Title: Evaluating and Selecting Kinetic and Isotherm Models for Copper and Nickel Removal Using Cow Bone Char as an Adsorbent via Excel Solver Functions
<br>Cover Date: 2025-05-01
<br>Cover Display Date: May 2025
<br>DOI: 10.3390/ijms26094316
<br>Description: This study explores the effectiveness of cow bone char as a low-cost, eco-friendly, and biodegradable adsorbent for removing Cu(II) and Ni(II) ions from acidic wastewater as challenging is due to heavy metal-contaminated industrial wastewater. Batch adsorption experiments were conducted to evaluate performance, with advanced nonlinear kinetic and isotherm models applied to analyze the adsorption behavior. Model fitting was performed using Microsoft Excel Solver, and model selection was validated using the Akaike Information Criterion and Average Absolute Relative Deviation Percentage. The FL-PFO kinetic model provided the best fit for time-dependent data, while the Liu and Toth isotherm models most accurately described equilibrium adsorption. Maximum adsorption capacities were 110 mg g<sup>−1</sup> for Cu(II) and 95 mg g<sup>−1</sup> for Ni(II), with Cu(II) exhibiting faster and more complete removal. Reusability testing over five cycles showed good potential for repeated use, though with gradual efficiency decline due to structural degradation and limited site regeneration. These results confirm the suitability of cow bone char as a sustainable and effective adsorbent for heavy metal removal, particularly in low-resource or decentralized water treatment systems.
<br>Citations: 0
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: A COMPARATIVE STUDY OF MACHINE LEARNING AND DEEP LEARNING MODELS FOR SENTIMENT ANALYSIS ON THAI RESTAURANT REVIEWS
<br>Cover Date: 2025-04-01
<br>Cover Display Date: April 2025
<br>DOI: 10.24507/icicelb.16.04.379
<br>Description: Many techniques have been proposed to extract sentiments from restaurant reviews in different languages. However, Thai reviews present a unique challenge due to the language’s complexity, rendering sentiment analysis particularly arduous. This paper aims to conduct a comparative study between machine learning and deep learning models with different weighting methods for sentiment analysis on Thai restaurant reviews. First, restaurant reviews were collected and preprocessed, involving cleaning, segmentation, and stop word removal to extract a collection of features. Subsequently, all reviews were trans-formed into vectors employing different feature weighting methods, namely Boolean, TF, and TF-IDF. Then, the vectors were fed into machine learning and deep learning models. From the study, we found that SVM outperformed the other models when utilizing the TF-IDF weighting method for computing feature weights. SVM gave a high F1-score on both negative and positive classes.
<br>Citations: 0
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: INNOVATIVE HYBRID METHODOLOGY FOR A HEALTH-ORIENTED FOOD RECOMMENDATION SYSTEM
<br>Cover Date: 2025-03-01
<br>Cover Display Date: March 2025
<br>DOI: 10.24507/icicelb.16.03.269
<br>Description: This research project focuses on developing a food recommendation system that is beneficial to users through a combination of data filtering and food content analysis that can be used effectively to support online businesses and services by recommending products or services that match users’ needs and preferences. The results indicated that the system could recommend suitable new items, with a root mean square error value of 0.75 for predicting the liking score for new food items. This improvement can ensure accuracy and appropriateness regarding the recommended food items. In addition, it enhances the accuracy and variety of healthy food recommendations for users in cases where a new menu is not properly recommended. Therefore, this research is important in improving and increasing the efficiency of a food recommendation system, while also recommending food items correctly that are suitable for use and solve food requirement problems.
