• Journal of Information Science Theory and Practice
• /
• v.1 no.1
• /
• pp.10-26
• /
• 2013

Domain transfer is a widely recognized problem for machine learning algorithms because models built upon one data domain generally do not perform well in another data domain. This is especially a challenge for tasks such as opinion classification, which often has to deal with insufficient quantities of labeled data. This study investigates the feasibility of self-training in dealing with the domain transfer problem in opinion classification via leveraging labeled data in non-target data domain(s) and unlabeled data in the target-domain. Specifically, self-training is evaluated for effectiveness in sparse data situations and feasibility for domain adaptation in opinion classification. Three types of Web content are tested: edited news articles, semi-structured movie reviews, and the informal and unstructured content of the blogosphere. Findings of this study suggest that, when there are limited labeled data, self-training is a promising approach for opinion classification, although the contributions vary across data domains. Significant improvement was demonstrated for the most challenging data domain-the blogosphere-when a domain transfer-based self-training strategy was implemented.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.4
• /
• pp.474-484
• /
• 2024

Reinforcement learning, which are also studied in the field of defense, face the problem of sample efficiency, which requires a large amount of data to train. Transfer learning has been introduced to address this problem, but its effectiveness is sometimes marginal because the model does not effectively leverage prior knowledge. In this study, we propose a stochastic initial state randomization(SISR) method to enable robust knowledge transfer that promote generalized and sufficient knowledge transfer. We developed a simulation environment involving a cooperative robot transportation task. Experimental results show that successful tasks are achieved when SISR is applied, while tasks fail when SISR is not applied. We also analyzed how the amount of state information collected by the agents changes with the application of SISR.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.8
• /
• pp.2944-2958
• /
• 2021

Today, online education is becoming more important. The effectiveness of online education has been measured by student satisfaction and the possibility of substituting offline education. This study proposes a plan to increase the effectiveness of education in a new form by using online information. Education is the process of socializing and growing learners. Representative negative emotions experienced by learners are stress, anxiety, and depression (SAD). A reduction in SAD will promote student growth and improve educational outcomes. This paper considers online information by dividing it into online educational information support (OEDIS) and online emotional information support (OEMIS). We demonstrate that OEDIS reduces SAD, and OEMIS reduces stress and anxiety. By providing online information, negative emotions can be reduced, and educational outcomes can be improved. This study suggests a new role for online information support, such as emotional change in individuals and solving psychological problems. Online information support goes beyond knowledge transfer and can be used in various fields, such as online education that promotes human growth and positive change, and even healthcare.

• Journal of Internet Computing and Services
• /
• v.21 no.5
• /
• pp.57-65
• /
• 2020

At present, the existing virus recognition systems usually use signature approach to detect malicious executable files, but these methods often fail to detect new and invisible malware. At the same time, some methods try to use more general features to detect malware, and achieve some success. Moreover, machine learning-based approaches are applied to detect malware, which depend on features extracted from malicious codes. However, the different distribution of features oftraining and testing datasets also impacts the effectiveness of the detection models. And the generation oflabeled datasets need to spend a significant amount time, which degrades the performance of the learning method. In this paper, we use transfer learning to detect new and previously unseen malware. We first extract the features of Portable Executable (PE) files, then combine transfer learning training model with KNN approachto detect the new and unseen malware. We also evaluate the detection performance of a classifier in terms of precision, recall, F1, and so on. The experimental results demonstrate that proposed method with high detection rates andcan be anticipated to carry out as well in the real-world environment.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.12
• /
• pp.1138-1144
• /
• 2013

This paper proposes a tactile transfer and display method between a data glove and vibration motors module. The data glove is developed to capture the hand postures and to measure the grip forces. The measured data are simplified with the proposed 5-bit transfer and display algorithm, and the vibration motors module is developed to display the measured hand posture and grip force to the operator. The proposed 5-bit algorithm contains both an 8-step hand posture and 4-step grip force level information for tactile transfer to the vibration motors module. Also, the effectiveness of the proposed method is shown through several experiments.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.9
• /
• pp.70-79
• /
• 1996

