Ji Su Park, Jong Hyuk Park
Vol. 16, No. 5, pp. 1001-1007, Oct. 2020
Keywords: Deep Learning, Machine Learning, Reinforcement Learning, Q-learning
Show / Hide AbstractIn recent years, machine learning algorithms are continuously being used and expanded in various fields, such as facial recognition, signal processing, personal authentication, and stock prediction. In particular, various algorithms, such as deep learning, reinforcement learning, and Q-learning, are continuously being improved. Among these algorithms, the expansion of deep learning is rapidly changing. Nevertheless, machine learning algorithms have not yet been applied in several fields, such as personal authentication technology. This technology is an essential tool in the digital information era, walking recognition technology as promising biometrics, and technology for solving state-space problems. Therefore, algorithm technologies of deep learning, reinforcement learning, and Q-learning, which are typical machine learning algorithms in various fields, such as agricultural technology, personal authentication, wireless network, game, biometric recognition, and image recognition, are being improved and expanded in this paper.
Shuangbao Ma, Wen Liu, Changli You, Shulin Jia, Yurong Wu
Vol. 16, No. 5, pp. 1008-1014, Oct. 2020
Keywords: Defect Detection, Denim Fabric, False Defect Removal, Gabor filter, Iterative Segmentation
Show / Hide AbstractAiming at the defect detection quality of denim fabric, this paper designs an improved algorithm based on the optimized Gabor filter. Firstly, we propose an improved defect detection algorithm of jean fabric based on the maximum two-dimensional image entropy and the loss evaluation function. Secondly, 24 Gabor filter banks with 4 scales and 6 directions are created and the optimal filter is selected from the filter banks by the onedimensional image entropy algorithm and the two-dimensional image entropy algorithm respectively. Thirdly, these two optimized Gabor filters are compared to realize the common defect detection of denim fabric, such as normal texture, miss of weft, hole and oil stain. The results show that the improved algorithm has better detection effect on common defects of denim fabrics and the average detection rate is more than 91.25%.
Chengjuan Ren, Dae-Kyoo Kim, Dongwon Jeong
Vol. 16, No. 5, pp. 1015-1033, Oct. 2020
Keywords: Deep Learning, Agriculture, State-of-the-Art, Survey
Show / Hide AbstractWith promising results and enormous capability, deep learning technology has attracted more and more attention to both theoretical research and applications for a variety of image processing and computer vision tasks. In this paper, we investigate 32 research contributions that apply deep learning techniques to the agriculture domain. Different types of deep neural network architectures in agriculture are surveyed and the current state-of-the-art methods are summarized. This paper ends with a discussion of the advantages and disadvantages of deep learning and future research topics. The survey shows that deep learning-based research has superior performance in terms of accuracy, which is beyond the standard machine learning techniques nowadays.
Vol. 16, No. 5, pp. 1034-1047, Oct. 2020
Keywords: Electroencephalography, information security, Machine Learning, Personal Authentication
Show / Hide AbstractThe personal authentication technique is an essential tool in this complex and modern digital information society. Traditionally, the most general mechanism of personal authentication was using alphanumeric passwords. However, passwords that are hard to guess or to break, are often hard to remember. There are demands for a technology capable of replacing the text-based password system. Graphical passwords can be an alternative, but it is vulnerable to shoulder-surfing attacks. This paper looks through a number of recently developed graphical password systems and introduces a personal authentication system using a machine learning technique with electroencephalography (EEG) signals as a new type of personal authentication system which is easier for a person to use and more difficult for others to steal than other preexisting authentication systems.
