Skip to main content
main-content
Top

About this book

This book constitutes the proceedings of the 17th International Conference on Cooperative Design, Visualization, and Engineering, CDVE 2020, held in Bangkok, Thailand, in October 2020.*

The 33 full papers and 7 short papers presented were carefully reviewed and selected from 74 submissions. The achievement, progress and future challenges are reported in areas such as health care, industrial design, banking IT systems, cultural activities support, operational maritime cybersecurity assurance, emotion communication, and social network data analytics.

* The conference was held virtually due to the COVID-19 pandemic.

Table of Contents

Frontmatter

A Home-Based Adaptive Collaborative System for Stroke Patient Rehabilitation

This paper describes research into the development of a collaborative home-based patient-therapist system for stroke patient rehabilitation. Our prototype system is designed so that home-based rehabilitation exercises are interactive and adapt to the progress of the patient. This way patients are encouraged to do the exercises most appropriate for their stage in the recovery process and can make the most of the time spent working on their rehabilitation. The system also keeps a record of patient progress that is communicated to the patient and medical professionals via mobile or personal-computer interfaces so they can work together towards a more effective overall plan for rehabilitation. This allows the physician to be better informed to make clinical decisions based on the progress of the patient. Results of early evaluations demonstrate the utility of our prototype system to provide users with a stimulating interactive experience as well as the systems potential to support medical experts to make more informed decisions relating to patient treatment. Results also indicate that patients feel more involved in their rehabilitation and that general communication between the medical experts and patients is improved.

Paul Craig, Yanhao Jin, Jie Sun

User Comfort Achievement by Fuzzy Preferences Through an Emotion Communication System

An emotion communication system based on linearly ordered fuzzy preferences is proposed, whose objective is to determine the appropriate actions on the environment in order to enhance user comfort. Once a subset of elementary preferences is obtained via basic human-machine interactions, the rest of preference relations are determined in such a way that the consistency of the system is guaranteed. For this purpose, the Łukasiewicz t-conorm is applied as a rule for aggregation.

Pilar Fuster-Parra, Sebastià Galmés

A Personalized Food Recommendation Chatbot System for Diabetes Patients

Diabetes is a disorder of the body that is unable to produce enough insulin. Diabetes causes the body to improperly burn sugar, which affects the blood sugar level leaving a sugar residue. Diabetes is related to genes, body weight, lack of exercise and aging. When patients with diabetes neglect good nutrition this can cause many health problems. This research, therefore, develops a chatbot named “Waan-Noy” to recommend a diet suitable for individuals with diabetes and build a cooperative health society. Our chatbot recommends personalized eating. It is suitable for use by diabetes patients as indicated by their evaluations. Through use of nutrition therapy controls, Waan-Noy recommends specific foods. The user’s evaluation is divided into 3 areas: content, design, and implementation to determine user degree of satisfaction with Waan-Noy.

Phupat Thongyoo, Phuttipong Anantapanya, Pornsuree Jamsri, Supannada Chotipant

Collaborative Design Automation Toolkit for Power Controllers in Aerospace Applications

In this work we present the latest status on our rapid design process and automated toolkit for aerospace power controllers. The goal is to generate correct-by-design flight hardware from high level requirements with a minimum of manual engineering work. This is achieved by maintaining a database of readily usable design elements (circuit designs, PCB layouts, simulation models and documentation snippets). In this paper we focus on the different roles of human interaction with the toolkit and how we can streamline the process to final flight worthy hardware by parallelizing single design tasks.

Janis Sebastian Häseker, Niklas Aksteiner

Collaborative Product Design for Product Customization: An Industrial Case of Fashion Product

This paper proposes a new platform of collaborative product design for product customization. The proposed platform of the collaborative product design process is scoped in internal enterprise level, which includes customers, designers, engineers, and technologists into a single platform. The platform can generate a design solution to the design objective. The collaborative design platform was developed in term of an interactive design on a Computer-Aided Design (CAD) software. In the platform, customer can input the design requirements, designer can monitor the shape generation and improve the resulting design, engineer can define the manufacturing conditions, and technologist can perform the optimization of design and process parameters. At the end of the collaborative design process, the design solution, therefore, is generated in terms of a three-dimensional (3D) model, which is directly integrated to the manufacturing process in line, until obtaining the physical product. This platform has been implemented in a jewelry product enterprise, and the result indicates that it can reduce time in design and manufacturing process approximately 66%.