Block data transfer poses a serious problem is a pipelined bus where each data transfer step is pipelined. In this paper, we describe the design and implementation of a variable data block transfer protocol for a pipelined bus of a shared-memory multiprocessor. The proposed method maintains compatibility with the existing protocol for the pipelined bus and ensures fairness and effectiveness by preventing starvation. We present flow charts of requester and responder during a block transfer in the pipelined bus that uses the proposed protocol. The proposed protocol was implemented for the TICOM-III HiPi+Bus.

• Journal of Photoscience
• /
• v.9 no.3
• /
• pp.37-40
• /
• 2002

Astronauts are constantly exposed to space radiation at a low-dose rate during long-tenn stays in space. Therefore, it is important to determine correctly the biological effects of space radiation on human health. Space radiations contain various kinds of different energy particles, especially high linear energy transfer (LET) particles. Therefore, we have to study the relative biological effectiveness (RBE) of space radiation under microgravity environment which may change RBE from a stress for cells. Furthermore, the research about space radiation might give us useful information about birth and evolution of life on the earth. We also can realize the importance of preventing the ozone layer from depletion by use of exposure equipment to sunlight at International Space Station (ISS).

• Journal of Information Processing Systems
• /
• v.20 no.2
• /
• pp.149-158
• /
• 2024

Traditional manual identification of crop leaf diseases is challenging. Owing to the limitations in manpower and resources, it is challenging to explore crop diseases on a large scale. The emergence of artificial intelligence technologies, particularly the extensive application of deep learning technologies, is expected to overcome these challenges and greatly improve the accuracy and efficiency of crop disease identification. Crop leaf disease identification models have been designed and trained using large-scale training data, enabling them to predict different categories of diseases from unlabeled crop leaves. However, these models, which possess strong feature representation capabilities, require substantial training data, and there is often a shortage of such datasets in practical farming scenarios. To address this issue and improve the feature learning abilities of models, this study proposes a deep transfer learning adaptation strategy. The novel proposed method aims to transfer the weights and parameters from pre-trained models in similar large-scale training datasets, such as ImageNet. ImageNet pre-trained weights are adopted and fine-tuned with the features of crop leaf diseases to improve prediction ability. In this study, we collected 16,060 crop leaf disease images, spanning 12 categories, for training. The experimental results demonstrate that an impressive accuracy of 98% is achieved using the proposed method on the transferred ResNet-50 model, thereby confirming the effectiveness of our transfer learning approach.

• Proceedings of the KIEE Conference
• /
• 2006.04a
• /
• pp.333-335
• /
• 2006

In this page, we developed the inspection system for automobile parts using the laser vision sensor. Laser vision sensor has gotten 2 dimensions information and third dimension information of laser vision camera using the vision camera. Used JIG and ROBOT for inspection position transfer. Also, computer integration system developed that control system component pal1s and manage data measurement information. Compare sensor measurement result with CAD Data and verified measurement result effectiveness taking advantage of CAD to get information of measurement object.

• Journal of Korean Institute of Industrial Engineers
• /
• v.27 no.2
• /
• pp.140-149
• /
• 2001

The paper discusses the problem of finding the Origin-Destination(O-D) shortest paths in internodal transportation networks with time-schedule constraints. The shortest path problem on the internodal transportation network is concerned with finding a path with minimum distance, time, or cost from an origin to a destination using all possible transportation modalities. The time-schedule constraint requires that the departure time to travel from a transfer station to another node takes place only at one of pre-specified departure times. The scheduled departure times at the transfer station are the times when the passengers are allowed to leave the station to another node using the relative transportation modality. Therefore, the total time of a path in an internodal transportation network subject to time-schedule constraints includes traveling time and transfer waiting time. In this paper, a genetic algorithm (GA) approach is developed to deal with this problem. The effectiveness of the GA approach is evaluated using several test problems.