<br>Citations: 0
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: THE COMPARISON OF DEPRESSIVE SYMPTOMS CLASSIFICATION FROM TWITTER BETWEEN NAÏVE BAYES, MOADSP, AND LSTM BASED ON DSM-5
<br>Cover Date: 2025-03-01
<br>Cover Display Date: March 2025
<br>DOI: 10.24507/icicelb.16.03.259
<br>Description: The depressive disorder is suffered by over 264 million people worldwide, especially among youth and teenagers. This research proposes 2 phases for detecting depressive disorder from Twitter that are Phase 1: comparing 9 depressive symptoms that are 1) Depressed mood, 2) Diminished interest, 3) Change in sleep, 4) Change in appetite, 5) Slowed thinking, 6) Worthlessness or guilt, 7) Fatigue, 8) Agitation or retardation and 9) Suicidal ideation classification from Twitter’s tweets between the classical machine learning called Naïve Bayes and the new deep-learning algorithm called LSTM (Long Short-Term Memory), and Phase 2: the depressive disorder classification using DSM-5 from the American Psychiatric Association. The accuracy, precision, recall, and F-measure in Phase 1 demonstrate these algorithms’ performance. The proposed method, LSTM, performs better than Naïve Bayes and double classical algorithms on all the measurements, being 0.97, 0.96, 0.93, and 0.95. In Phase 2, LSTM performs better than classical Naïve Bayes and MOADSP, at 0.74, 0.86, 0.84, and 0.85.
<br>Citations: 0
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Depressive Disorder Classification from Twitter using Transformer Algorithms
<br>Cover Date: 2025-01-01
<br>Cover Display Date: 2025
<br>DOI: 10.1109/KST65016.2025.11003328
<br>Description: This study focuses on classifying depression from Twitter posts using deep learning techniques, particularly through the Deep learning model. Depression is a critical issue impacting both individuals and society, with potentially severe consequences, including mortality. The study leverages social media data to identify signs of depression, offering a technological approach to understanding and predicting depressive behaviors. By collecting English text data, including hash-tagged tweets indicative of depressive symptoms, and classifying data into nine categories of depressive symptoms, the study enhances the accuracy and prediction capacity of the model. The proposed classification system aims to support efforts in identifying and providing early intervention for individuals at risk of depression.
<br>Citations: 0
<br>Aggregation Type: Conference Proceeding
<br>-------------------
<br><br><br>Title: DEVELOPING AN AUTOMATIC OPEN QUESTION AND ANSWERING OF ASSOCIATION QUESTION DATA FOR COMMUNITY TOURISM
<br>Cover Date: 2024-05-01
<br>Cover Display Date: 1 May 2024
<br>DOI: 10.24507/icicelb.15.05.455
<br>Description: The research aims to develop automatic questions and answers using Open-QA, resolving the problem of tourists’ spatial information access from the association question data. The difficulty of Thai language processing is that the language has no space in a sentence, without punctuation or word separation. Correctly tokenizing or separating words affects precision and accuracy. The efficient data access of the tourists is a challenge of this research. The similarity method, the cosine similarity technique, is based on the Vector Space Model (VSM) using TF-IDF weighting and Bag of Words (BoWs). It is efficient by bringing the outstanding points of text vectorization to calcu-late and acquire the crucial features for being the document representative efficiently. The result of the Bows stage is 19,501 terms from 1,237 documents. The evaluation of model effectiveness has an Accuracy value of 99%, which best indicates the ability to describe the answer and efficacy of the model.
<br>Citations: 0
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Ladybug: An Automated Cultivation Robot for Addressing the Manpower Shortage in the Agricultural Industry
<br>Cover Date: 2024-04-01
<br>Cover Display Date: April 2024
<br>DOI: 10.37936/ecti-cit.2024182.254769
<br>Description: The agricultural sector is projected to need more labor as a result odeclining interest in careers within this domain. Despite the escalating demand for agricultural goods, previous endeavors to mitigate this challenge through the deployment of robotic prototypes have encountered hindrances such as issues pertaining to automation, adaptability to varying tasks, and the financial burdens associated with development. To address this exigency, we have developed an automated cultivation robot utilizing advancements in the Internet of Things (IoT), Image Processing, and Artificial Intelligence (AI) for seeding in pots. The robot demonstrates the capacity to sow seeds in 257 pots per hour, accomplish a mission within 12.53 minutes, traverse at a velocity of 360 meters per hour, and seed pots at a rate of 13.37 seconds per pot. It possesses an operational duration oapproximately two hours, completing nine cycles and seeding 486 pots on a single charge. Notably, the robot exhibits a mission success rate of 1.00 and a seeding accuracy 0.78. Moreover, it features an adaptable workspace and a lightweight frame weighing 20 kg, rendering it a cost-effective solution for mass production.
