Yu-Kai Chiu, S. Ruan, Chung-An Shen, Chun-Chi Hung
Packet classification has been recognized as one of the most significant functions in contemporary network infrastructures. Furthermore, a number of modern applications such as IoTs contain very strict constraints on the latency of network transmissions. This paper presents the design and implementation of a novel packet classification based on FPGA architecture. The proposed design contains a Latency Compression Scheme (LCS) to achieve the low-latency packet processing. Furthermore, this structure supports 12-tuple fields for the modern Internet traffics. The experimental results show that the proposed packet classification scheme reduces the delay of packet processing by 2.18× compared to the state-of-the-art works.
{"title":"The Design and Implementation of a Latency-Aware Packet Classification for OpenFlow Protocol based on FPGA","authors":"Yu-Kai Chiu, S. Ruan, Chung-An Shen, Chun-Chi Hung","doi":"10.1145/3301326.3301368","DOIUrl":"https://doi.org/10.1145/3301326.3301368","url":null,"abstract":"Packet classification has been recognized as one of the most significant functions in contemporary network infrastructures. Furthermore, a number of modern applications such as IoTs contain very strict constraints on the latency of network transmissions. This paper presents the design and implementation of a novel packet classification based on FPGA architecture. The proposed design contains a Latency Compression Scheme (LCS) to achieve the low-latency packet processing. Furthermore, this structure supports 12-tuple fields for the modern Internet traffics. The experimental results show that the proposed packet classification scheme reduces the delay of packet processing by 2.18× compared to the state-of-the-art works.","PeriodicalId":294040,"journal":{"name":"Proceedings of the 2018 VII International Conference on Network, Communication and Computing","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116954903","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}
With the continuous development of computer technology, traditional large-scale business systems are increasingly unable to meet the needs. Business systems based on workflow, small and light, and scalable are gradually becoming the mainstream. This paper takes the solution to the dilemma faced by the printing and publishing industry as the starting point, based on the workflow technology, and utilizes the unique organizational structure and data management technology advantages of workflow technology. The application of streaming technology in the traditional printing and publishing industry has been analyzed and researched, according to the requirements analysis, model abstraction, business process design, and authority configuration steps. The modeling methods and business process design schemes of workflow technology applied in the printing and publishing industry have been proposed. The key technologies required for system implementation are analyzed. The paper also provides ideas and methods in order to solve the current problems in the printing and publishing industry: the data is numerous, the management efficiency is low and other issues.
{"title":"Application Research of Workflow Technology in Printing and Publishing Industry","authors":"Shaopeng Wang, Shulin Yang, H. Cai","doi":"10.1145/3301326.3301345","DOIUrl":"https://doi.org/10.1145/3301326.3301345","url":null,"abstract":"With the continuous development of computer technology, traditional large-scale business systems are increasingly unable to meet the needs. Business systems based on workflow, small and light, and scalable are gradually becoming the mainstream. This paper takes the solution to the dilemma faced by the printing and publishing industry as the starting point, based on the workflow technology, and utilizes the unique organizational structure and data management technology advantages of workflow technology. The application of streaming technology in the traditional printing and publishing industry has been analyzed and researched, according to the requirements analysis, model abstraction, business process design, and authority configuration steps. The modeling methods and business process design schemes of workflow technology applied in the printing and publishing industry have been proposed. The key technologies required for system implementation are analyzed. The paper also provides ideas and methods in order to solve the current problems in the printing and publishing industry: the data is numerous, the management efficiency is low and other issues.","PeriodicalId":294040,"journal":{"name":"Proceedings of the 2018 VII International Conference on Network, Communication and Computing","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114848112","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}
In the past few decades, biometrics have developed rapidly, and such achievements are inseparable from the support of a variety of single-mode and multi-modal biometric databases. The use of a biometric database makes it possible to compare the performance consistency of different recognition technologies. The collection of these databases is a time-consuming and resource-intensive task for researchers, especially for multimodal databases involving multiple biological characteristics. This paper reviews some single-mode and multi-mode biometric databases which are widely used in the world at present.
