Pub Date : 2018-10-01DOI: 10.1109/CCCS.2018.8586818
Young-Gyu Kim, Dae-ui Lim, Jong-Hyun Ryu, T. Park
Surface Mount Technology (SMT) is a manufacturing process in which chips are mounted on the surface of a printed circuit board (PCB). The automatic optical inspection system (AOI) has mainly used the learning-based method for the defect classification of the SMT process, and recently the CNN-based classification method has appeared. However, existing techniques do not consider the area margin of the part and uneven color distribution according to the position of the chip, so the classification accuracy decreases. In this paper, we propose a system that can extract the chip region and improve the color distribution by the input image transformation. We extract the correct chip area through vertical and horizontal projection, and the color improvement enhance the brightness value distribution of the chip image through local histogram stretching. By experimental result, we prove the performance of the proposed classification method.
{"title":"SMD Defect Classification by Convolution Neural Network and PCB Image Transform","authors":"Young-Gyu Kim, Dae-ui Lim, Jong-Hyun Ryu, T. Park","doi":"10.1109/CCCS.2018.8586818","DOIUrl":"https://doi.org/10.1109/CCCS.2018.8586818","url":null,"abstract":"Surface Mount Technology (SMT) is a manufacturing process in which chips are mounted on the surface of a printed circuit board (PCB). The automatic optical inspection system (AOI) has mainly used the learning-based method for the defect classification of the SMT process, and recently the CNN-based classification method has appeared. However, existing techniques do not consider the area margin of the part and uneven color distribution according to the position of the chip, so the classification accuracy decreases. In this paper, we propose a system that can extract the chip region and improve the color distribution by the input image transformation. We extract the correct chip area through vertical and horizontal projection, and the color improvement enhance the brightness value distribution of the chip image through local histogram stretching. By experimental result, we prove the performance of the proposed classification method.","PeriodicalId":6570,"journal":{"name":"2018 IEEE 3rd International Conference on Computing, Communication and Security (ICCCS)","volume":"48 1","pages":"180-183"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85454519","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 : 2018-10-01DOI: 10.1109/CCCS.2018.8586840
Abhishek Divekar, Meet Parekh, Vaibhav Savla, Rudra Mishra, M. Shirole
Machine Learning has been steadily gaining traction for its use in Anomaly-based Network Intrusion Detection Systems (A-NIDS). Research into this domain is frequently performed using the KDD CUP 99 dataset as a benchmark. Several studies question its usability while constructing a contemporary NIDS, due to the skewed response distribution, non-stationarity, and failure to incorporate modern attacks. In this paper, we compare the performance for KDD-99 alternatives when trained using classification models commonly found in literature: Neural Network, Support Vector Machine, Decision Tree, Random Forest, Naive Bayes and K-Means. Applying the SMOTE oversampling technique and random undersampling, we create a balanced version of NSL-KDD and prove that skewed target classes in KDD-99 and NSL-KDD hamper the efficacy of classifiers on minority classes (U2R and R2L), leading to possible security risks. We explore UNSW-NB15, a modern substitute to KDD-99 with greater uniformity of pattern distribution. We benchmark this dataset before and after SMOTE oversampling to observe the effect on minority performance. Our results indicate that classifiers trained on UNSW-NB15 match or better the Weighted F1-Score of those trained on NSL-KDD and KDD-99 in the binary case, thus advocating UNSW-NB15 as a modern substitute to these datasets.
