Earticle

The intelligent reflecting surface (IRS) technology can enhance coverage in wireless networks by detouring a blocked path, where the phases of its passive elements are controlled to reinforce reflected signals in the desired directions, as the massive MIMO does. As a massive IRS system is introduced in the millimeter wave (mmWave) and tera-hertz (THz) bands, the optimal phase control induces computational complexity, and its complexity is doubled in multiuser systems. We propose a computationally efficient phase control algorithm in IRS-aided multiuser systems, where the reflected signals are sequentially aligned to search for optimal phases to maximize the total SNR of all users in service. The proposed scheme is evaluated with continuous phase and discrete phases with 1, 2, and 3 bits and compared with the random phase and full-search cases.

Recently, as data demand has increased owing to the rapidly increasing demand for wireless devices and the influence of data traffic, various technologies are being developed to support it. Among them, millimeter-wave (mmWave) frequencies with rich spectra and high data-transmission rates suffer from the problem of large path loss. Accordingly, there is a growing interest in unmanned aerial vehicles (UAVs) and reconfigurable intelligent surfaces (RISs), which can be utilized advantageously to reconstruct wireless communication environments. Therefore, this work considers a large-scale system comprising a number of users and Flying RISs, combining UAVs and RISs to increase algorithm utilization. We propose a deep neural network-based algorithm that places Flying RISs in an appropriate location so that they can support as many users as possible. Simulation results confirmed that the proposed technique could place Flying RISs in an efficient location with higher accuracy and speed in large-scale systems compared to existing techniques.

신체영역무선통신망(WBAN)에서 클러스터 헤드(CH) 선출 및 최적경로의 라우팅은 에너지 효율 향상과 네트워크 노드 운영수명 연장을 위해 해결해야 할 이슈이다. 이러한 연구를 위해 본 논문에서는 BKOA알고리즘과 그리드 기반 멀티홉 라우팅 프레임워크를 결합한 하이브리드 BKOA-GRID를 제안한다. 시뮬레이션 수행결과 제안된 BKOA-GRID는 PSO, LEACH, EEUC 등 기존 알고리즘보다 노드생존율 90%, 잔류에너지 지속성은 총 에너지의 약 60%를 유지하여 높은 에너지 효율을 보였다.

Cluster head(CH) election and optimal path routing in a Wireless Body Area Network(WBAN) are issues that must be addressed to improve energy efficiency and extend the operating life of network nodes. To address these issues, this paper proposes a hybrid BKOA-GRID (Black Kite Optimization Algorithm-GRID) framework, which integrates the Black Kite Optimization Algorithm with a grid-based multi-hop routing structure. Simulation results demonstrate that the proposed BKOA-GRID exhibits superior energy efficiency compared to existing algorithms such as PSO, LEACH, and EEUC, maintaining a node survival rate of 90% and preserving approximately 60% of the total residual energy.

본 연구에서는 레이저유도붕괴분광(Laser Induced Breakdown Spectroscopy, LIBS)을 이용하여 방사형 기저함수 신경회로망(Radial Basis Function Neural Networks, RBFNNs) 분류기 설계방법론을 개발하고 실제 폐소형가전제품의 플라스틱 분류 시스템에 적용하였다. ABS, PP, PS와 같은 검정색 플라스틱을 구별하기 위해, 지능형 알고리즘 중 하나인 방사형 기저함수 신경회로망 분류기를 설계하였다. 획득한 입력변수는 주성분 분석법(Principal Component Analysis, PCA)을 이용하여 축소시켰으며, 군집화기법 중 하나인K-means 클러스터링 방법을 이용해 여러 그룹으로 분할하였다. 전체 데이터는 학습 데이터와 테스트 데이터를 4:1의 비율로 나누었으며, 제안된 분류기의 성능 및 신뢰도를 평가하기 위하여 5-FCV(5-Fold Cross Validation) 기법을 사용하였다. 입력변수와 클러스터의 개수가 각각 5개인 경우, 제안된 분류기의 분류 성능은 96.78%로 나타났다. 또한, 제안된 분류기는 다른 분류기들과 비교하였을 경우 분류 성능의 관점에서 우수성을 보여주었다.

