Sinan Chen

Sinan Chen

Kobe University

H-index: 9

Asia-Japan

About Sinan Chen

Sinan Chen, With an exceptional h-index of 9 and a recent h-index of 9 (since 2020), a distinguished researcher at Kobe University, specializes in the field of Smart Home, Cloud Computing, Computer Vision, Machine Learning, Software Engineering.

His recent articles reflect a diverse array of research interests and contributions to the field:

A Study of Promotion Method for Energy-Saving Behavior in Homes with Personalized Adaptive Interaction

Employing Large Language Models for Dialogue-Based Personalized Needs Extraction in Smart Services

Using Speech Dialogue Agent to Extract User Needs for Service Personalization

Developing a Finger-Dexterity Measuring System Integrating Image Recognition and Touch Panel Operation

データ連携基盤を活用したロケーションアウェアサービスプラットフォームの提案

Long-Term Forecast of Emergency Demand Using EMS Big Data and Population Estimates by Age

Study of Measuring Motor Function in Dementia by Tapping Task Using IoT and Image Recognition

Proposing a Feature-Analysis Method of Finger-Movement Data for Predicting Cognitive Function of Elderly People

Sinan Chen Information

University

Kobe University

Position

Graduate School of System Informatics

Citations(all)

174

Citations(since 2020)

174

Cited By

11

hIndex(all)

9

hIndex(since 2020)

9

i10Index(all)

7

i10Index(since 2020)

7

Email

University Profile Page

Kobe University

Sinan Chen Skills & Research Interests

Smart Home

Cloud Computing

Computer Vision

Machine Learning

Software Engineering

Top articles of Sinan Chen

A Study of Promotion Method for Energy-Saving Behavior in Homes with Personalized Adaptive Interaction

Authors

Shun Hirai,Hiro Okamoto,Sinan Chen,Sachio Saiki,Masahide Nakamura

Journal

IEICE Technical Report; IEICE Tech. Rep.

Published Date

2024/3/6

(in English) In recent years, climate change, including global warming, has become a serious issue, and Japan is aiming to realize a zero carbon society. Zero carbon means reducing the net emissions of greenhouse gases to zero by balancing the amount emitted and absorbed, which is crucial for reducing CO2 emissions. This study focuses on energy reduction through in-home energy-saving actions, addressing issues such as the lack of acquisition of appliance-specific electricity consumption data, lack of personal adaptation, and oversight of notifications. To address these, a method that integrates a power consumption management service using IoT devices and baselines with a virtual agent (VA) was proposed and implemented. The evaluation experiment confirmed that the introduction of VA led to a reduction in power consumption, and an improvement in energy-saving consciousness and behavioral …

Employing Large Language Models for Dialogue-Based Personalized Needs Extraction in Smart Services

Authors

Takuya Nakata,Sinan Chen,Sachio Saiki,Masahide Nakamura

Journal

CS & IT Conference Proceedings

Published Date

2023/12/23

Research concerning the personalization of services encompasses approaches such as machine learning and dialogue agents; however, the explainability of the recommendation process remains a challenge. Previous studies have proposed dialogue-based needs extraction systems utilizing the 6W1H need model, but extracting complex needs using simple natural language processing proved challenging. In this research, we embark on the development of an Application Programming Interface (API) that extracts user needs from natural language by leveraging the rapidly advancing Large Language Models (LLM), and on constructing a dialogue-based needs extraction system using this API. For evaluation, we conducted a verification on 100 needs with the aim of assessing the accuracy and comprehensiveness of the outputs from the needs extraction and restoration API. Through this study, it became feasible …

Using Speech Dialogue Agent to Extract User Needs for Service Personalization

Authors

Takuya Nakata,Sinan Chen,Sachio Saiki,Masahide Nakamura

Journal

IEICE Technical Report; IEICE Tech. Rep.

Published Date

2023/1/12

(in English) In recent years, there has been a lot of research on service personalization. Although there are many prior studies based on deep learning and dialogue, it is difficult to overcome the shortcomings of machine learning and the strengths of big data utilization. In this study, we propose a user needs model that combines user readability, ease of extraction through dialogue, and expandability to machine learning, and design and build a method for extracting the proposed needs using spoken dialogue. This research will contribute to the realization of effective personalized service personalization that is both acceptable to users and effective.

Developing a Finger-Dexterity Measuring System Integrating Image Recognition and Touch Panel Operation

Authors

Yuki Kashihara,Sinan Chen,Atsuko Hayashi,Masahide Nakamura

Journal

IEICE Technical Report; IEICE Tech. Rep.