Somlak Wannarumon Kielarova, Prapasson Pradujphongphet

Towards Automatic Generation of Storyline Aided by Collaborative Creative Design

This paper proposes a new collaborative design on an educational platform that supports automatic game generation based on graph rules. The platform enables computer game researchers to analyze and discuss students’ needs and preferences. In this approach, the computer game is created on the basis of a layered graph representing the functional elements of the story, characters, locations, and objects. This layered graph is dynamic changed by graph rules whose sequence represents the player’s actions. The goal of the cooperative work that took place at the Jagiellonian University in Poland was to create, prepare and implement the plot of the adventure game in such a way as to design a set of singular player actions. A player in any game can use prepared actions in any number of tasks, sequentially and repeatedly, to create their own way to achieve the goal. All student work was placed in a system implemented on the base of Godot Engine, enabling the creation graph structures and graph rules as well as automatic generation of animations. At the final stage of the project, students have the opportunity to evaluate the game and analyze the narrative sequences, their length and objects used in the context of the story. In the future, our research can be also treated as a study of the preferences of computer game players obtained thanks to the suggestions of a selected group of people without professional or specialized knowledge in the field of computer game design.

Iwona Grabska-Gradzińska, Ewa Grabska, Leszek Nowak, Wojciech Palacz

Cooperative Design of an Interactive Museum Guide

This paper deals with the problem of supporting museum visitors in searching for interesting artworks and finding their visiting routes compatible with personal preferences. The proposed application uses knowledge related to museum building structure and topology, and to substantive content of museum collections. Therefore the cooperation between the designer of a museum guide with the museum curator, who provides information about artworks and their assignment to exhibitions, collections and rooms, is indispensable. All this data is stored in a graph, where nodes represent building spaces, edges correspond to accessibility relations between these spaces, while node attributes describe both geometrical properties of spaces and semantic information related to art pieces and collections. The user can specify artworks, exhibitions, collections he wants to visit together with personal preferences concerning the visiting path (like using lifts). Then graph algorithms are used to find the most appropriate route for the user. Moreover, the user can define personalized collections and share them with other users of the application.

Grażyna Ślusarczyk, Barbara Strug, Andrzej Kapanowski

A Hybrid Architecture for Tiered Storage with Fuzzy Logic and AutoML

The explosion of storage needs pauses a multifaceted challenge for organizations, not only it exerts a large pressure on precious resources, but also creates a sub-optimal data environment where the noise level may overwhelm the actual signal. However, despite the economies of scale achieved by major cloud platforms, the fundamental issue of storage optimization did not go away.The past few years witnessed a renewed interest in storage optimization strategies beyond the brute force of cloud scale, one of these strategies is storage tiering, which provides the capability of a dynamic and optimized matching between data and storage systems.In this paper we propose an enhanced architecture that involves the synthesis of fuzzy logic and automated machine learning (AutoML) for an intelligent tierd storage system.

Marwan Batrouni

Textual Representation of Pushout Transformation Rules

This paper is concerned with representing graphs and graph transformation rules using ASCII text only. It proposes an approach based on the textual graph representation used in Cypher Query Language and PGQL. Replacing visual rule languages with a pure text-based language eliminates the need for specialized graphical rule editors. Instead, standard software engineering tools can be used to collaboratively develop a set of graph rules.