In this study, the design methodology of Radial Basis Function Neural Networks is developed with the aid of Laser Induced Breakdown Spectroscopy and also applied to the practical plastics sorting system. To identify black plastics such as ABS, PP, and PS, RBFNNs classifier as a kind of intelligent algorithms is designed. The dimensionality of the obtained input variables are reduced by using PCA and divided into several groups by using K-means clustering which is a kind of clustering techniques. The entire data is split into training data and test data according to the ratio of 4:1. The 5-fold cross validation method is used to evaluate the performance as well as reliability of the proposed classifier. In case of input variables and clusters equal to 5 respectively, the classification performance of the proposed classifier is obtained as 96.78%. Also, the proposed classifier showed superiority in the viewpoint of classification performance where compared to other classifiers.

본 연구의 목적은 이용자의 탐색 행태, 시스템의 정보 구축 행태를 기반으로 초기 질의어의 범주에 해당하는 연관 용어들(해당 용어의 지식구조와 관련된 연관 용어들)을 학습기능을 통해 자동으로 제시해 줄 수 있는 지능형 검색 시스템을 구현하는 것이다. 이를 위해 학습을 통해 전문가 수준의 색인어를 추출할 수 있는 지능형자동색인 알고리즘, 자동분류에 관련한 클러스터링 알고리즘과 문서 범주화 알고리즘 그리고 범주 표현 알고리즘에 대한 이론적 연구를 수행하였으며, 이들 이론적 연구를 근거로 비용과 시간적인 측면에서 그리고 재현율과 정도율이란 측면에서 우수한 성능을 발휘할 수 있는 지능형검색시스템을 구현하였다.

This is to develop Intelligent Retrieval System which can automatically present early query's category terms(association terms connected with knowledge structure of relevant terminology) through learning function and it changes searching form automatically and runs it with association terms. For the reason, this theoretical study of Intelligent Automatic Indexing System abstracts expert's index term through learning and clustering algorism about automatic classification, text mining(categorization), and document category representation. It also demonstrates a good capacity in the aspects of expense, time, recall ratio, and precision ratio.

기술의 발전에 따라 소프트웨어 교육의 중요성이 점차 부각 되고 있다. 이에 따라 정보 교과에 대한 관심도가 높아지고 있으나 초등과정 학습자를 대상으로 전문적인 IT 기술에 대한 알고리즘을 학습하도록 유도하는 것은 학습자 의 흥미를 떨어트릴 수 있다. 본 논문에서는 2015 개정 교육과정 분석, 교육 프로그램 운영 계획 개발, 대상 학생 선정 및 프로그램 적용 결과 분석 및 평가의 4가지 단계를 거쳤다. 초등과정의 학습자를 대상으로, 인공지능을 적용하여 피사 체에서 얼굴을 추출하는 지능형 CCTV의 알고리즘을 그림이나 말풍선 상징물과 같은 다양한 도구를 이용하여 자유롭게 표현하도록 유도하였다. 또한 지능형 CCTV의 알고리즘을 학습자가 쉽고 다양하게 표현할 수 있도록 리치픽처 기법을 적용하여 학습자의 흥미를 높일수 있는 교육 프로그램을 제안한다. 본 교육 프로그램은 플로우차트를 이용함으로서 학 습자에게 알고리즘의 원리를 파악할 수 있도록 도울 수 있으며. 결과에 따라, 제안된 프로그램의 수정과 개발을 통해 다양한 분야에서 적용할 수 있는 IT 창의교육의 연구를 진행할 예정이다.

As technology advances, the importance of software education is increasing. Accordingly, interest in information subjects is increasing, but intending elementary learners to show algorithms only for specialized IT skills that could spoil the interest. In this paper for the elementary school students, through the four stages, 2015 revision curriculum analysis, creating of training program development operating plans, applying programs for the targeting students and analysis of results and evaluation, using Rich Picture technique which is various tools such as pictures and speech bubble symbols for the learners can express the intelligent CCTV algorithm freely and easily so they can understand fully about the algorithm of intelligent CCTV that uses artificial intelligence to extract faces from subjects. Suggest on this paper, the proposal of educational program can help the learner to grasp the principle of the algorithm by using the flowchart. As the result, Through the modification and development of the proposed program, we will conduct research on IT creative education that can be applied in various areas.

