Pub Date : 2021-05-24DOI: 10.1109/ICICS52457.2021.9464553
Alanoud Alguzo, A. Alzu’bi, Firas AlBalas
In epidemic situations, as in the current COVID-19 pandemic, wearing face-masks is one of the most effective practices imposed to protect people lives. This will be one of the daily-life routines for a prolonged period, especially in public areas. Therefore, there is a demand to provide an efficient face detection method to help in dealing with such abnormal situations where people wearing masks are under monitoring. In this paper, we propose a deep learning model based on multi-graph convolutional networks (MGCN) to accurately detect people wearing masks. Unlike conventional GCNs, the proposed model includes many convolutional filters to produce multi-graph structure in which we use a 4D facet tensor as an input function and a convergence layer to capture multiple face expressions. This multi-graph version of spectral convolution transforms the extracted facial relief and generalizes image frequencies using graph rows and columns eigenvalues. The proposed architecture is simple yet efficient with several layers, including multi-graph convolutional, max pooling, dropout and softmax. We evaluate the performance of masked-faces detection on the publicly available real-world masked face dataset (RWMFD). The experimental results show an accuracy of 97.9%, which proves the efficiency of our proposed model in detecting people wearing facemasks.
{"title":"Masked Face Detection using Multi-Graph Convolutional Networks","authors":"Alanoud Alguzo, A. Alzu’bi, Firas AlBalas","doi":"10.1109/ICICS52457.2021.9464553","DOIUrl":"https://doi.org/10.1109/ICICS52457.2021.9464553","url":null,"abstract":"In epidemic situations, as in the current COVID-19 pandemic, wearing face-masks is one of the most effective practices imposed to protect people lives. This will be one of the daily-life routines for a prolonged period, especially in public areas. Therefore, there is a demand to provide an efficient face detection method to help in dealing with such abnormal situations where people wearing masks are under monitoring. In this paper, we propose a deep learning model based on multi-graph convolutional networks (MGCN) to accurately detect people wearing masks. Unlike conventional GCNs, the proposed model includes many convolutional filters to produce multi-graph structure in which we use a 4D facet tensor as an input function and a convergence layer to capture multiple face expressions. This multi-graph version of spectral convolution transforms the extracted facial relief and generalizes image frequencies using graph rows and columns eigenvalues. The proposed architecture is simple yet efficient with several layers, including multi-graph convolutional, max pooling, dropout and softmax. We evaluate the performance of masked-faces detection on the publicly available real-world masked face dataset (RWMFD). The experimental results show an accuracy of 97.9%, which proves the efficiency of our proposed model in detecting people wearing facemasks.","PeriodicalId":421803,"journal":{"name":"2021 12th International Conference on Information and Communication Systems (ICICS)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126448085","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}
Pub Date : 2021-05-24DOI: 10.1109/ICICS52457.2021.9464617
M. B. Yassein, Haneen Al Nassan, W. Mardini, Yaser M. Khamayseh
The IEEE 802.15.4/LR-WPAN medium access control (MAC) protocol, aims to achieve low data rate, low power consumption, low power means limited range. The MAC contain a super frame structure that’s divide into two portion the active portion and the inactive portion, to find out the duration of these portions two values found macSuperFrameOrder and the macBeaconOrder. SO is describe the first portion (active portion) length of the super frame structure, the BO describes at which interval the coordinator should transmit BF (beacon frame). BF is used for the synchronization process. Our goal is to find the optimal (BO, SO) let say from 1 to 14 for different arrival rates (O.1sec, 1sec, 2sec and 3sec) with CBR applications for a seven clients star topology, the optimal BO and SO values should have the maximum throughput value, minimum delay value and minimum energy consuming, depending on what the application require but the value of the application requirement should have acceptable values for the other requirements.
