Skip to main content
main-content
Top

About this book

This book constitutes the refereed post-conference proceedings of the International Conferences ICCASA and ICTCC 2020, held in November 2020 in Thai Nguyen, Vietnam.

The 27 revised full papers presented were carefully selected from 68 submissions. The papers of ICCASA cover a wide spectrum in the area of context-aware-systems. CAS is characterized by its self- facets such as self-organization, self-configuration, self-healing, self-optimization, self-protection used to dynamically control computing and networking functions. The papers of ICTCC cover formal methods for self-adaptive systems and discuss natural approaches and techniques for computation and communication.

Table of Contents

Frontmatter

Context Aware Systems and Applications

Frontmatter

Formal Verification of Multi-agent Plans for Vehicle Platooning

Abstract
The collaboration and coordination of autonomous vehicles into convoys or platoons have been used on our highways. However, before deploying such vehicles on the real road, their autonomous behaviors must be certified to act safely. The vehicle platooning can be considered as a multi-agent system where each agent can make its own autonomous decisions. In order to ensure that these decision-making agents in the platoon never violate safety properties, we use the Uppaal model checker to verify them. Furthermore, to facilitate the checking process and create a consistent translation process, we have developed an automated translation program that can map our multi-agent plans to the Uppaal model checker format.
Thao Nguyen Van, Kurt Geihs

Contextual Defeasible Reasoning Framework for Heterogeneous Systems

Abstract
This paper presents a contextual defeasible reasoning based multi-agent formalism to model heterogeneous systems using the notion of a multi-context system. This framework relies on the semantic knowledge sources which allow us to model context-aware non-monotonic reasoning agents to infer the desired goals using the extracted rules from the ontologies and handles inconsistencies using conflicting contextual information. We illustrate the validity and correctness of the proposed formalism using a simple case study of a smart healthcare system with the prototypal implementation of the system.
Salwa Muhammad Akhtar, Hafiz Mahfooz Ul Haque

Abnormality Bone Detection in X-Ray Images Using Convolutional Neural Network

Abstract
Medical imaging plays a role as a crucial source of data for disease detection and diagnosis. Recent advancements in machine learning and deep learning have become an efficient tool for medical image analysis. Medical image research laboratories are rapidly creating machine learning systems to achieve the professional performance of humans. However, both machine learning and deep learning methods are complex and require a lot of expertise, resources, knowledge, and time to train. Those create a significant barrier for researchers. In this study, we propose a convolutional neural network architecture to detect abnormalities in bone images. The proposed method provides insight into medical images and explains in detail how the model supports the diagnosis.
Hiep Xuan Huynh, Hang Bich Thi Nguyen, Cang Anh Phan, Hai Thanh Nguyen

Statistical Properties and Modelling of DDoS Attacks

Abstract
The work presented in this paper is an implementation of a design of a DDoS simulation testbed that uses parameter estimation and probability fitting of source IP address features of a network. We explored the issue of lack of adequate and recent evaluation datasets, we therefore designed a way that can be used to generate synthetic data that simulates a DDoS attack. We found that the Gaussian probability distribution best represents the normal operations of a network, while the Poisson probability distribution represents the operations of a network under a DDoS attack.
Pheeha Machaka, Antoine Bagula

Estimating Land Surface Temperature from Landsat-8 Images Based on a Cloud-Based Automated Processing Service

Abstract
As the biggest city in Vietnam, Ho Chi Minh City (HCMC) usually suffers from a number of environmental issues such as traffic jam, subsidence and inundation, river and air pollution, high temperature, etc. Therefore, a hazard maps system helps the city government and population understand well environmental risks. The main data sources for such system is a combination of in-situ measurements in ground and remotely sensed images from space. Popular satellite data products available and free of charge are used to environmental monitoring, consisting of Sentinel, Landsat, and Terra/Aqua MODIS. In this paper, we focus on estimating land surface temperature (LST) from Landsat-8 images based on a cloud-based automated processing service. The LST image is computed from red, near-infrared and thermal infrared bands. The service can be integrated as a part of a hazard map system when its data are collected from different sources.
Phan Hien Vu, Tan-Long Le, Cuong Pham-Quoc

A Comparison Between Stacked Auto-Encoder and Deep Belief Network in River Run-Off Prediction