Vol. 16, No. 5, pp. 1048-1063, Oct. 2020
Keywords: CSMA/CA, ns-3, ns3-gym, Q-learning, Reinforcement Learning
Show / Hide AbstractIn this study, we propose a reinforcement learning agent to control the data transmission rates of nodes in carrier sensing multiple access with collision avoidance (CSMA/CA)-based wireless networks. We design a reinforcement learning (RL) agent, based on Q-learning. The agent learns the environment using the timeout events of packets, which are locally available in data sending nodes. The agent selects actions to control the data transmission rates of nodes that adjust the modulation and coding scheme (MCS) levels of the data packets to utilize the available bandwidth in dynamically changing channel conditions effectively. We use the ns3-gym framework to simulate RL and investigate the effects of the parameters of Q-learning on the performance of the RL agent. The simulation results indicate that the proposed RL agent adequately adjusts the MCS levels according to the changes in the network, and achieves a high throughput comparable to those of the existing data transmission rate adaptation schemes such as Minstrel.
An Evaluative Study of the Operational Safety of High-Speed Railway Stations Based on IEM-Fuzzy Comprehensive Assessment TheoryLi Wang, Chunling Jin, Chongqi Xu
Vol. 16, No. 5, pp. 1064-1073, Oct. 2020
Keywords: Comprehensive Evaluation, Fuzzy Mathematical Theory, High-Speed Railway Terminal, Interval Eigenvalue Method (IEM), Operational Security
Show / Hide AbstractThe general situation of system composition and safety management of high-speed railway terminal is investigated and a comprehensive evaluation index system of operational security is established on the basis of railway laws and regulations and previous research results to evaluate the operational security management of the high-speed railway terminal objectively and scientifically. Index weight is determined by introducing interval eigenvalue method (IEM), which aims to reduce the dependence of judgment matrix on consistency test and improve judgment accuracy. Operational security status of a high-speed railway terminal in northwest China is analyzed using the traditional model of fuzzy comprehensive evaluation, and a general technique idea and references for the operational security evaluation of the high-speed railway terminal are provided. IEM is introduced to determine the weight of each index, overcomes shortcomings of traditional analytic hierarchy process (AHP) method, and improves the accuracy and scientificity of the comprehensive evaluation. Risk factors, such as terrorist attacks, bad weather, and building fires, are intentionally avoided in the selection of evaluation indicators due to the complexity of risk factors in the operation of high-speed railway passenger stations and limitation of the length of the paper. However, such risk factors should be considered in the followup studies.
Comparison of Reinforcement Learning Activation Functions to Improve the Performance of the Racing Game Learning AgentDongcheul Lee
Vol. 16, No. 5, pp. 1074-1082, Oct. 2020
Keywords: Activation Function, Racing Game, Reinforcement Learning
Show / Hide AbstractRecently, research has been actively conducted to create artificial intelligence agents that learn games through reinforcement learning. There are several factors that determine performance when the agent learns a game, but using any of the activation functions is also an important factor. This paper compares and evaluates which activation function gets the best results if the agent learns the game through reinforcement learning in the 2D racing game environment. We built the agent using a reinforcement learning algorithm and a neural network. We evaluated the activation functions in the network by switching them together. We measured the reward, the output of the advantage function, and the output of the loss function while training and testing. As a result of performance evaluation, we found out the best activation function for the agent to learn the game. The difference between the best and the worst was 35.4%.
Guoqing Xu, Shouxiang Zhang
Vol. 16, No. 5, pp. 1083-1094, Oct. 2020
Keywords: Image retrieval, K-NN, Leaf Recognition, multi-scale, SVM
Show / Hide AbstractRecognizing plant species based on leaf images is challenging because of the large inter-class variation and inter-class similarities among different plant species. The effective extraction of leaf descriptors constitutes the most important problem in plant leaf recognition. In this paper, a multi-scale angular description method is proposed for fast and accurate leaf recognition and retrieval tasks. The proposed method uses a novel scalegeneration rule to develop an angular description of leaf contours. It is parameter-free and can capture leaf features from coarse to fine at multiple scales. A fast Fourier transform is used to make the descriptor compact and is effective in matching samples. Both support vector machine and k-nearest neighbors are used to classify leaves. Leaf recognition and retrieval experiments were conducted on three challenging datasets, namely Swedish leaf, Flavia leaf, and ImageCLEF2012 leaf. The results are evaluated with the widely used standard metrics and compared with several state-of-the-art methods. The results and comparisons show that the proposed method not only requires a low computational time, but also achieves good recognition and retrieval accuracies on challenging datasets.
