Book recommender systems play an important role in book search engines, digital library or book shopping sites. In the field of recommender systems, processing data, selecting suitable data features, and classification methods are always challenging to decide the performance of a recommender system. This paper presents some solutions of data process, feature and classifier selection in order to build an efficient book recommender system. The Book-Crossing dataset, which has been studied in many book recommender systems, is taken into account as a case study. The attributes of books are analyzed and processed to increase the classification accuracy. Some well-known classification algorithms, such as, Naïve Bayes, decision tree, etc., are utilized to predict user interests in books and evaluated in several experiments. It has been found that Naïve Bayes is the best selection for book recommendation with acceptable run-time and accuracy.
{"title":"Model-Based Book Recommender Systems using Naïve Bayes enhanced with Optimal Feature Selection","authors":"Thi Thanh Sang Nguyen","doi":"10.1145/3316615.3316727","DOIUrl":"https://doi.org/10.1145/3316615.3316727","url":null,"abstract":"Book recommender systems play an important role in book search engines, digital library or book shopping sites. In the field of recommender systems, processing data, selecting suitable data features, and classification methods are always challenging to decide the performance of a recommender system. This paper presents some solutions of data process, feature and classifier selection in order to build an efficient book recommender system. The Book-Crossing dataset, which has been studied in many book recommender systems, is taken into account as a case study. The attributes of books are analyzed and processed to increase the classification accuracy. Some well-known classification algorithms, such as, Naïve Bayes, decision tree, etc., are utilized to predict user interests in books and evaluated in several experiments. It has been found that Naïve Bayes is the best selection for book recommendation with acceptable run-time and accuracy.","PeriodicalId":268392,"journal":{"name":"Proceedings of the 2019 8th International Conference on Software and Computer Applications","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126767268","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}
Aiming at the problem of rich websites in campus without targeted recommendation, which makes it difficult for users to find the information resources of high interest and high quality, this paper proposes an implicit feedback recommendation algorithm in campus network based on user's changing interest and user influence. Based on the traditional collaborative filtering algorithm, introduces time function that adapting to user's changing interest and user's influence factors. The score matrix based on time weight is integrated with the influence matrix to solve the problem that user similarity calculation is too single, and improves the accuracy and explanatory of the recommendation results. Experimental results show that the algorithm can effectively reduce the sparsity and cold start problem of the dataset, and has better recommendation quality than traditional collaborative filtering algorithm.
{"title":"Implicit Recommendation with Interest Change and User Influence","authors":"Qiaoqiao Tan, Fang’ai Liu, Shuning Xing","doi":"10.1145/3316615.3316680","DOIUrl":"https://doi.org/10.1145/3316615.3316680","url":null,"abstract":"Aiming at the problem of rich websites in campus without targeted recommendation, which makes it difficult for users to find the information resources of high interest and high quality, this paper proposes an implicit feedback recommendation algorithm in campus network based on user's changing interest and user influence. Based on the traditional collaborative filtering algorithm, introduces time function that adapting to user's changing interest and user's influence factors. The score matrix based on time weight is integrated with the influence matrix to solve the problem that user similarity calculation is too single, and improves the accuracy and explanatory of the recommendation results. Experimental results show that the algorithm can effectively reduce the sparsity and cold start problem of the dataset, and has better recommendation quality than traditional collaborative filtering algorithm.","PeriodicalId":268392,"journal":{"name":"Proceedings of the 2019 8th International Conference on Software and Computer Applications","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126144195","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 widespread adoption of electronic voting, various voting protocols have been proposed. Voting protocols need to satisfy security requirements, including privacy protection and the prevention of illegal voting (e.g., double voting). Our research focuses on the most important property of voting protocols, namely whether all votes are reflected in the voting results accurately. We formalized and verified this for one voting protocol using strand space analysis. We can also consider multiple security requirements depending on the extent to which the voting result is reflected accurately. These properties are discussed.
{"title":"Verification of Verifiability of Voting Protocols by Strand Space Analysis","authors":"Shigeki Hagihara, Masaya Shimakawa, N. Yonezaki","doi":"10.1145/3316615.3316629","DOIUrl":"https://doi.org/10.1145/3316615.3316629","url":null,"abstract":"With the widespread adoption of electronic voting, various voting protocols have been proposed. Voting protocols need to satisfy security requirements, including privacy protection and the prevention of illegal voting (e.g., double voting). Our research focuses on the most important property of voting protocols, namely whether all votes are reflected in the voting results accurately. We formalized and verified this for one voting protocol using strand space analysis. We can also consider multiple security requirements depending on the extent to which the voting result is reflected accurately. These properties are discussed.","PeriodicalId":268392,"journal":{"name":"Proceedings of the 2019 8th International Conference on Software and Computer Applications","volume":"65-66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123129932","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}
Reusing software components from third-party vendors is one of the key technologies to gain shorter time-to-market and better quality of the software system. These components, also known as OTS (Off-the-Shelf) components, come in two types: COTS (Commercial Off-The-Shelf) and OSS (Open-Source Software). To utilize OSS components effectively, it is necessary to figure out how the development processes and methods to be adapted. Most current studies are either theoretical proposals without empirical assessment or case studies in similar project contexts. It is therefore necessary to conduct more empirical studies on how process improvement and risk management can be performed and what are the results in various project contexts.