Published Date

2023/6/9

(in English) Dementia has become a significant problem in modern Japanese society. In diagnosing and rehabilitating dementia, it is important to measure the motor function of the fingers. This study aims to develop a web application for measuring the tapping task, which assesses manual dexterity. Our key idea is to combine finger recognition using a web camera with touch panel input to measure finger movements. In our proposed method, we utilize a live image captured by the web camera and input it into the hand. js library of MediaPipe for finger recognition. It automatically outputs 21 feature points of the fingers. Simultaneously, we set up touch panel operation buttons on the web interface. In the scenario of the operation screen, participants must move their fingers corresponding to the displayed numbers or characters at intervals of 2 seconds and press the buttons using touch panel input. It allows for …

データ連携基盤を活用したロケーションアウェアサービスプラットフォームの提案

Authors

中橋友郎, 陳思楠, 中村匡秀, 佐伯幸郎

Journal

研究報告ソフトウェア工学 (SE)

Published Date

2023/7/13

論文抄録センシング技術の発展により, 昨今では車両や人など移動体の位置情報を活用し, 位置に応じたサービスを提供するロケーションアウェア (LA) サービスの開発が著しい. しかしながら, 現状では LA サービスの開発は, 移動体の位置情報の管理や, 位置情報に基づく条件の評価, 条件を満たした際の処理を含んだシステムを個別で構築する必要がある. システムがサイロ化されることで, 収集したデータの再利用性が低下し, また, 機能の再開発のコストがかかる. 本研究では, LA サービス開発を効率化する LA プラットフォームを提案する. LA プラットフォームは, 従来では LA サービス毎に開発する必要があったオブジェクトの情報管理や条件の登録・評価機能などを LA サービスから切り出したサービスとして提供することで, LA サービスの実装範囲を低減し, 開発コスト削減を実現する. ケーススタディでは, LA プラットフォームを活用し, 人と部屋の位置関係に応じて入退室を通知する LA サービスの開発を行った.

Long-Term Forecast of Emergency Demand Using EMS Big Data and Population Estimates by Age

Authors

Masaki Kaneda,Sinan Chen,Masahide Nakamura,Sachio Saiki

Published Date

2023/9/12

In recent years, Japan has been facing a super- aging society. The problems of tight emergency medical care and an increase in the number of emergency medical transports have become ¶uite serious. In response to this situation, our research group has been conducting joint research with the Kobe City Fire Department. This study aims to propose and establish a method for medium to long-term prediction of the number of emergency medical transports and to provide an indicator for the strategic deployment of Emergency Medical Services (EMS) and the expansion and contraction of the scale of medical services in the field. This medium to long-term prediction of the number of ambulance transports is achieved by analyzing big data, population data, and future population estimates in each region without machine learning. The proposed method was evaluated in Kobe City, Japan. The results showed that the …

Study of Measuring Motor Function in Dementia by Tapping Task Using IoT and Image Recognition

Authors

Sinan Chen,Atsuko Hayashi,Masahide Nakamura

Published Date

2023/11/22

Dementia has emerged as a significant issue in contemporary Japanese society. Assessing finger motor function is pivotal for diagnosing and rehabilitating individuals with dementia. In this study, we design a web application to gauge manual dexterity through tapping exercises. Our fundamental concept combines finger identification using a web camera and tactile panel input to quantify finger actions. In our proposed methodology, we amalgamate real-time visuals captured by a web camera into the hand.js module within the MediaPipe framework, autonomously generating 21 critical finger data points. Concurrently, we establish touch panel control buttons on the web interface. In the context of the operating interface, participants manipulate their fingers in sync with numbers or features displayed every two seconds and utilize touch panel input to log button presses. This approach facilitates an all-encompassing …

Proposing a Feature-Analysis Method of Finger-Movement Data for Predicting Cognitive Function of Elderly People

Authors

Hayato Seiichi,Sinan Chen,Atsuko Hayashi,Masahide Nakamura

Journal

IEICE Technical Report; IEICE Tech. Rep.