{"title":"Biometric Recognition Databases: A Survey","authors":"Xinman Zhang, Weiyong Gong, Xuebin Xu, Yuchen Zhang","doi":"10.1145/3301326.3301384","DOIUrl":"https://doi.org/10.1145/3301326.3301384","url":null,"abstract":"In the past few decades, biometrics have developed rapidly, and such achievements are inseparable from the support of a variety of single-mode and multi-modal biometric databases. The use of a biometric database makes it possible to compare the performance consistency of different recognition technologies. The collection of these databases is a time-consuming and resource-intensive task for researchers, especially for multimodal databases involving multiple biological characteristics. This paper reviews some single-mode and multi-mode biometric databases which are widely used in the world at present.","PeriodicalId":294040,"journal":{"name":"Proceedings of the 2018 VII International Conference on Network, Communication and Computing","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133961137","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}
In recently, semantic image is an active problem in the digital image processing field. A large number of new techniques and systems have researcher involved and attempted to improve the problems. The most of techniques is done by keyword searching model. Therefore, we propose a new approach to classify the relationships between object and action. The approach is composed of three main phases: (1) data preprocessing, (2) relationship between contents, and (3) measurement and evaluation. We train and test our model on a largescale image dataset of actions. The major information contents use the relationships between object and action. The results indicated that the proposed method offers significant performance improvements in semantic classification with a maximum success rate of 80.9%.
{"title":"Spatial Semantic Images with Relationship Contents by Using Convolutional Neural Network and Support Vector Machine","authors":"N. Chinpanthana, Tejtasin Phiasai","doi":"10.1145/3301326.3301350","DOIUrl":"https://doi.org/10.1145/3301326.3301350","url":null,"abstract":"In recently, semantic image is an active problem in the digital image processing field. A large number of new techniques and systems have researcher involved and attempted to improve the problems. The most of techniques is done by keyword searching model. Therefore, we propose a new approach to classify the relationships between object and action. The approach is composed of three main phases: (1) data preprocessing, (2) relationship between contents, and (3) measurement and evaluation. We train and test our model on a largescale image dataset of actions. The major information contents use the relationships between object and action. The results indicated that the proposed method offers significant performance improvements in semantic classification with a maximum success rate of 80.9%.","PeriodicalId":294040,"journal":{"name":"Proceedings of the 2018 VII International Conference on Network, Communication and Computing","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131763989","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}
Byung-Hoon Lee, Tea-Yeong Hah, W. Jeong, Kyung-Seok Kim
Recently, recognition systems of finger vein have been used for personal identification. Finger vein is more promising than the existing biometric system in terms of security and convenience. However, accuracy may be reduced depending on the performance of the machine or the environment surrounding it. We propose an algorithm to improve recognition systems of finger vein. Extracted the finger vein apply the modified median filter and image expansion. The simulations used data from MMCBNU_6000 of Chungbuk National University and the performance were analyzed using the FAR, FRR, and EER.
{"title":"Enhanced Approach for Finger-Vein Extraction","authors":"Byung-Hoon Lee, Tea-Yeong Hah, W. Jeong, Kyung-Seok Kim","doi":"10.1145/3301326.3301353","DOIUrl":"https://doi.org/10.1145/3301326.3301353","url":null,"abstract":"Recently, recognition systems of finger vein have been used for personal identification. Finger vein is more promising than the existing biometric system in terms of security and convenience. However, accuracy may be reduced depending on the performance of the machine or the environment surrounding it. We propose an algorithm to improve recognition systems of finger vein. Extracted the finger vein apply the modified median filter and image expansion. The simulations used data from MMCBNU_6000 of Chungbuk National University and the performance were analyzed using the FAR, FRR, and EER.","PeriodicalId":294040,"journal":{"name":"Proceedings of the 2018 VII International Conference on Network, Communication and Computing","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132732438","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}
Since the multispectral palmprint has more spatial and frequency characteristics than the natural light condition, we can extract more feature information and obtain higher recognition accuracy. In recent years, many scholars have committed themselves to multispectral palmprint recognition studying. In this paper, a novel robust p-norm regularization model is proposed to implement the multispectral palmprint recognition. Then, a proximal iterative reweighted algorithm is employed to solve this model. Finally, we utilize the weighted fusion strategy to calculate the representation residual and carry out the recognition task efficiently. Extensive experiments on PolyU multispectral palmprint database illustrate that the proposed algorithm can achieve outstanding recognition accuracy and outperform some conventional representation methods.