机器学习在基于异常的网络入侵检测系统(A-NIDS)中的应用一直在稳步获得关注。对这个领域的研究经常使用KDD CUP 99数据集作为基准。一些研究质疑其在构建当代NIDS时的可用性，因为响应分布偏斜、非平稳性和未能纳入现代攻击。在本文中，我们比较了在使用文献中常见的分类模型(神经网络、支持向量机、决策树、随机森林、朴素贝叶斯和K-Means)训练KDD-99备选方案时的性能。利用SMOTE过采样技术和随机欠采样，我们创建了一个平衡版本的NSL-KDD，并证明了KDD-99和NSL-KDD中倾斜的目标类别阻碍了分类器对少数类别(U2R和R2L)的有效性，从而导致可能的安全风险。我们探索的UNSW-NB15是KDD-99的现代替代品，具有更均匀的格局分布。我们在SMOTE过采样之前和之后对该数据集进行基准测试，以观察对少数派性能的影响。我们的研究结果表明，在二元情况下，UNSW-NB15训练的分类器与NSL-KDD和KDD-99训练的分类器的加权F1-Score相当或更好，因此提倡UNSW-NB15作为这些数据集的现代替代品。
{"title":"Benchmarking datasets for Anomaly-based Network Intrusion Detection: KDD CUP 99 alternatives","authors":"Abhishek Divekar, Meet Parekh, Vaibhav Savla, Rudra Mishra, M. Shirole","doi":"10.1109/CCCS.2018.8586840","DOIUrl":"https://doi.org/10.1109/CCCS.2018.8586840","url":null,"abstract":"Machine Learning has been steadily gaining traction for its use in Anomaly-based Network Intrusion Detection Systems (A-NIDS). Research into this domain is frequently performed using the KDD CUP 99 dataset as a benchmark. Several studies question its usability while constructing a contemporary NIDS, due to the skewed response distribution, non-stationarity, and failure to incorporate modern attacks. In this paper, we compare the performance for KDD-99 alternatives when trained using classification models commonly found in literature: Neural Network, Support Vector Machine, Decision Tree, Random Forest, Naive Bayes and K-Means. Applying the SMOTE oversampling technique and random undersampling, we create a balanced version of NSL-KDD and prove that skewed target classes in KDD-99 and NSL-KDD hamper the efficacy of classifiers on minority classes (U2R and R2L), leading to possible security risks. We explore UNSW-NB15, a modern substitute to KDD-99 with greater uniformity of pattern distribution. We benchmark this dataset before and after SMOTE oversampling to observe the effect on minority performance. Our results indicate that classifiers trained on UNSW-NB15 match or better the Weighted F1-Score of those trained on NSL-KDD and KDD-99 in the binary case, thus advocating UNSW-NB15 as a modern substitute to these datasets.","PeriodicalId":6570,"journal":{"name":"2018 IEEE 3rd International Conference on Computing, Communication and Security (ICCCS)","volume":"20 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81890080","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 : 2018-10-01DOI: 10.1109/CCCS.2018.8586843
S. Sudarsan, Devina Mohan, S. Rohit
Industrial control systems are used to automate process industries. Over 50 billion USD worth such systems are more than 20 years old resulting in their hardware having become outdated. Yet the process remains very little altered. These legacy systems need to be migrated to newer hardware and software platforms to ensure support and compliance to current standards. The time elapsed has resulted in shortage of subject matter and system experts available to understand the nitty gritties of the process functionality implementation in the legacy system using control language of that era. Documentation, if at all existing, is as built and not as running. Hence there is a need to generate documentation that could be understood by current generation automation and process engineers from the back-up of the running legacy system. This paper proposes a novel software tool to generate documents from the legacy industrial control system back-up. We test it with a real legacy system and verify the documents with actual back up. This helps in brownfield engineering migration projects.
{"title":"Industrial Control Systems - Legacy System Documentation and Augmentation","authors":"S. Sudarsan, Devina Mohan, S. Rohit","doi":"10.1109/CCCS.2018.8586843","DOIUrl":"https://doi.org/10.1109/CCCS.2018.8586843","url":null,"abstract":"Industrial control systems are used to automate process industries. Over 50 billion USD worth such systems are more than 20 years old resulting in their hardware having become outdated. Yet the process remains very little altered. These legacy systems need to be migrated to newer hardware and software platforms to ensure support and compliance to current standards. The time elapsed has resulted in shortage of subject matter and system experts available to understand the nitty gritties of the process functionality implementation in the legacy system using control language of that era. Documentation, if at all existing, is as built and not as running. Hence there is a need to generate documentation that could be understood by current generation automation and process engineers from the back-up of the running legacy system. This paper proposes a novel software tool to generate documents from the legacy industrial control system back-up. We test it with a real legacy system and verify the documents with actual back up. This helps in brownfield engineering migration projects.","PeriodicalId":6570,"journal":{"name":"2018 IEEE 3rd International Conference on Computing, Communication and Security (ICCCS)","volume":"103 1","pages":"167-170"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76869627","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 : 2018-10-01DOI: 10.1109/cccs.2018.8586836
Muhammad Ishtiaq Ali, A. Rehman, Shamaz Hafeez
Data mining is vast area that co-relates diverse branches i.e Statistics, Data Base, Machine learning and Artificial intelligence. Various applications are accessible in various areas. Churning of the Customer is the behavior when client never again needs to stay with his association with the company. Customer Churn Management is assuming essential job in client management. Nowadays different telecommunication companies are concentrating on distinguishing high esteemed and potential churning clients to expand benefit and share market. It is comprehended that making new clients are costlier than to holding existing client. There is a current issue that customer leave the organization because of obscure reasons. In our investigation, we predict churn behavior of the client by utilizing diverse data mining methods. It will in the long run help in breaking down client's behavior and characterize whether it is a churning client or not. We utilize online accessible data set available at Kaggle repository and for forecasting of Customer behavior we utilized different algorithms while we achieved 99.8% accuracy level using Bagging Algorithms.
