Debbie Honghee Ko, Ammar Ul Hassan, Saima Majeed, Jaeyoung Choi
Vol. 17, No. 1, pp. 1-13, Feb. 2021
Keywords: Generative Adversarial Network, Image-to-Image Translation, Skeletonization, Style Transfer
Show / Hide AbstractIn this research, we study the problem of font image skeletonization using an end-to-end deep adversarial network, in contrast with the state-of-the-art methods that use mathematical algorithms. Several studies have been concerned with skeletonization, but a few have utilized deep learning. Further, no study has considered generative models based on deep neural networks for font character skeletonization, which are more delicate than natural objects. In this work, we take a step closer to producing realistic synthesized skeletons of font characters. We consider using an end-to-end deep adversarial network, SkelGAN, for font-image skeletonization, in contrast with the state-of-the-art methods that use mathematical algorithms. The proposed skeleton generator is proved superior to all well-known mathematical skeletonization methods in terms of character structure, including delicate strokes, serifs, and even special styles. Experimental results also demonstrate the dominance of our method against the state-of-the-art supervised image-to-image translation method in font character skeletonization task.
Development of a Targeted Recommendation Model for Earthquake Risk Prevention in the Whole Disaster ChainXiaohui Su, Keyu Ming, Xiaodong Zhang, Junming Liu, Da Lei
Vol. 17, No. 1, pp. 14-27, Feb. 2021
Keywords: Android Application, Earthquake, Risk Prevention Products, rule base, Targeted Recommendation Model
Show / Hide AbstractStrong earthquakes have caused substantial losses in recent years, and earthquake risk prevention has aroused a significant amount of attention. Earthquake risk prevention products can help improve the self and mutualrescue abilities of people, and can create convenient conditions for earthquake relief and reconstruction work. At present, it is difficult for earthquake risk prevention information systems to meet the information requirements of multiple scenarios, as they are highly specialized. Aiming at mitigating this shortcoming, this study investigates and analyzes four user roles (government users, public users, social force users, insurance market users), and summarizes their requirements for earthquake risk prevention products in the whole disaster chain, which comprises three scenarios (pre-quake preparedness, in-quake warning, and post-quake relief). A targeted recommendation rule base is then constructed based on the case analysis method. Considering the user’s location, the earthquake magnitude, and the time that has passed since the earthquake occurred, a targeted recommendation model is built. Finally, an Android APP is implemented to realize the developed model. The APP can recommend multi-form earthquake risk prevention products to users according to their requirements under the three scenarios. Taking the 2019 Lushan earthquake as an example, the APP exhibits that the model can transfer real-time information to everyone to reduce the damage caused by an earthquake.
Jung Hyun Im, Ha-Ryoung Oh, Yeong Rak Seong
Vol. 17, No. 1, pp. 28-36, Feb. 2021
Keywords: Discrete Event System Specification, Mobile IoT System, modeling and simulation
Show / Hide AbstractThis paper proposes two novel methods to model and simulate a mobile Internet of Things (IoT) system using the discrete event system specification (DEVS) formalism. In traditional simulation methods, it is advantageous to partition the simulation area hierarchically to reduce simulation time; however, in this case, the structure of the model may change as the IoT nodes to be modeled move. The proposed methods reduce the simulation time while maintaining the model structure, even when the IoT nodes move. To evaluate the performance of the proposed methods, a prototype mobile IoT system was modeled and simulated. The simulation results show that the proposed methods achieve good performance, even if the number of IoT nodes or the movement of IoT nodes increases.
Li Wang, Guodong Wang
Vol. 17, No. 1, pp. 37-50, Feb. 2021
Keywords: caching, Frequent Sub-query Trajectory, Nested Data, Query Optimization, Service Tree
Show / Hide AbstractQuery applications based on nested data, the most commonly used form of data representation on the web, especially precise query, is becoming more extensively used. MapReduce, a distributed architecture with parallel computing power, provides a good solution for big data processing. However, in practical application, query requests are usually concurrent, which causes bottlenecks in server processing. To solve this problem, this paper first combines a column storage structure and an inverted index to build index for nested data on MapReduce. On this basis, this paper puts forward an optimization strategy which combines query execution service tree and frequent sub-query trajectory to reduce the response time of frequent queries and further improve the efficiency of multi-user concurrent queries on large scale nested data. Experiments show that this method greatly improves the efficiency of nested data query.