{"title":"Risk Management in Projects Based on Open-Source Software","authors":"Nguyen Duc Linh, P. D. Hung, V. Diep, Ta Duc Tung","doi":"10.1145/3316615.3316648","DOIUrl":"https://doi.org/10.1145/3316615.3316648","url":null,"abstract":"Reusing software components from third-party vendors is one of the key technologies to gain shorter time-to-market and better quality of the software system. These components, also known as OTS (Off-the-Shelf) components, come in two types: COTS (Commercial Off-The-Shelf) and OSS (Open-Source Software). To utilize OSS components effectively, it is necessary to figure out how the development processes and methods to be adapted. Most current studies are either theoretical proposals without empirical assessment or case studies in similar project contexts. It is therefore necessary to conduct more empirical studies on how process improvement and risk management can be performed and what are the results in various project contexts.","PeriodicalId":268392,"journal":{"name":"Proceedings of the 2019 8th International Conference on Software and Computer Applications","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124142473","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}
People of the modern times are becoming more prone to have spinal curvature disorder due to the improper habits especially those that stays at desk more often. To diagnose this disorder, method such as radiography and other conventional method are used. Conventional method such as goniometry require human skills can be time consuming which eventually lead to exhaustion of logistic. These problems can be solved by using 3D photogrammetry method. This research uses Kinect obtain the 3D human body model and find the optimum parameters to capture the 3D model for body posture screening. The most optimum parameters that set to capture the 3D model of the subject is at 1.3 m distance between subject and camera, 80 lux and at chest level. The 3D model reconstructed from these parameters shows 100% accuracy of the point needed to be assessed. This papers highlight the validation of optimum parameters that will affect the performance of capturing 3D human reconstructed model for measuring the spinal curvature.
{"title":"Development of Assessment System for Spine Curvature Angle Measurement","authors":"Chua Shanyu, L. C. Chin, S. Basah, A. F. Azizan","doi":"10.1145/3316615.3316647","DOIUrl":"https://doi.org/10.1145/3316615.3316647","url":null,"abstract":"People of the modern times are becoming more prone to have spinal curvature disorder due to the improper habits especially those that stays at desk more often. To diagnose this disorder, method such as radiography and other conventional method are used. Conventional method such as goniometry require human skills can be time consuming which eventually lead to exhaustion of logistic. These problems can be solved by using 3D photogrammetry method. This research uses Kinect obtain the 3D human body model and find the optimum parameters to capture the 3D model for body posture screening. The most optimum parameters that set to capture the 3D model of the subject is at 1.3 m distance between subject and camera, 80 lux and at chest level. The 3D model reconstructed from these parameters shows 100% accuracy of the point needed to be assessed. This papers highlight the validation of optimum parameters that will affect the performance of capturing 3D human reconstructed model for measuring the spinal curvature.","PeriodicalId":268392,"journal":{"name":"Proceedings of the 2019 8th International Conference on Software and Computer Applications","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126453593","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}
Saurabh Shukla, M. Hassan, L. T. Jung, A. Awang, Muhammad Khalid Khan
Healthcare Internet-of-things comprises a huge number of wearable sensors and interconnected computers. The high volume of IoT data is transacted over servers leading to servers overloading with high traffic causing network congestion. These cloud servers are typically for analyzing, retrieving and storing the large data generated from IoT devices. There exist challenges regarding sending real-time healthcare data from cloud servers to end-users. These challenges include the high computational latency, high communication latency, and high network latency. Due to these challenges, IoTs may not be able to send data in real-time to end-users. Fog nodes can be used to play a major role in reducing the high delay and high traffic. It can be a solution to increase system performance. In this paper, we proposed a 3-tier architecture, an analytical model for healthcare IoT using a hybrid approach consisting of fuzzy logic and reinforcement learning in a fog computing environment. The aim is to minimize network latency. The proposed model and 3-tier architecture are simulated using iFogSim simulator.
