Cobalt

Q4

FallNeXt: A Deep Residual Model based on Multi-Branch Aggregation for Sensor-based Fall Detection

Mekruksavanich S., Jitpattanakul A.

Q4

ECTI Transactions on Computer and Information Technology, 2022, цитирований: 36,

open access

,

doi.org, Abstract

Falls are uncommon and pose a substantial health danger to adults and the elderly. These situations are a leading cause of severe injury. More harm could be averted if the faller could be located in time. The rising older population necessitates the rapid development of fall detection and prevention technologies. The burgeoning technology industry is focused on developing such technologies to improve the living conditions for the elderly in particular. A fall detection system monitors falls and provides an assistance notice to support mitigation of falls. This study proposes a sensor-based solution based on a deep learning network named FallNeXt to safeguard individual privacy and increase fall detection performance. This proposed network is a novel deep residual network that utilizes multi-branch aggregation to enhance fall detection capability. The detection effectiveness of this study was evaluated using three benchmark datasets for sensor-based fall detection: UpFall, SisFall, and UMAFall datasets. Compared to benchmark deep learning models on the three datasets, the experimental findings indicate that the proposed FallNeXt network scored the most significant overall accuracy and F1-score, with 96.16% and 99.12%, respectively. The benefit of the FallNeXt model's small but highly effective size for fall detection is its portability.

Q4

A unified convolution neural network for dental caries classification

Wantanajittikul K., Panyarak W., Jira-apiwattana D., Wantanajittikul K.

Q4

ECTI Transactions on Computer and Information Technology, 2022, цитирований: 4,

open access

,

doi.org, Abstract

Dental caries is one of the most common chronic diseases in the oral cavity. The early detection of initial dental caries is needed for treatment. It is problematic to diagnose the initial carious lesion, as known as enamel caries, due to the similarity of a tiny hole to human perception error. In this paper, we propose a unified convolution neural network to improve the diagnostic and treatment performance for dentists using classification from bitewing radiographs. We adapt the AlexNet and ResNet models to properly classify the dental caries dataset. The modified ResNet successfully achieves excellent binary-classification performance with accuracy of 86.67%, 87.78% and 82.78% of teeth with all conditions, teeth without dental restoration, and only teeth with dental restorations, respectively. For multilevel classification, our model has good performance with 5-class average accuracy of 80%. Remarkably, our adapted ResNet-18 has good performance with enamel caries and secondary caries with accuracy of 86.67% and 77.78%, respectively. Conversely, our ResNet-50 and ResNet-101 have contradictory low performance with enamel and secondary caries but high performance with sound teeth, dentin caries and teeth with restoration of 90%, 78.89% and 88.89%, respectively. The accuracies of our model are good enough that our model could support dentists to enhance diagnostic performance.

Q4

A Study on Usability and Motion Sickness of Locomotion Techniques for Virtual Reality

Khundam C.

Q4

ECTI Transactions on Computer and Information Technology, 2021, цитирований: 7,

open access

,

doi.org, Abstract

   Virtual Reality (VR) is widely used today in both research and entertainment. The continuous growth of this technology makes VR consumer hardware now available for masses. The new trend in the next generation of VR devices is a VR headset and controllers with inside-out technology. These VR devices will become an important basis for the future of VR applications. Virtual travel or locomotion inside VR experiences is the important part in the VR application development, which affected to the users preference. The goal of this research is to study the difference of locomotion in VR with new trend devices consisting of VR headset and controllers without using other accessories. Three locomotion techniques: controller-based, motion-based and teleportation-based were used to analyze the differences. The VR scene with virtual environments was created to use in the experiment where the users have to move with different locomotion technique. The Usability Questionnaire (UQ) is used to evaluate the usability value of each locomotion technique, while Simulator Sickness Questionnaire (SSQ) is used to assess the motion sickness value. The results showed that the usability (p-value=0.02007) and motion sickness (p-value=0.00014) of all locomotion techniques are different and the usability affected to the user preference. The conclusions of VR locomotion studies were discussed with the limitations of the study and the future work for this research.  

Q4

Damaged Vehicle Parts Detection Platforms using Deep Learning Technique

Thonglek K., Urailertprasert N., Pattiyathanee P., Chantrapornchai C.

