The Journal of Information Processing Systems (JIPS) publishes a wide range of topics related to a wide variety of advanced information and communication technologies, including systems, networks, architectures, algorithms, applications, and security. As the official international journal published by the Korea Information Processing Society, JIPS is the world's leading academic journal indexed by ESCI, SCOPUS, EI COMPENDEX, DOI, DBLP, EBSCO, Google Scholar, and CrossRef. The purpose of JIPS is to provide an outstanding, influential forum where researchers and experts gather to promote, share, and discuss crucial research issues and developments. The published theoretical and practical articles contribute to the relevant research area by presenting cutting-edge techniques related to information processing including new theories, approaches, concepts, analysis, functional experience reports, implementations, and applications. Topics covered in this journal include, but are not limited to, computer systems and theory, multimedia systems and graphics, communication systems and security, software systems, and applications.
With the rapid development of the science and technology, it has been becoming more and more convenient to obtain abundant information via the diverse multimedia medium. However, the contents of the multimedia are easily altered with different editing software, and the authenticity and the integrity of multimedia content are under threat. Forensics technology is developed to solve this problem. We focus on reviewing the blind image forensics technologies for copy-move forgery in this survey. Copy-move forgery is one of the most common manners to manipulate images that usually obscure the objects by flat regions or append the objects within the same image. In this paper, two classical models of copy-move forgery are reviewed, and two frameworks of copy-move forgery detection (CMFD) methods are summarized. Then, massive CMFD methods are mainly divided into two types to retrospect the development process of CMFD technologies, including block-based and keypoint-based. Besides, the performance evaluation criterions and the datasets created for evaluating the performance of CMFD methods are also collected in this review. At last, future research directions and conclusions are given to provide beneficial advice for researchers in this field.
The digitization of music has seen a considerable increase in audience size from a few localized listeners to a wider range of global listeners. At the same time, the digitization brings the challenge of smoothly retrieving music from large databases. To deal with this challenge, many systems which support the smooth retrieval of musical data have been developed. At the computational level, a query music piece is compared with the rest of the music pieces in the database. These systems, music information retrieval (MIR systems), work for various applications such as general music retrieval, plagiarism detection, music recommendation, and musicology. This paper mainly addresses two parts of the MIR research area. First, it presents a general overview of MIR, which will examine the history of MIR, the functionality of MIR, application areas of MIR, and the components of MIR. Second, we will investigate music similarity measurement methods, where we provide a comparative analysis of state of the art methods. The scope of this paper focuses on comparative analysis of the accuracy and efficiency of a few key MIR systems. These analyses help in understanding the current and future challenges associated with the field of MIR systems and music similarity measures
Security issue in mobile ad hoc network (MANET) is a promising research. In 2011, we had accomplished a survey of black hole attacks in MANETs. However network technology is changing with each passing day, a vast number of novel schemes and papers have been proposed and published in recent years. In this paper, we survey the literature on malicious attacks in MANETs published during past 5 years, especially the black hole attack. Black hole attacks are classified into non-cooperative and collaborative black hole attacks. Except black hole attacks, other attacks in MANET are also studied, e.g., wormhole and flooding attacks. In addition, we conceive the open issues and future trends of black hole detection and prevention in MANETs based on the survey results of this paper. We summarize these detection schemes with three systematic comparison tables of non-cooperative black hole, collaborative black hole and other attacks, respectively, for a comprehensive survey of attacks in MANETs
Twitter is one of the most popular social platforms for online users to share trendy information and views on any event. Twitter reports an event faster than any other medium and contains enormous information and views regarding an event. Consequently, Twitter topic summarization is one of the most convenient ways to get instant gist of any event. However, the information shared on Twitter is often full of nonstandard abbreviations, acronyms, out of vocabulary (OOV) words and with grammatical mistakes which create challenges to find reliable and useful information related to any event. Undoubtedly, Twitter event summarization is a challenging task where traditional text summarization methods do not work well. In last decade, various research works introduced different approaches for automatic Twitter topic summarization. The main aim of this survey work is to make a broad overview of promising summarization approaches on a Twitter topic. We also focus on automatic evaluation of summarization techniques by surveying recent evaluation methodologies. At the end of the survey, we emphasize on both current and future research challenges in this domain through a level of depth analysis of the most recent summarization approaches.
