Pub Date : 2021-10-01DOI: 10.4018/ijcini.20211001.oa20
Lei Yang, Xin Hu, Hui Wang, Wensheng Zhang, K. Huang, Dongya Wang
To overcome shortcomings when the ant colony optimization clustering algorithm (ACOC) deal with the clustering problem, this paper introduces a novel ant colony optimization clustering algorithm with chaos. The main idea of the algorithm is to apply the chaotic mapping function in the two stages of ant colony optimization: pheromone initialization and pheromone update. The application of chaotic mapping function in the pheromone initialization phase can encourage ants to be distributed in as many different initial states as possible. Applying the chaotic mapping function in the pheromone update stage can add disturbance factors to the algorithm, prompting the ants to explore new paths more, avoiding premature convergence and premature convergence to suboptimal solutions. Extensive experiments on the traditional and proposed algorithms on four widely used benchmarks are conducted to investigate the performance of the new algorithm. These experiments results demonstrate the competitive efficiency, effectiveness, and stability of the proposed algorithm.
{"title":"An ACO-Based Clustering Algorithm With Chaotic Function Mapping","authors":"Lei Yang, Xin Hu, Hui Wang, Wensheng Zhang, K. Huang, Dongya Wang","doi":"10.4018/ijcini.20211001.oa20","DOIUrl":"https://doi.org/10.4018/ijcini.20211001.oa20","url":null,"abstract":"To overcome shortcomings when the ant colony optimization clustering algorithm (ACOC) deal with the clustering problem, this paper introduces a novel ant colony optimization clustering algorithm with chaos. The main idea of the algorithm is to apply the chaotic mapping function in the two stages of ant colony optimization: pheromone initialization and pheromone update. The application of chaotic mapping function in the pheromone initialization phase can encourage ants to be distributed in as many different initial states as possible. Applying the chaotic mapping function in the pheromone update stage can add disturbance factors to the algorithm, prompting the ants to explore new paths more, avoiding premature convergence and premature convergence to suboptimal solutions. Extensive experiments on the traditional and proposed algorithms on four widely used benchmarks are conducted to investigate the performance of the new algorithm. These experiments results demonstrate the competitive efficiency, effectiveness, and stability of the proposed algorithm.","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":"67 1","pages":"1-21"},"PeriodicalIF":0.9,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82959788","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}
Recognition and classification of traffic signs and other numerous displays on the road are very crucial for autonomous driving, navigation, and safety systems on roads. Machine learning or deep learning methods are generally employed to develop a traffic sign recognition (TSR) system. This paper proposes a novel two-step TSR approach consisting of contrast limited adaptive histogram equalization (CLAHE)-based image enhancement and convolutional neural network (CNN) as multiclass classifier. Three CNN architectures viz. LeNet, VggNet, and ResNet were employed for classification. All the methods were tested for classification of German traffic sign recognition benchmark (GTSRB) dataset. The experimental results presented in the paper endorse the capability of the proposed work. Based on experimental results, it has also been illustrated that the proposed novel architecture consisting of CLAHE-based image enhancement & ResNet-based classifier has helped to obtain better classification accuracy as compared to other similar approaches.
{"title":"Efficient Traffic Sign Recognition Using CLAHE-Based Image Enhancement and ResNet CNN Architectures","authors":"Utkarsh Dubey, R. Chaurasiya","doi":"10.4018/ijcini.295811","DOIUrl":"https://doi.org/10.4018/ijcini.295811","url":null,"abstract":"Recognition and classification of traffic signs and other numerous displays on the road are very crucial for autonomous driving, navigation, and safety systems on roads. Machine learning or deep learning methods are generally employed to develop a traffic sign recognition (TSR) system. This paper proposes a novel two-step TSR approach consisting of contrast limited adaptive histogram equalization (CLAHE)-based image enhancement and convolutional neural network (CNN) as multiclass classifier. Three CNN architectures viz. LeNet, VggNet, and ResNet were employed for classification. All the methods were tested for classification of German traffic sign recognition benchmark (GTSRB) dataset. The experimental results presented in the paper endorse the capability of the proposed work. Based on experimental results, it has also been illustrated that the proposed novel architecture consisting of CLAHE-based image enhancement & ResNet-based classifier has helped to obtain better classification accuracy as compared to other similar approaches.","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":"42 1","pages":"1-19"},"PeriodicalIF":0.9,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77640137","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 study shows an enhancement of IoT which gets sensor data and performs real-time face recognition to screen physical areas to find strange situations and send an alarm mail to the client to make remedial moves to avoid any potential misfortune in the environment. Sensor data is pushed onto the local system and GoDaddy Cloud, whenever the camera detects a person to optimize the Physical Location Monitoring System by reducing the bandwidth requirement and storage cost onto the Cloud using edge computation. The study reveals that Decision Tree (DT) and Random Forest give reasonably similar macro average f1-score to predict a person using sensor data. Experimental results show that DT is the most reliable predictive model for the Cloud datasets of three different physical locations to predict a person using timestamp with an accuracy of 83.99%, 88.92%, and 80.97%. This study also explains multivariate time series prediction using Vector Auto Regression that gives reasonably good Root Mean Squared Error to predict Temperature, Humidity, Light Dependent Resistor, and Gas time series.