Wojciech Palacz, Iwona Grabska-Gradzińska

Blockchain vs GDPR in Collaborative Data Governance

Data Governance is the trending topic in today’s security-privacy-concerned digital ecosystem. Blockchain technology is probably one of the most acclaimed evolutions in recent times. Blockchain technologies can be a game-changer for data governance in the areas of transparency and data provenance. As a distributed ledger technology (DLT), blockchain is being touted as a potentially transformational force in collaborative data governance. The General Data Protection Regulation (GDPR) entered into force on May 25, 2018. It is the latest in a series of European Union (EU) legislative measures designed to give EU citizens more control over their data. GDPR, which directs a centralized ‘data controller’ (GDPR Article 4) to manage user data, clashes with the blockchain’s decentralized data storage and management process. The GDPR and the blockchain both have a common ideological ground, emphasizing the need for a change in managing personal data. While GDPR takes care of the policy side by setting up a standard, the blockchain helps enable the implementation side by providing a unique framework. In this paper, the authors analyze the clashes between the two and the potential solutions to those clashes for blockchain to comply with GDPR.

Rahul Dutta, Arijit Das, Ayan Dey, Sukriti Bhattacharya

Cooperative Decision Making in Crowdfunding – Applying Theory of Behavior and Exemplary Empirical Validation

Cooperative issues gained attention with fast growing digitalization and social networks. Especially, research in advanced cooperative funding, i.e. crowdfunding, is rapidly increasing. Hence, this paper addresses behavioral issues in the highly complex decision-making processes from the viewpoint of various actors in crowdfunding. It provides a detailed overview of major behavioral models by focusing on (i) the theory or reasoned action, (ii) its application and (iii) its exemplary empirical validation. The empirical study examines the crowdfunding process by targeting 416 entrepreneurs and by analyzing their behavior towards Kickstarter.com and Indiegogo.com.

Valerie Busse, Christine Strauss, Michal Gregus

FireBird: A Fire Alert and Live Fire Monitoring System Based on Social Media Contribution

Social media renders real-time updates, which are, in many cases, much faster than the traditional media. Due to this reason, social media is rapidly becoming an essential aspect of emergency response and recovery. This paper proposes a collaborative approach for a more coordinated emergency response system during a fire incident from Twitter. The method is implemented in a visual tool, called Firebird. Firebird attempts to source first-hand situational information from Twitter feeds. Using a combination of NLP and deep learning techniques, Firebird offers real-time fire detection, fact-checking, and incident location sharing with the firefighters to speed up the response efforts at a scale close to real-time.

Arijit Das, Rahul Dutta, Ayan Dey, Thomas Tamisier, Sukriti Bhattacharya

Clustering of Time-Series Balance History Data Streams Using Apache Spark

Clustering customers, predicting account balances, scoring credits, detecting risk cash flows, etc. are the problems that have been focused on research in the banking sector. With the explosion of big data, these problems will take a new approach. This paper proposes a new solution based on historical information of balances to cluster customers. The work has implemented clustering algorithms for time series in a big data environment. In addition, stream data clustering was tested with positive results. The result of customer clustering helps to make marketing decisions, forecasting of customer deposits in the following month, etc.

Do Quang Dat, Phan Duy Hung

Integrated Evolution Model of Service Internet Based on an Improved Logistic Growth Model

Service Internet is a complex, networked, and comprehensive service system formed by a large number of service units in different networks through a highly cooperative relationship. It can effectively and accurately create value for service stakeholders, and provide basic theoretical support for service application in many different situations. Nevertheless, there is a lack of systematic research on the overall dynamic evolution of service Internet, which leads to the lack of relevant mathematical models and theoretical guidance on the control and optimization for the overall service Internet. Therefore, considering the system characteristics such as cooperation and competition in service internet, this paper puts forward an overall evolution model of service Internet based on the logistic growth model, and then makes a theoretical analysis of its life cycle and evolution path. Finally, we use real-world electronic technology industry cluster data to verify the proposed model. Experiment results show that our model can better reflect and predict the evolution trend of service Internet.

Zhixuan Jia, Shuangxi Huang, Yushun Fan

A Data-Driven Platform for Predicting the Position of Future Wind Turbines

Optimal location of wind turbines is a complex decision problem involving environmental, performance, societal and other parameter. This paper investigates the domain by describing WindturbinesPlanner: by providing machine learning models trained on various data sources, the platform can help to anticipate the potential location of future onshore wind turbines in Luxembourg, France, Belgium and Germany.