Q4

ECTI Transactions on Computer and Information Technology, 2021, цитирований: 5,

open access

,

doi.org, Abstract

   Automatic vehicle damage detection platform can increase the market value of car insurance. The es- timation process is usually manual and requires hu- man experts and their time to evaluate the damage cost. Intelligent Vehicle Accident Analysis (IVAA) system provides an artificial intelligence as a service (AIaaS) for building a system that can automatically assess vehicle parts’ damage and severity level. The insurance company can adopt our service to build the application to speedup the claiming process. There are four main elements in the service system which support four stakeholders in an insurance company: insurance experts, data scientists, operators and field employees. Insurance experts utilize the data label- ing tool to label damaged parts of a vehicle in a given image as a training data building process. Data scientists iterate to the deep learning model build- ing process for continuous model updates. Opera- tors monitor the visualization system for daily statis- tics related to the number of accidents based on lo- cations. Field employees use LINE Official integra- tion to take a photo of damaged vehicle at the acci- dent site and retrieve the repair estimation. IVAA is built on the docker image which can scale-in or scale- out the system depend on utilization efficiently. We deploy the Faster Region-based convolutional neural network, along with residual Inception network to lo- calize the damage region and classify into 5 damage levels for a vehicle part. The accuracy of the localiza- tion is 93.28 % and the accuracy of the classification is 98.47%.  

Q4

Evaluation of a Textile PIFA for Wearable IoT Application and its Challenges

Aliakbarian H., Hajiahmadi A., Mohamad Saaid N., Jack Soh P.

Q4

ECTI Transactions on Computer and Information Technology, 2021, цитирований: 1,

open access

,

doi.org, Abstract

The ever increasing use of body-worn systems in the Internet of Things application such as needs better antenna subsystem designs compatible with its requirements. Several challenges limiting the performance of a body-worn system, from materials, and environmental conditions to the effects of on body application and its hazards are discussed. As a test case, a flexible textile planar inverted-F antenna is presented and discussed. The choice of this topology is due to its simplicity in design and fabrication, relatively broad bandwidth and the presence of a rear ground plane, which minimizes the impacts of the human body on the antenna performance. It is designed on a felt substrate, whereas Aaronia-shield conductive textile is utilized as its conductive parts (radiator, shorting wall and ground plane). The antenna performance are studied in two cases, first in free space and then in bent conditions in the close proximity to the human body. The influence of the relative humidity on the textile antenna performance is also investigated numerically. Simulated and measured results indicated good agreements. Finally, the proposed antenna is integrated with a transceiver module and evaluated on the body in practice. Its wireless link quality is assessed in an indoor laboratory.

Q4

Application of an Analytic Hierarchy Process to Select the Level of a Cyber Resilient Capability Maturity Model in Digital Supply Chain Systems

Uraipan N., Praneetpolgrang P., Manisri T.

Q4

ECTI Transactions on Computer and Information Technology, 2021, цитирований: 4,

open access

,

doi.org, Abstract

Cyber resilient is the ability to prepare for, respond to and recover from cyber attacks. Cyber resilient has emerged over the past few years because traditional cybersecurity measures are no longer enough to protect organizations from the spate of persistent attacks. It helps an organization protect against cyber risks, defend against and limit the severity of attacks, and ensure its continued survival despite an attack.The cyber resilient capability maturity model is a very important element within an effective in digital supply chain. The maturity model has 6 components: identify, protect, detect, respond, recover and continuity which affect the cybersecurity of the organization. To measure the maturity level needs a holistic approach. Therefore, the analytic hierarchy process (AHP) approach which allows both multi-criteria and simultaneous evaluation. Generally, the factors affecting cyber resilient in digital supply chain have non-physical structures. Therefore, the real problem can be represented in a better way by using fuzzy numbers instead of numbers to evaluate these factors. In this study, a fuzzy AHP approach is proposed to determine the cyber resilient capability maturity level in digital supply chain. The proposed method is applied in a real SMEs company. In the application, factors causing are weighted with triangular fuzzy numbers in pairwise comparisons. The result indicate that the weight factors from comparing the relationship of all factors put the importance of identify factors first, followed by protect, detect, respond, recover and continuity respectively.

Q4

Optimal Energy Management and Sizing of a Community Smart Microgrid Using Demand Side Management with Load Uncertainty

KUMAR M., Tyagi B.