{"title":"An Optimal (BO, SO) Values for Different Arrival Rates IEEE 802.15.4/ LR-WPAN","authors":"M. B. Yassein, Haneen Al Nassan, W. Mardini, Yaser M. Khamayseh","doi":"10.1109/ICICS52457.2021.9464617","DOIUrl":"https://doi.org/10.1109/ICICS52457.2021.9464617","url":null,"abstract":"The IEEE 802.15.4/LR-WPAN medium access control (MAC) protocol, aims to achieve low data rate, low power consumption, low power means limited range. The MAC contain a super frame structure that’s divide into two portion the active portion and the inactive portion, to find out the duration of these portions two values found macSuperFrameOrder and the macBeaconOrder. SO is describe the first portion (active portion) length of the super frame structure, the BO describes at which interval the coordinator should transmit BF (beacon frame). BF is used for the synchronization process. Our goal is to find the optimal (BO, SO) let say from 1 to 14 for different arrival rates (O.1sec, 1sec, 2sec and 3sec) with CBR applications for a seven clients star topology, the optimal BO and SO values should have the maximum throughput value, minimum delay value and minimum energy consuming, depending on what the application require but the value of the application requirement should have acceptable values for the other requirements.","PeriodicalId":421803,"journal":{"name":"2021 12th International Conference on Information and Communication Systems (ICICS)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125538980","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}
Pub Date : 2021-05-24DOI: 10.1109/ICICS52457.2021.9464613
B. Alsaify, Mahmoud M. Almazari, R. Alazrai, M. Daoud
Human activity recognition is gaining much attention due to its role in medical alert systems, interactive video games, smart home systems, and many more. One of the main objectives of any human activity recognition system is recognizing the different human activities without affecting them. In this work, we utilize the information embedded in the overflowing Wi-Fi signal to determine which activity is being performed. A dataset obtained by observing 20 subjects performing activities in two different environments adds to this study’s credibility. The performed experiments show that an average activity recognition accuracy of 94% is possible.
{"title":"Exploiting Wi-Fi Signals for Human Activity Recognition","authors":"B. Alsaify, Mahmoud M. Almazari, R. Alazrai, M. Daoud","doi":"10.1109/ICICS52457.2021.9464613","DOIUrl":"https://doi.org/10.1109/ICICS52457.2021.9464613","url":null,"abstract":"Human activity recognition is gaining much attention due to its role in medical alert systems, interactive video games, smart home systems, and many more. One of the main objectives of any human activity recognition system is recognizing the different human activities without affecting them. In this work, we utilize the information embedded in the overflowing Wi-Fi signal to determine which activity is being performed. A dataset obtained by observing 20 subjects performing activities in two different environments adds to this study’s credibility. The performed experiments show that an average activity recognition accuracy of 94% is possible.","PeriodicalId":421803,"journal":{"name":"2021 12th International Conference on Information and Communication Systems (ICICS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134283517","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}
Pub Date : 2021-05-24DOI: 10.1109/ICICS52457.2021.9464556
D. Castro, C. Werner
Software reuse (SR) is a crucial software engineering discipline that seeks to create new components through preexisting ones. Using the concepts of this discipline correctly can bring several advantages, such as: reducing product cost, reducing the number of errors, and producing more efficient coding, among others. However, this approach is often proposed but fails; one of the possible causes is being a short time for teaching this discipline. To study software reuse teaching, this work performed a systematic mapping to identify what are the main difficulties, characteristics and importance of teaching this discipline. Through this mapping, it was possible to observe that SR is not a discipline commonly presented in academic curriculum of universities and that the approaches that have been used to teach this discipline are very similar despite the passing of years. The main problems found are the lack of practical training and the lack of student’s engagement and motivation. Based on these problems, possible solutions were proposed to help in the discipline’s teaching scenario.