Abstract
The application of deep neural networks in forecasting hydrological time series data is increasingly popular, aiming to improve prediction accuracy in this challenging problem. As for river runoff prediction, Deep Belief Network (DBN) and Stacked Autoencoder (SAE) are two kinds of deep neural networks which are commonly used for extracting meaningful features from the data before prediction. In this study, we aim to compare the prediction performance of SAE model with that of DBN model on the runoff data of Srepok River in Central Highlands of Vietnam. Experiments are conducted by using historical data of the Srepok River that were collected in 11 years. The experimental results in this case study show that SAE brings out better prediction accuracy than DBN in terms of three evaluation criteria: correlation, root mean square error, and mean absolute percentage error.
Bui Tan Kinh, Duong Tuan Anh, Duong Ngoc Hieu

Developing Data Model Managing Residents by Space and Time in Three-Dimensional Geographic Space

Abstract
A major challenge currently of levels of government and construction contractors is how to manage population growth by geographic location and over time. The population increases by geographic location and over time leading to the increase of positive and negative aspects in the community. Managing people living and working on the territory by space and time is a very important and urgent job. The levels of government must regularly manage the people living and working on their localities, which are always associated with the management of permanent populations, temporary populations, blood relations, social relations, previous conviction relations, previous offence relations and birth or death relations that all of this management takes place at a specific geographic location and time. The paper proposes to develop a spatial - temporal - residential data model that is capable of managing human activities at the place of residence, at the workplace and at the location of the relations by geographic location and over time, this model is called STRDM. The paper illustrates empirical results with visual forms through the use of queries by space, time, resident, and search for ancestor and descendant. These empirical results show that it can be applied to residential data management systems in new urban areas.
Dang Van Pham

Trigger2B: A Tool Generating Event-B Models from Database Triggers

Abstract
Triggers are commonly used many traditional database applications that can be checked if they are correct after execution or manual inspection. Formal methods are techniques complementing to testing that ensure the correctness of software. In practical aspect, one limitation of formal techniques is the complexity that makes software developers lazy to use in the development. This paper introduces a tool named Trigger2B which partly supports for translating DML triggers to Event-B models. From the targeted model, we can verify the data constraints and detect infinite loops of trigger execution with RODIN. Finally, we take an example for illustration purpose. The proposed tool overcomes the complexity of formal modeling and makes them practical in the development.
Hong Anh Le

Predicting the Level of Hypertension Using Machine Learning

Abstract
In recent years, data mining has been put into research and application in many different areas in the world such as economy, education, sports, telecommunications, etc. And the health - health care [1] sector is not out of this trend. If it is possible to successfully analyze the data [24] from the huge amount of data of diseases, patients and hospitals every day, it can help a lot of doctors in the process of diagnosis, examination and treatment of diseases for patients. The problem raised here is whether we can accurately diagnose the patient’s disease based on the information provided. The information provided may be age, gender, occupation, symptoms, test information, etc. from which it is necessary to achieve the most accurate diagnosis possible to minimize the work pressure for the medical team as well as minimize the time of diagnosis.
Pham Thu Thuy, Nguyen Thanh Tung, Chu Duc Hoang

Can Blockchain Fly the Silver Fern?

Exploring the Opportunity in New Zealand’s Primary Industries
Abstract
Blockchain is an emerging technology perceived as ground-breaking. Yet, technology service providers are not realising the untapped market potential as quick as it was predicted. New Zealand is not any different. Currently, the number of blockchain-based solutions available in the country is rather limited. A clear understanding of the market of blockchain is critical for service providers to recognise the opportunities and the challenges. It has been suggested that multiple industries could utilise blockchain technology to attain numerous benefits. The primary industries of New Zealand will be one of them that remains underexplored. Therefore, in this study, we use total addressable market (TAM), a technique to estimate the market size, to explore the available economic opportunity of blockchain-based solutions in New Zealand’s primary industries. Our estimation suggests that it may be close to NZ$1.65 billion per year, including self-employed enterprises; or NZ$496 million per year, excluding self-employed enterprises. Besides, our review of secondary sources indicates that blockchain technology could tackle some of the challenges the primary industries are facing like food fraud and foodborne illness. However, lack of strong and practical use cases, lack of streamlined practice for data management, lack of understanding of the technology and its implication to business, and lack of regulation and legislation are the major impediments to blockchain adoption.
Mahmudul Hasan, Johnny Chan

Design and Implementation of a Real-Time Web Service for Monitoring Soil Moisture and Landslide in Lai Chau Province, Viet Nam

Abstract
Web service technology has been recognized as one of key factors for developing natural hazards monitoring systems. This study proposes an open source web service solution for monitoring soil moisture in Lai Chau, a northern province of Vietnam. The system supports a real-time mechanism for data communication with gateway and mobile applications via http-based protocol. It receives structured data packets from the gateway, then makes the visualization on map and immediately alerts users if data is in warning range. Mobile applications are also capable to retrieve web map services by using provided RESTful APIs. The system has made a great contribution to the local government for natural disasters monitoring and management in Lai Chau province.
Hong Anh Le, Bao Ngoc Dinh, Dung Nguyen