Q4

ECTI Transactions on Computer and Information Technology, 2021, цитирований: 8,

open access

,

doi.org, Abstract

This paper presents an optimal energy management and sizing of a smart community microgrid (MG) with the uncertainty in load demand. An isolated small scale microgrid is considered with no access to the main supply grid. For simplicity, a small community of 15 houses located in a remote area is considered, and the loads are divided into controllable and uncontrollable categories. Demand side management (DSM) is being utilized to produce a feasible alteration to the controllable part of the load. The Overall problem is formulated to fix the optimal size of distributed generations (DGs) used in the MG by using a heuristic approach to minimize the net cost-based optimization problem. This cost includes initial capital costs, operation, and maintenance costs, and other running costs associated with MG. The optimization is completed in two parts. The first part of optimization is done without DSM implementation, and second part optimization is done on the modified system peak load after DSM implementation. Quantitative results on a numerical case study give an optimal number of distributed generation (DGs), their corresponding optimal ratings, optimal cost value, reduction in carbon footprint, and annual cost savings in the form of CO2 emission tax.

Q4

Glaucoma Detection in Mobile Phone Retinal Images Based on ADI-GVF Segmentation with EM initialization

Khaing T.T., Ruennark T., Aimmanee P., Makhanov S., Kanchanaranya N.

Q4

ECTI Transactions on Computer and Information Technology, 2021, цитирований: 6,

open access

,

doi.org, Abstract

The advanced development of mobile phone and lens technology has made retinal imaging more convenient than ever before. In the digital health era, mobile phone fundus photography has evolved into a low-cost alternative to the standard ophthalmoscope. Existing image processing algorithms have a problem with handling the narrow field of view and poor quality of retinal images from a mobile phone. This paper enhances the accuracy of our previously proposed scheme, ADI-GVF snakes, to improve the segmentation of the optic disk (OD) and the optic cup (OC) for glaucoma pre-screening [1] from retinal images obtained from a mobile phone. This work integrated a better OD localization method, namely, the exclusion method (EM) with ADI-GVF segmentation for the OD and the OC. The improved algorithm can segment the regions of the OD and OC more accurately, resulting in a more precise value of the cup-to-disk area ratio (CDAR). The proposed method yields as high as 93.33% for true positive rate (TPR) and 93.87% for true negative rate (TNR) and as low as 6.12% and 6.66% for false omission rate (FOR), and false discovery rate (FDR). It also improves TPR, TNR, FOR, and FDR of the previous scheme [1] by 4.45%, 4.08%, 4.08%, and 4.44% respectively.

Q4

Bimodal Emotion Recognition Using Deep Belief Network

Jaratrotkamjorn A.

Q4

ECTI Transactions on Computer and Information Technology, 2021, цитирований: 3,

open access

,

doi.org, Abstract

The emotions are very important in human daily life. In order to make the machine can recognize the human emotional state, and it can intelligently respond to need for human, which are very important in human-computer interaction. The majority of existing work concentrate on the classification of six basic emotions only. In this research work propose the emotion recognition system through the multimodal approach, which integrated information from both facial and speech expressions. The database has eight basic emotions (neutral, calm, happy, sad, angry, fearful, disgust, and surprised). Emotions are classified using deep belief network method. The experiment results show that the performance of bimodal emotion recognition system, it has better improvement. The overall accuracy rate is 97.92%.

Q4

Information Extraction Tasks based on BERT and SpaCy on Tourism Domain

Chantrapornchai C., Tunsakul A.

Q4

ECTI Transactions on Computer and Information Technology, 2021, цитирований: 13,

open access

,

Обзор, doi.org, Abstract

In this paper, we present two methodologies to extract particular information based on the full text returned from the search engine to facilitate the users. The approaches are based three tasks: name entity recognition (NER), text classiﬁcation and text summarization. The ﬁrst step is the building training data and data cleansing. We consider tourism domain such as restaurant, hotels, shopping and tourism data set crawling from the websites. First, the tourism data are gathered and the vocabularies are built. Several minor steps include sentence extraction, relation and name entity extraction for tagging purpose. These steps are needed for creating proper training data. Then, the recognition model of a given entity type can be built. From the experiments, given review texts, we demonstrate to build the model to extract the desired entity,i.e, name, location, facility as well as relation type, classify the reviews or summarize the reviews. Two tools, SpaCy and BERT, are used to compare the performance of these tasks.

