• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권3호
• /
• pp.958-979
• /
• 2023

Due to laws, regulations, privacy, etc., between 70-90 percent of providers do not share medical data, forming a "data island". It is essential to collaborate across multiple institutions without sharing patient data. Most existing methods adopt distributed learning and centralized federal architecture to solve this problem, but there are problems of resource heterogeneity and data heterogeneity in the practical application process. This paper proposes a collaborative deep learning modelling method based on the blockchain network. The training process uses encryption parameters to replace the original remote source data transmission to protect privacy. Hyperledger Fabric blockchain is adopted to realize that the parties are not restricted by the third-party authoritative verification end. To a certain extent, the distrust and single point of failure caused by the centralized system are avoided. The aggregation algorithm uses the FedProx algorithm to solve the problem of device heterogeneity and data heterogeneity. The experiments show that the maximum improvement of segmentation accuracy in the collaborative training mode proposed in this paper is 11.179% compared to local training. In the sequential training mode, the average accuracy improvement is greater than 7%. In the parallel training mode, the average accuracy improvement is greater than 8%. The experimental results show that the model proposed in this paper can solve the current problem of centralized modelling of multicenter data. In particular, it provides ideas to solve privacy protection and break "data silos", and protects all data.

• International Journal of Quality Innovation
• /
• 제4권1호
• /
• pp.131-147
• /
• 2003

This paper considers that a public department under specialized TQM manpower constraints have to implement multiple total quality management (TQM) policies to promote its service performance (fundamental goal) by adopting a centralized sequential advancement strategy (CSAS). Under CSAS, the decision-makers (DMs) start off by focusing specialized TQM manpower on a single policy, then transfer the specialized TQM manpower to the next policy when the first policy reaches the predetermined implementation time limit (in terms of education and training). Suppose that each TQM policy has a different desirous education and training goal. When the desirous goals for all TQM policies are achieved, we say that the fundamental goal will be satisfied. Within the limitation of total implementation period of time for all policies, assume the desirous goals for all TQM policies cannot be achieved completely. Under this premise, the optimal implementation sequence for all TQM policies must be calculated to maximize the weighted achievement of the desirous goal. We call this optimization problem a TQM case of "centralized sequential decision-making problem (CSDMP)". The achievement of the desirous goal for each TQM policy is usually affected by the experience in prior implemented policies, which makes solving CSDMP quite difficult. As a result, this paper introduces the concepts of sequential effectiveness and path effectiveness. The structural properties are then studied to propose theoretical methods for solving CSDMP. Finally, a numerical example is proposed to demonstrate CSDMP′s usability.

• 현장농수산연구지
• /
• 제10권1호
• /
• pp.137-151
• /
• 2008

This research was conducted to suggest a policy plan for intensive major course in recurrent education system of KNAC. A survey was answered by students, graduates, field professors and (full-time) professors. The results are summarized as follows; 1. In the item of educational operation system, there were some differences in preference among 4 examinee groups. Students preferred 'semester system', graduates and field professors did 'once per week system', and professors 'cyber+centralized training system'. 2. As entering time, students and graduates preferred 'immediately after graduation'. However, field and full-time professors preferred '1 to 3 years after graduation' that became reality. 3. As board and lodging, all examinee groups wanted 'dormitory in college'. Students and graduates were open to pay educational expenses as a level of national colleges. 4. As a curriculum, the most preferred subject by all groups was 'major field technique', which was followed by 'marketing/sale' and 'farm management' in the order of preference.

• 융합보안논문지
• /
• 제15권1호
• /
• pp.49-57
• /
• 2015

자본주의 사회가 본격화 되면서 개인의 이익실현을 위해 거짓이 날로 증가하고 있다. 이러한 거짓을 판별해 내기 위하여 오래전부터 연구를 거듭해온 결과 오늘날의 거짓말탐지기가 생겨나게 된 계기라고 본다. 우리나라에서 거짓말탐지기는 현재 수사기관에서 적극적으로 사용하고 있으며, 소극적으로는 수사기관에서 거짓말탐지기 검사관으로 재직하셨던 분이 퇴직 후 사설업체를 차려 거짓말탐지기 검사를 하고 있다. 각 수사기관에서는 엄격한 자격조건과 양성교육을 거쳐 거짓말탐지기 검사관으로 채용하고 있다. 거짓말탐지기 검사결과에 대한 대법원 판례의 판시사항으로는 검사장비의 성능, 질문방법, 검사관의 자질 등 신뢰도에 있어 증거능력을 부인하고 있다. 판례에서 언급한 문제점의 가장 근본적인 원인은 각 수사기관의 검사관들이 일원화된 교육이 아닌 이원화된 교육을 받고 있다는 것이다. 따라서 각 수사기관에서 자체적으로 교육을 이수하고 검사관으로 활동하고 있는 실정으로 검사기관마다 또는 검사관마다 편차가 발생할 수 있다고 사료되어 일원화된 교육시스템 확보가 필요하다고 본다. 이와 같이 일원화된 교육시스템이 확보된다면 거짓말탐지기 검사결과의 신뢰도 향상 및 각 수사기관의 검사관 양성에 따른 교육예산 절감효과에 기여할 수 있을 것이다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권2호
• /
• pp.742-756
• /
• 2022