Gwang Bok Kim, Cheol Hong Kim
Vol. 17, No. 1, pp. 51-62, Feb. 2021
Keywords: Bypassing, Cache, GPU, Miss Rate, Performance
Show / Hide AbstractOn-chip caches of graphics processing units (GPUs) have contributed to improved GPU performance by reducing long memory access latency. However, cache efficiency remains low despite the facts that recent GPUs have considerably mitigated the bottleneck problem of L1 data cache. Although the cache miss rate is a reasonable metric for cache efficiency, it is not necessarily proportional to GPU performance. In this study, we introduce a second key determinant to overcome the problem of predicting the performance gains from L1 data cache based on the assumption that miss rate only is not accurate. The proposed technique estimates the benefits of the cache by measuring the balance between cache efficiency and throughput. The throughput of the cache is predicted based on the warp occupancy information in the warp pool. Then, the warp occupancy is used for a second bypass phase when workloads show an ambiguous miss rate. In our proposed architecture, the L1 data cache is turned off for a long period when the warp occupancy is not high. Our two-level bypassing technique can be applied to recent GPU models and improves the performance by 6% on average compared to the architecture without bypassing. Moreover, it outperforms the conventional bottleneck-based bypassing techniques.
Liquan Zhao, Shuaichao Guo
Vol. 17, No. 1, pp. 63-74, Feb. 2021
Keywords: Cluster Head Election, Energy Efficient Routing Protocol, Heterogeneous Wireless Sensor Network, multi-hop
Show / Hide AbstractAccording to the double-phase cluster-head election method (DCE), the final cluster heads (CHs) sometimes are located at the edge of cluster. They have a long distance from the base station (BS). Sensor data is directly transmitted to BS by CHs. This makes some nodes consume much energy for transmitting data and die earlier. To address this problem, energy efficient multi-hop cluster-head election strategy (EEMCE) is proposed in this paper. To avoid taking these nodes far from BS as CH, this strategy first introduces the distance from the sensor nodes to the BS into the tentative CH election. Subsequently, in the same cluster, the energy of tentative CH is compared with those of other nodes, and then the node that has more energy than the tentative CH and being nearest the tentative CH are taken as the final CH. Lastly, if the CH is located at the periphery of the network, the multi-hop method will be employed to reduce the energy that is consumed by CHs. The simulation results suggest that the proposed method exhibits higher energy efficiency, longer stability period and better scalability than other protocols.
Ying Chen, Ruirui Zhang
Vol. 17, No. 1, pp. 75-88, Feb. 2021
Keywords: Credit Loan, Default prediction, Random Forest, Support Vector Machine
Show / Hide AbstractAutomobile credit business has developed rapidly in recent years, and corresponding default phenomena occur frequently. Credit default will bring great losses to automobile financial institutions. Therefore, the successful prediction of automobile credit default is of great significance. Firstly, the missing values are deleted, then the random forest is used for feature selection, and then the sample data are randomly grouped. Finally, six prediction models of support vector machine (SVM), random forest and k-nearest neighbor (KNN), logistic, decision tree, and artificial neural network (ANN) are constructed. The results show that these six machine learning models can be used to predict the default of automobile credit. Among these six models, the accuracy of decision tree is 0.79, which is the highest, but the comprehensive performance of SVM is the best. And random grouping can improve the efficiency of model operation to a certain extent, especially SVM.
Hongbo Shi, Xin Chen, Min Guo
Vol. 17, No. 1, pp. 89-106, Feb. 2021
Keywords: Imbalanced Data, Safe Sample Screening, Re-SSS-IS, Re-SSS-WSMOTE
Show / Hide AbstractDifferent samples can have different effects on learning support vector machine (SVM) classifiers. To rebalance an imbalanced dataset, it is reasonable to reduce non-informative samples and add informative samples for learning classifiers. Safe sample screening can identify a part of non-informative samples and retain informative samples. This study developed a resampling algorithm for Rebalancing imbalanced data using Safe Sample Screening (Re-SSS), which is composed of selecting Informative Samples (Re-SSS-IS) and rebalancing via a Weighted SMOTE (Re-SSS-WSMOTE). The Re-SSS-IS selects informative samples from the majority class, and determines a suitable regularization parameter for SVM, while the Re-SSS-WSMOTE generates informative minority samples. Both Re-SSS-IS and Re-SSS-WSMOTE are based on safe sampling screening. The experimental results show that Re-SSS can effectively improve the classification performance of imbalanced classification problems.