Olivier Parisot

Cooperative Designing of Machine Layout Using Teaching Learning Based Optimisation and Its Modifications

A variation of customer demand over time periods has resulted in production layout’s efficiency especially in term of material handling cost. Machine re-location approach can help to maintain the flow distances but the costs related to the machine movement may be imposed. Cooperative redesigning of machine layouts between time periods was proposed to minimise both material handling and relocation costs. In this work, Teaching-Learning-Based Optimisation (TLBO) and its modifications were applied to solve non-identical machine layout redesign (MLRD) problem in multi-period multi-row configuration with demand uncertainty scenario. The computational experiments were carried out using eleven benchmarking datasets. The performance of the proposed methods was compared with the conventional Genetic Algorithm, Backtracking Search Algorithm. The effect of relocation cost on the layout design approach was also investigated.

Srisatja Vitayasak, Pupong Pongcharoen

Making Sociological Theories Come Alive

Cooperative Work on Collective Memories Regarding Frontier Zones

The aim of this paper is to demonstrate how the medium film is able not only to challenge, but also to push toward further development of some of the basic assumptions in sociological spatial theories as used within cultural area research. In so doing, we wish to increase knowledge on a central epistemological question for the field of Spatial Turn, namely how field research, by using film and playing it back to the field, can be a vehicle for new methodology in making theories collectively come alive.The paper reflects on thoughts about Frontier Zones developed from the interpretations of space and its history as presented by students of cultural studies. The students’ interpretations are according to the theory of memory by Aleida Assman, to the understanding of the structure of power by Michel Foucault, and to the symbolic power and the habitus of the place by Pierre Bourdieu. In this sense, the concept of Frontier Zones contributes in two directions: in the practical experiments that seek to highlight and read the Frontier Zones that are expressed in the urban dynamics as well as to highlight the Frontier Zones between areas of knowledge seeking to understand and redefine them. The perception of the Frontier Zones allows us to recognize the levels of belonging, diversity and composition.

Ursula Kirschner

Designing a Culturally Inspired Mobile Application for Cooperative Learning

Cooperative learning is shown to build positive relationships among students and improve one’s achievement. In most cases, studies focus on improving the type of learning technologies and other associated challenges pertaining to infrastructural needs. Little attention is given to understand specific knowledge that could enable advancement in learning, particularly in places that are culturally diverse with traditional knowledge. If cultural underpinnings are not carefully considered, it may hinder students to collaborate. This work adopted a user-centered approach to gain user needs and requirements to design and test a mobile application that fosters cooperative learning. The study also discovered the importance of having cultural elements and the need for having a system that recognizes and supports cooperative learning.

Philemon Yalamu, Wendy Doube, Caslon Chua

CLASS-O, A Cooperative Language Assessment System with Ontology

This paper describes the design, development and test of a novel Computerized Adaptive Testing (CAT) system for English language based on a testing process using features of Item Response Theory and an Ontology of English Language (ELO). The testing process employs a variable branching procedure to deliver the best next test item to the examinee based on the ability level shown so far. The formative assessment part is based on ELO, which acts as knowledge base for giving efficient and detailed feedback to the examinee. The summative part of the feedback consists of the percentage of correct answers regarding the three sections covered in the test: vocabulary, reading comprehension, and structure. It includes the proficiency level and places examinees into one of three groups: high, medium and low proficiency. After the test has terminated, each examinee contributes to a new version of the item bank by feeding back the individual response parameters, which refines item data for subsequent tests.

Chakkrit Snae Namahoot, Michael Brückner, Chayan Nuntawong

Comparing Machine Learning Algorithms to Predict Topic Keywords of Student Comments

Student comments as a kind of online teaching feedback in higher education organizations are becoming important which provides the evidence to improve the quality of teaching and learning. Effectively extracting useful information from the comments is critical. On the other hand, machine learning algorithms have achieved great performance in automatically extracting information and making predictions. This research compared the performance of three statistical machine learning algorithms and two deep learning methods on topic keyword extraction.