최근 개발자와 사용자 사이에서 게임의 인공지능에 대한 관심이 늘어나고 있다. 그래픽과 사운드 요소의 한계로 인 해 화려하고 웅장한 게임보다 다양한 재미를 줄 수 있는 게임을 원하기 때문이다. 기존의 게임 인공지능 기법은 단순 하여 쉽게 질리고, 사용자에게 다양한 재미를 지속적으로 제공하기 어렵다. 그러나 학습 능력을 갖춘 게임은 다양하고 예측하기 어려운 특성으로 인해 사용자에게 끝없는 재미를 제공할 수 있다. 본 논문에서는 이러한 학습 능력을 게임 내의 에이전트에게 부여하기 위해 심리학 이론 중 하나인 관찰학습 이론을 적용한 알고리즘을 제시하고자 한다.

유비쿼터스 기술이 발달하면서 모바일 기기를 통해 다양한 콘텐츠를 사용자에게 적합한 정보 만을 제공하기 위한 연구가 활발하게 진행되고 있다. 그러나 모바일 기기의 작은 사용자 인터페 이스로 인해 정보제공에 한계가 있다. 본 논문에서는 이런 문제점을 해결하고 모바일 환경에 적 합한 지능형 에이전트 모델과, 각 개인 사용자들이 관심 있는 일자리 정보를 능동적으로 제공할 수 있는 시스템을 제안한다. 사용자 행동패턴을 감시하는 Personalization Engine과, 모바일 기 기에 정보제공을 위한 Learning Algorithm 으로 구성되었다. 조사를 통해 성별, 나이, 학력 에 따라 선호하는 직업 항목이 다른 것을 알았으며, 지역은 직업을 검색 할 때 많은 영향을 주는 것으로 나타났다.

As ubiquitous technology develops, there are many studies to provide various contents proper to users through a mobile device. However, there is a limit of information provision due to a small user interface of a mobile device. This study proposes a system that can solve a problem and provide an intelligent agent model appropriate to a mobile environment and job information positively that an individual user is interested. It is composed of a personalization engine to monitor users' behavior patterns and a learning algorithm to provide information to a mobile device. Analysis shows that preferred job items are different by sex, age and education, while a region affects job searching significantly.

본 연구는 4차 산업혁명과 윤리규범을 위한 AI알고리즘 규제에 관한 연구로써, 국가행 정과 지방자치를 위한 지능정보화의 방향을 모색하였다. 본 연구는 인공지능 알고리즘에 대한 개념과 현상을 고찰하고, 인공지능에 대한 각국의 전략과 투자, 미국의 인공지능 윤 리원칙과 한국의 인공지능 윤리기준, EU의 인공지능 법안 등을 분석하였다. 본 연구는 4차 산업혁명과 인공지능을 둘러싼 문제로 효율성의 추구에 기인하는 (1) 인 간의 존엄성과 인권문제, (2) 인간의 실업과 생존문제, (3) 효율성과 윤리적 문제 등을 제 시하였다. 또한, 인공지능 알고리즘 규제를 위하여 (1) 인공지능 알고리즘에 대한 법적인 정의와 범위 설정, (2) 인공지능에 대한 기초적인 법률안 마련을 바탕으로, (3) 인공지능 알고리즘 규제와 특례에 대한 논의, (4) 인공지능에 의한 인위적인 의사결정 개입방지, (5) 빅데이터의 활용 혹은 정보유통과정에서 동의 없는 개인정보와 프라이버시 침해방지 등 을 제안한다. 이와 함께, 본 연구는 4차 산업혁명과 인공지능에 의해 유발되는 문제해결을 위해 (1) 새로운 윤리규범의 설정과 (2) 윤리규범의 설정을 위한 거버넌스의 구성, (3) 4차 산업혁 명과 인공지능에 대한 공적인 담론형성, (4) 수용성 확보를 위한 정책홍보와 정책참여의 활성화, (5) 보편적인 개인정보와 프라이버시 침해방지를 위한 강력한 규제법안에 대한 논의의 필요성 등을 제기하였다. 마지막으로, 국가행정과 지방자치의 방향성 설정을 위해 4차 산업혁명의 대응전략 추진을 (1) 중앙-광역-지방정부-기업-NGO-정책전문가집단-지 역주민 등이 협업하는 거버넌스 체계의 구성 및 정책참여의 필요성, (2) 각 참여자별 책 임성 소재를 명확하게 하는 제도적 장치의 설정과 준비, (3) 4차 산업혁명의 대응전략을 위한 다양한 담론조성의 필요성 등을 제시한다. 본 연구는 4차 산업혁명과 인공지능 알고 리즘을 둘러싼 문제들과 새로운 규범정립의 요구들로 4차 산업혁명과 인공지능의 문제에 대한 시사점을 도출하였다. 본 연구는 4차 산업혁명과 윤리규범을 위한 AI알고리즘 규제 의 필요성을 제기하고 연구를 종결하였다.

