE) it came more than 0.05and Cronbach alpha exceeded 0.70. The results revealed the fitness of the proposed model to measure differences in behavioral intentions towards adopting mobile cloud services between faculty members and employees. Moreover, the results showed that work type had some interesting moderating impact on the tested relationships. Moreover, the results showed that there is a high Behavioral Intention (BI) between faculty and staff to use mobile cloud services and solutions within their workplace. In addition, the results showed some inequalities of the behavioral intention toward the adoption of mobile cloud services in Jordanian Universities between the two groups. These results call the university administration to clarify these factors for user groups to obtain a better judgment on investment and future practices for using new technologies.","PeriodicalId":13624,"journal":{"name":"Int. Arab J. Inf. Technol.","volume":"3 1","pages":"203-213"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85608523","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The recognition of human facial expressions with the variation of poses is one of the challenging tasks in real-time applications such as human physiological interaction detection, intention analysis, marketing interest evaluation, mental disease diagnosis, etc. This research work addresses the problem of expression recognition from different facial poses at the yaw angle. The major contribution of the paper is the proposal of an autonomous pose variant facial expression recognition framework using the amalgamation of a hybrid deep learning model with an improved quantum inspired gravitational search algorithm. The hybrid deep learning model is the integration of the convolutional neural network and recurrent neural network. The applicability of the hybrid deep learning model can be considered as significant if the feature set is efficiently optimized to have the discriminative features respective to each expression class. Here, the Improved Quantum Inspired Gravitational Search Algorithm (IQI-GSA) is utilized for the selection and optimization of features. The IQI-GSA method is significant for optimizing the features compared to quantum-behaved binary gravitation search algorithm for handing the local optima and stochastic characteristics. Comparing with state-of-art techniques, the proposed framework exhibits the outperformed recognition rate for experimentation on Karolinska Directed Emotional Faces (KDEF) and Japanese Female Facial Expression (JAFFE) datasets.
{"title":"Multi-pose facial expression recognition using hybrid deep learning model with improved variant of gravitational search algorithm","authors":"Y. Kumar, S. K. Verma, Sandeep Sharma","doi":"10.34028/iajit/19/2/15","DOIUrl":"https://doi.org/10.34028/iajit/19/2/15","url":null,"abstract":"The recognition of human facial expressions with the variation of poses is one of the challenging tasks in real-time applications such as human physiological interaction detection, intention analysis, marketing interest evaluation, mental disease diagnosis, etc. This research work addresses the problem of expression recognition from different facial poses at the yaw angle. The major contribution of the paper is the proposal of an autonomous pose variant facial expression recognition framework using the amalgamation of a hybrid deep learning model with an improved quantum inspired gravitational search algorithm. The hybrid deep learning model is the integration of the convolutional neural network and recurrent neural network. The applicability of the hybrid deep learning model can be considered as significant if the feature set is efficiently optimized to have the discriminative features respective to each expression class. Here, the Improved Quantum Inspired Gravitational Search Algorithm (IQI-GSA) is utilized for the selection and optimization of features. The IQI-GSA method is significant for optimizing the features compared to quantum-behaved binary gravitation search algorithm for handing the local optima and stochastic characteristics. Comparing with state-of-art techniques, the proposed framework exhibits the outperformed recognition rate for experimentation on Karolinska Directed Emotional Faces (KDEF) and Japanese Female Facial Expression (JAFFE) datasets.","PeriodicalId":13624,"journal":{"name":"Int. Arab J. Inf. Technol.","volume":"29 1","pages":"281-287"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73645461","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Indian sign language (ISL) is the commonly used language by the deaf-mute community in the Indian continent. Effective feature extraction is essential for the automatic recognition of gestures. This paper aims at developing an efficient feature extraction technique using FAST, SIFT, and CNN. Features from Fast Accelerated Segment Test(FAST) with Scale-invariant Feature Transformation(SIFT) are used to detect and compute features, respectively. CNN is used for classification with the hybridization of FAST-SIFT features. The system is implemented and tested using the python-based library Keras. The results of the proposed techniques have been tested on 34 gestures of ISL (24 alphabet sets and 10 digit sets) and then compared with the CNN and SIFT_CNN, and it is also tested on two publicly available datasets on Jochen Trisech Dataset(JTD) and NUS-II dataset. The proposed study outperformed some existing ISLR works with an accuracy of 97.89%, 95.68%, 94.90% and 95.87% for ISL-alphabets, MNIST, JTD and NUS-II, respectively.
{"title":"Hybrid FiST_CNN approach for feature extraction for vision-based indian sign language recognition","authors":"Akansha Tyagi, Sandhya Bansal","doi":"10.34028/iajit/19/3/15","DOIUrl":"https://doi.org/10.34028/iajit/19/3/15","url":null,"abstract":"Indian sign language (ISL) is the commonly used language by the deaf-mute community in the Indian continent. Effective feature extraction is essential for the automatic recognition of gestures. This paper aims at developing an efficient feature extraction technique using FAST, SIFT, and CNN. Features from Fast Accelerated Segment Test(FAST) with Scale-invariant Feature Transformation(SIFT) are used to detect and compute features, respectively. CNN is used for classification with the hybridization of FAST-SIFT features. The system is implemented and tested using the python-based library Keras. The results of the proposed techniques have been tested on 34 gestures of ISL (24 alphabet sets and 10 digit sets) and then compared with the CNN and SIFT_CNN, and it is also tested on two publicly available datasets on Jochen Trisech Dataset(JTD) and NUS-II dataset. The proposed study outperformed some existing ISLR works with an accuracy of 97.89%, 95.68%, 94.90% and 95.87% for ISL-alphabets, MNIST, JTD and NUS-II, respectively.","PeriodicalId":13624,"journal":{"name":"Int. Arab J. Inf. Technol.","volume":"65 1","pages":"403-411"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74945876","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：