{"title":"A 3-Tier Architecture for Network Latency Reduction in Healthcare Internet-of-Things Using Fog Computing and Machine Learning","authors":"Saurabh Shukla, M. Hassan, L. T. Jung, A. Awang, Muhammad Khalid Khan","doi":"10.1145/3316615.3318222","DOIUrl":"https://doi.org/10.1145/3316615.3318222","url":null,"abstract":"Healthcare Internet-of-things comprises a huge number of wearable sensors and interconnected computers. The high volume of IoT data is transacted over servers leading to servers overloading with high traffic causing network congestion. These cloud servers are typically for analyzing, retrieving and storing the large data generated from IoT devices. There exist challenges regarding sending real-time healthcare data from cloud servers to end-users. These challenges include the high computational latency, high communication latency, and high network latency. Due to these challenges, IoTs may not be able to send data in real-time to end-users. Fog nodes can be used to play a major role in reducing the high delay and high traffic. It can be a solution to increase system performance. In this paper, we proposed a 3-tier architecture, an analytical model for healthcare IoT using a hybrid approach consisting of fuzzy logic and reinforcement learning in a fog computing environment. The aim is to minimize network latency. The proposed model and 3-tier architecture are simulated using iFogSim simulator.","PeriodicalId":268392,"journal":{"name":"Proceedings of the 2019 8th International Conference on Software and Computer Applications","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133192908","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}
It is of significance to identify the source of malicious information in social networks, since this information diffusion is already a problem, which can seriously affect social stability. In this paper, we develop a propagation path based approach where the estimator of information source is chosen to be the root node associated with the propagation path that most likely leads to the monitored state of network. When the information diffusion process follows the Susceptible-Infected (SI) model and satisfying the instant forwarding hypothesis, we proved that the source estimator we proposed is the root node of the network shortest arborescence. Finally, multiple simulations on networks with different structure show that our method outperforms existing algorithms.
{"title":"An Information Source Identification Algorithm Based on Shortest Arborescence of Network","authors":"Zhong Li, Chunhe Xia, Tianbo Wang, Xiaochen Liu","doi":"10.1145/3316615.3316686","DOIUrl":"https://doi.org/10.1145/3316615.3316686","url":null,"abstract":"It is of significance to identify the source of malicious information in social networks, since this information diffusion is already a problem, which can seriously affect social stability. In this paper, we develop a propagation path based approach where the estimator of information source is chosen to be the root node associated with the propagation path that most likely leads to the monitored state of network. When the information diffusion process follows the Susceptible-Infected (SI) model and satisfying the instant forwarding hypothesis, we proved that the source estimator we proposed is the root node of the network shortest arborescence. Finally, multiple simulations on networks with different structure show that our method outperforms existing algorithms.","PeriodicalId":268392,"journal":{"name":"Proceedings of the 2019 8th International Conference on Software and Computer Applications","volume":"169 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132413806","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}
Mohammed Al-habib, Dong-jun Huang, Majjed Al-Qatf, Kamal Al-Sabahi
Deep neural network algorithms have shown promising performance for many tasks in computer vision field. Several neural network-based methods have been proposed to recognize group activities from video sequences. However, there are still several challenges that are related to multiple groups with different activities within a scene. The strong correlation that exists among individual motion, groups and activities can be utilized to detect groups and recognize their concurrent activities. Motivated by these observations, we propose a unified deep learning framework for detecting multiple groups and recognizing their corresponding collective activity based on Long Short-Term Memory (LSTM) network. In this framework, we use a pre-trained convolutional neural network (CNN) to extract features from the frames and appearances of persons. An objective function has been proposed to learn the amount of pairwise interaction between persons. The obtained individual features are passed to a clustering algorithm to detect groups in the scene. Then, an LSTM based model is used to recognize group activities. Together with this, a scene level CNN followed by LSTM is used to extract and learn scene level feature. Finally, the activities from the group level and the scene context level are integrated to infer the collective activity. The proposed method is evaluated on the benchmark collective activity dataset and compared with several baselines. The experimental results show its competitive performance for the collective activity recognition task.