Optimizing the Operational Time of IoT Devices in Cloud-Fog Systems

Abstract
With the increasing number of connected devices, sensors, data generated need to be analyzed. The current cloud computing model, which concentrate on computing and storage resources in a few large data centers, will inevitably lead to excessive network load, end-to-end service latency, and overall power consumption. This leads to the creation of new network architectures that extend computing and storage capabilities to the edge of the network, close to end-users. The emerging problem is how to efficiently deploy the services to the system that satisfies service resource requirements and QoS constraints while maximizing resource utilization.
In this paper, we investigate the problem of IoT services deployment in Cloud Fog system to provide IoT services with minimal energy consumption. We formulate the problem using a Linear Programming (LP) model to maximize the operational time of Cloud-Fog system as well as the IoT services specific requirements [1]. We propose a new heuristic algorithm to simplify the problem. We compare the lifetime of the proposed algorithm with the optimal solution solved by Linear Programming. The experimental results show that our proposed solution is very close to optimum solutions in terms of energy efficiency.
Nguyen Thanh Tung

Proposing Spatial - Temporal - Semantic Data Model Managing Genealogy and Space Evolution History of Objects in 3D Geographical Space

Abstract
Managing construction projects in new urban areas is an essential work for construction contractors as well as authorities at all levels. In this management, managing the spatial evolutionary history of two-dimensional (2D), two-point-five-dimensional (2.5D) and three-dimensional (3D) spatial objects over time and semantics in 3D geographical space is an urgent and extremely important work. This paper proposes a spatial - temporal - semantic data model (STSDM), spatial queries over time and semantics, and algorithms finding the ancestors and descendants of space objects (ASA and DSA). The paper presents some empirical results about the spatial evolutionary history of spatial objects over time and semantics. The experimental results show that it can completely be used to trace the space evolution history of bridges, houses and apartments at a given time or in a given period in new urban management applications.
Dang Van Pham

Modelling Situation-Aware Formalism Using BDI Reasoning Agents

Abstract
Natural or man-made disasters are unavoidable situations that can occur anytime and anywhere. Timely disaster response plays a vital role in reducing its after-effects and can save countless lives. Over the years, people have been developing the guidelines and processes to cope up with such kinds of hazardous situations. In recent years, situation-awareness has been considered to be the most fascinating approach for the situation assessment and provides decision support accordingly. Situation-aware systems observe/perceive dynamic changes in the environment, understand/comprehend the situation, and perform actions according to the environment. Although state-of-the-art formalisms have been developed to handle such kinds of hazardous situations intelligently and rescue the victims. However, there are still many uncontrolled challenging issues. In this paper, we present a Belief-Desire-Intention (BDI) based multi-agent formalism to model the context-aware decision support system dynamically in order to achieve the desired goals. To illustrate the use of the proposed formalism, we develop a simple case study in which BDI agents are modeled and simulated to present results in terms of agents’ reasoning processes. The behavior of the system has been tested using the NetLogo simulation environment to rigorously evaluate the validity of the system.
Kiran Saleem, Hafiz Mahfooz Ul Haque

Using Empathy Mapping in Design Thinking Process for Personas Discovering

Abstract
Exploring user attitudes and behaviors within the domain of interests helps the user experience team to match the user with a deeper understanding. The mapping process also reveals any gap in existing user data. Design thinking is the ground-breaking and cooperative approach to problem-solving that puts the user first to make user-centered products and services. There are many various design thinking activities that use to generate a thoughtful of the users or customer, including the conception of personas. This paper revisits the concept of persona and draws the connection of using empathy map to build persona within the design thinking process. Also showing the benefit of empathizing method to construct the effective persona. This can be used for the benefit in Human Computer Interaction(HCI) designing processes or marketing analysis.
Waralak Vongdoiwang Siricharoen

Taiwanese Stock Market Forecasting with a Shallow Long Short-Term Memory Architecture

Abstract
The trading of stock in companies holds an important part in numerous economies. Stock Forecast which is popularly published in the public domain in the forms of newsletters, investment promotion organizations, public/private forums, and scientific forecast services is very necessary to contribute successes in financial for individuals or organizations. Leveraging advancements in machine learning, we propose an approach based on Long Short-Term Memory model and compare the performance to the classic machine learning such as Random Forest model and Support Vector Regression model when we do forecast tasks on Taiwanese stock market. The proposed method with deep learning algorithm shows better performance comparing to the classic machine learning in the tasks of forecasting the stock market in Taiwan.
Phuong Ha Dang Bui, Toan Bao Tran, Hai Thanh Nguyen