Feng Liu, Xiaodi Huang, Weidong Huang

Logging and Monitoring System for Streaming Data

Logging and monitoring data is very important during the development process as well as the operation of information systems. As the data grows to TB every day, this problem becomes more complicated. Companies can generally buy big data analytics platforms or build it by themselves. Whether buying or building, it is important to have a realistic expectation of time and budget needed to successfully implement, roll out and provide ongoing support. There was a lot of confusion and frustration as the data platform market grew. Suppliers sell their capabilities instead of the actual needs of their customers. Contrary to that trend, some companies would like to build the platform using open source systems such as Apache Flume, Apache Spark Streaming and some other auxiliary technologies at a reasonable cost. This study analyzes requirements, introduces system architecture, and builds a logging and monitoring system for streaming data. The work is also a real project in the field of advertising.

Nguyen Ngoc Chung, Phan Duy Hung

Active Learning with Crowdsourcing for the Cold Start of Imbalanced Classifiers

We present a novel cooperative strategy based on active learning and crowdsourcing, dedicated to provide a solution to the cold start stage, i.e. initializing the classification of a large set of data with no attached labels. The strategy is moreover designed to handle an imbalanced context in which random selection is highly inefficient. In this purpose, our method is guided by an unsupervised clustering, and the computation of cluster quality and impurity indexes, updated at each active learning step. The strategy is explained on a case study of annotating Twitter content w.r.t. a real flood event. We also show that our technique can cope with multiple heterogeneous data representations.

Etienne Brangbour, Pierrick Bruneau, Thomas Tamisier, Stéphane Marchand-Maillet

A Dynamic Visualization Platform for Operational Maritime Cybersecurity

Increasing cyberattacks in the maritime industry have highlighted the need for innovative approaches for effective cybersecurity responses. Considering the multiple stakeholders involved in maritime, collaboration and information sharing are essential for responding to cyber incidents and mitigation. However operational cybersecurity awareness is currently very low. This short paper presents the ongoing development of a dynamic security visualization platform for operational maritime cybersecurity. The platform can flexibly support collaboration among multiple stakeholders in the port ecosystem, while introducing multiple security roles to increase situational awareness. It also provides interfaces for communication among these roles as well as offering composable visualization widgets that can be customized to user needs.

Hanning Zhao, Bilhanan Silverajan

Collaborative Visual Analytics Using Blockchain

Blockchain, a decentralized, distributed and encrypted ledger, was created to eliminate the need for a central trusted entity. Blockchains provide users with a secure, trusted, auditable, and immutable record of transactions and are applicable to systems that require a trustworthy record of information. Our work explores the use of blockchain in collaborative visual analytics systems where users share and store a record of the visual analysis of some data. We built Share.va, a framework that allows users to store and share the states of visual analytics dashboards through a blockchain. We apply Share.va to an existing visual analytics dashboard and conduct a pilot study to understand the effectiveness and limitations of blockchain in collaborative visual analytics.

Darius Coelho, Rubin Trailor, Daniel Sill, Sophie Engle, Alark Joshi, Serge Mankovskii, Maria Velez-Rojas, Steven Greenspan, Klaus Mueller

The Development of an Asynchronous Web Application for Family Social Media Communication

In Asia countries, a family usually encourages their children to acquire a better education in a prestige university even though it is far from their hometown. The distance can affect to family relationship for this opportunity in life. A social media becomes one of the communication channels which usually insufficient to maintain proper communication and relationships due to the downside of synchronous communication. KUMAMI, a multi-platform web application, is developed by using an asynchronous communication. A solution to provides a better experience while communicating among family members with familiar features, members status, family notes. This method reduces expectation of an immediate response in the family as ordinary social media platforms.

Thanathep Thaithae, Apichaya Towsakul, Pornsuree Jamsri

Analysis of Scholarship Consideration Using J48 Decision Tree Algorithm for Data Mining

Consideration of scholarships is a common occurrence in educational institutions such as in a university. The scholarship selection committees play an essential role in judgment, which must pay attention to considering issues efficiently. However, they may make mistakes because an applicant’s information is complicated. This research proposes a scholarship analytic for the award of a student scholarship at university by using Data Mining techniques. The study was designed with seven variables on 468 samples, which were only selected with complete attributes from 2,549 student documents by a decision tree, J48 and J48graft algorithm with percentage split method at 20%, 30%, and 60%, k-fold cross validation both 5-folds and 10-folds. The development model’s results found that the model created by a decision tree with the J48 algorithm and percentage split method at 66% is most effective, with the precision value at 77.35%. Therefore, we choose to model with the J48 algorithm by percentage split method at 66% to develop the web application, which is useful for students to assess themselves before applying and will decrease the committee’s workload for the assessment of student’s scholarship applications.