{"title":"Prediction of Churning Behavior of Customers in Telecom Sector Using Supervised Learning Techniques","authors":"Muhammad Ishtiaq Ali, A. Rehman, Shamaz Hafeez","doi":"10.1109/cccs.2018.8586836","DOIUrl":"https://doi.org/10.1109/cccs.2018.8586836","url":null,"abstract":"Data mining is vast area that co-relates diverse branches i.e Statistics, Data Base, Machine learning and Artificial intelligence. Various applications are accessible in various areas. Churning of the Customer is the behavior when client never again needs to stay with his association with the company. Customer Churn Management is assuming essential job in client management. Nowadays different telecommunication companies are concentrating on distinguishing high esteemed and potential churning clients to expand benefit and share market. It is comprehended that making new clients are costlier than to holding existing client. There is a current issue that customer leave the organization because of obscure reasons. In our investigation, we predict churn behavior of the client by utilizing diverse data mining methods. It will in the long run help in breaking down client's behavior and characterize whether it is a churning client or not. We utilize online accessible data set available at Kaggle repository and for forecasting of Customer behavior we utilized different algorithms while we achieved 99.8% accuracy level using Bagging Algorithms.","PeriodicalId":6570,"journal":{"name":"2018 IEEE 3rd International Conference on Computing, Communication and Security (ICCCS)","volume":"7 1","pages":"143-147"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74399714","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}
EEG(Electroencephalogram) signals generated within the brain can be extracted using sensors. Thus generated signals can be classified based on the feature that are embedded within it. The signals once recognized can act as alternative inputs for users suffering from severe motor impairment. The inputs can be used for motion signal i.e directions left, right, up and down. In this paper, the raw EEG signals and power signals generated from NeuroSky Mindwave device have been classified using deep neural networks. Bi-directional Long Short Term Network architecture(Bi-LSTM) and a model which uses Long Short Term Memory(LSTM) with Attention layer have been implemented for the purpose. An accuracy of 56% was obtained using bi-directional LSTM network with raw signals, 44.75% accuracy with power signals, and with attention network using raw signals an accuracy of 63% was obtained.
{"title":"EEG based Directional Signal Classification using RNN Variants","authors":"Bikram Adhikari, Ankit Shrestha, Shailesh Mishra, Suyog Singh, Arun K. Timalsina","doi":"10.1109/CCCS.2018.8586823","DOIUrl":"https://doi.org/10.1109/CCCS.2018.8586823","url":null,"abstract":"EEG(Electroencephalogram) signals generated within the brain can be extracted using sensors. Thus generated signals can be classified based on the feature that are embedded within it. The signals once recognized can act as alternative inputs for users suffering from severe motor impairment. The inputs can be used for motion signal i.e directions left, right, up and down. In this paper, the raw EEG signals and power signals generated from NeuroSky Mindwave device have been classified using deep neural networks. Bi-directional Long Short Term Network architecture(Bi-LSTM) and a model which uses Long Short Term Memory(LSTM) with Attention layer have been implemented for the purpose. An accuracy of 56% was obtained using bi-directional LSTM network with raw signals, 44.75% accuracy with power signals, and with attention network using raw signals an accuracy of 63% was obtained.","PeriodicalId":6570,"journal":{"name":"2018 IEEE 3rd International Conference on Computing, Communication and Security (ICCCS)","volume":"309 1","pages":"218-223"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78363504","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 : 2018-10-01DOI: 10.1109/cccs.2018.8586806
{"title":"[Title page]","authors":"","doi":"10.1109/cccs.2018.8586806","DOIUrl":"https://doi.org/10.1109/cccs.2018.8586806","url":null,"abstract":"","PeriodicalId":6570,"journal":{"name":"2018 IEEE 3rd International Conference on Computing, Communication and Security (ICCCS)","volume":"80 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88591047","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 : 2018-10-01DOI: 10.1109/CCCS.2018.8586810
Kulvinder Singh, Ajit Singh
This paper focuses on Memcached security from DDoS attacks during all stages of attack life cycle. It identifies Memcached architecture flaws on the one hand (which are long been ignored by developers of Memcached) and preventions/mitigation of DDoS attacks through several techniques depending on the type of vulnerability being exploited by the attacker on the other hand. In this paper we have explained the Memcached operations and architecture to identify and show the possible flaws in both of them. We have also taken reference of largest DDoS attacks ever recorded in the history of computer networks and as a follow up to recent attacks on Memcached this paper presents a fresh and strong list of simple commands and configuration security steps that are capable to avoid or mitigate Memcached DDoS attacks.
