• Journal of Information Processing Systems
• /
• v.18 no.1
• /
• pp.12-25
• /
• 2022

In recent years, deep convolutional neural networks have made significant progress in the research of single image super-resolution. However, it is difficult to be applied in practical computing terminals or embedded devices due to a large number of parameters and computational effort. To balance these problems, we propose CSRNet, a lightweight neural network based on channel split residual learning structure, to reconstruct highresolution images from low-resolution images. Lightweight refers to designing a neural network with fewer parameters and a simplified structure for lower memory consumption and faster inference speed. At the same time, it is ensured that the performance of recovering high-resolution images is not degraded. In CSRNet, we reduce the parameters and computation by channel split residual learning. Simultaneously, we propose a double-upsampling network structure to improve the performance of the lightweight super-resolution network and make it easy to train. Finally, we propose a new evaluation metric for the lightweight approaches named 100_FPS. Experiments show that our proposed CSRNet not only speeds up the inference of the neural network and reduces memory consumption, but also performs well on single image super-resolution.

• Electronics and Telecommunications Trends
• /
• v.37 no.6
• /
• pp.32-42
• /
• 2022

Recently, decentralized approaches to artificial intelligence (AI) development, such as federated learning are drawing attention as AI development's cost and time inefficiency increase due to explosive data growth and rapid environmental changes. Collaborative AI technology that dynamically organizes collaborative groups between different agents to share data, knowledge, and experience and uses distributed resources to derive enhanced knowledge and analysis models through collaborative learning to solve given problems is an alternative to centralized AI. This article investigates and analyzes recent technologies and applications applicable to the research of multi-agent collaboration of AI bots, which can provide collaborative AI functionality autonomously.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.539-541
• /
• 2023

COVID-19 is a viral pandemic disease that spreads widely all around the world. The only way to identify COVID-19 patients at an early stage is to stop the spread of the virus. Different approaches are used to diagnose, such as RT-PCR, Chest X-rays, and CT images. However, these are time-consuming and require a specialized lab. Therefore, there is a need to develop a time-efficient diagnosis method to detect COVID-19 patients. The proposed machine learning (ML) approach predicts the presence of coronavirus based on clinical symptoms. The clinical dataset is collected from the Israeli Ministry of Health. We used different ML classifiers (i.e., XGB, DT, RF, and NB) to diagnose COVID-19. Later, classifiers are optimized with the Bayesian hyperparameter optimization approach to improve the performance. The optimized RF outperformed the others and achieved an accuracy of 97.62% on the testing data that help the early diagnosis of COVID-19 patients.

• KIISE Transactions on Computing Practices
• /
• v.23 no.4
• /
• pp.244-249
• /
• 2017

Steganalysis is to detect information hidden by steganography inside general data such as images. There are stegoanalysis techniques that use machine learning (ML). Existing ML approaches to steganalysis are based on extracting features from stego images and modeling them. Recently deep learning-based methodologies have shown significant improvements in detection accuracy. However, all the existing methods, including deep learning-based ones, have a critical limitation in that they can only detect stego images that are created by a specific steganography method. In this paper, we propose a generalized steganalysis method that can model multiple types of stego images using deep learning. Through various experiments, we confirm the effectiveness of our approach and envision directions for future research. In particular, we show that our method can detect each type of steganography with the same level of accuracy as that of a steganalysis method dedicated to that type of steganography, thereby demonstrating the general applicability of our approach to multiple types of stego images.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.12
• /
• pp.321-332
• /
• 2020

Decentralized approaches are extensively researched by academia and industry in order to cover up the flaws of existing systems in terms of data privacy. Blockchain and decentralized learning are prominent representatives of a deconcentrated approach. Blockchain is secure by design since the data record is irrevocable, tamper-resistant, consensus-based decision making, and inexpensive of overall transactions. On the other hand, decentralized learning empowers a number of devices collectively in improving a deep learning model without exposing the dataset publicly. To motivate participants to use their resources in building models, a decent and proportional incentive system is a necessity. A centralized incentive mechanism is likely inconvenient to be adopted in decentralized learning since it relies on the middleman that still suffers from bottleneck issues. Therefore, we design an incentive model for decentralized learning applications by leveraging the Ethereum smart contract. The simulation results satisfy the design goals. We also outline the concerns in implementing the presented scheme for sensitive data regarding privacy and data leakage.