{"title":"A Novel Robust Multispectral Palmprint Recognition Algorithm Based on P-Norm Regularization","authors":"Xinman Zhang, Dongxu Cheng, Xuebin Xu","doi":"10.1145/3301326.3301383","DOIUrl":"https://doi.org/10.1145/3301326.3301383","url":null,"abstract":"Since the multispectral palmprint has more spatial and frequency characteristics than the natural light condition, we can extract more feature information and obtain higher recognition accuracy. In recent years, many scholars have committed themselves to multispectral palmprint recognition studying. In this paper, a novel robust p-norm regularization model is proposed to implement the multispectral palmprint recognition. Then, a proximal iterative reweighted algorithm is employed to solve this model. Finally, we utilize the weighted fusion strategy to calculate the representation residual and carry out the recognition task efficiently. Extensive experiments on PolyU multispectral palmprint database illustrate that the proposed algorithm can achieve outstanding recognition accuracy and outperform some conventional representation methods.","PeriodicalId":294040,"journal":{"name":"Proceedings of the 2018 VII International Conference on Network, Communication and Computing","volume":"153 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115670992","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}
Since the era of data explosion, data mining in transactional databases has become more and more important. There are many data mining techniques like association rule mining, the most important and well-researched one. Furthermore, closed frequent itemset mining is one of the fundamental but time-consuming steps in association rule mining. Most of the algorithms used in literature find closed frequent itemsets on search space items having at least a minsup and are not reused for mining next time. To deal with this problem, NOV-CFI algorithms are proposed as a new approach in order to quickly detect closed frequent itemsets from transactional databases using an array of co-occurrences and occurrences of kernel item in at least one transaction. Advantages of NOV-CFI algorithms are reuse and easily expanded in distributed systems. Finally, experimental results show that the proposed algorithms are better than other existing algorithms on both real and synthetic datasets.
{"title":"NOV-CFI: A Novel Algorithm for Closed Frequent Itemsets Mining in Transactional Databases","authors":"H. Phan","doi":"10.1145/3301326.3301363","DOIUrl":"https://doi.org/10.1145/3301326.3301363","url":null,"abstract":"Since the era of data explosion, data mining in transactional databases has become more and more important. There are many data mining techniques like association rule mining, the most important and well-researched one. Furthermore, closed frequent itemset mining is one of the fundamental but time-consuming steps in association rule mining. Most of the algorithms used in literature find closed frequent itemsets on search space items having at least a minsup and are not reused for mining next time. To deal with this problem, NOV-CFI algorithms are proposed as a new approach in order to quickly detect closed frequent itemsets from transactional databases using an array of co-occurrences and occurrences of kernel item in at least one transaction. Advantages of NOV-CFI algorithms are reuse and easily expanded in distributed systems. Finally, experimental results show that the proposed algorithms are better than other existing algorithms on both real and synthetic datasets.","PeriodicalId":294040,"journal":{"name":"Proceedings of the 2018 VII International Conference on Network, Communication and Computing","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115777243","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}
Shortest Path Problem is one of the problems addressed in graph theory. One of the examples is the Travelling Sales Person which finds the shortest path from source to destination. Because it is a NP-complete problem, it uses brute force in finding the optimal solution. However, the solution was prone to stagnation since optimal solution is easy to reach its limits when applied to real-world scenarios. A solution was derived through the enhancement of the ant algorithm which is the inverse ant algorithm where an alternate route is provided in case a limit is reached. However, the selection process of path of the inverse ant algorithm increases time complexity. Path selection process is addressed through the enhancement of ant algorithm using the path elimination rule. This process of enhancing is applied to the inverse ant algorithm to enhance its performance.