<br>Citations: 0
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Developing an Intelligent Farm System to Automate Real-time Detection of Fungal Diseases in Mushrooms
<br>Cover Date: 2024-01-01
<br>Cover Display Date: 2024
<br>DOI: 10.55003/cast.2023.255708
<br>Description: Mushrooms are economically valuable crops of high nutritional value. However, during cultivation they are continually threatened by fungal diseases, even in controlled-condition farm ecosystems. Fungal diseases significantly affect mushroom growth and can rapidly contaminate an entire crop. Farmer inspections can be hazardous to farmer health. This paper contributes an automated fungal disease detection system for the Sajor-caju mushrooms together with an intelligent farm system for precise cultivation environment control. The objective was to create and test a detection system that could detect fungal diseases rapidly, reduce farmer exposure to fungal spores, and alert farmers when fungal disease was detected. The system is composed of three parts: (i) a high-precision environment control system, (ii) an innovative imaging robot system, and (iii) a real-time fungal disease prognosis system using deep learning, with an alarm system. The trial results show that the real-time disease prognosis system has 94.35% precision (89.47% F1-score, n=13,500), and its twice daily inspections detect and report fungal disease typically within 6 to 12 h. The innovative farm’s overall capability for mushroom cultivation (environment control) is regarded as excellent and has precise control (99.6% capability, over 3-months). The innovative imaging robot’s overall operational trial performance is effective (at 99.7%). Moreover, the system effectively notifies farmers via smartphone when a fungal disease is detected.
<br>Citations: 5
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Associations Between Health Literacy and Dietary Intake: A Cross-sectional Study of Adults With Metabolic Syndrome in Thailand
<br>Cover Date: 2023-09-01
<br>Cover Display Date: September 2023
<br>DOI: 10.34172/jech.2447
<br>Description: Background: Health literacy (HL) is an indicator of health outcomes, but its role in dietary intake has received little attention. Excessive dietary intake increases the risk of metabolic syndrome (MetS). Therefore, this study aimed to investigate the HL score, dietary intake, and nutrient intake of participants and the relationship between HL score and dietary intake among adults with MetS in Thailand. Methods: In this cross-sectional study, 2527 adults aged 18–59 years in primary care services, Phetchaburi, Thailand were included in the study using a multistage sampling technique. We determined HL scores using the Health Literacy Questionnaire (HLQ) and dietary intake using a semiquantitative Food Frequency Questionnaire. We used multiple linear regression analysis to investigate the associations between HL score and dietary intake. Results: HL scores were significantly lower in patients with MetS compared with participants without it (P< 0.05). Participants with MetS had significantly higher calorie and fat intake than participants without it (P< 0.05), and participants with MetS had higher fat and lower carbohydrate intake. The results of multiple linear regression showed a significant negative association between HL score and dietary intake, after controlling for potential confounding variables (β = −0.053, P< 0.05). Conclusion: Our findings suggest that low HL score is associated with high dietary intake. Therefore, improving HL might play an important role in reducing dietary intake to decrease the risk of MetS.
<br>Citations: 2
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: A NEW PROBABILISTIC WEIGHTED VOTING MODEL FOR DEPRESSIVE DISORDER CLASSIFICATION FROM CAPTIONS AND COLORS OF IMAGES
<br>Cover Date: 2023-05-01
<br>Cover Display Date: May 2023
<br>DOI: 10.24507/icicel.17.05.531
<br>Description: Depression disorder is a significant issue leading to suicide. Previously published research on depression has found many associations with posted images, personalities, and emotions of social media users. Identifying patients early at a primary stage will help reduce the graveness levels and consequently the morality rate of attempted suicide. We use a sample taken from Twitter and Instagram. This research aims 1) to find an optimal number of features, and the proper number of classifiers, and 2) to propose a new probabilistic weighted voting model for depressive disorder classification from captions and colors of images. This method uses the single classification combinations of being support vector machine, K-nearest neighbors, decision trees, Naïve Bayes, gradient boosting tree, and generalized linear models. Giving probabilistic weight to single classifiers, up to 6 probabilistic weighted voting ensembles were created. The proposed model achieved an accuracy of 87.23% and was more effective than other models. It theoretically and experimentally performed significantly better than single classifiers and majority vote ensemble models alone. Finally, the model effectively classified patients with depression disorder using the captions and colors of images that they have posted on social media.