{"title":"Systematic Mapping on Software Reuse Teaching","authors":"D. Castro, C. Werner","doi":"10.1109/ICICS52457.2021.9464556","DOIUrl":"https://doi.org/10.1109/ICICS52457.2021.9464556","url":null,"abstract":"Software reuse (SR) is a crucial software engineering discipline that seeks to create new components through preexisting ones. Using the concepts of this discipline correctly can bring several advantages, such as: reducing product cost, reducing the number of errors, and producing more efficient coding, among others. However, this approach is often proposed but fails; one of the possible causes is being a short time for teaching this discipline. To study software reuse teaching, this work performed a systematic mapping to identify what are the main difficulties, characteristics and importance of teaching this discipline. Through this mapping, it was possible to observe that SR is not a discipline commonly presented in academic curriculum of universities and that the approaches that have been used to teach this discipline are very similar despite the passing of years. The main problems found are the lack of practical training and the lack of student’s engagement and motivation. Based on these problems, possible solutions were proposed to help in the discipline’s teaching scenario.","PeriodicalId":421803,"journal":{"name":"2021 12th International Conference on Information and Communication Systems (ICICS)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128813233","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}
Pub Date : 2021-05-24DOI: 10.1109/ICICS52457.2021.9464603
Qusai Q. Abuein, Mothanna Almahmoud, Omar N. Elayan
The importance of universities' global ranking lies in providing a trusty resource, which helps students in choosing the right place to complete their academic future. The global ranking systems are based on several metrics that focus on the study environment, the quality of the provided services, the scientific publications, and the extent of the authors' strength. Quacquarelli Symonds (QS) is the most popular global ranking system, it has Citations Per Faculty (CPF) evaluation metric, which constitutes 20% of the total ranking score. In this research, we aim to find the effect of the research collaboration on increasing the CPF score, in which we apply descriptive analytics on a dataset for Jordan University of Science and Technology (JUST) authors, that is scrapped from the official websites of Google Scholar and Researchgate. Then, we find the authors who have a moderate collaboration through building a classification model using machine learning techniques. The results proved that the research collaboration has a significant impact in increasing authors publications that positively correlated with their total citations, which in turn gives a great opportunity to increase the CPF score. Also, the Support Vector Machine classifier has obtained a 95.27% level of accuracy, which considers as an efficient method in classifying the authors research collaboration into strong and moderate collaboration. Finally, the proposed method can be used to improve the QS ranking and obtain a high scientific standing level for academic institutes.
{"title":"Improving QS Rank Based on The Classification of Authors Research Collaboration Using Machine Learning Techniques","authors":"Qusai Q. Abuein, Mothanna Almahmoud, Omar N. Elayan","doi":"10.1109/ICICS52457.2021.9464603","DOIUrl":"https://doi.org/10.1109/ICICS52457.2021.9464603","url":null,"abstract":"The importance of universities' global ranking lies in providing a trusty resource, which helps students in choosing the right place to complete their academic future. The global ranking systems are based on several metrics that focus on the study environment, the quality of the provided services, the scientific publications, and the extent of the authors' strength. Quacquarelli Symonds (QS) is the most popular global ranking system, it has Citations Per Faculty (CPF) evaluation metric, which constitutes 20% of the total ranking score. In this research, we aim to find the effect of the research collaboration on increasing the CPF score, in which we apply descriptive analytics on a dataset for Jordan University of Science and Technology (JUST) authors, that is scrapped from the official websites of Google Scholar and Researchgate. Then, we find the authors who have a moderate collaboration through building a classification model using machine learning techniques. The results proved that the research collaboration has a significant impact in increasing authors publications that positively correlated with their total citations, which in turn gives a great opportunity to increase the CPF score. Also, the Support Vector Machine classifier has obtained a 95.27% level of accuracy, which considers as an efficient method in classifying the authors research collaboration into strong and moderate collaboration. Finally, the proposed method can be used to improve the QS ranking and obtain a high scientific standing level for academic institutes.","PeriodicalId":421803,"journal":{"name":"2021 12th International Conference on Information and Communication Systems (ICICS)","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128073409","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}