Sanya Khruahong, Pirayu Tadkerd

Centralized Access Point for Information System Integration Problems in Large Enterprises

The role of information systems is extremely important for a business, especially those operating in the field of technology. The information system works with people, information technology and processes to accomplish business objectives. In the development process of large companies, the member units create many applications to serve their purposes. Increasing the number of applications or portals consumes employees’ time, and they may eventually be unable to keep track of all the necessary or useful information. That is why it is necessary to build a centralized and intelligent information access point for large organizations. The paper presents such a solution for the largest software company in Vietnam, the FPT software company. The paper describes the architectures and technologies applied to build an access point that brings whole new experiences to all employees. By integrating smart features based on artificial intelligence, the work contributed to enhancing performance and quality of work for 28,000 internal users. The approaches and results of the paper are completely applicable to similar large company models.

Mai Minh Hai, Phan Duy Hung

Cooperation Between Performance and Innovation Engine: An Exploratory Study of Digital Innovation Labs in Family Business

Digital innovation laboratories (DILs) constitute a promising approach to supporting a firm’s digital transformation. Whereas the firm’s existent departments, which form the so-called performance engine, can keep focusing on daily operations, the DIL representing the innovation engine executes digital innovation tasks. Cooperation between the performance engine and the innovation engine—including, but not limited to, the continuous exchange of information—is critical for the success of such an organizational setting. As research in this specific field of cooperative organization is still scarce, we employed an explorative case-study approach based on interviews with managers from DILs in family firms. Family business was chosen because it plays a prominent role in the German economy and it shall identify its own best practice in facing the digital future. We investigated on drivers, challenges, and organizational issues for establishing and operating such DILs. The findings provide valuable insights for practitioners in family business and may serve as a starting point for further research to examine differences between DILs in family and non-family business.

Melina Schleef, Jasper Steinlechner, Christine Strauss, Christian Stummer

Dynamic Network Visualization of Space Use Patterns to Support Agent-based Modelling for Spatial Design

Urban planning practice and architectural design increasingly adopt agent-based models and simulations to support decision-making for spatial design. Nonetheless, although essential, a reliable representation of human spatial behaviour in a socially rich context is still challenging. The study presents a framework built on a Dynamic Network Visualization of space use patterns based on a Post Occupancy Evaluation in the case study of a hospital ward, which is intended to develop an agent-based spatial analysis. A functional and organizational redesign of the ward plan is proposed following the analysis of social and spatial behaviour of agents. The outlined methodology aims to prepare the development of a multi-agent software simulation to validate the proposed redesign from a human-centred perspective. Findings indicate the relevance of the proposed approach starting from organizational contexts with complex workflows where cooperation between agents is widely exist, such as in healthcare environments. The framework is structured as a methodology to support the practice of architectural design and urban planning for the realization of more efficient and sustainable cities.

Dario Esposito, Ilenia Abbattista

Challenges Related to 4D BIM Simulation in the Construction Industry

This research explores the points of view of practitioners regarding the challenges associated with 4D BIM in Quebec. Quantitative and qualitative data were collected, through an online survey and interviews with various professionals, to understand the current challenges associated with the use of 4D simulation in the construction industry. The importance of certain challenges, from the perspectives of different professionals, are determined, particularly in terms of organization and contracts, IT infrastructures and software, and staff training. The results proposed a new perspective based on the opinions of professionals in the construction industry in Quebec regarding the issues surrounding 4D simulation.