Performance of web query processing becomes slow caused by increasing number of data. In this paper, intelligent algorithm was created to fix this problem. Four main components involved in this intelligent algorithm are assigning initial query, exploit query, assign to any possible query and query matching. Firstly, web user is needed to enter a keyword then this keyword automatically will assign as an initial query. After that, this initial query must be exploited before assigning process to any possible queries. These possible queries will match to existing query form temporary file that contains data schema and map to only select data sources. In this methodology, XML will use for mapping to heterogeneous databases. XML is really effective for mapping to heterogeneous databases. This methodology has been implemented in a prototype and applied to web queries. Another issue in with web query is difficult to search for information that best reflects the user’s need information. According this problem, intelligent algorithm was created and tested by developing simple application based on system architecture. This intelligent algorithm that was good for fixed problems by improving web query processing for heterogeneous databases. The intelligent algorithm was implemented and tested for heterogeneous database environment.

As an important subject of image processing, image restoration is a kind of degeneration by establishing the mathematical model of reverse deduction arithmetic, and the image processing technology of the original image is obtained.Traditional image restoration algorithm by image dimension is low, the method of single factors such as limit, image restoration effect is limited.Combined with adaptive chaotic genetic algorithm, this paper proposes an improved image restoration intelligent algorithm.Through analysis and experiment comparison, the new algorithm can get better effect of image restoration.

The development of the Internet brought us into an era of big data information, give people bring convenient while and also make people ragged when choosing the required information and recommendation system arises at the historic moment, and get the wide attention and applications. Therefore, to enhance the traditional method, we propose a novel intelligent recommendation algorithm based on Web data mining technique under the background of the deep neural network. Firstly, we review the state-of-the-art web data mining algorithms and revise the traditional ones with the parallel data mining algorithm on the multiple processors to perform tasks that will enhance the accuracy and efficiency. Then, we analyze basic neural network model through the inner connection and weight transfer. Later, we introduce the deep network structure to enhance the traditional network. Finally, we combine the revised prior theories into the recommending tasks for enhancement. The experimental analysis show that our algorithm accuracy is enhanced by the extent of 56% and overall time is reduced to the 87% of traditional ones which proves the feasibility. Later, more optimization work will be introduced to modify the current methodology.

A hybrid intelligent optimization algorithm based on quantum particle swarm is presented to solve the problem that the local search ability of traditional SFLA is poor and converges very slowly. The particle is quantized and introduced chaos mechanism in the algorithm in order to enhance the global search ability, using the escape strategy, the group is divided into three clusters and mutation operation on the cluster within individuals, not only improves the convergence speed and ensure the performance of the algorithm. Experiments show that the improved algorithm has the characteristics of strong optimization capability and performance is improved greatly in whether comparison of the baseline function or analysis of universal database, compared with the other two algorithms have obvious advantages.

