Hyungjun Park

Hyungjun Park, Chang-Yun Woo, Seungjo Lim et al.

Objective To develop an LLM based realtime compound diagnostic medical AI interface and performed a clinical trial comparing this interface and physicians for common internal medicine cases based on the United States Medical License Exam (USMLE) Step 2 Clinical Skill (CS) style exams. Methods A nonrandomized clinical trial was conducted on August 20, 2024. We recruited one general physician, two internal medicine residents (2nd and 3rd year), and five simulated patients. The clinical vignettes were adapted from the USMLE Step 2 CS style exams. We developed 10 representative internal medicine cases based on actual patients and included information available on initial diagnostic evaluation. Primary outcome was the accuracy of the first differential diagnosis. Repeatability was evaluated based on the proportion of agreement. Results The accuracy of the physicians' first differential diagnosis ranged from 50% to 70%, whereas the realtime compound diagnostic medical AI interface achieved an accuracy of 80%. The proportion of agreement for the first differential diagnosis was 0.7. The accuracy of the first and second differential diagnoses ranged from 70% to 90% for physicians, whereas the AI interface achieved an accuracy rate of 100%. The average time for the AI interface (557 sec) was 44.6% shorter than that of the physicians (1006 sec). The AI interface ($0.08) also reduced costs by 98.1% compared to the physicians' average ($4.2). Patient satisfaction scores ranged from 4.2 to 4.3 for care by physicians and were 3.9 for the AI interface Conclusion An LLM based realtime compound diagnostic medical AI interface demonstrated diagnostic accuracy and patient satisfaction comparable to those of a physician, while requiring less time and lower costs. These findings suggest that AI interfaces may have the potential to assist primary care consultations for common internal medicine cases.

Hyungjun Park, Daiki Min, Jong-hyun Ryu et al.

Typical reinforcement learning (RL) methods show limited applicability for real-world industrial control problems because industrial systems involve various constraints and simultaneously require continuous and discrete control. To overcome these challenges, we devise a novel RL algorithm that enables an agent to handle a highly constrained action space. This algorithm has two main features. First, we devise two distance-based Q-value update schemes, incentive update and penalty update, in a distance-based incentive/penalty update technique to enable the agent to decide discrete and continuous actions in the feasible region and to update the value of these types of actions. Second, we propose a method for defining the penalty cost as a shadow price-weighted penalty. This approach affords two advantages compared to previous methods to efficiently induce the agent to not select an infeasible action. We apply our algorithm to an industrial control problem, microgrid system operation, and the experimental results demonstrate its superiority.

Hyungjun Park, Daiki Min, Jong-hyun Ryu et al.

A microgrid is an innovative system that integrates distributed energy resources to supply electricity demand within electrical boundaries. This study proposes an approach for deriving a desirable microgrid operation policy that enables sophisticated controls in the microgrid system using the proposed novel credit assignment technique, delayed-Q update. The technique employs novel features such as the ability to tackle and resolve the delayed effective property of the microgrid, which prevents learning agents from deriving a well-fitted policy under sophisticated controls. The proposed technique tracks the history of the charging period and retroactively assigns an adjusted value to the ESS charging control. The operation policy derived using the proposed approach is well-fitted for the real effects of ESS operation because of the process of the technique. Therefore, it supports the search for a near-optimal operation policy under a sophisticatedly controlled microgrid environment. To validate our technique, we simulate the operation policy under a real-world grid-connected microgrid system and demonstrate the convergence to a near-optimal policy by comparing performance measures of our policy with benchmark policy and optimal policy.

Hyungjun Park, Min Kyu Sim, Dong Gu Choi

Portfolio traders strive to identify dynamic portfolio allocation schemes so that their total budgets are efficiently allocated through the investment horizon. This study proposes a novel portfolio trading strategy in which an intelligent agent is trained to identify an optimal trading action by using deep Q-learning. We formulate a Markov decision process model for the portfolio trading process, and the model adopts a discrete combinatorial action space, determining the trading direction at prespecified trading size for each asset, to ensure practical applicability. Our novel portfolio trading strategy takes advantage of three features to outperform in real-world trading. First, a mapping function is devised to handle and transform an initially found but infeasible action into a feasible action closest to the originally proposed ideal action. Second, by overcoming the dimensionality problem, this study establishes models of agent and Q-network for deriving a multi-asset trading strategy in the predefined action space. Last, this study introduces a technique that has the advantage of deriving a well-fitted multi-asset trading strategy by designing an agent to simulate all feasible actions in each state. To validate our approach, we conduct backtests for two representative portfolios and demonstrate superior results over the benchmark strategies.

Zulqarnain H. Khattak, Hyungjun Park, Seongah Hong et al.

Active Traffic Management (ATM) systems have been introduced by transportation agencies to manage recurrent and non-recurrent congestion. ATM systems rely on the interconnectivity of components made possible by wired and/or wireless networks. Unfortunately, this connectivity that supports ATM systems also provides potential system access points that results in vulnerability to cyberattacks. This is becoming more pronounced as ATM systems begin to integrate internet of things (IoT) devices. Hence, there is a need to rigorously evaluate ATM systems for cyberattack vulnerabilities, and explore design concepts that provide stability and graceful degradation in the face of cyberattacks. In this research, a prototype ATM system along with a real-time cyberattack monitoring system were developed for a 1.5-mile section of I-66 in Northern Virginia. The monitoring system detects deviation from expected operation of an ATM system by comparing lane control states generated by the ATM system with lane control states deemed most likely by the monitoring system. In case of any deviation between two sets of states, the monitoring system displays the lane control states generated by the back-up data source. In a simulation experiment, the prototype ATM system and cyberattack monitoring system were subject to emulated cyberattacks. The evaluation results showed that when subject to cyberattack, the mean speed reduced by 15% compared to the case with the ATM system and was similar to the baseline case. This illustrates that the effectiveness of the ATM system was negated by cyberattacks. The monitoring system however, allowed the ATM system to revert to an expected safe state and reduced the negative impact of cyberattacks. These results illustrate the need to revisit ATM system design concepts as a means to protect against cyberattacks in addition to traditional system intrusion prevention approaches.