{"title":"Memcached DDoS Exploits: Operations, Vulnerabilities, Preventions and Mitigations","authors":"Kulvinder Singh, Ajit Singh","doi":"10.1109/CCCS.2018.8586810","DOIUrl":"https://doi.org/10.1109/CCCS.2018.8586810","url":null,"abstract":"This paper focuses on Memcached security from DDoS attacks during all stages of attack life cycle. It identifies Memcached architecture flaws on the one hand (which are long been ignored by developers of Memcached) and preventions/mitigation of DDoS attacks through several techniques depending on the type of vulnerability being exploited by the attacker on the other hand. In this paper we have explained the Memcached operations and architecture to identify and show the possible flaws in both of them. We have also taken reference of largest DDoS attacks ever recorded in the history of computer networks and as a follow up to recent attacks on Memcached this paper presents a fresh and strong list of simple commands and configuration security steps that are capable to avoid or mitigate Memcached DDoS attacks.","PeriodicalId":6570,"journal":{"name":"2018 IEEE 3rd International Conference on Computing, Communication and Security (ICCCS)","volume":"06 1","pages":"171-179"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81899111","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 : 2018-10-01DOI: 10.1109/CCCS.2018.8586820
Lyla B. Das, J. G., J. E.P., V. K, K. Chandra, M. N. Reddy, B. Yaswant, A. Vivek
The project aims to build a multipurpose autonomous rover that could move by itself or by a remote controlled mechanism. It can be sent to hostile and hazardous places where it is unsafe for humans, like mines, radioactive prone areas, etc. thereby reducing human risk. The rover is provided with various sensors that monitors parameter like temperature and smoke. The sensors continuously monitors the environment and update the value to the cloud server, enabling the user to view the values in a website, in real time. The rover could be controlled from smartphone with the help of a Bluetooth app. In addition to this, the webpage has buttons to control the rover. Also, a camera mounted on the rover live streams the video to the webpage, assisting in controlling the movement. The rover can also be used for surveillance, with the help of camera and motion detection algorithms. There is also an automatic mode in which the rover moves on its own in a predefined path.