Published Date

2023/6/9

(in English) In recent years, a growing body of research has suggested a relationship between cognitive function and manual dexterity. However, studies on all aspects of human fingertip movements have been limited, and analysis methods still need to be well-established. Our research group is developing a finger motion measurement system that combines image recognition and touch panel manipulation. Therefore, the purpose of this study is to utilize the finger motion data extracted using our developed system and propose an analysis method for assessing manual dexterity. Our key idea is to focus on irregularly sampled finger motion time-series data and analyze it using a state-space model. The proposed method follows steps:(Step 1) Data loading and organization.(Step 2) Coordinate data transformation.(Step 3) Individual comparison of data features. In a case study, we extract data measured according to …

Extracting User Needs for Personalized Smart Services Using Dialogue Agent with LLM

Authors

Takuya Nakata,Sinan Chen,Sachio Saiki,Masahide Nakamura

Journal

IEICE Technical Report; IEICE Tech. Rep.

Published Date

2023/7/13

(in English) Research on service personalization involves approaches such as machine learning and dialogue agents, but the explainability of the recommendation process remains a challenge. Previous studies proposed a dialogue-based needs extraction system using the 6W1H needs model, but complex needs extraction was difficult with simple natural language processing. In this study, we focus on developing an API that extracts user needs from natural language using large-scale language models (LLMs) and constructing a dialogue-based needs extraction system using the API. We conducted verification on 100 needs to evaluate the accuracy and comprehensiveness of the output results from the needs extraction and restoration API. This study enables accurate and comprehensive extraction of needs from complex natural language using LLMs.

Proposal an Automated Management Service for Hybrid Meeting Spaces Using Uni-Messe and IoT

Authors

Takeshi Yoshida,Sinan Chen,Masahide Nakamura,Sachio Saiki

Published Date

2023/9/12

In recent years, Japan has been actively promoting the concept of a super-smart society, which aims to leverage various scientific technologies to address societal challenges spanning environmental issues, energy management, and disaster preparedness. Within this context, our focus lies on harnessing the potential of Internet of Things (IoT) devices to playa pivotal role in advancing these objectives. The purpose of this paper is to propose an innovative service that streamlines the automatic management of hybrid conferences. To achieve this, we introduce a service coordination platform that leverages the Unified Rule- Based Message Delivery Service (Uni-messe). Our proposed approach involves the initial implementation of a simplified service version, followed by a case study specifically tailored to the conference setting. Throughout our study, we identified two key areas that require further improvement …

Using Data Integration Platform for Effective Location-Aware Service Development Platform

Authors

Tomoro Nakahashi,Sinan Chen,Sachio Saiki,Masahide Nakamura

Published Date

2023/11/8

Due to the advancement of sensing technology, the development of Location-Aware (LA) services that utilize the location information of moving entities such as vehicles and people to provide location-based services has been remarkable in recent times. However, currently, the development of LA services requires the individual construction of systems that encompass the management of location information for moving entities, the evaluation of conditions based on location information, and the processing when conditions are satisfied. This situation results in system silos, leading to reduced reusability of collected data and increased costs associated with redeveloping functionalities. In this study, we propose "LA platform" to streamline the development of LA services. The LA platform leverages a data integration platform to provide functions such as information management of objects and registration/evaluation of …

Creating Conversation Opportunities For Elderly People At Home By Linking Virtual Agents And Video Conferencing Services

Authors

Hiro Okamoto,Sinan Chen,Masahide Nakamura,Sachio Saiki

Journal

IEICE Technical Report; IEICE Tech. Rep.

Published Date

2023/3/6

(in English) The increase in single-person households and the onset of" corona frailty" due to the new coronavirus have become problems. In previous research, we worked on the development of a virtual agent using speech recognition technology. In this service, we examined promoting self-care by increasing opportunities for conversation by the agent listening to the elderly. However, this service is intended for self-help support, and there is a problem that it cannot increase opportunities for dialogue with family and friends that lead to mutual help support. In this study, elderly people at home use the virtual agent listening service. We proposed and implemented" Easy Video Chat Service", a service that increases conversation opportunities by enabling conversations with friends and family.

A Study for Estimating Caregiving Contexts Based on Extracting Nonverbal Information from Elderly People at Home

Authors

Sinan Chen,Masahide Nakamura,Kiyoshi Yasuda

Published Date

2023/7/9

In order to reduce the burden on family caregivers, machine-assisted estimation of situations (called “caregiving contexts”) necessary for the care of elderly people at home is becoming increasingly important. Older adults at home usually express their feelings through nonverbal information such as facial expressions, movements, and postures, except in daily conversation. This study aims to examine a method for estimating the caregiving context based on extracting nonverbal information from older adults at home. Our key idea is to input real-time image data captured by a USB camera into a pre-trained model that can be run in an edge environment and subject the results to analysis that aggregates a set of features for each location in the home. We expect that the results of this research will allow us to build a classifier of caregiving contexts unique to each household and to analyze better and infer the caregiving …