Thanks to its potential in many applications, Blockchain has recently been nominated as one of the technologies exciting intense attention. Blockchain has solved the problem of changing the original low-trust centralized ledger held by a single third-party, to a high-trust decentralized form held by different entities, or in other words, verifying nodes. The key contribution of the work of Blockchain is the consensus algorithm, which decides how agreement is made to append a new block between all nodes in the verifying network. Blockchain algorithms can be categorized into two main groups. The first group is proof-based consensus, which requires the nodes joining the verifying network to show that they are more qualified than the others to do the appending work. The second group is voting-based consensus, which requires nodes in the network to exchange their results of verifying a new block or transaction, before making the final decision. In this paper, we present a review of the Blockchain consensus algorithms that have been researched and that are being applied in some well-known applications at this time
The crowdsourcing software development (CSD) is growing rapidly in the open call format in a competitive environment. In CSD, tasks are posted on a web-based CSD platform for CSD workers to compete for the task and win rewards. Task searching and assigning are very important aspects of the CSD environment because tasks posted on different platforms are in hundreds. To search and evaluate a thousand submissions on the platform are very difficult and time-consuming process for both the developer and platform. However, there are many other problems that are affecting CSD quality and reliability of CSD workers to assign the task which include the required knowledge, large participation, time complexity and incentive motivations. In order to attract the right person for the right task, the execution of action plans will help the CSD platform as well the CSD worker for the best matching with their tasks. This study formalized the task assignment method by utilizing different situations in a CSD competition-based environment in artificial intelligence (AI) planning. The results from this study suggested that assigning the task has many challenges whenever there are undefined conditions, especially in a competitive environment. Our main focus is to evaluate the AI automated planning to provide the best possible solution to matching the CSD worker with their personality type
Social data such as users’ comments are unstructured in nature and up-to-date technologies for analyzing such data are constrained by the available storage space and processing time when fast storing and processing is required. On the other hand, it is even difficult in using a huge amount of dynamically generated social data to analyze the user features in a high speed. To solve this problem, we design and implement a topic association analysis system based on the latent Dirichlet allocation (LDA) model. The LDA does not require the training process and thus can analyze the social users’ hourly interests on different topics in an easy way. The proposed system is constructed based on the Spark framework that is located on top of Hadoop cluster. It is advantageous of high-speed processing owing to that minimized access to hard disk is required and all the intermediately generated data are processed in the main memory. In the performance evaluation, it requires about 5 hours to analyze the topics for about 1 TB test social data (SNS comments). Moreover, through analyzing the association among topics, we can track the hourly change of social users’ interests on different topics.
We propose a novel deep neural network model for detecting human activities in untrimmed videos. The process of human activity detection in a video involves two steps: a step to extract features that are effective in recognizing human activities in a long untrimmed video, followed by a step to detect human activities from those extracted features. To extract the rich features from video segments that could express unique patterns for each activity, we employ two different convolutional neural network models, C3D and I-ResNet. For detecting human activities from the sequence of extracted feature vectors, we use BLSTM, a bi-directional recurrent neural network model. By conducting experiments with ActivityNet 200, a large-scale benchmark dataset, we show the high performance of the proposed DeepAct model.
Currently, electricity consumption and feedback mechanisms are being widely researched in Internet of Things (IoT) areas to realise power consumption monitoring and management through the remote control of appliances. This paper aims to develop a smart electricity utilisation IoT platform with a deep belief network for electricity utilisation feature modelling. In the end node of electricity utilisation, a smart monitoring and control module is developed for automatically operating air conditioners with a gateway, which connects and controls the appliances through an embedded ZigBee solution. To collect electricity consumption data, a programmable smart IoT gateway is developed to connect an IoT cloud server of smart electricity utilisation via the Internet and report the operational parameters and working states. The cloud platform manages the behaviour planning functions of the energy-saving strategies based on the power consumption features analysed by a deep belief network algorithm, which enables the automatic classification of the electricity utilisation situation. Besides increasing the user’s comfort and improving the user’s experience, the established feature models provide reliable information and effective control suggestions for power reduction by refining the air conditioner operation habits of each house. In addition, several data visualisation technologies are utilised to present the power consumption datasets intuitively
This paper presents a novel convolutional neural network based multi-feature fusion learning method for nonrigid 3D model retrieval, which can investigate the useful discriminative information of the heat kernel signature (HKS) descriptor and the wave kernel signature (WKS) descriptor. At first, we compute the 2D shape distributions of the two kinds of descriptors to represent the 3D model and use them as the input to the networks. Then we construct two convolutional neural networks for the HKS distribution and the WKS distribution separately, and use the multi-feature fusion layer to connect them. The fusion layer not only can exploit more discriminative characteristics of the two descriptors, but also can complement the correlated information between the two kinds of descriptors. Furthermore, to further improve the performance of the description ability, the cross-connected layer is built to combine the low-level features with high-level features. Extensive experiments have validated the effectiveness of the designed multi-feature fusion learning method
To combat the adverse impact imposed by illumination variation in the face recognition process, an effective and feasible algorithm is proposed in this paper. Firstly, an enhanced local texture feature is presented by applying the central symmetric encode principle on the fused component images acquired from the wavelet decomposition. Then the proposed local texture features are combined with Deep Belief Network (DBN) to gain robust deep features of face images under severe illumination conditions. Abundant experiments with different test schemes are conducted on both CMU-PIE and Extended Yale-B databases which contain face images under various illumination condition. Compared with the DBN, LBP combined with DBN and CSLBP combined with DBN, our proposed method achieves the most satisfying recognition rate regardless of the database used, the test scheme adopted or the illumination condition encountered, especially for the face recognition under severe illumination variation.