Q4

Storytelling Platform for Interactive Digital Content in Virtual Museum

Khundam C.

Q4

ECTI Transactions on Computer and Information Technology, 2020, цитирований: 7,

open access

,

doi.org, Abstract

Virtual Reality (VR) generates realistic visualization and sensation applied to various practises. Virtual Museum (VM) is a use case where VR may be applied to convince museum visitors to participate with a story told through digital content. Recently, immersive VR technologies are intensively developed providing a lot of devices which support interactive VM application. In a development of interactive VM, interaction is always depending on the selected device. Then content is tuned to fit specific device capacity; major development must be addressed again whenever the virtual environment is adapted to a new device. This paper proposed a storytelling platform to assist interactive content design which is device independent. Our framework provides high-level abstraction of story and interaction which is then translated to any low-level device. Storytelling model and interaction model are introduced to create a common language for story making. It works with a viewer, an asset manager, an event editor and a timeline to achieve virtual environments organization and interaction assignment. An example of interactive content design on our platform is presented to demonstrate the development process which can be applied to collaborative interactive content designing in the future work.

Q4

Animal Monitoring Scheme in Smart Farm using Cloud-Based System

Park J.K., Park E.Y.

Q4

ECTI Transactions on Computer and Information Technology, 2020, цитирований: 8,

open access

,

doi.org, Abstract

   Currently, many operations are carried out manually on farms for raising livestock. In particular, it does not use equipment to understand the condition of animals, but relies only on the farmer’s perspective. If information can be obtained by monitoring farm animals, manager can determine the behavior of the animals and use this information to predict the health of the animals. In this paper, we propose a livestock monitoring system based on WSN. The proposed system can monitor farm animals using IoT equipment and cloud platforms. A collar was mounted on the neck of an animal using IoT equipment, and the activity of the livestock was monitored. Farming man- ager can supervises live information by transmitting livestock observation information to cloud platforms. Through actual implementation, we verified that the proposed system can monitor animals on farms in real time.  

Q4

Software Defect Prediction Based on Feature Subset Selection and Ensemble Classification

Saifan A.A., Abu-wardih L.

Q4

ECTI Transactions on Computer and Information Technology, 2020, цитирований: 9,

open access

,

doi.org, Abstract

Two primary issues have emerged in the machine learning and data mining community: how to deal with imbalanced data and how to choose appropriate features. These are of particular concern in the software engineering domain, and more specifically the field of software defect prediction. This research highlights a procedure which includes a feature selection technique to single out relevant attributes, and an ensemble technique to handle the class-imbalance issue. In order to determine the advantages of feature selection and ensemble methods we look at two potential scenarios: (1) Ensemble models constructed from the original datasets, without feature selection; (2) Ensemble models constructed from the reduced datasets after feature selection has been applied. Four feature selection techniques are employed: Principal Component Analysis (PCA), Pearson’s correlation, Greedy Stepwise Forward selection, and Information Gain (IG). The aim of this research is to assess the effectiveness of feature selection techniques using ensemble techniques. Five datasets, obtained from the PROMISE software depository, are analyzed; tentative results indicate that ensemble methods can improve the model's performance without the use of feature selection techniques. PCA feature selection and bagging based on K-NN perform better than both bagging based on SVM and boosting based on K-NN and SVM, and feature selection techniques including Pearson’s correlation, Greedy stepwise, and IG weaken the ensemble models’ performance.

Q4

An Optimization of Multi-Class Document Classification with Computational Search Policy

KYAW K.S., Limsiroratana S.-.

Q4

ECTI Transactions on Computer and Information Technology, 2020, цитирований: 4,

open access

,

doi.org, Abstract

In the era of internet communication, many electronic documents are spread and flow on the platform of website in every splits of seconds. The research interest for the process of knowledge discovery is changed from the traditional data to online data such as online news document classification. Most percentage of the online data is text document and therefore the optimization of multi-class document classification is becoming a challenge for today society. Traditional search policy for feature selection process is degrading with exhaustive search for complex feature in document classification. Therefore, meta-heuristic based computational search is also becoming good solution to overcome the problem of exhaustive search with exploitation process. The search policy of computational algorithm can provide the global optimal solution with random search approach on both exploitation and exploration process, and the selected search results of feature subsets can support the optimal classification results.

