Sunghoon Lim 교수

Due to the increase in motor vehicle accidents, there is a growing need for high-performance car crash detection systems. The authors of this research propose a car crash detection system that uses both video data and audio data from dashboard cameras in order to improve car crash detection performance. While most existing car crash detection systems depend on single modal data (i.e., video data or audio data only), the proposed car crash detection system uses an ensemble deep learning model bas

The authors propose a time series model that predicts future values of various types of liquid cargo traffic based on long short-term memory (LSTM), a deep learning technique. Existing liquid cargo traffic prediction models are based on traditional time series models, such as autoregressive integrated moving average (ARIMA) and vector autoregression (VAR). Some of these models, which do not consider linear dependencies among the values of different types of liquid cargo traffic, have limitations

The authors of this work propose an algorithm that determines optimal search keyword combinations for querying online product data sources in order to minimize identification errors during the product feature extraction process. Data-driven product design methodologies based on acquiring and mining online product-feature-related data are presented with two fundamental challenges: (1) determining optimal search keywords that result in relevant product related data being returned and (2) determini

Abstract Due to the increasing global availability of the internet, online learning platforms such as Massive Open Online Courses (MOOCs), have become a new paradigm for distance learning in engineering education. While interactions between instructors and students are readily observable in a physical classroom environment, monitoring student engagement is challenging in MOOCs. Monitoring student engagement and measuring its impact on student performance are important for MOOC instructors, who a

An anomaly-based intrusion detection system (A-IDS) provides a critical aspect in a modern computing infrastructure since new types of attacks can be discovered. It prevalently utilizes several machine learning algorithms (ML) for detecting and classifying network traffic. To date, lots of algorithms have been proposed to improve the detection performance of A-IDS, either using individual or ensemble learners. In particular, ensemble learners have shown remarkable performance over individual lea

Classification algorithms are widely taken into account for clinical decision support systems. However, it is not always straightforward to understand the behavior of such algorithms on a multiple disease prediction task. When a new classifier is introduced, we, in most cases, will ask ourselves whether the classifier performs well on a particular clinical dataset or not. The decision to utilize classifiers mostly relies upon the type of data and classification task, thus making it often made ar

The authors present an expert and intelligent system that (1) identifies influential term groups having causal relationships with real-world enterprise outcomes from Twitter data and (2) quantifies the appropriate time lags between identified influential term groups and enterprise outcomes. Existing expert and intelligent systems, which are defined as computer systems that imitate the ability of human decision making, could enable computers to identify the spread of Twitter users’ enterprise-rel

The authors of this work present a model that reduces product rating biases that are a result of varying degrees of customers' optimism/pessimism. Recently, large-scale customer reviews and numerical product ratings have served as substantial criteria for new customers who make their purchasing decisions through electronic word-of-mouth. However, due to differences among reviewers' rating criteria, customer ratings are often biased. For example, a three-star rating can be considered low for an o

Recently, social media has emerged as an alternative, viable source to extract large-scale, heterogeneous product features in a time and cost-efficient manner. One of the challenges of utilizing social media data to inform product design decisions is the existence of implicit data such as sarcasm, which accounts for 22.75% of social media data, and can potentially create bias in the predictive models that learn from such data sources. For example, if a customer says “I just love waiting all day

Crowdsourcing has become an important tool for gathering knowledge for urban planning problems. The questions posted to the crowd for urban planning problems are quite different from the traditional crowdsourcing models. Unlike the traditional crowdsourcing models, due to the constraints among the multiple components (e.g., multiple locations of facilities) in a single question and non-availability of the defined option sets, aggregating of multiple diverse opinions that satisfy the constraints

Delamination is a prevalent issue in carbon fiber-reinforced plastic (CFRP) drilling, significantly compromising the mechanical properties of the material. Considering that delamination can impact the long-term durability of the final products, it is essential for operators to promptly identify it. This paper proposes a machined surface image generation model, called Sensor2Image, that employs time-series force sensor data as input and generates drilled-hole surface images as output. Sensor2Imag

행정 분야에서 인공지능 활용이 확대될 것으로 예상되는 상황에서 인공지능 알고리즘이 가지는 예측불가능성과 자율성으로 말미암아 인공지능 알고리즘의 투명성 및 책임성을 어떻게 확보할 것인가가 문제된다. 이를 위하여 인공지능 활용에 대한 윤리적 대응이나 인공지능규제를 위한 특별법과 별도로 법치주의와 적법절차 관점에서 행정법적 대응이 검토되어야 한다.BR 미국에서는 인공지능 행정과 관련하여 최근에 인공지능에 의한 집행 대상 선정과 사회보장급부와 관련된 재결을 중심으로 다양한 논의가 이루어지고 있다. 인공지능 행정의 장점을 중시하면서 그 도입에 적극적인 입장에서는 인공지능의 블랙박스적 성격도 기존의 행정절차법상 투명성 내지 이유제시의 기준 및 행정소송에서의 법원의 존중 원칙에 비추어 수용가능하고, 청문 등 절차 적용이 반드시 요구되는 것이 아니며, 인공지능을 통한 규칙제정도 가능하다고 한다. 반면 자동화행정 및 인공지능의 블랙박스적 성격에 대한 대응을 강조하는 입장에서는 행정절차법상 투명성과