Xiaoli Wang, Feifei Wang, Yuhou Song, Guirong Zhang, Shaohui Wang
Vol. 16, No. 5, pp. 1095-1104, Oct. 2020
Keywords: Gas Valve, Intelligent Management and Service System, Server
Show / Hide AbstractThis paper introduces a design scheme of intelligent gas valve management and service system based on Internet. This scheme adds sensor and general packet radio service (GPRS) modules to the traditional gas valve and establishes communication connection between gas valve and the server through wireless packet communication technology, which makes the traditional gas valve have the networking ability. Compared with the traditional gas valve management and service business, the method proposed in this paper is more convenient and efficient.
Vol. 16, No. 5, pp. 1105-1112, Oct. 2020
Keywords: Convolutional Neural Network, gait recognition, Metric learning, k-nearest neighbors
Show / Hide AbstractGait recognition, as a promising biometric, can be used in video-based surveillance and other security systems. However, due to the complexity of leg movement and the difference of external sampling conditions, gait recognition still faces many problems to be addressed. In this paper, an improved convolutional neural network (CNN) based on Gabor filter is therefore proposed to achieve gait recognition. Firstly, a gait feature extraction layer based on Gabor filter is inserted into the traditional CNNs, which is used to extract gait features from gait silhouette images. Then, in the process of gait classification, using the output of CNN as input, we utilize metric learning techniques to calculate distance between two gaits and achieve gait classification by k-nearest neighbors classifiers. Finally, several experiments are conducted on two open-accessed gait datasets and demonstrate that our method reaches state-of-the-art performances in terms of correct recognition rate on the OULP and CASIA-B datasets.
Yongfei Ye, Xinghua Sun, Minghe Liu, Jing Mi, Ting Yan, Lihua Ding
Vol. 16, No. 5, pp. 1113-1128, Oct. 2020
Keywords: ad hoc network, Adaptive, Decision Tree, Intelligent Routing Protocol
Show / Hide AbstractAd hoc networks play an important role in mobile communications, and the performance of nodes has a significant impact on the choice of communication links. To ensure efficient and secure data forwarding and delivery, an intelligent routing protocol (IAODV) based on learning method is constructed. Five attributes of node energy, rate, credit value, computing power and transmission distance are taken as the basis of segmentation. By learning the selected samples and calculating the information gain of each attribute, the decision tree of routing node is constructed, and the rules of routing node selection are determined. IAODV algorithm realizes the adaptive evaluation and classification of network nodes, so as to determine the optimal transmission path from the source node to the destination node. The simulation results verify the feasibility, effectiveness and security of IAODV.
Vol. 16, No. 5, pp. 1129-1144, Oct. 2020
Keywords: image inpainting, Structural Constraint, Texture Synthesis, wavelet transform
Show / Hide AbstractThe thangka image inpainting method based on wavelet transform is not ideal for contour curves when the high frequency information is repaired. In order to solve the problem, a new image inpainting algorithm is proposed based on edge structural constraints and wavelet transform coefficients. Firstly, a damaged thangka image is decomposed into low frequency subgraphs and high frequency subgraphs with different resolutions using wavelet transform. Then, the improved fast marching method is used to repair the low frequency subgraphs which represent structural information of the image. At the same time, for the high frequency subgraphs which represent textural information of the image, the extracted and repaired edge contour information is used to constrain structure inpainting in the proposed algorithm. Finally, the texture part is repaired using texture synthesis based on the wavelet coefficient characteristic of each subgraph. In this paper, the improved method is compared with the existing three methods. It is found that the improved method is superior to them in inpainting accuracy, especially in the case of contour curve. The experimental results show that the hierarchical method combined with structural constraints has a good effect on the edge damage of thangka images.