{"title":"Multipurpose Unmanned Rover in WiFi Wireless Sensor Network","authors":"Lyla B. Das, J. G., J. E.P., V. K, K. Chandra, M. N. Reddy, B. Yaswant, A. Vivek","doi":"10.1109/CCCS.2018.8586820","DOIUrl":"https://doi.org/10.1109/CCCS.2018.8586820","url":null,"abstract":"The project aims to build a multipurpose autonomous rover that could move by itself or by a remote controlled mechanism. It can be sent to hostile and hazardous places where it is unsafe for humans, like mines, radioactive prone areas, etc. thereby reducing human risk. The rover is provided with various sensors that monitors parameter like temperature and smoke. The sensors continuously monitors the environment and update the value to the cloud server, enabling the user to view the values in a website, in real time. The rover could be controlled from smartphone with the help of a Bluetooth app. In addition to this, the webpage has buttons to control the rover. Also, a camera mounted on the rover live streams the video to the webpage, assisting in controlling the movement. The rover can also be used for surveillance, with the help of camera and motion detection algorithms. There is also an automatic mode in which the rover moves on its own in a predefined path.","PeriodicalId":6570,"journal":{"name":"2018 IEEE 3rd International Conference on Computing, Communication and Security (ICCCS)","volume":"44 1","pages":"20-24"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80263351","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 : 2018-10-01DOI: 10.1109/CCCS.2018.8586845
B. Manandhar, B. Joshi
Vehicular traffic in Urban areas of the globe is continuously increasing and the resulting congestion has become a major concern for transportation management. The traffic signal controls are the major way to manage vehicular flow at the intersections in these urban areas. However, traditional systems fail to adjust the timing pattern based on traffic which demands for need of developing adaptive systems. The focus is this study is to develop an intelligent system that is adaptive to the traffic flow at an intersection point of the real scenarios. A hybrid system comprising of Statistical Multiplexing and Particle Swarm Optimization(PSO) has been developed to control the flow of traffic. The performance of the developed algorithm was tested with both simulated and real traffic count of some major traffic congestion intersection of Kathmandu valley. It was observed that the average waiting time of vehicles on a junction has been reduced.
{"title":"Adaptive Traffic Light Control with Statistical Multiplexing Technique and Particle Swarm Optimization in Smart Cities","authors":"B. Manandhar, B. Joshi","doi":"10.1109/CCCS.2018.8586845","DOIUrl":"https://doi.org/10.1109/CCCS.2018.8586845","url":null,"abstract":"Vehicular traffic in Urban areas of the globe is continuously increasing and the resulting congestion has become a major concern for transportation management. The traffic signal controls are the major way to manage vehicular flow at the intersections in these urban areas. However, traditional systems fail to adjust the timing pattern based on traffic which demands for need of developing adaptive systems. The focus is this study is to develop an intelligent system that is adaptive to the traffic flow at an intersection point of the real scenarios. A hybrid system comprising of Statistical Multiplexing and Particle Swarm Optimization(PSO) has been developed to control the flow of traffic. The performance of the developed algorithm was tested with both simulated and real traffic count of some major traffic congestion intersection of Kathmandu valley. It was observed that the average waiting time of vehicles on a junction has been reduced.","PeriodicalId":6570,"journal":{"name":"2018 IEEE 3rd International Conference on Computing, Communication and Security (ICCCS)","volume":"87 1","pages":"210-217"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79378288","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 : 2018-10-01DOI: 10.1109/CCCS.2018.8586817
Nishanth Augustine, S. N. George
In this paper, an image fusion technique for fusing hyper spectral and multispectral images based on sparse regularization and subspace modeling is proposed. Here, the problem of fusion is modeled as a linear inverse problem and is solved in a lower dimensional subspace. Non Linear Mixing Model (NLMM) of hyper spectral image is used for the subspace identification and it gives better results than Linear Mixing Model (LMM). A sparse regularization term is generated through adaptive dictionary learning and the fusion task is solved by using alternating optimization technique. Subspace modeling reduces computational complexity considerably. Experimental results show that this method offers significant improvement in fusion performance when compared to that of existing methods.
{"title":"Sparse Regularization based Fusion Technique for Hyperspectral and Multispectral Images using Non-linear Mixing Model","authors":"Nishanth Augustine, S. N. George","doi":"10.1109/CCCS.2018.8586817","DOIUrl":"https://doi.org/10.1109/CCCS.2018.8586817","url":null,"abstract":"In this paper, an image fusion technique for fusing hyper spectral and multispectral images based on sparse regularization and subspace modeling is proposed. Here, the problem of fusion is modeled as a linear inverse problem and is solved in a lower dimensional subspace. Non Linear Mixing Model (NLMM) of hyper spectral image is used for the subspace identification and it gives better results than Linear Mixing Model (LMM). A sparse regularization term is generated through adaptive dictionary learning and the fusion task is solved by using alternating optimization technique. Subspace modeling reduces computational complexity considerably. Experimental results show that this method offers significant improvement in fusion performance when compared to that of existing methods.","PeriodicalId":6570,"journal":{"name":"2018 IEEE 3rd International Conference on Computing, Communication and Security (ICCCS)","volume":"64 1","pages":"56-63"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86664240","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：