• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.1989-2011
• /
• 2019

Vehicle detection based on aerial images is an interesting and challenging research topic. Most of the traditional vehicle detection methods are based on the sliding window search algorithm, but these methods are not sufficient for the extraction of object features, and accompanied with heavy computational costs. Recent studies have shown that convolutional neural network algorithm has made a significant progress in computer vision, especially Faster R-CNN. However, this algorithm mainly detects objects in natural scenes, it is not suitable for detecting small object in aerial view. In this paper, an accurate and effective vehicle detection algorithm based on Faster R-CNN is proposed. Our method fuse a hyperactive feature map network with Eltwise model and Concat model, which is more conducive to the extraction of small object features. Moreover, setting suitable anchor boxes based on the size of the object is used in our model, which also effectively improves the performance of the detection. We evaluate the detection performance of our method on the Munich dataset and our collected dataset, with improvements in accuracy and effectivity compared with other methods. Our model achieves 82.2% in recall rate and 90.2% accuracy rate on Munich dataset, which has increased by 2.5 and 1.3 percentage points respectively over the state-of-the-art methods.

• International Journal of Advanced Culture Technology
• /
• 제8권3호
• /
• pp.186-191
• /
• 2020

Artificial Intelligence (AI) technology is used in a variety of fields because it can make inferences and plans through learning processes. In the field of coding technologies, AI has been introduced as a tool for personalized and customized education to provide new educational environments. Also, it can be used as a virtual assistant in coding operations for easier and more efficient coding. Currently, as coding education becomes mandatory around the world, students' interest in programming is heightened. The purpose of coding education is to develop the ability to solve problems and fuse different academic fields through computational thinking and creative thinking to cultivate talented persons who can adapt well to the Fourth Industrial Revolution era. However, new non-computer science major students who take software-related subjects as compulsory liberal arts subjects at university came to experience many difficulties in these subjects, which they are experiencing for the first time. AI based coding technologies can be used to solve their difficulties and to increase the learning effect of non-computer majors who come across software for the first time. Therefore, this study examines the current state of AI based coding technologies and suggests the direction of future coding education.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권3호
• /
• pp.1111-1130
• /
• 2016

Cooperative communications can significantly improve the wireless transmission performance with the help of relay nodes. In cooperative communication networks, relay selection and power allocation are two key issues. In this paper, we propose a relay selection and power allocation scheme RS-PA-PSACO (Relay Selection-Power Allocation-Particle Swarm Ant Colony Optimization) based on PSACO (Particle Swarm Ant Colony Optimization) algorithm. This scheme can effectively reduce the computational complexity and select the optimal relay nodes. As one of the swarm intelligence algorithms, PSACO which combined both PSO (Particle Swarm Optimization) and ACO (Ant Colony Optimization) algorithms is effective to solve non-linear optimization problems through a fast global search at a low cost. The proposed RS-PA-PSACO algorithm can simultaneously obtain the optimal solutions of relay selection and power allocation to minimize the SER (Symbol Error Rate) with a fixed total power constraint both in AF (Amplify and Forward) and DF (Decode and Forward) modes. Simulation results show that the proposed scheme improves the system performance significantly both in reliability and power efficiency at a low complexity.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2023년도 학술발표회
• /
• pp.95-95
• /
• 2023

Common hydrological problems of developing countries include poor data management, insufficient measuring devices and ungauged watersheds, leading to small or unreliable data availability. This has greatly affected the adoption of artificial intelligence techniques for flood risk mitigation and damage control in several developing countries. While climate datasets have recorded resounding applications, but they exhibit more uncertainties than ground-based measurements. To encourage AI adoption in developing countries with small ground-based dataset, we propose data augmentation for regression tasks and compare performance evaluation of different AI models with and without data augmentation. More focus is placed on simple models that offer lesser computational cost and higher accuracy than deeper models that train longer and consume computer resources, which may be insufficient in developing countries. To implement this approach, we modelled and predicted streamflow data of the Asa River Watershed located in Ilorin, Kwara State Nigeria. Results revealed that adequate hyperparameter tuning and proper model selection improve streamflow prediction on small water dataset. This approach can be implemented in data-scarce regions to ensure timely flood intervention and early warning systems are adopted in developing countries.

• Journal of information and communication convergence engineering
• /
• 제21권2호
• /
• pp.117-129
• /
• 2023

High-utility itemset mining (HIUM) has emerged as a key data-mining paradigm for object-of-interest identification and recommendation systems that serve as frequent itemset identification tools, product or service recommendation systems, etc. Recently, it has gained widespread attention owing to its increasing role in business intelligence, top-N recommendation, and other enterprise solutions. Despite the increasing significance and the inability to provide swift and more accurate predictions, most at-hand solutions, including frequent itemset mining, HUIM, and high average- and fast high-utility itemset mining, are limited to coping with real-time enterprise demands. Moreover, complex computations and high memory exhaustion limit their scalability as enterprise solutions. To address these limitations, this study proposes a model to extract high-utility frequent closed itemsets based on an improved cumulative summary list structure (CSLFC-HUIM) to reduce an optimal set of candidate items in the search space. Moreover, it employs the lift score as the minimum threshold, called the cumulative utility threshold, to prune the search space optimal set of itemsets in a nested-list structure that improves computational time, costs, and memory exhaustion. Simulations over different datasets revealed that the proposed CSLFC-HUIM model outperforms other existing methods, such as closed- and frequent closed-HUIM variants, in terms of execution time and memory consumption, making it suitable for different mined items and allied intelligence of business goals.