Q4

Wind Power Forecasting using A Heterogeneous Ensemble of Decomposition-based NNRW Techniques

Musikawan P., Sunat K., Kongsorot Y.

Q4

ECTI Transactions on Computer and Information Technology, 2020, цитирований: 3,

open access

,

doi.org, Abstract

Accurate and reliable wind power forecasting plays a vital role in the operation and management of power systems. Hence, it has become necessary to research and develop a high-accuracy wind power forecasting model. However, owing to highly nonlinear and non-stationary patterns of wind power time-series, creating a wind forecasting model capable of predicting such series accurately is both complicated and challenging. Aiming at this challenge, this paper introduces a new decomposition-based hybrid model based on multiple decomposition techniques, neural network with random weights (NNRW), and linear combiner. In our approach, the original time-series is decomposed into a collection of sub-series by different decomposition techniques. Each sub-series is modeled and predicted separately using NNRW. The predicted signals of each decomposition model are then reconstructed independently. Finally, all of the reconstructed results are integrated by the combiner using a linear combination method. The predictive performance of the proposed method was compared with other state-of-the-art techniques in over 12 wind power time-series. The experimental results show that the predictive performance of the proposed method remarkably outperforms the other competitors, proving the developed model to be effective, efficient, and practicable.

Q4

Collaborative Learning of Estimation of Distribution Algorithm for RNA secondary structure prediction

Srikamdee S., Chongstitvatana P.

Q4

ECTI Transactions on Computer and Information Technology, 2020, цитирований: 1,

open access

,

doi.org, Abstract

Estimation of distribution algorithms (EDAs) are successfully applied in the fields of bioinformatics for tasks such as gene structure analysis, protein structure prediction, and RNA secondary structure prediction. This paper proposes a new method, namely collaborative learning of estimation of distribution algorithms, or Co-EDAs, based on an estimation of distribution algorithm for RNA secondary structure prediction using a single RNA sequence as input. The proposed method consists of two EDAs with minimum free energy objective. The Co-EDAs use both good and poor solutions to improve the algorithm’s to search throughout the search space. Using information from poor solutions can indicate which area is unappealing to explore when searching with high-dimensional data. The Co-EDAs method was tested with 750 known RNA structures from RNA STRAND v2.0. That database includes data with more than 14 RNA types. The proposed method was compared to three prediction programs that are based on dynamic programming algorithms called Mfold, RNAfold, and RNAstructure. These programs are available as services on web servers. The results on average show that the Co-EDAs yields approximately 6% better accuracy than those competitors in all metrics.

Q4

Enhanced Particle Swarm Optimization for Path Planning of Unmanned Aerial Vehicles

Kok K.Y., Rajendran P.

Q4

ECTI Transactions on Computer and Information Technology, 2020, цитирований: 1,

open access

,

doi.org, Abstract

This paper presents an enhanced particle swarm optimization (PSO) for the path planning of unmanned aerial vehicles (UAVs). An evolutionary algorithm such as PSO is costly because every application requires different parameter settings to maximize the performance of the analyzed parameters. People generally use the trial-and-error method or refer to the recommended setting from general problems. The former is time consuming, while the latter is usually not the optimum setting for various specific applications. Hence, this study focuses on analyzing the impact of input parameters on the PSO performance in UAV path planning using various complex terrain maps with adequate repetitions to solve the tuning issue. Results show that inertial weight parameter is insignificant, and a 1.4 acceleration coefficient is optimum for UAV path planning. In addition, the population size between 40 and 60 seems to be the optimum setting based on the case studies.

Q4

Emotion Classification System for Digital Music with a Cascaded Technique

Sorussa K., Choksuriwong A., Karnjanadecha M.