<br>Citations: 1
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Deep learning for classifying thai deceptive messages
<br>Cover Date: 2023-05-01
<br>Cover Display Date: May 2023
<br>DOI: 10.11591/ijeecs.v30.i2.pp1232-1241
<br>Description: Online deception has become a major problem affecting people, society, the economy, and national security. It is mostly done by spreading deceptive messages because message are quickly spread on social networks and are easily accessed by anyone. Detecting deceptive messages is challenging as the messages are unstructured, informal, and complex; this extends into Thai language messages. In this paper, various deep learning models are proposed to detect deceptive messages under two feature extraction trials. A balanced two-class dataset of deceptive and truthful Thai messages (n=2378) is collected from Facebook pages. Instance features are encoded using word embeddings (Thai2Fit) and one-hot encoding techniques. Five classification models, convolutional neural network (CNN), bidirectional long short-term memory (BiLSTM), bidirectional gated recurrent units (BiGRU), CNN-BiLSTM, and CNN-BiGRU, are proposed and evaluated upon the dataset with each feature extraction technique. The experimental results show that all the proposed models had excellent accuracy (95.59% to 98.74%) and BiLSTM with one-hot encoding gave the best performance, achieving 98.74% accuracy.
<br>Citations: 0
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Gender Differences Relevant to Metabolic Syndrome in a Working Population in Phetchaburi Province, Thailand
<br>Cover Date: 2023-04-01
<br>Cover Display Date: April 2023
<br>DOI: 10.35755/jmedassocthai.2023.04.13840
<br>Description: Background: The prevalence of metabolic syndrome (MetS) is increasing in the Thai working population. Thus, there is a need for an analysis of factors relevant to metabolic syndrome comparing the differences between females and males to improve, prevent, and reduce the risk of metabolic syndrome in the working population. Objective: To investigate the factors and the prevalence to identify gender-specific risk factors for MetS. Materials and Methods: The authors performed a cross-sectional study of 2,076 working adults living in the Phetchaburi Province in Central Thailand, defining MetS according to the International Diabetes Federation criteria. The authors used a self-administered structured questionnaire to collect the data, and calculated odds ratios (OR) with 95% confidence intervals (CI) stratified by gender. Results: The median age of participants was 50 years. The overall prevalence of MetS was higher in females (28.13%) than males (22.25%). MetS was associated with high body mass index (BMI), education, and exercise in both genders. Advanced age was a MetS risk factor in males (adjusted OR 3.22, 95% CI 1.42 to 7.32, p=0.005). The main MetS protective factors in females were nutrition literacy (adjusted OR 0.65, 95% CI 0.43 to 0.99, p=0.046) and behavior (adjusted OR 0.40, 95% CI 0.27 to 0.62, p<0.001). Conclusion: MetS risk factors are gender specific. Therefore, gender-specific public health strategies are required to prevent MetS.
<br>Citations: 2
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: THE DEVELOPMENT OF A NEW HYBRID K-MEANS AND ELBOW METHOD (C-ALGORITHM) FOR MULTIPLE DOMAIN CLUSTERING
<br>Cover Date: 2023-03-01
<br>Cover Display Date: March 2023
<br>DOI: 10.24507/icicel.17.03.269
<br>Description: This research aims to develop a new clustering algorithm called C-Algorithm that the document can classify to the previous domain or create a new domain and solve the K-means problem. This problem comes from the distance measurement of similarity from the new document to the centroid of each group. The new document will classify the group so that the relationship between groups and the new document is analogous or divergent. This experiment observes the proper group numbers using the Elbow method before starting the process. After this process, the Threshold value will be calculated from the centroid of the document in the group and percentile. The new document will compare with the Threshold and decision to set to the group or create the new document. This research compares the performance of the weight between the TF-IDF and BM25. These results show that the best performance comes from the BM25, Euclidean distance, and 80-85 percentile. The result of this research is more accurate than the traditional K-means algorithm.