{"title":"Cooperative Hierarchical Framework for Group Activity Recognition: From Group Detection to Multi-activity Recognition","authors":"Mohammed Al-habib, Dong-jun Huang, Majjed Al-Qatf, Kamal Al-Sabahi","doi":"10.1145/3316615.3316722","DOIUrl":"https://doi.org/10.1145/3316615.3316722","url":null,"abstract":"Deep neural network algorithms have shown promising performance for many tasks in computer vision field. Several neural network-based methods have been proposed to recognize group activities from video sequences. However, there are still several challenges that are related to multiple groups with different activities within a scene. The strong correlation that exists among individual motion, groups and activities can be utilized to detect groups and recognize their concurrent activities. Motivated by these observations, we propose a unified deep learning framework for detecting multiple groups and recognizing their corresponding collective activity based on Long Short-Term Memory (LSTM) network. In this framework, we use a pre-trained convolutional neural network (CNN) to extract features from the frames and appearances of persons. An objective function has been proposed to learn the amount of pairwise interaction between persons. The obtained individual features are passed to a clustering algorithm to detect groups in the scene. Then, an LSTM based model is used to recognize group activities. Together with this, a scene level CNN followed by LSTM is used to extract and learn scene level feature. Finally, the activities from the group level and the scene context level are integrated to infer the collective activity. The proposed method is evaluated on the benchmark collective activity dataset and compared with several baselines. The experimental results show its competitive performance for the collective activity recognition task.","PeriodicalId":268392,"journal":{"name":"Proceedings of the 2019 8th International Conference on Software and Computer Applications","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133905923","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}
Nowadays, with the improvement of social network check-in and positioning technology, the positioning information is more accurate, and a large amount of network check-in data is generated. The recommendation research of interest points based on social networks is also increasing. Most of the points of interest refer to rely on geography, time, space, and textual information. In spatial-temporal, most studies consider the check-in rules from the geographical distance and time series. This paper introduces a geographic spatial-temporal distance measurement model to map temporal space information into a three-dimensional elliptical spherical coordinate system. The spatial-temporal distance is measured under the same reference standard. Helps alleviate the problems caused by cold start and data sparseness for location recommendation accuracy. Based on the Bayesian personalized ranking, this paper measures the temporal and spatial distance by using a Gaussian kernel function to weight the spatial-temporal distance, and proposes a personalized ranking recommendation algorithm based on the spatial-temporal distance metric. And it performs well on both datasets and is superior to the benchmark method.
{"title":"Personalized Ranking Point of Interest Recommendation Based on Spatial-Temporal Distance Metric in LBSNs","authors":"Chang Su, Hao Li, Xianzhong Xie","doi":"10.1145/3316615.3316715","DOIUrl":"https://doi.org/10.1145/3316615.3316715","url":null,"abstract":"Nowadays, with the improvement of social network check-in and positioning technology, the positioning information is more accurate, and a large amount of network check-in data is generated. The recommendation research of interest points based on social networks is also increasing. Most of the points of interest refer to rely on geography, time, space, and textual information. In spatial-temporal, most studies consider the check-in rules from the geographical distance and time series. This paper introduces a geographic spatial-temporal distance measurement model to map temporal space information into a three-dimensional elliptical spherical coordinate system. The spatial-temporal distance is measured under the same reference standard. Helps alleviate the problems caused by cold start and data sparseness for location recommendation accuracy. Based on the Bayesian personalized ranking, this paper measures the temporal and spatial distance by using a Gaussian kernel function to weight the spatial-temporal distance, and proposes a personalized ranking recommendation algorithm based on the spatial-temporal distance metric. And it performs well on both datasets and is superior to the benchmark method.","PeriodicalId":268392,"journal":{"name":"Proceedings of the 2019 8th International Conference on Software and Computer Applications","volume":"933 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133418435","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 recent development of 3D sensing technology enables a number of consumer facing 3D cameras, such as Kinect, TrueDepth camera on IPhoneX etc., emerge. These cameras are much cheaper than conventional and professional 3D scanning devices, and thus they can be acquired by consumers easily. However, consumer 3D scanning applications bring a new set of challenges. One of the challenges is that it is difficult for consumers to obtain the full head model by self-scanning. The proposed algorithm in this paper aims at reconstructing 3D human back head model based on gradient filling method. Due to the lack of related researches, to be more specific, repairing large holes without extra information in the 3D scale, the problem is migrated to 2D scale by projecting 3D model to a spherical space. Then the depth value at each position in back head is calculated via gradient interpolation. The algorithm is simple and effective and it can reconstruct a model within seconds.
{"title":"Reconstruct the Back of 3D Face Model Using 2D Gradient Based Interpolation","authors":"W. Luo","doi":"10.1145/3316615.3316660","DOIUrl":"https://doi.org/10.1145/3316615.3316660","url":null,"abstract":"The recent development of 3D sensing technology enables a number of consumer facing 3D cameras, such as Kinect, TrueDepth camera on IPhoneX etc., emerge. These cameras are much cheaper than conventional and professional 3D scanning devices, and thus they can be acquired by consumers easily. However, consumer 3D scanning applications bring a new set of challenges. One of the challenges is that it is difficult for consumers to obtain the full head model by self-scanning. The proposed algorithm in this paper aims at reconstructing 3D human back head model based on gradient filling method. Due to the lack of related researches, to be more specific, repairing large holes without extra information in the 3D scale, the problem is migrated to 2D scale by projecting 3D model to a spherical space. Then the depth value at each position in back head is calculated via gradient interpolation. The algorithm is simple and effective and it can reconstruct a model within seconds.","PeriodicalId":268392,"journal":{"name":"Proceedings of the 2019 8th International Conference on Software and Computer Applications","volume":"190 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134515223","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：