The resource scheduling imbalance is a multi-objective optimization problem in cloud computing environment, this paper introduced the particle swarm optimization algorithm in cloud computing, a simulated annealing ideas is proposed in view of the prematurity of the algorithm, on the premise of performance determination, the position of the particle is determined by the probability choice, which helps the particle to escape. In order to enhance the global searching ability of the particle, the algorithm is combined with the chaotic mechanism to improve the accuracy of the algorithm. The inertia weight is adjusted dynamically according to the current state of the particle, accordingly, at the same time to obtain the optimal solution to ensure the convergence. Analysis of the experimental results show that the improved algorithm has a significant improvement in the ability of optimization and convergence speed, compared with other algorithms, the benchmark functions comparison is better, the different resource task proportion spent the shortest time and load balancing is the highest.

Coverage algorithm is one of the core technologies required for intelligent robots such as cleaning robots, harvesting robots, painting robots and lawn mowing robots. Although many smart coverage algorithms have been proposed, to the best of our knowledge, all of them make the same assumption that they have sufficient time to cover the entire target area. However, the time to completely cover the whole target area may not always be available. Therefore, in this paper, we propose another new coverage scheme, which we call the DmaxCoverage algorithm that decides the coverage path by considering the deadline for coverage. This approach can be beneficial when the time for the coverage is not sufficient to cover the entire target area. Experimental results show that the DmaxCoverage algorithm outperforms previous algorithms for these situations.

Vehicular ad hoc network is an emerging new technology and a promising platform for the intelligent transportation system. The most important application of VANET is disseminating emergency messages to warn drivers in case of dangerous events. The core technique relies on the design of a broadcast scheme. In this paper, we propose a hybrid intelligent broadcast algorithm for alert message dissemination in VANETs that is called Hi-CAST. To deliver alert message effectively, the proposed Hi-CAST algorithm uses delay and probabilistic broadcast protocols together with token protocol. The performance of the Hi-CAST is evaluated through simulation and compared with that of other alert message dissemination algorithms.

With the development of electronic commerce, the management mode of enterprises has been changed, E-business enterprises will also create new financial model, suitable for electronic commerce situation. In this paper, the author first put forward the data mining method based on SVM algorithm. Based on the empirical analysis, author research on the influence factors of e-commerce enterprise financial management mode, and makes a detailed analysis of the relationship between the environment, the network and the performance. For the electronic business enterprise, the solvency, development potential, innovation ability and adapt to the environment of the organization flexibility is the important index of E-enterprise performance evaluation index system.

There’re huge numbers of users and various tasks need to be handled in the cloud computing environment, the high effective task scheduling algorithm is one of the crucial problems that the cloud computing need to solve. Aiming to the model structure of cloud computing, in this article it introduces the Particle Swarm Optimization algorithm (PSO) and Ant Colony Optimization algorithm (ACO) to combine with optimized task scheduling algorithm. First it takes the particle swarm optimization algorithm to generate the initial scheduling results, and introduces the random inertia weight to improve the scheduling ability of the algorithm, then to take the generated results of improved particle swarm optimization algorithm as the initial pheromones of the ant colony algorithm to find out the optimal scheduling scheme, and use the elitist strategy and crossover operator in the genetic algorithm to improve the ant colony algorithm, among the algorithms to use multistage optimization algorithm to improve the operating efficiency. The experimental results show that under the same conditions, the total task completion time of improved algorithm has been reduced and its performance advantage are getting more obvious with the increased task measures.

The parameters’ adjustment of Control System is very complicated. Such as, the adjustment of voltage, temperature and liquid level, they have the characteristic of non-linear and mutation. The traditional PID control algorithm has the defect of overstrike and the low accuracy of adjustment, in order to improve the control performance of Control System, we proposed an improved intelligent PID algorithm for Control System parameters’ adjustment. First, we encode the three parameters of PID to a firefly position vector; then, find the optimal PID parameters by simulating the firefly population's food forage and mating behavior; last, adjusted the parameters of PID to intelligent control the Control System. We also using MATLAB toolbox to simulate the proposed algorithm, and give a group of contrast experiments about two control systems, the voltage adjustment and liquid level adjustment. The experiments' results show that contrast to the traditional PID parameters’ optimization algorithm, our improved algorithm can quick adjust the Control System along with less overshoot, the response time is faster and the system is more robust.