<br>Citations: 0
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: THE SENTIMENT CLASSIFICATION OF HOTEL REVIEWS AND HOTEL DESCRIPTION USING FEATURE-BASED TECHNIQUE FOR CUSTOMER RELATIONSHIP MANAGEMENT
<br>Cover Date: 2023-03-01
<br>Cover Display Date: March 2023
<br>DOI: 10.24507/icicel.17.03.279
<br>Description: Learning and understanding customer needs is one of the business strategies that will help build long-term customer relationships. This research has analyzed customer opinions compared to hotel features, and allowed the hoteliers to use this information to develop and improve their business to meet the needs of their guests. This research proposed: 1) compilation of English comments from the website, 2) word segmentation process consists of labeling the types of words using the Penn Treebank Target and extracting the types of words that are important to the analysis as follows: verbs, adjectives, and adverbs to be processed, 3) the customer feedback analysis process is used to identify the feedback poles of each feature, 4) extracting the hotel description, and 5) feature matching between hotel description and prediction result. It uses to check the consistency between the customer reviews and hotel strengths. The results showed that the efficacy of the analysis of hotel guest reviews with the highest and average F-measure values were 0.83 and 0.56, respectively.
<br>Citations: 1
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: The Feature selection and Comparison performance of Student's academic between Random Forest, Naïve bayes and XGboost
<br>Cover Date: 2023-01-01
<br>Cover Display Date: 2023
<br>DOI: 10.1109/TALE56641.2023.10398413
<br>Description: Academic performance is important for students and teachers or lecturers and contributes significant impacts for educational goals. This research aims to select the features and compare the student's academic performance between one of the Lazy algorithms and two of Eagle algorithms that exploit Random Forest, Naïve bayes and XGboost. Additionally, this proposed model reduces the number of features using Tree classifier from 16 features to 5 features and reduces more than 35% of the computational time. The Accuracy, Precision, Recall, F1-measure of the proposed method with the Logistics Regression are 0.76, 0.76, 0.76 and 0.75, respectively, which are lower than [5]. However, when comparing and testing the performance with the paired t-Test method, the result shows no statistically significant difference.
<br>Citations: 0
<br>Aggregation Type: Conference Proceeding
<br>-------------------
<br><br><br>Title: Weighted Voting Ensemble for Depressive Disorder Analysis with Multi-objective Optimization
<br>Cover Date: 2023-01-01
<br>Cover Display Date: January-February 2023
<br>DOI: 10.55003/cast.2022.01.23.015
<br>Description: The Twitter platform is a popular tool that is widely used by researchers to collect data on users’ personal lives, feelings and emotions. These data sets can be further analyzed using text mining techniques to predict the disorder of depression. There are nine symptoms of depression that are classified by American Psychiatric Association using DSM-5 criteria. The symptoms can be difficult to identify effectively. The unweighted vote ensemble is not practical for multi-class data. Therefore, this research proposes the multi-objective optimization algorithms for depressive symptom prediction modeling (MOADSP) for the weighted voting ensemble, which can improve its effectiveness compared to the singer model. The objectives of this research were 1) to find the appropriate number of features; 2) to improve the weights of the prediction models based on the recall of the class for the ensemble; and 3) to compare the performance of the single, unweighted, and weighted voting ensemble models for depressive disorder. An information gain was used to select the features. The single classification techniques used in the experiment that had their frameworks tested were the Naïve Bayes, Random Forest, and K-Nearest techniques, while the vote ensemble models used were the unweighted and weighted models. MOADSP was applied to the weighted vote ensemble models. The results showed that the best recall classifier was KNN (98.60%), and the highest recall classifier was AVG TP weighted (98.43%) for the training model. The highest recall in the class depressive classifier was AVG TP weighted (80.00%) for the testing. This proposed method was beneficial for the prediction of depressive disorder.