Jinlong Zhu, Fanhua Yu, Guangjie Liu, Mingyu Sun, Dong Zhao, Qingtian Geng, Jinbo Su
Vol. 16, No. 5, pp. 1145-1157, Oct. 2020
Keywords: Face Recognition, Game, ResNet Networks
Show / Hide AbstractA convolution neural networks (CNNs) has demonstrated outstanding performance compared to other algorithms in the field of face recognition. Regarding the over-fitting problem of CNN, researchers have proposed a residual network to ease the training for recognition accuracy improvement. In this study, a novel face recognition model based on game theory for call-over in the classroom was proposed. In the proposed scheme, an image with multiple faces was used as input, and the residual network identified each face with a confidence score to form a list of student identities. Face tracking of the same identity or low confidence were determined to be the optimisation objective, with the game participants set formed from the student identity list. Game theory optimises the authentication strategy according to the confidence value and identity set to improve recognition accuracy. We observed that there exists an optimal mapping relation between face and identity to avoid multiple faces associated with one identity in the proposed scheme and that the proposed game-based scheme can reduce the error rate, as compared to the existing schemes with deeper neural network.
Liquan Zhao, Kexin Zhang
Vol. 16, No. 5, pp. 1158-1168, Oct. 2020
Keywords: Communication Power, Distance Vector Hop Algorithm, Location Accuracy, Wireless Sensor Networks
Show / Hide AbstractThe distance vector-hop wireless sensor node location method is one of typical range-free location methods. In distance vector-hop location method, if a wireless node A can directly communicate with wireless sensor network nodes B and C at its communication range, the hop count from wireless sensor nodes A to B is considered to be the same as that form wireless sensor nodes A to C. However, the real distance between wireless sensor nodes A and B may be dissimilar to that between wireless sensor nodes A and C. Therefore, there may be a discrepancy between the real distance and the estimated hop count distance, and this will affect wireless sensor node location error of distance vector-hop method. To overcome this problem, it proposes a wireless sensor network node location method by modifying the method of distance estimation in the distance vector-hop method. Firstly, we set three different communication powers for each node. Different hop counts correspond to different communication powers; and so this makes the corresponding relationship between the real distance and hop count more accurate, and also reduces the distance error between the real and estimated distance in wireless sensor network. Secondly, distance difference between the estimated distance between wireless sensor network anchor nodes and their corresponding real distance is computed. The average value of distance errors that is computed in the second step is used to modify the estimated distance from the wireless sensor network anchor node to the unknown sensor node. The improved node location method has smaller node location error than the distance vector-hop algorithm and other improved location methods, which is proved by simulations.
A Hybrid Genetic Ant Colony Optimization Algorithm with an Embedded Cloud Model for Continuous OptimizationPeng Wang, Jiyun Bai, Jun Meng
Vol. 16, No. 5, pp. 1169-1182, Oct. 2020
Keywords: Ant Colony Algorithm, Cloud Model, genetic algorithm
Show / Hide AbstractThe ant colony optimization (ACO) algorithm is a classical metaheuristic optimization algorithm. However, the conventional ACO was liable to trap in the local minimum and has an inherent slow rate of convergence. In this work, we propose a novel combinatorial ACO algorithm (CG-ACO) to alleviate these limitations. The genetic algorithm and the cloud model were embedded into the ACO to find better initial solutions and the optimal parameters. In the experiment section, we compared CG-ACO with the state-of-the-art methods and discussed the parameter stability of CG-ACO. The experiment results showed that the CG-ACO achieved better performance than ACOR, simple genetic algorithm (SGA), CQPSO and CAFSA and was more likely to reach the global optimal solution.
Mai Thanh Nhat Truong, Sanghoon Kim
Vol. 16, No. 5, pp. 1183-1195, Oct. 2020
Keywords: Boolean Map, infrared image, Saliency detection
Show / Hide AbstractVisual saliency detection is an essential task because it is an important part of various vision-based applications. There are many techniques for saliency detection in color images. However, the number of methods for saliency detection in infrared images is limited. In this paper, we introduce a simple approach for saliency detection in infrared images based on the thresholding technique. The input image is thresholded into several Boolean maps, and an initial saliency map is calculated as a weighted sum of the created Boolean maps. The initial map is further refined by using thresholding, morphology operation, and a Gaussian filter to produce the final, highquality saliency map. The experiment showed that the proposed method has high performance when applied to real-life data.