Evaluating an In-Home Exercise Program Using Vision-Based Edge AI for Elderly Healthcare

Authors

Sinan Chen,Masahide Nakamura,Kiyoshi Yasuda

Published Date

2023/9/7

In Japan, many in-home exercise programs have appeared to improve the motor function of the elderly through self-care. However, a challenging point always exists in evaluating the process of exercise programs quantitively and non-invasively for further reflecting the health status. As a preliminary progress, we present and discuss a vision-based novel method on edge that aims to evaluate an in-home exercise program in this paper. Our key idea is to integrate multiple different vision-based pre-trained models. In the proposed method, we mainly integrate and call multiple pre-trained models to recognize human facial, skeletal, and hand movements with edge computing. Also, we propose to evaluate an in-home exercise program process from the Euclidean distance, velocity, and angle of the two-dimensional coordinates of feature points in the time series. Through experiments, we estimate the physical health …

A Study of Project Description Inference Using Method Name Elements for Software Upcycling

Authors

Kohei Terakawa,Sinan Chen,Sachio Saiki,Masahide Nakamura

Published Date

2023/11/8

In software development, there is often a situation where products developed in the past could be managed as more valuable assets. Conversely, such products may contain the reusable value. We are currently exploring utilizing existing project assets for new development, a concept we define as "software upcycling". To facilitate upcycling, the challenge lies in comprehending the software overview without documentation and making it easily referenceable. In a previous study, we proposed a methodology for inferring the system overview using a project corpus. We collected constituent words from class names and conducted a validation study to assess their utility in inferring the system’s overview. In this research, we shift our focus to method names in order to further enhance accuracy. We attempt to understand the software’s architecture efficiently by assigning weighted importance to words in the project corpus …

Quantitative Expression of Elderly Multi-Modal Emotions with Spoken Dialogue Agent and Edge AI

Authors

Sinan Chen,Hayato Ozono,Masahide Nakamura,Kiyoshi Yasuda

Published Date

2023/2/3

In a super-aging society, the problem of aging of the physical and cognitive functions of older adults receiving home care is becoming more serious. In the previous study, we developed a spoken dialogue agent system that allowed older adults to communicate with machines by voice. However, it was difficult to visualize the thoughts extracted from the spoken dialog of the elderly in detail. Therefore, this study was carried out to extract the emotional characteristics of the elderly and propose a method to visualize them quantitatively. The proposed method uses AI technology to extract and express emotional features from multiple perspectives while protecting the privacy of the elderly. In this way, the method objectively reflects the personality and preferences of the elderly and leads to the prevention of dementia.

Dialogue-Based User Needs Extraction for Effective Service Personalization

Authors

Takuya Nakata,Sinan Chen,Sachio Saiki,Masahide Nakamura

Published Date

2023/7/9

The research of service personalization is flourishing due to the development of machine learning and natural language processing. Despite the prevalence of prior research based on deep learning and dialogue, it remains challenging to reconcile the disadvantages of machine learning, such as explainability, with the strength of utilizing big data. This research proposes a user needs model that incorporates three elements: user readability, ease of extraction through dialogue, and the potential for advancement in machine learning. Additionally, a voice dialogue-based extraction method is designed and constructed to extract the proposed needs. Specifically, by adopting the 6W1H format for the needs model, a simple yet powerful dialogue flow is achieved and enables a comparison of existing services and needs simultaneously. The main modules of the system are a voice dialogue agent, a dialogue system, and a …

在宅高齢者の見守りのための画像に基づくエッジ AI を活用した人間中心のコンテキスト認識手法の考察

Authors

陳思楠, 中村匡秀, 安田清

Journal

研究報告ドキュメントコミュニケーション (DC)

Published Date

2023/7/28

論文抄録日本を含む世界人口の高齢化が進行する中, 介護の施設や人手不足によって従来の施設介護から在宅介護への転換が大きな傾向となっている. 施設より在宅生活に慣れやすい反面, 高齢者の日常生活の介護や見守りは, 家族介護者に大きな負担がかかっている. 先行研究では, 音声対話システムに基づく言葉による高齢者の 「こころ」 センシングや, 骨格センシング技術を活用した高齢者の宅内活動の品質付け手法等を提案している. しかしながら, 高齢者の顔表情や身体姿勢・行動 (コンテキストと呼ぶ) の変化等の認識は, 在宅高齢者の見守りに不可欠な技術であり, まだ実現できていない. そこで本研究では, 非言語的な特徴量をめぐる状況, 特に人間中心のコンテキスト認識手法を考察することを目的とする. 我々のキーアイデアは, 画像に基づく複数の事前学習済みモデルをエッジ環境で統合し, 人間中心の特徴量を抽出して, コンテキストとして性質づけることである. アプローチとして, 複数の事前学習済みモデルに基づき, ローカルで実行可能な画像認識技術を統合し, ライブ画像から人間中心のコンテキスト認識を行う. 本手法に従って, 汎用的なパソコンと定点 USB カメラのみを利用し, 一般家庭に導入しやすい在宅見守りシステムとして期待できる.