Q4

ECTI Transactions on Computer and Information Technology, 2020, цитирований: 6,

open access

,

doi.org, Abstract

Music selection is difficult without efficient organization based on metadata or tags, and one effective tag scheme is based on the emotion expressed by the music. However, manual annotation is labor intensive and unstable because the perception of music emotion varies from person to person. This paper presents an emotion classification system for digital music with a resolution of eight emotional classes. Russell’s emotion model was adopted as common ground for emotional annotation. The music information retrieval (MIR) toolbox was employed to extract acoustic features from audio files. The classification system utilized a supervised machine learning technique to recognize acoustic features and create predictive models. Four predictive models were proposed and compared. The models were composed by crossmatching two types of neural networks, i.e., Levenberg-Marquardt (LM) and resilient backpropagation (Rprop), with two types of structures: a traditional multiclass model and the cascaded structure of a binary-class model. The performance of each model was evaluated via the MediaEval Database for Emotional Analysis (DEAM) benchmark. The best result was achieved by the model trained with the cascaded Rprop neural network (accuracy of 89.5%). In addition, correlation coefficient analysis showed that timbre features were the most impactful for prediction. Our work offers an opportunity for a competitive advantage in music classification because only a few music providers currently tag music with emotional terms.

Q4

An Enhanced ABC algorithm to Solve the Vehicle Routing Problem with Time Windows

Kantawong K., Pravesjit S.

Q4

ECTI Transactions on Computer and Information Technology, 2020, цитирований: 8,

open access

,

doi.org, Abstract

This work proposes an enhanced artificial bee colony algorithm (ABC) to solve the vehicle routing problem with time windows (VRPTW). In this work, the fuzzy technique, scatter search method, and SD-based selection method are combined into the artificial bee colony algorithm. Instead of randomly producing the new solution, the scout randomly chooses the replacement solution from the abandoned solutions from the onlooker bee stage. Effective customer location networks are constructed in order to minimize the overall distance. The proposed algorithm is tested on the Solomon benchmark dataset where customers live in different geographical locations. The results from the proposed algorithm are shown in comparison with other algorithms in the literature. The findings from the computational results are very encouraging. Compared to other algorithms, the proposed algorithm produces the best result for all testing problem sets. More significantly, the proposed algorithm obtains better quality than the other algorithms for 39 of the 56 problem instances in terms of vehicle numbers. The proposed algorithm obtains a better number of vehicles and shorter distances than the other algorithm for 20 of the 39 problem instances.

Q4

Economic Dispatch Using Modified Hybrid BA/ATS

Chansareewittaya S.

Q4

ECTI Transactions on Computer and Information Technology, 2020, цитирований: 2,

open access

,

doi.org, Abstract

In this paper, a new modified algorithm is proposed. This modified algorithm is BA/ATS. The main modifications are including negative value into the main equation of the bee algorithm (BA) and integrating adaptive tabu search (ATS) into BA. BA/ATS aims to improve the performance of hybrid BA/TS. The economic dispatch (ED) is set as the main problem to solve with the proposed algorithm. The operation of each generator is limit by constraints. All test results indicate that the overall costs of operation when using the proposed algorithm are better than test results from other compared algorithms. This means the modified hybrid BA/ATS is a good algorithm for the solving the ED problem.

Q4

A comparative study of rice variety classification based on deep learning and hand-crafted features

TRUONG HOANG V., Van Hoai D.P., Surinwarangkoon T., Duong H., Meethongjan K.

Q4

ECTI Transactions on Computer and Information Technology, 2020, цитирований: 19,

open access

,

doi.org, Abstract

Rice is vital to people all around the world. The demand for an efficient method in rice seed variety classification is one of the most essential tasks for quality inspection. Currently, this task is done by technicians based on experience by investigating the similarity of colour, shape and texture of rice. Therefore, we propose to find an appropriate process to develop an automation system for rice recognition. In this paper, several hand-crafted descriptors and Convolutional Neural Networks (CNN) methods are evaluated and compared. The experiment is simulated on the VNRICE dataset on which our method shows a significant result. The highest accuracy obtained is 99.04% by using DenNet21 framework.

Q4

A System for Sleepwalking Accident Prevention Utilizing the Remote Sensor of Wearable Device

Damkliang K., Andritsch J., Khamkom K., Thongthep N.