Pub Date : 2021-05-24DOI: 10.1109/ICICS52457.2021.9464596
Mohammed N. AlJarrah, Mo’ath M Zyout, R. Duwairi
Automatic handwritten characters’ recognition is one of Artificial intelligence applications which is considered an interesting research area and important in various fields. Many studies have been conducted for the recognition of English handwritten characters and fewer works are available for the Arabic language because of the diversity in characters’ shapes according to their positions in the words. Convolutional Neural Networks are efficient for handwritten characters’ recognition. In this paper, a Convolutional Neural Network has been proposed for handwritten characters’ recognition. The model has been trained on a dataset of 16,800 images of handwritten Arabic characters with different shapes to perform classification. The proposed model achieved high recognition accuracy of 97.2%, outperforming other state-of-art models. When applying data augmentation, the model achieved better results and accuracy of 97.7%
{"title":"Arabic Handwritten Characters Recognition Using Convolutional Neural Network","authors":"Mohammed N. AlJarrah, Mo’ath M Zyout, R. Duwairi","doi":"10.1109/ICICS52457.2021.9464596","DOIUrl":"https://doi.org/10.1109/ICICS52457.2021.9464596","url":null,"abstract":"Automatic handwritten characters’ recognition is one of Artificial intelligence applications which is considered an interesting research area and important in various fields. Many studies have been conducted for the recognition of English handwritten characters and fewer works are available for the Arabic language because of the diversity in characters’ shapes according to their positions in the words. Convolutional Neural Networks are efficient for handwritten characters’ recognition. In this paper, a Convolutional Neural Network has been proposed for handwritten characters’ recognition. The model has been trained on a dataset of 16,800 images of handwritten Arabic characters with different shapes to perform classification. The proposed model achieved high recognition accuracy of 97.2%, outperforming other state-of-art models. When applying data augmentation, the model achieved better results and accuracy of 97.7%","PeriodicalId":421803,"journal":{"name":"2021 12th International Conference on Information and Communication Systems (ICICS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129667663","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}
Pub Date : 2021-05-24DOI: 10.1109/ICICS52457.2021.9464580
Saeed Shurrab, Abdulkarem Almshnanah, R. Duwairi
Tool life and tool wear contribute significantly to any machining activity and directly affect the quality of the machined part, machining device performance as well as the production rates and costs. This research aims to investigate the performance of six supervised learning algorithms in predicting the cutting tool condition in Computer Numerical Control (CNC) milling operations using a novel form of CNC internal data that eliminate the need for sensory devices installation during the machining process for data acquisition purposes. The employed supervised learning algorithms include Decision Tree, Artificial Neural Network, Support Vector Machine, k-Nearest Neighbor, Logistic Regression and Naive Bayes. The results showed that Decision Tree, Artificial Neural Network, K-Nearest Neighbors and Support Vector Machine achieved overall classification accuracy greater than (85%) while Logistic Regression and Naive Bayes achieved overall classification accuracy of (57.1%) and (60.1%) respectively. Further, naive Bayes was able to correctly predict the cutting tool as worn from the test set despite its lower overall accuracy. In addition, features importance and decision rules were extracted from the Decision Tree algorithm as it achieved the highest overall accuracy score to investigate the most important features that influence the tool condition. The result showed that only three features have the highest influence on the tool condition while decision rules were used to investigate the value of these features to cause the cutting tools to be worn.