A Convolutional Neural Network on X-Ray Images for Pneumonia Diagnosis

Abstract
The application of AI in general and Deep learning, in particular, is becoming increasingly popular in human life. AI has been able to replace people in many fields, with data already synthesized and stored by computers that will help AI become smarter. One of the areas where AI can be applied very well is the medical field, especially X-ray imaging. In this study, we propose a convolutional network architecture to classify chest X-ray images as well as apply explanatory methods to trained models to support disease diagnosis. The proposed method provides insight into medical imaging to support the diagnosis of Pneumonia.
Hiep Xuan Huynh, Son Hai Dang, Cang Anh Phan, Hai Thanh Nguyen

Counterbalancing Asymmetric Information: A Process Driven Systems Thinking Approach to Information Sharing of Decentralized Databases

Abstract
This paper explores asymmetric information and how to counterbalance it. It utilizes the case study of a hypothetical company called “Hashable”. The purpose of this case study is to exemplify a proposed solution to address the information asymmetry faced by buyers of residential real estate in New Zealand. A procedural response is provided for organizing the information needed to make an informed decision on purchasing a property. A causal loop diagram is introduced to develop an understanding of the various stakeholders involved in the proposed solution and their interaction with the information they provide. This paper highlights the core problems regarding information asymmetry within a transaction. It also provides procedural and technological solutions to counterbalance this information asymmetry while simultaneously reducing information costs and increasing reliability of the information provided.
Mark Hoksbergen, Johnny Chan, Gabrielle Peko, David Sundaram

Nature of Computation and Communication

Frontmatter

Towards Service Co-evolution in SOA Environments: A Survey

Abstract
In a Service-Oriented Architecture (SOA), the need for service evolution comes from service providers and their clients due to changes in requirements and environments. However, enabling controlled service evolution is a critical challenge for the developers since services may be part of different business processes and depend on other services. This paper presents the state of the art of service evolution and in particular, of service co-evolution. The paper also gives an outlook to an emerging trend named microservice and analyzes its advantages and challenges related to service co-evolution. The survey aims to provide a technical overview document to researchers and practitioners who are building industrial-strength adaptive applications related to service co-evolution.
Huu Tam Tran, Van Thao Nguyen, Cong Vinh Phan

Analysis of a HIPS Solution Use in Power Systems

Abstract
The aim of this paper is to conduct a performance comparative analysis of open-source HIPS (Host Intrusion Prevention System) solutions in order to improve security measures in power systems. First, the HIPS technology is introduced with an emphasis on its use for increasing security within power systems. Secondly, selected HIPS solutions are introduced in order to conduct the comparative analysis. Finally, the results of the comparative analysis of the individual solutions are presented with an emphasis on the use of system resources in the deployment of HIPS solutions on Windows workstations.
Tomas Svoboda, Josef Horalek, Vladimir Sobeslav

Behavioral Analysis of SIEM Solutions for Energy Technology Systems

Abstract
The aim of this article is to analyze SIEM solutions. Emphasizing the use of these systems to ensure data confidentiality, availability, and integrity monitoring energy technology systems. First, the issue of security in the area of energy systems is introduced. In order to maintain the availability, confidentiality and data integrity, the user behavioral analysis modules in SIEM systems are also introduced. The next section presents specific SIEM solutions that can be currently used not only in ICS environments and which will be subject to comparative analysis. This is IBM Security QRadar SIEM and LogRhythm NextGen SIEM. What follows is the introduction and implementation of modules for user behavioral analysis in the mentioned SIEM solutions, including testing own Use Case for testing user behavioral analysis modules. The results of the comparative analysis of user behavioral analysis modules in selected SIEM solutions are presented in the last section.
Tomas Svoboda, Josef Horalek, Vladimir Sobeslav

Threads Efficiency Analysis of Selected Operating Systems

Abstract
The aim of the article is to present results of the testing focused on efficiency of CPU performance and its threads in single-threading and multithreading modes in various versions of operating systems from the family of Microsoft Windows. The main task was to verify whether the chosen operating system version affects the efficiency of using threads by the operating system, with the emphasis of their upgrade in technological and industrial systems.
Josef Horalek, Vladimir Sobeslav