A flood of information has occurred with the rise of the internet and digital devices in the fourth industrial revolution era. Every millisecond, massive amounts of structured and unstructured data are generated; smartphones, wearable devices, sensors, and self-driving cars are just a few examples of devices that currently generate massive amounts of data in our daily. Machine learning has been considered an approach to support and recognize patterns in data in many areas to provide a convenient way to other sectors, including the healthcare sector, government sector, banks, military sector, and more. However, the conventional machine learning model requires the data owner to upload their information to train the model in one central location to perform the model training. This classical model has caused data owners to worry about the risks of transferring private information because traditional machine learning is required to push their data to the cloud to process the model training. Furthermore, the training of machine learning and deep learning models requires massive computing resources. Thus, many researchers have jumped to a new model known as "Federated Learning". Federated learning is emerging to train Artificial Intelligence models over distributed clients, and it provides secure privacy information to the data owner. Hence, this paper implements Federated Averaging with a Deep Neural Network to classify the handwriting image and protect the sensitive data. Moreover, we compare the centralized machine learning model with federated averaging. The result shows the centralized machine learning model outperforms federated learning in terms of accuracy, but this classical model produces another risk, like privacy concern, due to the data being stored in the data center. The MNIST dataset was used in this experiment.

• 전자통신동향분석
• /
• 제38권4호
• /
• pp.95-103
• /
• 2023

The importance of the decentralized training with decentralized execution (DTDE) framework is well-known in the study of multiagent reinforcement learning. In many real-world environments, agents cannot share information. Hence, they must be trained in a decentralized manner. However, the DTDE framework has been less studied than the centralized training with decentralized execution framework. One of the main reasons is that many problems arise when training agents in a decentralized manner. For example, DTDE algorithms are often computationally demanding or can encounter problems with non-stationarity. Another reason is the lack of simulation environments that can properly handle the DTDE framework. We discuss current research trends in the DTDE framework.

• International Journal of Internet, Broadcasting and Communication
• /
• 제16권2호
• /
• pp.161-168
• /
• 2024

As the size of big data models grows, distributed training is emerging as an essential element for large-scale machine learning tasks. In this paper, we propose ParamHub for distributed data training. During the training process, this agent utilizes the provided data to adjust various conditions of the model's parameters, such as the model structure, learning algorithm, hyperparameters, and bias, aiming to minimize the error between the model's predictions and the actual values. Furthermore, it operates autonomously, collecting and updating data in a distributed environment, thereby reducing the burden of load balancing that occurs in a centralized system. And Through communication between agents, resource management and learning processes can be coordinated, enabling efficient management of distributed data and resources. This approach enhances the scalability and stability of distributed machine learning systems while providing flexibility to be applied in various learning environments.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 춘계학술발표대회
• /
• pp.264-267
• /
• 2022

Recently, federated learning (FL) has increased prominence as a viable approach for enhancing user privacy and data security by allowing collaborative multi-party model learning without exchanging sensitive data. Despite this, most present FL systems still depend on a centralized aggregator to generate a global model by gathering all submitted models from users, which could expose user privacy and the risk of various threats from malicious users. To solve these issues, we suggested a safe FL framework that employs differential privacy to counter membership inference attacks during the collaborative FL model training process and empowers blockchain to replace the centralized aggregator server.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.151-153
• /
• 2023

Federated learning (FL)-based network intrusion detection techniques have enormous potential for securing the Industrial Internet of Things (IIoT) cybersecurity. The openness and connection of systems in smart industrial facilities can be targeted and manipulated by malicious actors, which emphasizes the significance of cybersecurity. The conventional centralized technique's drawbacks, including excessive latency, a congested network, and privacy leaks, are all addressed by the FL method. In addition, the rich data enables the training of models while combining private data from numerous participants. This research aims to create an FL-based architecture to improve cybersecurity and intrusion detection in IoT networks. In order to assess the effectiveness of the suggested approach, we have utilized well-known cybersecurity datasets along with centralized and federated machine learning models.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2016년도 춘계학술대회
• /
• pp.284-285
• /
• 2016

본 논문에서는 사용자의 실시간 뇌파를 계측 및 집중력 지표를 반영하여 집중력 훈련이 가능한 게임 형 콘텐츠를 구현하였다. 구현된 콘텐츠는 보다 효과적인 훈련을 위하여 사용자별 뇌파 차이를 토대로 집중력 지표를 반영함으로써, 수준별 훈련이 가능하다. 구현된 콘텐츠의 유용성을 평가하기 위하여 피실험자 5명을 대상으로 집중력 향상 훈련을 진행하였고 집중력 지표의 변화를 비교 분석을 통하여 사용자의 집중력 향상을 확인할 수 있었다.