{"title":"Tool Wear Prediction in Computer Numerical Control Milling Operations via Machine Learning","authors":"Saeed Shurrab, Abdulkarem Almshnanah, R. Duwairi","doi":"10.1109/ICICS52457.2021.9464580","DOIUrl":"https://doi.org/10.1109/ICICS52457.2021.9464580","url":null,"abstract":"Tool life and tool wear contribute significantly to any machining activity and directly affect the quality of the machined part, machining device performance as well as the production rates and costs. This research aims to investigate the performance of six supervised learning algorithms in predicting the cutting tool condition in Computer Numerical Control (CNC) milling operations using a novel form of CNC internal data that eliminate the need for sensory devices installation during the machining process for data acquisition purposes. The employed supervised learning algorithms include Decision Tree, Artificial Neural Network, Support Vector Machine, k-Nearest Neighbor, Logistic Regression and Naive Bayes. The results showed that Decision Tree, Artificial Neural Network, K-Nearest Neighbors and Support Vector Machine achieved overall classification accuracy greater than (85%) while Logistic Regression and Naive Bayes achieved overall classification accuracy of (57.1%) and (60.1%) respectively. Further, naive Bayes was able to correctly predict the cutting tool as worn from the test set despite its lower overall accuracy. In addition, features importance and decision rules were extracted from the Decision Tree algorithm as it achieved the highest overall accuracy score to investigate the most important features that influence the tool condition. The result showed that only three features have the highest influence on the tool condition while decision rules were used to investigate the value of these features to cause the cutting tools to be worn.","PeriodicalId":421803,"journal":{"name":"2021 12th International Conference on Information and Communication Systems (ICICS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128922905","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}
Pub Date : 2021-05-24DOI: 10.1109/ICICS52457.2021.9464611
O. Al-Khaleel, S. Baktir, Alptekin Küpçü
In this work, an elliptic curve cryptography (ECC) processor is proposed. The ECC processor has been designed based on Edwards curves defined over the finite prime field GF ((213 − 1)13). Modular multiplication in the proposed ECC processor is carried out in the frequency domain using a Discrete Fourier Transform (DFT) modular multiplier. Different base field adders and base field multipliers have been designed and utilized in the design of the DFT modular multiplier. The ECC processor has been described and functionally tested using the VHDL language and the simulation tool in the Xilinx ISE14.2. Furthermore, the ECC processor has been synthesized using the synthesis tool in the Xilinx ISE14.2, targeting the Virtex-5 FPGA family. Our synthesis results show that the proposed ECC processor achieves higher speed with minor area penalty compared to the similar work in the literature.
{"title":"FPGA Implementation of an ECC Processor Using Edwards Curves and DFT Modular Multiplication","authors":"O. Al-Khaleel, S. Baktir, Alptekin Küpçü","doi":"10.1109/ICICS52457.2021.9464611","DOIUrl":"https://doi.org/10.1109/ICICS52457.2021.9464611","url":null,"abstract":"In this work, an elliptic curve cryptography (ECC) processor is proposed. The ECC processor has been designed based on Edwards curves defined over the finite prime field GF ((213 − 1)13). Modular multiplication in the proposed ECC processor is carried out in the frequency domain using a Discrete Fourier Transform (DFT) modular multiplier. Different base field adders and base field multipliers have been designed and utilized in the design of the DFT modular multiplier. The ECC processor has been described and functionally tested using the VHDL language and the simulation tool in the Xilinx ISE14.2. Furthermore, the ECC processor has been synthesized using the synthesis tool in the Xilinx ISE14.2, targeting the Virtex-5 FPGA family. Our synthesis results show that the proposed ECC processor achieves higher speed with minor area penalty compared to the similar work in the literature.","PeriodicalId":421803,"journal":{"name":"2021 12th International Conference on Information and Communication Systems (ICICS)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115572226","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 color scheme plays an important role in different aspects of our everyday lives, such as web design and human-computer interaction. The generation of color scheme requires a long-term accumulation of design experience and advanced knowledge of color matching. However, there is little work focusing on the automatic generation of color scheme based on learning capabilities. In this work, we propose a novel color scheme designer, SmartColor, which incorporates deep learning methods with knowledge of color psychology. The Generative Adversarial Network (GAN) is used to learn experienced insights from widely recognized color schemes obtained from online color matching websites. Color schemes based on various themes are transformed as statistical constraints in the construction of the objective function of GAN. SmartColor is both data-driven and knowledge-driven. In contrast to current color scheme solutions. SmartColor will automatically create color schemes based on the input theme. Experimental results show that SmartColor was successful in creating color schemes for websites.