Jeanne Campagna-Wilson, Conrad Boton

The Cooperative Management of Complex Knowledge in Planning: Building a Semantic-Based Model for Hydrological Issues

The management of issues related to water resources, a highly complex domain, has increasingly highlighted the critical role of knowledge towards shared, useful and effective planning decisions.Hydrology is an applied science with a very large theoretical base, its corpus borders with many others science domains. The clarification of theoretical, methodological, data, language and meaning issues and differences is of central importance. Therefore, the development of a knowledge management system with semantic extensions can meet some of the needs described.The main objective of this work is to investigate the potential for implementing a knowledge management system with semantic extensions, as well as to propose a functional architecture.To achieve that, first a KMS with semantic exstensions has been implemented and then the same system has been populated with an experimental knowledge content.Furthermore, a bottom-up extraction from the KMS of a simple ontology representing the data inserted in the KMS is considered, in order to show the KMS feature of clarifying and improving inter-domain communication, to enhance a common semantic understanding.

Mauro Patano, Domenico Camarda, Vito Iacobellis

A Collaborative Web Application Based on Incident Management Framework for Financial System

This study developed a system that utilizes incident management in the service operation area for systematic IT service management (ITSM). The implemented system utilizes Information Technology Infrastructure Library (ITIL) to enable efficient problem resolution through fast user error handling on the collaborative side and automatic identification as well as handling of the system. In addition, it is integrated with the system’s dashboard to quickly solve problems based on a multi-tiered system through SSO-based authentication. This study is expected to provide a systematic and efficient IT service along with aspect of cooperative through the development and experimentation of ITIL incident management processes and programs, which based on the Service Level Agreement, the analyzed system as well as the management process defined in the real bank system.

Chung Min Tae, Phan Duy Hung

Early Warning System for Shock Points on the Road Surface

Transportation is one of the fields with many special applications of information technology. These include major applications such as self-driving cars, intelligent traffic control, etc. supportive solutions for drivers with digital maps, anti drowsiness devices, automatic parking, alert cameras for speed and traffic signs, etc. This paper presents an early warning system for shock points on the road surface, the road positions that when the vehicle runs at high speed across it, the vehicle will bounce. This will endanger the occupants and cause the vehicle to break down quickly. The causes may be potholes, elephant potholes or the points connecting the road with the bridge, unusually subsided road points, etc. Such warning systems are especially useful when the vehicle is running at high speed on long roads or highways. Early warning helps drivers proactively slow down when receiving an alert from the system via a mobile application. The system allows user contributions for more updated and reliable information. Managers can also use this information to plan repair or maintenance of routes.

Phan Duy Hung

Vehicle Motion Simulation Method in Urban Traffic Scene

Vehicle motion simulation is an important part of traffic scene simulation, which is helpful for urban road planning and design, road capacity testing and other applications. Based on the characteristics of urban traffic scene, this paper studies the vehicle’s movement behavior. On the basis of the intelligent car following model based on safe distance, an improved car following model is constructed by adding acceleration adjustment items which is suitable for real urban traffic scene. Besides, an improved vehicle lane change model is construct on the basis of two-lane change model based on acceleration analysis. Experiments show that the two vehicle motion models proposed in this paper are effective in simulating vehicle stop, start and lane change in urban traffic scene.

Jinlian Du, Hao Zhou, Xueyun Jin

Collaborative Application for Rapid Design of Paintings in Vector Format

Online cooperative or collaborative work have become common nowadays, because this helps to do any job without require meet together physically in one place. On the other hand, due to out current reality, inherent to many health conditions, traffic difficulties, and social insecurity; virtual or distance education is increasingly being promoted. In that sense, the main goal of this research work is develop a web based collaborative tool for rapid designing paints. This could be useful in many different areas, like as replacing the classical whiteboard, or express ideas to a workgroup, or even to design any realistic picture. This application allows to work together with a group of around ten connected users to collaborate virtually designing drawings in real time. The interaction experience depends on the internet bandwidth of all the users. For the implementation, many open source popular frameworks and programming utilities have been used. The presented results demonstrate the high scalability and versatility of our system being capable of managing hundreds of objects in real time.