<br>Citations: 5
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Classification of chest X-ray images using a hybrid deep learning method
<br>Cover Date: 2022-02-01
<br>Cover Display Date: February 2022
<br>DOI: 10.11591/ijeecs.v25.i2.pp867-874
<br>Description: This work presents a technique for classifying X-ray images of the chest (CXR) by applying deep learning-based techniques. The CXR will be classified into three different types, i.e. (i) normal, (ii) COVID-19, and (iii) pneumonia. The classification challenge is raised when the X-ray images of COVID-19 and pneumonia are subtle. The CXR images of the chest are first proceeded to be standardized and to improve the visual contrast of the images. Then, the classification is performed by applying a deep learning-based technique that binds two deep learning network architectures, i.e., convolution neural network (CNN) and long short-term memory (LSTM), to generate a hybrid model for the classification problem. The deep features of the images are extracted by CNN before the final classification is performed using LSTM. In addition to the hybrid models, this work explores the validity of image pre-processing methods that improve the quality of the images before the classification is performed. The experiments were conducted on a public image dataset. The experimental results demonstrate that the proposed technique provides promising results and is superior to the baseline techniques.
<br>Citations: 8
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Tourist information-seeking behaviours using association rule mining
<br>Cover Date: 2021-09-01
<br>Cover Display Date: September 2021
<br>DOI: 10.24507/icicel.15.09.915
<br>Description: The evolution of information technology and social media today affects the behaviour and expectations of tourist knowledge and information-seeking. Proper answers can enhance the opportunity of travel decision-making. The purpose of this research is to study tourist information-seeking behaviours. Such behaviours derive from the question items that are frequently asked by association rule mining (ARM). Following previous research, the questions were clustered into four groups in what is termed the ESAN model, which is the input data to ARM with default parameters in Weka. It was found that the question patterns generated by the ARM, consisting of clusters E, S, A, and N, had a value of conf. > 98%, and the value of supp. was 0.980-0.987, 1, 0.988-0.994, and 0.983-0.996, respectively. The utilization of this result includes 1) the representation of a data preparation model to access information quickly and to meet the needs of tourists and 2) the provision of guidelines for the Chatbot design by the rules-based Chatbot.
<br>Citations: 5
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Book Cover and Content Similarity Retrieval Using Computer Vision and NLP Techniques
<br>Cover Date: 2021-01-01
<br>Cover Display Date: 2021
<br>DOI: 10.1007/978-3-030-80253-0_4
<br>Description: This paper proposes a computer vision and machine learning application for recognizing book covers and automatically retrieve similar book contents from the database. Recognizing the book covers relies on extracting the key points from the images of the book covers before they are used in a matching process. Moreover, the book description will automatically extract, retrieve, and generate a book representation using a Bag of Word (BOW) algorithm. The similarity function will use to measure the contents of the books. The experiments are conducted and evaluate the performance using the 30 real-image book covers. The output shows that the accuracy of book cover image recognition is 89.33% and from book description is 63.33%.
<br>Citations: 1
<br>Aggregation Type: Book Series
<br>-------------------
<br><br><br>Title: Finding association patterns of disease co-occurrence by using closed association rule generation
<br>Cover Date: 2020-01-01
<br>Cover Display Date: 2020
<br>DOI: 10.25046/AJ050579
<br>Description: This paper proposes a closed association rule generation technique to investigate the association patterns of diseases that are frequent co-occurrence. Diseases records of 5,000 patients are studied to find the association patterns of disease co-occurrence. The CHARM algorithm is adapted to find frequent diseases that can cover all-important patterns with a small number. Then the association patterns of disease co-occurrence are created in a form of association rules from the frequent diseases. The rules represent diseases associated with other diseases. Accuracy and prediction ratio are defined to evaluate the generated association patterns. From the experimental results, the generated association patterns give 79.76% of accuracy and 84.03% of prediction ratio although the number of generated association patterns is small. Moreover, the top-10 association patterns of disease co-occurrence are investigated. Besides, the 5 most frequent diseases are found to deeply study the other related diseases of them. From the investigation, we found that diabetes mellitus, metabolic disorders, and renal failure are highly related to hypertensive diseases with 88.81% of confidence. In addition, we found that influenza and pneumonia, plastic and other anemias are highly related to metabolic disorders.
