연세대학교 · 공학
아슈토시쉬 미스트라 교수의 연구실은 뇌 전기생리학, 환경 모니터링, 스마트 농업, 자율주행차 제어 등 다양한 분야에서 데이터 기반의 지능형 분석과 시스템 설계를 중심으로 연구를 진행하고 있습니다. 특히 뇌의 전기적 활동을 기하학적 관점에서 분석하는 EEG 마이크로스테이트 분석과, 강의 수질 오염 평가를 위한 다변량 통계 기법 적용이 두드러지며, 스마트 센서 기반의 수직 농업 및 자율주행차의 다에이전트 강화학습 응용도 핵심 연구 주제입니다. 연구는 실생활 문제 해결에 초점을 맞춘 응용 기반의 과학 기술 혁신을 추구합니다.
표시된 성과는 수집된 데이터 기준으로 산출되며, 일부 차이가 있을 수 있습니다.
In recent years, EEG microstate analysis has gained popularity as a tool to characterize spatio-temporal dynamics of large-scale electrophysiology data. It has been used in a wide range of EEG studies and the discovered microstates have been linked to cognitive function and brain diseases. EEG microstates are assumed to (1) be winner-take-all, meaning that the topography at any given time point is in one state; and (2) discretely transition from one state into another. In this study we investiga
In this review, recent works on the preferential oxidation of carbon monoxide in hydrogen rich gases for fuel cell applications are summarized. H2 is used as a fuel for polymer-electrolyte membrane fuel cell (PEMFC). It is produced by reforming of natural gas or liquid fuels followed by water gas shift reaction. The produced gas consists of H2, CO, and CO2. In which CO content is around 1%, which is highly poisonous for the Pt anode of the PEMFC so that further removal of CO is needed. Catalytic
In present study multivariate statistical approaches are used; interpretation of large and complex data matrix obtained during a monitoring of the river Ganges in Varanasi. 16 physicochemical and bacteriological variables have been analyzed in water samples collected every three months for two years from six sampling sites where river affected by man made and seasonal influences. The dataset was treated using Principal Component Analysis (PCA) to extract the parameters that are most important in
Smart sensing devices enabled hydroponics, a concept of vertical farming that involves soilless technology that increases green area. Although the cultivation medium is water, hydroponic cultivation uses 13 ± 10 times less water and gives 10 ± 5 times better quality products compared with those obtained through the substrate cultivation medium. The use of smart sensing devices helps in continuous real-time monitoring of the nutrient requirements and the environmental conditions required by the c
Various physico chemical characteristics of the river Ganga in Varanasi were studied in the Oct 2005 to Nov 2006. Ecological parameters like dissolved oxygen(DO), pH, nitrate(NO3-),PO43- and bacterial population were analyzed and compared with standard permissible limits to assess the best designated use of the river water for various purposes. Study revealed that the water quality at Varanasi was not safe for human use. Result shows that Fecal coliform (20.9×103/ 100mL), Fecal streptococci (93/
Connected and automated vehicles (CAVs) require multiple tasks in their seamless maneuverings. Some essential tasks that require simultaneous management and actions are motion planning, traffic prediction, traffic intersection management, etc. A few of them are complex in nature. Multi-agent reinforcement learning (MARL) can solve complex problems involving simultaneous controls. Recently, many researchers applied MARL in such applications. However, there is a lack of extensive surveys on the on
Porcelain and toughened glass suspension type insulators that were removed after 25-30 years of service were evaluated in the laboratory with the objectives of understanding failure mechanisms and assessing the condition of similar insulators in the field. The remaining electrical and mechanical strength was highly variable for porcelain and for some they were significantly reduced from the rated value. Scanning electron microscopy and electric field calculations provided an insight into the fai
In this paper, we have demonstrated a robust in-cabin monitoring system (IMS) for safety, security, surveillance, and monitoring, including privacy concerns for personal and shared autonomous vehicles (AVs). It consists of a set of monitoring cameras and an onboard device (OBD) equipped with artificial intelligence (AI). Hereafter, this combination of a camera and an OBD is referred to as the AI camera. We have investigated the issues for mobility services in higher levels of autonomous driving,
India has a unique climate system dominated by the monsoon, and the major physiographic features that drive this monsoon are its location in the globe, the Himalayas, the central plateau, the western and Eastern Ghats and the oceans surrounding the region. The country is considered highly vulnerable to climate change, not only because of high physical exposure to climate-related disasters, but also because of the dependency of its economy and majority of population on climate-sensitive sectors (
This book explores new methods, architectures, tools and algorithms for Artificial Intelligence Hardware Accelerators.
An authorized traffic controller (ATC) has the highest priority for direct road traffic. In some irregular situations, the ATC supersedes other traffic control. Human drivers indigenously understand such situations and tend to follow the ATC; however, an autonomous vehicle (AV) can become confused in such circumstances. Therefore, autonomous driving (AD) crucially requires a human-level understanding of situation-aware traffic gesture recognition. In AVs, vision-based recognition is particularly
Present paper deals with the question whether the intense cyclones have become more frequent over the north Indian Ocean, especially in Bay of Bengal region, posing a more serious threat to the vulnerable coastal population of the region, and whether the temperature trend has backed and stimulated this trend. The results of the study, which has considered the data of 122 years of tropical cyclone frequency over the north Indian Ocean from 1891 to 2013, have shown that there is indeed a trend of