{"title":"Optimization of IoT-Enabled Physical Location Monitoring Using DT and VAR","authors":"A. S. Shitole, M. Devare","doi":"10.4018/IJCINI.287597","DOIUrl":"https://doi.org/10.4018/IJCINI.287597","url":null,"abstract":"This study shows an enhancement of IoT which gets sensor data and performs real-time face recognition to screen physical areas to find strange situations and send an alarm mail to the client to make remedial moves to avoid any potential misfortune in the environment. Sensor data is pushed onto the local system and GoDaddy Cloud, whenever the camera detects a person to optimize the Physical Location Monitoring System by reducing the bandwidth requirement and storage cost onto the Cloud using edge computation. The study reveals that Decision Tree (DT) and Random Forest give reasonably similar macro average f1-score to predict a person using sensor data. Experimental results show that DT is the most reliable predictive model for the Cloud datasets of three different physical locations to predict a person using timestamp with an accuracy of 83.99%, 88.92%, and 80.97%. This study also explains multivariate time series prediction using Vector Auto Regression that gives reasonably good Root Mean Squared Error to predict Temperature, Humidity, Light Dependent Resistor, and Gas time series.","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":"26 1","pages":"1-28"},"PeriodicalIF":0.9,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75789365","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 : 2021-10-01DOI: 10.4018/IJCINI.20211001.OA40
Safia Bekhouche, Y. M. B. Ali
GPCRs are the largest family of cell surface receptors; many of them remain orphans. The GPCR functions prediction represents a very important bioinformatics task. It consists in assigning to the protein the corresponding functional class. This classification step requires a good protein representation method and a robust classification algorithm. However, the complexity of this task could be increased because of the great number of GPCRs features in most databases, which produce combinatorial explosion. In order to reduce complexity and optimize classification, the authors propose to use bio-inspired metaheuristics for both the feature selection and the choice of the best couple (feature extraction strategy [FES], data mining algorithm [DMA]). The authors propose to use the BAT algorithm for extracting the pertinent features and the genetic algorithm to choose the best couple. They compared the results they obtained with two existing algorithms. Experimental results indicate the efficiency of the proposed system.
{"title":"Bio-Inspired Data Mining for Optimizing GPCR Function Identification","authors":"Safia Bekhouche, Y. M. B. Ali","doi":"10.4018/IJCINI.20211001.OA40","DOIUrl":"https://doi.org/10.4018/IJCINI.20211001.OA40","url":null,"abstract":"GPCRs are the largest family of cell surface receptors; many of them remain orphans. The GPCR functions prediction represents a very important bioinformatics task. It consists in assigning to the protein the corresponding functional class. This classification step requires a good protein representation method and a robust classification algorithm. However, the complexity of this task could be increased because of the great number of GPCRs features in most databases, which produce combinatorial explosion. In order to reduce complexity and optimize classification, the authors propose to use bio-inspired metaheuristics for both the feature selection and the choice of the best couple (feature extraction strategy [FES], data mining algorithm [DMA]). The authors propose to use the BAT algorithm for extracting the pertinent features and the genetic algorithm to choose the best couple. They compared the results they obtained with two existing algorithms. Experimental results indicate the efficiency of the proposed system.","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":"4 1","pages":"1-31"},"PeriodicalIF":0.9,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80953921","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}
Previous research has shown that tracking algorithms cannot capture long-distance information and lead to the loss of the object when the object was deformed, the illumination changed, and the background was disturbed by similar objects. To remedy this, this article proposes an object-tracking method by introducing the Global Context attention module into the Multi-Domain Network (MDNet) tracker. This method can learn the robust feature representation of the object through the Global Context attention module to better distinguish the background from the object in the presence of interference factors. Extensive experiments on OTB2013, OTB2015, and UAV20L datasets show that the proposed method is significantly improved compared with MDNet and has competitive performance compared with more mainstream tracking algorithms. At the same time, the method proposed in this article achieves better results when the video sequence contains object deformation, illumination change, and background interference with similar objects.