Yu-Jeong Yang, Ki Yong Lee
Vol. 17, No. 1, pp. 107-123, Feb. 2021
Keywords: Hierarchical Classification, Purchase History, Sequence Similarity, Similarity Measure
Show / Hide AbstractIn an online shopping site or offline store, products purchased by each customer over time form the purchase history of the customer. Also, in most retailers, products have a product taxonomy, which represents a hierarchical classification of products. Considering the product taxonomy, the lower the level of the category to which two products both belong, the more similar the two products. However, there has been little work on similarity measures for sequences considering a hierarchical classification of elements. In this paper, we propose new similarity measures for purchase histories considering not only the purchase order of products but also the hierarchical classification of products. Unlike the existing methods, where the similarity between two elements in sequences is only 0 or 1 depending on whether two elements are the same or not, the proposed method can assign any real number between 0 and 1 considering the hierarchical classification of elements. We apply this idea to extend three existing representative similarity measures for sequences. We also propose an efficient computation method for the proposed similarity measures. Through various experiments, we show that the proposed method can measure the similarity between purchase histories very effectively and efficiently.
Changjian Zhou, Jinge Xing, Haibo Liu
Vol. 17, No. 1, pp. 124-135, Feb. 2021
Keywords: Moving object detection, Multiple Properties, SIFT Vector Field
Show / Hide AbstractObject detection is a fundamental yet challenging task in computer vision that plays an important role in object recognition, tracking, scene analysis and understanding. This paper aims to propose a multiproperty fusion algorithm for moving object detection. First, we build a scale-invariant feature transform (SIFT) vector field and analyze vectors in the SIFT vector field to divide vectors in the SIFT vector field into different classes. Second, the distance of each class is calculated by dispersion analysis. Next, the target and contour can be extracted, and then we segment the different images, reversal process and carry on morphological processing, the moving objects can be detected. The experimental results have good stability, accuracy and efficiency.
Hongqiang Jiao, Wanning Ding, Xinxin Wang
Vol. 17, No. 1, pp. 136-150, Feb. 2021
Keywords: Chain Iteration, Supply Chain, trust evaluation
Show / Hide AbstractThe modern market is highly competitive. It has progressed from traditional competition between enterprises to competition between supply chains. To ensure that enterprise can form the best strategy consistently, it is necessary to evaluate the trust of other enterprises in the supply chain. First, this paper analyzes the background and significance of supply chain trust research, analyzes and expounds on the qualitative and quantitative methods of supply chain trust evaluation, and summarizes the research in this field. Analytic hierarchy process (AHP) is the most frequently used method in the literature to evaluate and rank criteria through data analysis. However, the input data for AHP analysis is based on human judgment, and hence there is every possibility that the data may be vague to some extent. Therefore, in view of the above problems, this study improves the global trust method based on chain iteration. The improved global trust evaluation method based on chain iteration is more flexible and practical, hence, it can more accurately evaluate supply chain trust. Finally, combined with an actual case of Zhaoxian Chengji Food Co. Ltd., the paper qualitatively analyzes the current situation of supply chain trust management and effectively strengthens the supervision of enterprises to cooperative enterprises. Thus, the company can identify problems on time and strategic adjustments can be implemented accordingly. The effectiveness of the evaluation method proposed in this paper is demonstrated through a quantitative evaluation of its trust in downstream enterprise A. Results suggest that the subjective preferences of and historical transactions together affect the final evaluation of trust.
Dohyun Kim, Jungho Kang, Tae Woo Kim, Yi Pan, Jong Hyuk Park
Vol. 17, No. 1, pp. 151-162, Feb. 2021
Keywords: Quantum Information, Quantum, Sensing, Computing, Communication
Show / Hide AbstractQuantum information has passed the theoretical research period and has entered the realization step for its application to the information and communications technology (ICT) sector. Currently, quantum information has the advantage of being safer and faster than conventional digital computers. Thus, a lot of research is being done. The amount of big data that one needs to deal with is expected to grow exponentially. It is also a new business model that can change the landscape of the existing computing. Just as the IT sector has faced many challenges in the past, we need to be prepared for change brought about by Quantum. We would like to look at studies on quantum communication, quantum sensing, and quantum computing based on quantum information and see the technology levels of each country and company. Based on this, we present the vision and challenge for quantum information in the future. Our work is significant since the time for first-time study challengers is reduced by discussing the fundamentals of quantum information and summarizing the current situation.