Yalmar Ponce Atencio, Manuel J. Ibarra, Herwin Huillcen Baca

Implementation of Cooperative Sub-systems for Mobile Robot Navigation

This work addresses the issue of mobile robot navigation system consisting of two cooperative sub-systems: a path planner sub-system and localizer sub-system. In the navigation system, the robot needs to localize itself and make its way to its desired location. Hence, the robot’s behavioral ability in finding its position becomes a major issue, along with its ability to plan a path to its goal. In the proposed work, the localization and path planning techniques have been adopted, and a series of experiments have been conducted using ROS based mobile robot. The experimental results reveal that the implemented sub-systems can work cooperatively as the localizer can effectively guarantee the accuracy of the robot’s current position and its orientation while the path planner can ensure that the robot maintains a safe distance from obstacles concurrent with finding an optimal path from its current position to the desired goal.

Panus Nattharith

Searching for Extreme Portions in Distributions: A Comparison of Pie and Bar Charts

Aggregated data visualizations are often used by collaborative teams to gain a common understanding of a complex situations and issues. Pie and bar charts are both widely used for visualizing distributions. The study of pie versus bar charts has a long history and the results are seemingly inconclusive. Many report authors prefer pie charts while visualization theory often argues for bar graphs. Most of the studies that conclude in favor of pie charts have focused on how well they facilitate the identification of parts to the whole. This study set out to collect empirical evidence on which chart type that most rapidly and less erroneously facilitate the identification of extreme parts such as the minimum, or the maximum, when the distributions are similar, yet not identical. The results show that minimum values are identified in shorter time with bar charts compared to pie charts. Moreover, the extreme values are identified with fewer errors with bar charts compared to pie charts. One implication of this study is that bar charts are recommended in visualization situations where important decisions depend on rapidly identifying extreme values.

Frode Eika Sandnes, Aina Flønes, Wei-Ting Kao, Patrick Harrington, Meisa Issa

Visualizing Features on Classified Fauna Images Using Class Activation Maps

This article highlights first the power of deep learning in a collaborative context for the automatic extraction of information from images and complementarily the benefit of Class Activation Maps (CAM) for identifying in a visual way the features taken into account for extracting this information. Experimental results illustrate the approach as a whole on a significant challenge of classifying newt images.

Yoanne Didry, Xavier Mestdagh, Thomas Tamisier

Social Media Analytics in Comments of Multiple Vehicle Brands on Social Networking Sites in Thailand

This paper proposes data analytics in comments of multiple vehicle brands by using Social Media Analytics (SMA), which collects data from social networking sites. Generally, it can intensively evaluate the information to make business decisions and find trends or some significance. However, Google research has shown that vehicle companies should study consumer behaviors from the Internet when people decide to buy a new car. Therefore, SMA can lead to creating motivation or a strategy for the business model. This research investigates the use of comments on social networking sites to analyze the relationship model of car purchase decisions of consumers in Thailand that relate to public relations, marketing, awareness, and the company’s brand value. We use the principles of the online social data analysis process, which are 1) Capture 2) Understanding 3) Presenting and is called the CUP framework, by collecting 76,331 comments on ten vehicle brands. Finally, the results show that the positive sentiment has a suitable average to be more than 69.85%, and the average negative sentiment should not exceed 30.15%. This result may help the automobile business entrepreneurs to determine the guidelines for marketing activities in the vehicle industry in Thailand.

Sanya Khruahong, Anirut Asawasakulson, Woradech Na Krom

Static and Dynamic Parameter Settings of Accelerated Particle Swarm Optimisation for Solving Course Scheduling Problem

The university course timetabling problem (UCTP) is one of the most challenging scheduling problems and also classified to be a Non-deterministic Polynomial (NP)-hard problem. An Accelerated Particle Swarm Optimisation based Timetabling (APSOT) program was developed to generate the best-so-far timetables with the minimal total operating costs. Two new variants of Accelerated Particle Swarm Optimisation (APSO) including Static and Dynamic (S-APSO and D-APSO) were proposed and embedded into the APSOT tool. The analysis of variance on the experimental results indicated that the main effects and interactions of D-APSO were statistically significant with a 95% confidence interval. The S-APSO and Maurice Clerc PSO (MCPSO) outperformed the other variants of PSO for most datasets whereas the execute times required by all variants of PSO were slightly different.

Thatchai Thepphakorn, Saisumpan Sooncharoen, Pupong Pongcharoen

Backmatter

Additional information