logo

:::Location:Home > Research

 Research


Pioneer studies on opinion mining and sentiment analysis

Pioneer studies on opinion mining and sentiment analysis

Opinion mining and sentiment analysisOpinion mining and sentiment analysis, a practical application of natural language processing (NLP), has attracted attention for more than a decade because a large amount of opinionated information is generated and disseminated across various platforms on the internet. On the one hand, people are willing to share their feelings and thoughts. On the other hand, people often refer to majority opinions before making decisions. The Natural Language Processing Lab...

System for automatic ICD-10 classification from free-text medical data

System for automatic ICD-10 classification from free-text medical data

Our study aimed to construct a system for ICD-10 coding systems produced by supervised machine learning techniques to categorize automatically free-text medical data using solely their content. We used numerous machine learning techniques, such as supervised machine learning approaches. At present, disease classification relies heavily on human labor to read a large amount of written material, such as discharge diagnoses, chief complaints, medical histories, and operation records, as the basis f...

Artificial, augmented, and human intelligence for medical image analysis for our health

Artificial, augmented, and human intelligence for medical image analysis for our health

We all aspire to be healthy. Can artificial intelligence (AI) help us in our quest?Thanks to ubiquitously available datasets, fast-growing computing power, and the latest innovative algorithms, AI continues to surprise us by changing the world at a rapid pace. AI unmanned vehicles have been around for some time. The FDA approved the first AI-powered diabetic retinopathy diagnostic device that does not require a doctor's supervision in April 2018. Google recently claimed that its AI voice technol...

AttriRank: the state-of-the-art model for unsupervised ranking

AttriRank: the state-of-the-art model for unsupervised ranking

Node ranking in a graph is an important technique underlying many real-world applications. Take web search for example. This task is essential for returning important (or highly ranked) websites that are relevant to a query. Because the entire Internet with all of its webpages and hyperlinks forms a graph, a technique that ranks nodes in a graph becomes essential for this application. Such a ranking technique would also be useful in identifying influential persons or opinion leaders in a large s...

Deep learning for malicious encrypted traffic detection

Deep learning for malicious encrypted traffic detection

The use of encrypted traffic on the Internet has become increasingly popular in recent years. Google and the Mozilla Foundation have released statistical data indicating that more than half of their browser users used HTTPS protocol-encrypted connections in 2016. Encrypted network traffic may conceal malicious software connections and hacker attack activities. According to Cisco’s reports, malicious software that communicates via TLS-encrypted connections accounted for 2.21% in 2015, where...

Can a machine learn human language without human teaching by means of a generative adversarial network?

Can a machine learn human language without human teaching by means of a generative adversarial network?

Human infants acquire language with little formal teaching, but machines need large amounts of annotated data, which makes the development of natural language processing technology challenging. Although deep learning has already had tremendous success in natural language processing, the training is usually supervised. Only large companies can collect large amounts of labeled data to build high-quality automatic speech recognition (ASR) systems and then build systems that understand spoken langua...

Dependency structure matrix genetic algorithm II

Dependency structure matrix genetic algorithm II

Introduction In 2015, we proposed the dependency structure matrix genetic algorithm II (DSMGA-II) [1], which is currently a state-of-the-art discrete genetic algorithm. Based on the dependency structure matrix (DSM), a new linkage model called the incremental linkage set (ILS) is adopted in DSMGA-II to provide potential models for mixing. Restricted mixing and back mixing are the major recombination operators of DSMGA-II. Such a combination significantly reduces the number of function evaluat...

IdenNet:Facial Action Unit Detection Using Identity Normalization

IdenNet:Facial Action Unit Detection Using Identity Normalization

Facial action unit (AU) detection is an important task that enables emotion recognition from facial movements. Figure 1 shows a few AU examples that illustrate the advanced ability to decently describe facial expressions across primary categories such as neutral, happy, and sad. Prof. Hsu’s team is motivated to conduct this research to improve the social ability of robots when interacting with humans. To that end, the team proposes a novel algorithm using identity normalization to address ...

Video summarization through action localization on a social robot

Video summarization through action localization on a social robot

Using a robot to help family members look after seniors living alone With a large portion of Taiwan’s population becoming aged, Dr. Yang aims to investigate the feasibility of applying video summarization techniques using a social robot to help family members look after seniors living alone. The setting is a home where an elderly person lives alone, whose family members are willing to care for the person but too busy to assist every day. A household robot will help if it can follow the ...

Designing for complex creative task solving

Designing for complex creative task solving

Solving creative problems such as those pertaining to writing or design is challenging because such problems are open-ended and require people to spend much time and effort to achieve high-quality results through trial and error. Feedback plays a critical role in this process because it can help people recognize and fix errors, leading to better results. However, high-quality feedback is difficult to obtain due to the limited pool of experts available. To address the issues of scalability and hi...