• English Language & Literature Teaching
• /
• v.13 no.1
• /
• pp.181-210
• /
• 2007

This study is to suggest systematic and effective reading comprehension techniques or strategies to be used in EFL reading classes. According to the definition of reading and reading process, six essential elements of reading comprehension are categorized: 1) reading speed; 2) skimming and scanning; 3) logical organization; 4) pleasure reading; 5) vocabulary; 6) cultural background and world knowledge. To present a more effective teaching and learning approach to EFL reading comprehension than ever, an experiment was performed. The hypothesis of the experimental study was that there would be a difference in students' reading speed as well as reading comprehension and vocabulary between an experimental group and a control group depending upon the teaching approaches (experimental vs. traditional). The result of the study indicates that the experimental teaching approach which intensifies speed reading and pleasure reading techniques as well as 4 other essential techniques of reading comprehension is more effective than the traditional one in teaching and learning reading comprehension.

• International Journal of Advanced Culture Technology
• /
• v.7 no.4
• /
• pp.283-288
• /
• 2019

Neural networks have been reborn as a Deep Learning thanks to big data, improved processor, and some modification of training methods. Neural networks used to initialize weights in a stupid way, and to choose wrong type activation functions of non-linearity. Weight initialization contributes as a significant factor on the final quality of a network as well as its convergence rate. This paper discusses different approaches to weight initialization. MNIST dataset is used for experiments for comparing their results to find out the best technique that can be employed to achieve higher accuracy in relatively lower duration.

• Korean Medical Education Review
• /
• v.19 no.3
• /
• pp.158-168
• /
• 2017

There is a more urgent call for educational methods of machine learning in medical education, and therefore, new approaches of teaching and researching machine learning in medicine are needed. This paper presents a case using machine learning through text analysis. Topic modeling of news articles with the keyword 'asbestos' were examined. Two hypotheses were tested using this method, and the process of machine learning of texts is illustrated through this example. Using an automated text analysis method, all the news articles published from January 1, 1990 to November 15, 2016 in South Korea which included 'asbestos' in the title and the body were collected by web scraping. Differences in topics were analyzed by structured topic modelling (STM) and compared by press companies and periods. More articles were found in liberal media outlets. Differences were found in the number and types of topics in the articles according to the partisanship and period. STM showed that the conservative press views asbestos as a personal problem, while the progressive press views asbestos as a social problem. A divergence in the perspective for emphasizing the issues of asbestos between the conservative press and progressive press was also found. Social perspective influences the main topics of news stories. Thus, the patients' uneasiness and pain are not presented by both sources of media. In addition, topics differ between news media sources based on partisanship, and therefore cause divergence in readers' framing. The method of text analysis and its strengths and weaknesses are explained, and an application for the teaching and researching of machine learning in medical education using the methodology of text analysis is considered. An educational method of machine learning in medical education is urgent for future generations.

• Journal of Advanced Marine Engineering and Technology
• /
• v.38 no.10
• /
• pp.1281-1286
• /
• 2014

This paper presents an iterative learning control (ILC) approach for tracking problems with specified data points that are desired points at certain time instants. To design ILC systems for such problems, unlike traditional ILC approaches, an algorithm which updates not only the control signal but also the reference trajectory at each trial will be developed. The relationship between the reference trajectory and ILC control in tracking problems where there are specified data points through which the system should pass is investigated as the rate of convergence. In traditional ILC, the desired data is stored in a tracking profile file. Due to the huge size of the data file containing the target points, it is important to reduce the computational cost. Finally, simulation results of the presented technique are mentioned and compared to other related works to confirm the effectiveness of proposed scheme.

• Research in Mathematical Education
• /
• v.9 no.1 s.21
• /
• pp.47-58
• /
• 2005

Although student-centered teaching practices have been advocated in mathematics education reform, implementing them at the classroom level remains challenging. This exploratory case study examined two unevenly successful student-centered approaches to see how teachers understand and characterize reform, and to articulate issues in implementing reform ideas. The comparison and contrast between the classrooms showed similar classroom social norms but dramatically different mathematical practices. This affords the possibility of exploring the challenges of reform for teachers and other personnel who are attempting to move teaching practices towards the student-centered ideals.