Deep learning using convolutional neural networks (CNNs) is being studied in various fields of image recognition and these studies show excellent performance. In this paper, we compare the performance of CNN architectures, KCR-AlexNet and KCR-GoogLeNet. The experimental data used in this paper is obtained from PHD08, a large-scale Korean character database. It has 2,187 samples of each Korean character with 2,350 Korean character classes for a total of 5,139,450 data samples. In the training results, KCR-AlexNet showed an accuracy of over 98% for the top-1 test and KCR-GoogLeNet showed an accuracy of over 99% for the top-1 test after the final training iteration. We made an additional Korean character dataset with fonts that were not in PHD08 to compare the classification success rate with commercial optical character recognition (OCR) programs and ensure the objectivity of the experiment. While the commercial OCR programs showed 66.95% to 83.16% classification success rates, KCR-AlexNet and KCR-GoogLeNet showed average classification success rates of 90.12% and 89.14%, respectively, which are higher than the commercial OCR programs’ rates. Considering the time factor, KCR-AlexNet was faster than KCR-GoogLeNet when they were trained using PHD08; otherwise, KCR-GoogLeNet had a faster classification speed.
Vocal effort detection is important for both robust speech recognition and speaker recognition. In this paper, the spectral information entropy feature which contains more salient information regarding the vocal effort level is firstly proposed. Then, the model fusion method based on complementary model is presented to recognize vocal effort level. Experiments are conducted on isolated words test set, and the results show the spectral information entropy has the best performance among the three kinds of features. Meanwhile, the recognition accuracy of all vocal effort levels reaches 81.6%. Thus, potential of the proposed method is demonstrated
With the rapid advancement of Internet services, there has been a dramatic increase in services that dynamically provide Internet resources on demand, such as cloud computing. In a cloud computing service, because the number of users in the cloud is changing dynamically, it is more efficient to utilize a flexible network technology such as software-defined networking (SDN). However, to efficiently support the SDNbased cloud computing service with limited resources, it is important to effectively manage the flow table at the SDN switch. Therefore, in this paper, a new flow management scheme is proposed that is able to, through efficient management, speed up the flow-entry search speed and simultaneously maximize the number of flow entries. The proposed scheme maximizes the capacity of the flow table by efficiently storing flow entry information while quickly executing the operation of flow-entry search by employing a hash index. In this paper, the proposed scheme is implemented by modifying the actual software SDN switch and then, its performance is analyzed. The results of the analysis show that the proposed scheme, by managing the flow tables efficiently, can support more flow entries
In existing cloud services, information security and privacy concerns have been worried, and have become one of the major factors that hinder the popularization and promotion of cloud computing. As the cloud computing infrastructure, the security of virtual machine systems is very important. This paper presents an immune-inspired intrusion detection model in virtual machines of cloud computing environment, denoted IVMIDS, to ensure the safety of user-level applications in client virtual machines. The model extracts system call sequences of programs, abstracts them into antigens, fuses environmental information of client virtual machines into danger signals, and implements intrusion detection by immune mechanisms. The model is capable of detecting attacks on processes which are statically tampered, and is able to detect attacks on processes which are dynamically running. Therefore, the model supports high real time. During the detection process, the model introduces information monitoring mechanism to supervise intrusion detection program, which ensures the authenticity of the test data. Experimental results show that the model does not bring much spending to the virtual machine system, and achieves good detection performance. It is feasible to apply IVMIDS to the cloud computing platform.
The era of information technologies has stimulated the demand of educational reform based on the use of information and communication technology (ICT). It requires explicit guidelines, vibrant objectives, mobilization of resources and political commitment at all levels of the country to achieve the desired results. However, change is not easy, it requires to overcome the impediments that hinder the successful integration of ICT in public schools. The pace of this reform is active in developed countries, while developing countries are lagging behind in achieving the required goals. The foremost purpose of this study is to highlight the barriers in the effective integration of ICT faced by developed countries in general and developing countries in particular. Reviewing the impediments to the integration of ICT in public schools may assist educators to become technology adopters in the future. Findings of the study reveal that intrinsic barriers are easy to surmount; once extrinsic barriers have been subdued successfully.
PCI Express (PCIe) bus, which was only used as an internal I/O bus of a computer system, has expanded its function to outside of a system, with progress of PCIe switching processor. In particular, advanced features of PCIe switching processor enable PCIe bus to serve as an interconnection network as well as connecting external devices. As PCIe switching processors more advanced, it is required to consider the different adapter card architecture. This study developed multipurpose adapter cards by applying an on-board optical module, a latest optical communications element, in order to improve transfer distance and utilization. The performance evaluation confirmed that the new adapter cards with long cable can provide the same bandwidth as that of the existing adapter cards with short copper cable.