Sehrish Malik, Israr Ullah, DoHyeun Kim, KyuTae Lee
Vol. 16, No. 5, pp. 1196-1213, Oct. 2020
Keywords: Prediction Algorithms, Smart Cities, Smart Service
Show / Hide AbstractThere is a growing interest in the development of smart environments through predicting the behaviors of inhabitants of smart spaces in the recent past. Various smart services are deployed in modern smart cities to facilitate residents and city administration. Prediction algorithms are broadly used in the smart fields in order to well equip the smart services for the future demands. Hence, an accurate prediction technology plays a vital role in the smart services. In this paper, we take out an extensive survey of smart spaces such as smart homes, smart farms and smart cars and smart applications such as smart health and smart energy. Our extensive survey is based on more than 400 articles and the final list of research studies included in this survey consist of 134 research papers selected using Google Scholar database for period of 2008 to 2018. In this survey, we highlight the role of prediction algorithms in each sub-domain of smart Internet of Things (IoT) environments. We also discuss the main algorithms which play pivotal role in a particular IoT subfield and effectiveness of these algorithms. The conducted survey provides an efficient way to analyze and have a quick understanding of state of the art work in the targeted domain. To the best of our knowledge, this is the very first survey paper on main categories of prediction algorithms covering statistical, heuristic and hybrid approaches for smart environments.
Sung-Bong Jang, Young-Woong Ko
Vol. 16, No. 5, pp. 1214-1222, Oct. 2020
Keywords: Augmented Object Similarity, Context Awareness, Mobile Augmented Reality, Object Augmentation
Show / Hide AbstractPervasive augmented reality (AR) technology can be used to efficiently search for the required information regarding products in stores through text augmentation in an Internet of Things (IoT) environment. The evolution of context awareness and image processing technologies are the main driving forces that realize this type of AR service. One of the problems to be addressed in the service is that augmented objects are fixed and cannot be replaced efficiently in real time. To address this problem, a real-time mobile AR framework is proposed. In this framework, an optimal object to be augmented is selected based on object similarity comparison, and the augmented objects are efficiently managed using distributed metadata servers to adapt to the user requirements, in a given situation. To evaluate the feasibility of the proposed framework, a prototype system was implemented, and a qualitative evaluation based on questionnaires was conducted. The experimental results show that the proposed framework provides a better user experience than existing features in smartphones, and through fast AR service, the users are able to conveniently obtain additional information on products or objects.
Sangchul Woo, Yunsick Sung
Vol. 16, No. 5, pp. 1223-1230, Oct. 2020
Keywords: Dance Tutorial System, Q-learning, Reinforcement Learning, Virtual Tutor
Show / Hide AbstractRecently, extensive studies have been conducted to apply deep learning to reinforcement learning to solve the state-space problem. If the state-space problem was solved, reinforcement learning would become applicable in various fields. For example, users can utilize dance-tutorial systems to learn how to dance by watching and imitating a virtual instructor. The instructor can perform the optimal dance to the music, to which reinforcement learning is applied. In this study, we propose a method of reinforcement learning in which the action space is dynamically adjusted. Because actions that are not performed or are unlikely to be optimal are not learned, and the state space is not allocated, the learning time can be shortened, and the state space can be reduced. In an experiment, the proposed method shows results similar to those of traditional Q-learning even when the state space of the proposed method is reduced to approximately 0.33% of that of Q-learning. Consequently, the proposed method reduces the cost and time required for learning. Traditional Q-learning requires 6 million state spaces for learning 100,000 times. In contrast, the proposed method requires only 20,000 state spaces. A higher winning rate can be achieved in a shorter period of time by retrieving 20,000 state spaces instead of 6 million.