{"title":"Object Tracking Based on Global Context Attention","authors":"Yucheng Wang, Xi Chen, Zhongjie Mao, Jia Yan","doi":"10.4018/ijcini.287595","DOIUrl":"https://doi.org/10.4018/ijcini.287595","url":null,"abstract":"Previous research has shown that tracking algorithms cannot capture long-distance information and lead to the loss of the object when the object was deformed, the illumination changed, and the background was disturbed by similar objects. To remedy this, this article proposes an object-tracking method by introducing the Global Context attention module into the Multi-Domain Network (MDNet) tracker. This method can learn the robust feature representation of the object through the Global Context attention module to better distinguish the background from the object in the presence of interference factors. Extensive experiments on OTB2013, OTB2015, and UAV20L datasets show that the proposed method is significantly improved compared with MDNet and has competitive performance compared with more mainstream tracking algorithms. At the same time, the method proposed in this article achieves better results when the video sequence contains object deformation, illumination change, and background interference with similar objects.","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":"7 1","pages":"1-16"},"PeriodicalIF":0.9,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81991681","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 : 2021-10-01DOI: 10.4018/ijcini.20211001.oa17
Anbang Wang, Lihong Guo, Yuan Chen, Junjie Wang, Luo Liu, Yuanzhang Song
The travelling salesman problem (TSP) is an NP-hard problem in combinatorial optimization. It has assumed significance in operations research and theoretical computer science. The problem was first formulated in 1930 and since then, has been one of the most extensively studied problems in optimization. In fact, it is used as a benchmark for many optimization methods. This paper represents a new method to addressing TSP using an improved version of cuckoo search (CS) with Stud (SCS) crossover operator. In SCS method, similar to genetic operators used in various metaheuristic algorithms, a Stud crossover operator that is originated from classical Stud genetic algorithm, is introduced into the CS with the aim of improving its effectiveness and reliability while dealing with TSP. Various test functions had been used to test this approach, and used subsequently to find the shortest path for Chinese TSP (CTSP). Experimental results presented clearly demonstrates SCS as a viable and attractive addition to the portfolio of swarm intelligence techniques.
{"title":"An Improved Cuckoo Search Algorithm With Stud Crossover for Chinese TSP Problem","authors":"Anbang Wang, Lihong Guo, Yuan Chen, Junjie Wang, Luo Liu, Yuanzhang Song","doi":"10.4018/ijcini.20211001.oa17","DOIUrl":"https://doi.org/10.4018/ijcini.20211001.oa17","url":null,"abstract":"The travelling salesman problem (TSP) is an NP-hard problem in combinatorial optimization. It has assumed significance in operations research and theoretical computer science. The problem was first formulated in 1930 and since then, has been one of the most extensively studied problems in optimization. In fact, it is used as a benchmark for many optimization methods. This paper represents a new method to addressing TSP using an improved version of cuckoo search (CS) with Stud (SCS) crossover operator. In SCS method, similar to genetic operators used in various metaheuristic algorithms, a Stud crossover operator that is originated from classical Stud genetic algorithm, is introduced into the CS with the aim of improving its effectiveness and reliability while dealing with TSP. Various test functions had been used to test this approach, and used subsequently to find the shortest path for Chinese TSP (CTSP). Experimental results presented clearly demonstrates SCS as a viable and attractive addition to the portfolio of swarm intelligence techniques.","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":"28 1","pages":"1-26"},"PeriodicalIF":0.9,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89273195","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}
Information technology is developing rapidly, which not only brings opportunities to the society, but also causes various problems of mobile internet information security. Quantum circuits have many characteristics, such as high-complexity and no feedback. This paper applies quantum circuits to the field of encryption technology. A quantum circuit encryption system is designed based on AES. The system uses quantum circuits to construct the encryption algorithm and realizes the mathematical operations and transformation in quantum logic which can be realized through quantum logic gates. Encryption system of quantum circuits can improve the encryption complexity. Its anti-attack ability is (2^n-1)! times of the traditional method, thus it can effectively protect the information security of the IoT. In order to increase the practicability of the system, an interface module is also designed to facilitate the interaction of the system with the outside world. Finally, the encryption rate, resource utilization, and encryption effect of the quantum circuit encryption system are tested, which shows the advantages of it.