• International Journal of Computer Science & Network Security
• /
• 제23권10호
• /
• pp.49-56
• /
• 2023

Computer architecture serves as a link between application requirements and underlying technology capabilities such as technical, mathematical, medical, and business applications' computational and storage demands are constantly increasing. Machine learning these days grown and used in many fields and it performed better than traditional computing in applications that need to be implemented by using mathematical algorithms. A mathematical algorithm requires more extensive and quicker calculations, higher computer architecture specification, and takes longer execution time. Therefore, there is a need to improve the use of computer hardware such as CPU, memory, etc. optimization has a main role to reduce the execution time and improve the utilization of computer recourses. And for the importance of execution time in implementing machine learning supervised module linear regression, in this paper we focus on optimizing machine learning algorithms, for this purpose we write a (Diabetes prediction program) and applying on it a Practical Swarm Optimization (PSO) to reduce the execution time and improve the utilization of computer resources. Finally, a massive improvement in execution time were observed.

• 산업융합연구
• /
• 제20권2호
• /
• pp.29-36
• /
• 2022

디지털 사회를 위한 AI와 빅데이터 시대의 컴퓨팅 사고는 컴퓨터가 실행할 수 있는 방식으로 우리가 해결하고자 하는 문제와 솔루션을 표현하는 일련의 문제해결 방법을 의미한다. 컴퓨팅 사고는 컴퓨터 과학의 기본 개념을 도출함으로써 문제를 해결하고 시스템을 설계하고 인간의 행동을 이해하는 것으로, 학생들에게는 어려운 문제와 애매한 퍼즐을 맞추는 접근법이다. 본 논문에서 우리는 컴퓨팅 사고를 댄스 동작과 융합하여 학생들이 문제를 해결할 수 있는 수업 모델을 개발하였다. 개발된 수업 모델을 가지고 ◯◯대학교 1학년 예비교원 93명을 대상으로 1학기 동안 수업한 결과, 수업 참가자들은 비디오 수준의 만족스러운 알고리즘을 만들어 냈다. 또한, 제안된 모델이 수업 참여 학생들의 컴퓨팅 사고 이해에 크게 기여함을 알 수 있었다.

• 한국CDE학회논문집
• /
• 제5권2호
• /
• pp.127-135
• /
• 2000

Emergent computing paradigms such as genetic algorithms have found increased use in problems in engineering design. These computational tools have been shown to be applicable in the solution of generically difficult design optimization problems characterized by nonconvexities in the design space and the presence of discrete and integer design variables. Another aspect of these computational paradigms that have been lumped under the bread subject category of soft computing, is the domain of artificial intelligence, knowledge-based expert system, and machine learning. The paper explores a machine learning paradigm referred to as teaming classifier systems to construct the high-quality global function approximations between the design variables and a response function for subsequent use in design optimization. A classifier system is a machine teaming system which learns syntactically simple string rules, called classifiers for guiding the system's performance in an arbitrary environment. The capability of a learning classifier system facilitates the adaptive selection of the optimal number of training data according to the noise and multimodality in the design space of interest. The present study used the polynomial based response surface as global function approximation tools and showed its effectiveness in the improvement on the approximation performance.

• Computers and Concrete
• /
• 제12권3호
• /
• pp.243-259
• /
• 2013

Recent developments in Artificial Intelligence (AI) and computational intelligence have made it viable in the construction industry and structural analysis. This study usesthe Adaptive Network-based Fuzzy Inference System (ANFIS) as a modelling tool to predict the strain in tie section for High Strength Self Compacting Concrete (HSSCC) deep beams. 3773 experimental data were collected. The input data andits corresponding strains in tie section as output data were recorded at all loading stages. Results from ANFIS are compared with the classical linear regression (LR). The comparison shows that the ANFIS's results are highly accurate, precise and satisfactory.

• KIEAE Journal
• /
• 제3권2호
• /
• pp.25-32
• /
• 2003

This study deals with the investigation of recognition structure on architectural environment and reconstruction of it by artificial intelligence. To test the possibility of the reconstruction, recognition structure on architectural environment is analysed and each steps of the structure are matched with computational methods. Edge Detection and Neural Network were selected as matching methods to each steps of recognition process. Visual perception system established by selected methods is trained and tested, and the result of the system is compared with that of experiment of human. Assuming that the artificial system resembles the process of human recognition on architectural environment, does the system give similar response of human? The result shows that it is possible to establish artificial visual perception system giving similar response with that of human when it models after the recognition structure and process of human.