An Architecture for Intelligent e-Learning Platform for Student’s Lab Deployment

Abstract
For better understanding and better learning of new technologies, there is welcome to have some hands-on experiences with these subjects. This helps with knowledge adoption and also increases learning efficiency. In this article, there is analyzed inputs for a proposal of this system and requirements, which should be meet for such system, and also there is identified learning subjects and areas, which could use this tools. This article deals with and describes an architecture, which can help with automation and deployment labs, which can students use for learning and their research. There is described the architecture for a system, which is able to deploy these environment into more cloud type providers and also is open and able to handle more types run-time technologies, especially virtualization (e.g. OpenStack, Kubernetes and more). The architecture describes platform, which consists an portal or a learning web-based tool, which can be used for learning and also for interface of student labs, which can be automatically deployed based on input conditions with automation tools to some public or private cloud services.
Peter Mikulecky, Vladimir Sobeslav, Matej Drdla, Hana Svecova

Improved Packet Delivery for Wireless Sensor Networks Using Local Automate Based Autonomic Network Architecture in a ZigBee Environment

Abstract
A low cost, low power personal area network is formalized by IEEE 802.15.4 standard ZigBee Wireless Sensor Network. The most common way to construct a WSN using ZigBee is to use tree type network topology. This leads to large amount of energy consumption because of congestion in network. The node failures in a network topology, results in reconstructing the route of existing structure. Thus, a Local automate based autonomic network architecture is deployed at the MAC layer of ZigBee protocol. The architecture considers previous occurrences of probabilities of nodes and learns their behavior during transmission. This record an active state of each node, that inturn reduces congestion when neighboring node failure occurs. Simulation results provide 20% increase in unicast and multicast delivery rate. Finally, throughput of an entire network in a larger density dynamic environment increases.
K. N. Sanjay, K. Shaila, K. R. Venugopal

Hybrid Domain Steganography for Embedding DES Encrypted QR Code Using Random Bit Binary Search

Abstract
Steganography is a technology used for hiding the digital information into an electronic document so that it can be used only by the authorized entity and not available to trespassers. In the recent era, QR code is used versatile in all the applications. The data capacity of QR code is more as the information is codified in the form of image. Image Steganography can be achieved in spatial, transformation or hybrid domain. In this paper, a novel hybrid domain Steganography is employed for embedding encrypted QR code image in Source Image to get stego Image using Discrete Wavelet Transforms and Random Bit Binary Search (DWT - RBBS) technique. The information is encrypted using DES encryption algorithm and is codified to QR code image. This QR code image is then embedded into the source image using DWT-RBBS technique resulting in multiple level of security.
B. S. Shashikiran, K. Shaila, K. R. Venugopal

Design and Testing a Single-Passenger Eco-Vehicle

Abstract
Protection of the living environment for sustainable development is a concern of mankind. In particular, reducing CO2 emissions is the top criteria. A number of technologies that include a method of improving fossil fuel consumption effectiveness have been introduced into new automobiles in order to limit the negative effects caused by CO2. In this paper, new technological solutions will be proposed. They are combined in a novel method in order to improve vehicle engine performance, to improve ignition and air return systems and to reduce friction between vehicle and environment when it is moving. The propsed method is applied into a new implemented vehicle for Eco Mileage Challenge (EMC) 2019 which is organized annually by Honda Vietnam Compapy. All tests and tournament results of 240 km per liter of RON98 gasoline in average prove that the propsed method is feasible and effective in fuel savings.
Tri Nhut Do, Quang Minh Pham, Hoa Binh Le-Nguyen, Cao Tri Nguyen, Hai Minh Nguyen-Tran

A Study on the Methology of Increasing Safety for Cometto MSPE System

Abstract
In recent years, the heavy transport industry has been developing strongly, the transportation of super long and overweight packages is more advantageous due to modern transportation systems applying the achievements and development of technology. The leading trailer manufactors in the world such as: Cometto, Nicolas, Kamag, and Goldhofer… increasingly research and manufacture for this heavy transport industry. In Vietnam, leading transport companies have invested in self-propelled tractors from Cometto (Italy) to transport these goods. However, during operation, safety has been revealed. Therefore, in order to further enhance the safety of the entire system when transporting large economic parcels to the required location, a method is proposed that the throttle valve have been attached to appropriate position in the hydraulic pump system. The efficiency of throttle assembly is verified in practice when applying this improved trailer system for transporting the drilling rigs up to 3,200 tons in Vietnam.
Hai Minh Nguyen Tran, Quang Minh Pham, Hoa Binh Le Nguyen, Cao Tri Nguyen, Tri Nhut Do

Backmatter

Additional information

Premium Partner

    Image Credits