{"title":"SmartColor: Automatic Web Color Scheme Generation Based on Deep Learning","authors":"Zhitao Feng, Mingliang Hou, Huiyang Liu, Mujie Liu, Achhardeep Kaur, F. Febrinanto, Wenhong Zhao","doi":"10.1109/ICICS52457.2021.9464536","DOIUrl":"https://doi.org/10.1109/ICICS52457.2021.9464536","url":null,"abstract":"The color scheme plays an important role in different aspects of our everyday lives, such as web design and human-computer interaction. The generation of color scheme requires a long-term accumulation of design experience and advanced knowledge of color matching. However, there is little work focusing on the automatic generation of color scheme based on learning capabilities. In this work, we propose a novel color scheme designer, SmartColor, which incorporates deep learning methods with knowledge of color psychology. The Generative Adversarial Network (GAN) is used to learn experienced insights from widely recognized color schemes obtained from online color matching websites. Color schemes based on various themes are transformed as statistical constraints in the construction of the objective function of GAN. SmartColor is both data-driven and knowledge-driven. In contrast to current color scheme solutions. SmartColor will automatically create color schemes based on the input theme. Experimental results show that SmartColor was successful in creating color schemes for websites.","PeriodicalId":421803,"journal":{"name":"2021 12th International Conference on Information and Communication Systems (ICICS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115725626","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}
Pub Date : 2021-05-24DOI: 10.1109/ICICS52457.2021.9464593
Manel Khelifi, Ali Lahreche, Ismail Grine, Ahmed Alioua
Energy harvesting is a promising paradigm in the Internet of things based on wireless sensor networks (IoT-based WSNs) for emerging applications such as smart cities, healthcare, and farming. Although the amalgamation of energy harvesting in WSNs (EH-WSNs) fostered many new opportunities, they still face challenging requirements to achieve high sustainability. Nowadays, most research efforts are focused on curtailing the limitation of the energy supply of IoT sensors, which strongly impacts their design. Therefore, new efficient energy harvesting routing protocols need to be developed, while ensuring network reliability and continuity. In this paper, we proposed a new energy harvesting greedy perimeter stateless routing protocol (EH-GPSR) to address the issue of limited sensor energy. EH-GPSR employs an EH rate in a cost function, derived from the randomized minimum path recovery time (R-MPRT) algorithm, to measure the harvested energy. Farther, it improves the greedy routing mechanism. Specifically, it uses a weighted function that combines the destination distance information with the EH rate-based cost to adaptively select the next hop. The simulation results showed that our protocol EH-GPSR extends the network lifetime and allows a better packet delivery rate by more than 20% compared to the GPSR protocol.
{"title":"EH-GPSR: An Energy Harvesting Protocol for IoT-based Wireless Sensor Networks","authors":"Manel Khelifi, Ali Lahreche, Ismail Grine, Ahmed Alioua","doi":"10.1109/ICICS52457.2021.9464593","DOIUrl":"https://doi.org/10.1109/ICICS52457.2021.9464593","url":null,"abstract":"Energy harvesting is a promising paradigm in the Internet of things based on wireless sensor networks (IoT-based WSNs) for emerging applications such as smart cities, healthcare, and farming. Although the amalgamation of energy harvesting in WSNs (EH-WSNs) fostered many new opportunities, they still face challenging requirements to achieve high sustainability. Nowadays, most research efforts are focused on curtailing the limitation of the energy supply of IoT sensors, which strongly impacts their design. Therefore, new efficient energy harvesting routing protocols need to be developed, while ensuring network reliability and continuity. In this paper, we proposed a new energy harvesting greedy perimeter stateless routing protocol (EH-GPSR) to address the issue of limited sensor energy. EH-GPSR employs an EH rate in a cost function, derived from the randomized minimum path recovery time (R-MPRT) algorithm, to measure the harvested energy. Farther, it improves the greedy routing mechanism. Specifically, it uses a weighted function that combines the destination distance information with the EH rate-based cost to adaptively select the next hop. The simulation results showed that our protocol EH-GPSR extends the network lifetime and allows a better packet delivery rate by more than 20% compared to the GPSR protocol.","PeriodicalId":421803,"journal":{"name":"2021 12th International Conference on Information and Communication Systems (ICICS)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128607670","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：