{"title":"Research and Application of Encryption System Based on Quantum Circuit for Mobile Internet Security","authors":"Yuehua Li, Chengcheng Wang, Jiahao Sun, Zhijin Guan, Jiaqing Chen, Zelin Wang","doi":"10.4018/IJCINI.20211001.OA26","DOIUrl":"https://doi.org/10.4018/IJCINI.20211001.OA26","url":null,"abstract":"Information technology is developing rapidly, which not only brings opportunities to the society, but also causes various problems of mobile internet information security. Quantum circuits have many characteristics, such as high-complexity and no feedback. This paper applies quantum circuits to the field of encryption technology. A quantum circuit encryption system is designed based on AES. The system uses quantum circuits to construct the encryption algorithm and realizes the mathematical operations and transformation in quantum logic which can be realized through quantum logic gates. Encryption system of quantum circuits can improve the encryption complexity. Its anti-attack ability is (2^n-1)! times of the traditional method, thus it can effectively protect the information security of the IoT. In order to increase the practicability of the system, an interface module is also designed to facilitate the interaction of the system with the outside world. Finally, the encryption rate, resource utilization, and encryption effect of the quantum circuit encryption system are tested, which shows the advantages of it.","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":"1 1","pages":"1-17"},"PeriodicalIF":0.9,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86425214","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 has attracted more and more attention in speech recognition, visual recognition and other fields. In the field of image processing, using deep learning method can obtain high recognition rate. In this paper, the convolution neural network is used as the basic model of deep learning. The shortcomings of the model are analyzed, and the DBN is used for the image recognition of diseases and insect pests. In the experiment, firstly, we select 10 kinds of disease and pest leaves and 50000 normal leaves, each of which is used for the comparison of algorithm performance.In the judgment of disease and pest species, the algorithm proposed in this study can identify all kinds of diseases and insect pests to the maximum extent, but the corresponding software (openCV, Access) recognition accuracy will gradually reduce along with the increase of the types of diseases and insect pests. In this study, the algorithm proposed in the identification of diseases and insect pests has been kept at about 45%.
{"title":"Research of Image Recognition of Plant Diseases and Pests Based on Deep Learning","authors":"W. Feng, Huang Xue Hua","doi":"10.4018/ijcini.295810","DOIUrl":"https://doi.org/10.4018/ijcini.295810","url":null,"abstract":"Deep learning has attracted more and more attention in speech recognition, visual recognition and other fields. In the field of image processing, using deep learning method can obtain high recognition rate. In this paper, the convolution neural network is used as the basic model of deep learning. The shortcomings of the model are analyzed, and the DBN is used for the image recognition of diseases and insect pests. In the experiment, firstly, we select 10 kinds of disease and pest leaves and 50000 normal leaves, each of which is used for the comparison of algorithm performance.In the judgment of disease and pest species, the algorithm proposed in this study can identify all kinds of diseases and insect pests to the maximum extent, but the corresponding software (openCV, Access) recognition accuracy will gradually reduce along with the increase of the types of diseases and insect pests. In this study, the algorithm proposed in the identification of diseases and insect pests has been kept at about 45%.","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":"58 1","pages":"1-21"},"PeriodicalIF":0.9,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86886313","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}
Automatic fake news detection is a challenging problem in deception detection. While evaluating the performance of deep learning-based models, if all the models are giving higher accuracy on a test dataset, it will make it harder to validate the performance of the deep learning models under consideration. So, we will need a complex problem to validate the performance of a deep learning model. LIAR is one such complex, much resent, labeled benchmark dataset which is publicly available for doing research on fake news detection to model statistical and machine learning approaches to combating fake news. In this work, a novel fake news detection system is implemented using Deep Neural Network models such as CNN, LSTM, BiLSTM, and the performance of their attention mechanism is evaluated by analyzing their performance in terms of Accuracy, Precision, Recall, and F1-score with training, validation and test datasets of LIAR.
{"title":"Attention-Based Deep Learning Models for Detection of Fake News in Social Networks","authors":"S. Ramya, R. Eswari","doi":"10.4018/ijcini.295809","DOIUrl":"https://doi.org/10.4018/ijcini.295809","url":null,"abstract":"Automatic fake news detection is a challenging problem in deception detection. While evaluating the performance of deep learning-based models, if all the models are giving higher accuracy on a test dataset, it will make it harder to validate the performance of the deep learning models under consideration. So, we will need a complex problem to validate the performance of a deep learning model. LIAR is one such complex, much resent, labeled benchmark dataset which is publicly available for doing research on fake news detection to model statistical and machine learning approaches to combating fake news. In this work, a novel fake news detection system is implemented using Deep Neural Network models such as CNN, LSTM, BiLSTM, and the performance of their attention mechanism is evaluated by analyzing their performance in terms of Accuracy, Precision, Recall, and F1-score with training, validation and test datasets of LIAR.","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":"80 1","pages":"1-25"},"PeriodicalIF":0.9,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84170355","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：