{"title":"Enhancing Inverse Ant Algorithm using Path Elimination Rules","authors":"Jaymer M. Jayoma, B. Gerardo, Ruji P. Medina","doi":"10.1145/3301326.3303713","DOIUrl":"https://doi.org/10.1145/3301326.3303713","url":null,"abstract":"Shortest Path Problem is one of the problems addressed in graph theory. One of the examples is the Travelling Sales Person which finds the shortest path from source to destination. Because it is a NP-complete problem, it uses brute force in finding the optimal solution. However, the solution was prone to stagnation since optimal solution is easy to reach its limits when applied to real-world scenarios. A solution was derived through the enhancement of the ant algorithm which is the inverse ant algorithm where an alternate route is provided in case a limit is reached. However, the selection process of path of the inverse ant algorithm increases time complexity. Path selection process is addressed through the enhancement of ant algorithm using the path elimination rule. This process of enhancing is applied to the inverse ant algorithm to enhance its performance.","PeriodicalId":294040,"journal":{"name":"Proceedings of the 2018 VII International Conference on Network, Communication and Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124388092","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 development of automated video surveillance has grown dramatically due to the increased concern with public safety and security. An automated surveillance with reliable human activity analysis is essential. In this paper, a localized spatio-temporal representation, alongside Motion History Image (MHI), Motion Energy Image (MEI) and Binarized Statistical Image Features (BSIF), is proposed for human action recognition. In this work, the information of timestamp and ratio of colors are extracted from the silhouette of MHI template. This information is then utilized to derive a temporal representation for encoding movement dynamics. This temporal representation preserves transient information of actions. Subsequently, local descriptors are computed from MHI and MEI temporal templates via BSIF. The computed localized temporal representation is classified by using a linear SVM. The proposed system offers promising performance in human action recognition with about 90% accuracy.
{"title":"Localized Temporal Representation in Human Action Recognition","authors":"Pang Ying Han, K. Yee, S. Ooi","doi":"10.1145/3301326.3301338","DOIUrl":"https://doi.org/10.1145/3301326.3301338","url":null,"abstract":"The development of automated video surveillance has grown dramatically due to the increased concern with public safety and security. An automated surveillance with reliable human activity analysis is essential. In this paper, a localized spatio-temporal representation, alongside Motion History Image (MHI), Motion Energy Image (MEI) and Binarized Statistical Image Features (BSIF), is proposed for human action recognition. In this work, the information of timestamp and ratio of colors are extracted from the silhouette of MHI template. This information is then utilized to derive a temporal representation for encoding movement dynamics. This temporal representation preserves transient information of actions. Subsequently, local descriptors are computed from MHI and MEI temporal templates via BSIF. The computed localized temporal representation is classified by using a linear SVM. The proposed system offers promising performance in human action recognition with about 90% accuracy.","PeriodicalId":294040,"journal":{"name":"Proceedings of the 2018 VII International Conference on Network, Communication and Computing","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127076988","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}
Xiaoliang Tang, Xuan Tang, Wanli Wang, Li Fang, Xian Wei
Most multi-view subspace clustering algorithms construct the affinity matrix with shallow features extracted from each view separately. The integration of multi-view features are left for extended spectral clustering algorithm. The lack of deep feature extraction and interaction across different views prevents the effective exploration of information complementary for multi-view datasets. To address this problem, this paper proposes a novel deep multi-view sparse subspace clustering (DMVSSC) model which consists of convolutional auto-encoders (CAEs) and CCA-based self-expressive module. The proposed model can not only extract deep features of each view data with few parameters but also integrate multi-view features based on CCA. Furthermore, a two-stage joint optimization strategy is proposed for tuning the whole model. Experiments on four benchmark data sets show that our proposed model significantly outperforms the state-of-the-art multi-view subspace clustering algorithms.
{"title":"Deep Multi-view Sparse Subspace Clustering","authors":"Xiaoliang Tang, Xuan Tang, Wanli Wang, Li Fang, Xian Wei","doi":"10.1145/3301326.3301391","DOIUrl":"https://doi.org/10.1145/3301326.3301391","url":null,"abstract":"Most multi-view subspace clustering algorithms construct the affinity matrix with shallow features extracted from each view separately. The integration of multi-view features are left for extended spectral clustering algorithm. The lack of deep feature extraction and interaction across different views prevents the effective exploration of information complementary for multi-view datasets. To address this problem, this paper proposes a novel deep multi-view sparse subspace clustering (DMVSSC) model which consists of convolutional auto-encoders (CAEs) and CCA-based self-expressive module. The proposed model can not only extract deep features of each view data with few parameters but also integrate multi-view features based on CCA. Furthermore, a two-stage joint optimization strategy is proposed for tuning the whole model. Experiments on four benchmark data sets show that our proposed model significantly outperforms the state-of-the-art multi-view subspace clustering algorithms.","PeriodicalId":294040,"journal":{"name":"Proceedings of the 2018 VII International Conference on Network, Communication and Computing","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130008269","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：