Succeed: Sharing upcycling cases with context and evaluation for efficient software development

Authors

Takuya Nakata,Sinan Chen,Sachio Saiki,Masahide Nakamura

Journal

Information

Published Date

2023/9/21

Software upcycling, a form of software reuse, is a concept that efficiently generates novel, innovative, and value-added development projects by utilizing knowledge extracted from past projects. However, how to integrate the materials derived from these projects for upcycling remains uncertain. This study defines a systematic model for upcycling cases and develops the Sharing Upcycling Cases with Context and Evaluation for Efficient Software Development (SUCCEED) system to support the implementation of new upcycling initiatives by effectively sharing cases within the organization. To ascertain the efficacy of upcycling within our proposed model and system, we formulated three research questions and conducted two distinct experiments. Through surveys, we identified motivations and characteristics of shared upcycling-relevant development cases. Development tasks were divided into groups, those that employed the SUCCEED system and those that did not, in order to discern the enhancements brought about by upcycling. As a result of this research, we accomplished a comprehensive structuring of both technical and experiential knowledge beneficial for development, a feat previously unrealizable through conventional software reuse, and successfully realized reuse in a proactive and closed environment through construction of the wisdom of crowds for upcycling cases. Consequently, it becomes possible to systematically perform software upcycling by leveraging knowledge from existing projects for streamlining of software development.

Empirical Evaluation of In-Home Elderly Support and Monitoring System Using Spoken Dialogue Agent

Authors

Hayato Ozono,Sinan Chen,Masahide Nakamura

Journal

IEICE Technical Report; IEICE Tech. Rep.

Published Date

2023/1/12

(in English) The world's population is aging. In Japan, it is a social problem that the shortage of nursing care workers and nursing care facilities. Therefore, we focus on the support by technology. Our research group is developing PC-Mei, a system that supports and monitors the daily lives of in-home elderly using a spoken dialogue agent. However, we have not yet examined the impact of this system on the elderly and their families. The purpose of this paper is to investigate the impact of PC-Mei on the elderly and their families, and to evaluate the system. As an approach, we conduct a demonstration experiment of PC-Mei with in-home elderly and their families. The participants are six elderly people in their 60s to 90s who lived alone and the period is about two weeks. We install the system in their rooms. Then, we evaluate the system based on the dialogue logs with the agent and the results of questionnaires. The …

See List of Professors in Sinan Chen University(Kobe University)

Sinan Chen FAQs

What is Sinan Chen's h-index at Kobe University?

The h-index of Sinan Chen has been 9 since 2020 and 9 in total.

What are Sinan Chen's top articles?

The articles with the titles of

A Study of Promotion Method for Energy-Saving Behavior in Homes with Personalized Adaptive Interaction

Employing Large Language Models for Dialogue-Based Personalized Needs Extraction in Smart Services

Using Speech Dialogue Agent to Extract User Needs for Service Personalization

Developing a Finger-Dexterity Measuring System Integrating Image Recognition and Touch Panel Operation

データ連携基盤を活用したロケーションアウェアサービスプラットフォームの提案

Long-Term Forecast of Emergency Demand Using EMS Big Data and Population Estimates by Age

Study of Measuring Motor Function in Dementia by Tapping Task Using IoT and Image Recognition

Proposing a Feature-Analysis Method of Finger-Movement Data for Predicting Cognitive Function of Elderly People

...

are the top articles of Sinan Chen at Kobe University.

What are Sinan Chen's research interests?

The research interests of Sinan Chen are: Smart Home, Cloud Computing, Computer Vision, Machine Learning, Software Engineering

What is Sinan Chen's total number of citations?

Sinan Chen has 174 citations in total.

What are the co-authors of Sinan Chen?

The co-authors of Sinan Chen are Masahide Nakamura.

    Co-Authors

    H-index: 24
    Masahide Nakamura

    Masahide Nakamura

    Kobe University

    academic-engine

    Useful Links