Q4

ECTI Transactions on Computer and Information Technology, 2020, цитирований: 1,

open access

,

doi.org, Abstract

Sleepwalking is a type of sleep disorder which originates during deep sleep and results in walking state and performing series of complex behaviors or actions while sleeping. In some cases, sleepwalking patients can injure themselves from their actions such as driving a car or climbing out of a window. In addition, to wake up the sleepwalkers can be difficult. The suddenly waking up and can cause them to be confused or even attack the person who wakes them. Therefore, detecting the sleepwalking incident in an early state can help the caretaker or family members to stop the patients before they harm themselves from any strange, inappropriate, or violent behaviors. In this research, we present a prototype system of sleepwalking detection algorithm and notification system using smart device which work coordinating with wearable device. There are two main groups of users; patients and caretakers. User Activity Sensor (UAS) in the wearable device is utilized for detecting User Activity Data (UAD) which is unusual activities of inducing a sleepwalking patient provided by the Remote Sensor SDK. The system returns the patient UAD states consisting of standing, walking, and running. The smart device accepts the UAD states from the wearable device, performs sleepwalking detection algorithms then, alarms caretakers when the sleepwalking state has already invoked. The system is implemented, built, tested and deployed. The threefold experimental measurement of physical user activites have been performed to validate our proposed sleepwalking detection algorithms. The system correctly detects the sleepwalking states and notifies the caretaker.

Q4

Analysing the EEG Signal Effectiveness of Chiang Rai Arabica Drip Coffee on Individual Human Brainwave

Chenghu C., Wicha S., Chaisricharoen R.

Q4

ECTI Transactions on Computer and Information Technology, 2020, цитирований: 2,

open access

,

doi.org, Abstract

This study focused on the impact of local Arabica coffee on the level of attention of individual brain waves, and how coffee affects Human EEG Frequency. Local Arabica coffee is adopted in this study as a medium to wake up the Beta wave. The Personal brainwave data is then recorded through EEG equipment and classified. The result showed that local coffee is helping to improve people's attention level — the study conducted on fifty participants: twenty-five males and twenty-five females aged between twenty to thirty years old. Brainwaves or Electroencephalography are collected twice before and after drinking coffee to compare the effects of Arabica on human brain waves by using NeuroSky mindwave mobile. The paired sample t-test test was employed for comparing two groups of Beta brainwaves experiment. Besides, the k-means algorithm is used to perform data mining on brain waves, and the differential brain wave signal data is clustered and divided into three levels. The experimental results showed that there was a statistically significant difference between the two paired samples. Therefore, the results confirmed that local Arabica coffee has a direct impact on personal attention.

Q4

A Review on Stereo Vision Algorithm: Challenges and Solutions

Kok K.Y., Rajendran P.

Q4

ECTI Transactions on Computer and Information Technology, 2020, цитирований: 7,

open access

,

Обзор, doi.org, Abstract

This paper presents a survey on existing stereo vision algorithms. The existing stereo vision algorithms are discussed in terms of concept, performance and related improvements. Also, a brief analysis of performance comparison among existing stereo vision algorithms is presented. Moreover, available improvements and solutions for stereo vision challenges such as computational complexity, occlusion, radiometric distortion, depth discontinuity and textureless region are reviewed.

Q4

Identification of L-Theanine Acid Effectiveness in Oolong Tea on Human Brain Memorization and Meditation

Srimaharaj W., Chaising S., Temdee P., Sittiprapaporn P., Chaisricharoen R.

Q4

ECTI Transactions on Computer and Information Technology, 2020, цитирований: 2,

open access

,

doi.org, Abstract

Oolong tea has an adequate amount of L-theanine acid, which can definitely affect human brain signal activity. Consequently, this study aimed to classify the effect level of L-theanine acid in Oolong tea relies on different participants focused on memorization and meditation state. An attention of the human brain was determined via electroencephalography (EEG) during the book reading state compared to not drinking and drinking conditions. To describe the memorization and meditation activity, this study focused on theta wave and alpha wave altogether. This properly measures a voltage fluctuation of these brain signals, as higher attention frequency indicated improving in mentioned state. Furthermore, Neural network performed the data classification of converted data in this study for high accuracy results. Each classified group was varied depending on the information of specified participants, i.e. gender, age, and body mass index (BMI). Obviously, several participants had a different effect level on L-theanine acid. Also, age, gender, and BMI of all participants were not totally affecting the effectiveness of L-theanine in this study. In conclusion, the results of this study represented that L-theanine in Oolong tea significantly affected the increasing of memorization and meditation. This result beneficially supports the production-proven of Oolong tea in the future apparently.