Thanh Ho, Tran Duy Thanh
Vol. 17, No. 1, pp. 163-177, Feb. 2021
Keywords: Clustering method, Community Interests, Feature Vectors Social Network, Topic Model, Time Factor, User eXperience
Show / Hide AbstractMany methods of discovering social networking communities or clustering of features are based on the network structure or the content network. This paper proposes a community discovery method based on topic models using a time factor and an unsupervised clustering method. Online community discovery enables organizations and businesses to thoroughly understand the trend in users’ interests in their products and services. In addition, an insight into customer experience on social networks is a tremendous competitive advantage in this era of ecommerce and Internet development. The objective of this work is to find clusters (communities) such that each cluster’s nodes contain topics and individuals having similarities in the attribute space. In terms of social media analytics, the method seeks communities whose members have similar features. The method is experimented with and evaluated using a Vietnamese corpus of comments and messages collected on social networks and ecommerce sites in various sectors from 2016 to 2019. The experimental results demonstrate the effectiveness of the proposed method over other methods.
Assisted Magnetic Resonance Imaging Diagnosis for Alzheimer’s Disease Based on Kernel Principal Component Analysis and Supervised Classification SchemesYu Wang, Wen Zhou, Chongchong Yu, Weijun Su
Vol. 17, No. 1, pp. 178-190, Feb. 2021
Keywords: Alzheimer’s disease, feature extraction, KPCA, Machine Learning, Structural Magnetic Resonance Imaging
Show / Hide AbstractAlzheimer’s disease (AD) is an insidious and degenerative neurological disease. It is a new topic for AD patients to use magnetic resonance imaging (MRI) and computer technology and is gradually explored at present. Preprocessing and correlation analysis on MRI data are firstly made in this paper. Then kernel principal component analysis (KPCA) is used to extract features of brain gray matter images. Finally supervised classification schemes such as AdaBoost algorithm and support vector machine algorithm are used to classify the above features. Experimental results by means of AD program Alzheimer’s Disease Neuroimaging Initiative (ADNI) database which contains brain structural MRI (sMRI) of 116 AD patients, 116 patients with mild cognitive impairment, and 117 normal controls show that the proposed method can effectively assist the diagnosis and analysis of AD. Compared with principal component analysis (PCA) method, all classification results on KPCA are improved by 2%–6% among which the best result can reach 84%. It indicates that KPCA algorithm for feature extraction is more abundant and complete than PCA.
On-Demand Remote Software Code Execution Unit Using On-Chip Flash Memory Cloudification for IoT Environment AccelerationDongkyu Lee, Moon Gi Seok, Daejin Park
Vol. 17, No. 1, pp. 191-202, Feb. 2021
Keywords: Edge-Side Acceleration, Memory Cloudification, On-Demand Remote Code Execution
Show / Hide AbstractIn an Internet of Things (IoT)-configured system, each device executes on-chip software. Recent IoT devices require fast execution time of complex services, such as analyzing a large amount of data, while maintaining low-power computation. As service complexity increases, the service requires high-performance computing and more space for embedded space. However, the low performance of IoT edge devices and their small memory size can hinder the complex and diverse operations of IoT services. In this paper, we propose a remote on-demand software code execution unit using the cloudification of on-chip code memory to accelerate the program execution of an IoT edge device with a low-performance processor. We propose a simulation approach to distribute remote code executed on the server side and on the edge side according to the program’s computational and communicational needs. Our on-demand remote code execution unit simulation platform, which includes an instruction set simulator based on 16-bit ARM Thumb instruction set architecture, successfully emulates the architectural behavior of on-chip flash memory, enabling embedded devices to accelerate and execute software using remote execution code in the IoT environment.
Vol. 17, No. 1, pp. 203-212, Feb. 2021
Keywords: Chinese Pronunciation Prediction, Component, Features, Statistical Machine Translation (SMT)
Show / Hide AbstractTo eliminate ambiguities in the existing methods to simplify Chinese pronunciation learning, we propose a model that can predict the pronunciation of Chinese characters automatically. The proposed model relies on a statistical machine translation (SMT) framework. In particular, we consider the components of Chinese characters as the basic unit and consider the pronunciation prediction as a machine translation procedure (the component sequence as a source sentence, the pronunciation, pinyin, as a target sentence). In addition to traditional features such as the bidirectional word translation and the n-gram language model, we also implement a component similarity feature to overcome some typos during practical use. We incorporate these features into a log-linear model. The experimental results show that our approach significantly outperforms other baseline models.