<br>Citations: 0
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: A Study of Features Affecting on Stroke Prediction Using Machine Learning
<br>Cover Date: 2019-01-01
<br>Cover Display Date: 2019
<br>DOI: 10.1007/978-3-030-33709-4_19
<br>Description: In 2021, Thailand will become an ageing society. The policy of the health of older people is a challenging task for the Thai government that has to be carefully planned. Stroke is the first leading cause of death of older people in Thailand. Knowing the risk factors for stroke will help people to prevent stroke. In this paper, features affecting stroke are studied based on machine learning. Factors and diseases occurring before stroke are studied as features to detect stroke and find affective factors of stroke. The detection of stroke is investigated based on learning classifiers, SVM, Naïve Bayes, KNN, and decision tree. Moreover, Chi2 is adopted to find affective factors of stroke. The four most affective factors of stroke are focused to know the risk of stroke. From the study, we can see that the factors are more affective than the diseases for detecting stroke and decision tree is the best classifier. Decision tree gives 72.10% of accuracy and 74.29% of F-measure. The factors affecting stroke are smoking, alcohol, cholesterol, blood pressure, sex, exercise, and occupation. Moreover, we found that no smoking can avoid stroke. Drinking alcohol, abnormal cholesterol, and abnormal blood pressure raise the risk of a stroke.
<br>Citations: 7
<br>Aggregation Type: Book Series
<br>-------------------
<br><br><br>Title: Automatic lyrics classification system using text mining technique
<br>Cover Date: 2018-05-30
<br>Cover Display Date: 30 May 2018
<br>DOI: 10.1109/IWAIT.2018.8369796
<br>Description: The human listens to the music for the entertainment and emotional expression. Nowadays, the music has many emotion, such as the love-music etc. The listener's playlist is made by manual. This paper proposes the automatic lyrics classification system using text mining technique by Naïve Bayes and Random forest based on the various weighting technique. The best of the accuracy is Naïve Bayes by the longest matching algorithm.
<br>Citations: 6
<br>Aggregation Type: Conference Proceeding
<br>-------------------
<br><br><br>Title: The marker detection from product logo for augmented reality technology
<br>Cover Date: 2016-01-01
<br>Cover Display Date: 2016
<br>DOI: 10.1007/978-3-319-49046-5_36
<br>Description: This paper proposed the development of an effective algorithm for marker detection from products for augmented reality by Speeded-Up Robust Features (SURF) algorithm that provided the efficiency in term of speed and accuracy. The SURF alorithm is consisted of 3 processes that are (1) feature extraction calculates the interested point and interested descriptions, (2) feature matching is that the correlation of all points is calculated from the distance of similarity of featuers, and (3) logo indentification is used to find the four corner point of the logo. This experiment is conducted from the recording video at 100 frames with resolution of 640×360 pixels and logo appeared all frames. Objects used in the experiment are consists of 3 shapes, cylindrical (can), rectangular (bag), and bottle. The logo template is divided into 5 sizes. The result of experiment found that the best detection accuracy of logo detection is from the size of 100×100 pixels. The accuracy of the region of marker detection compared with ground truth shows that the bag is equal to 94.96 %, can is equal to 93.99 %, and bottle is equal to 91.01 %, respectively. The difference of the logo is not affected with the computational time. However, the fast moving camera creates the blurred image and the reflection on the packaging creats a shiny surface which affects with the accuracy.
<br>Citations: 0
<br>Aggregation Type: Book Series
<br>-------------------
<br><br><br>Title: A novel and simple management system of interactive system using google street view
<br>Cover Date: 2015-01-01
<br>Cover Display Date: 2015
<br>DOI: 10.1007/978-3-319-10774-5_17
<br>Description: The Google street View (GSV) is used for many applications such as using for driver decision support system, collecting and merging the image for special purpose. The interactive system can be created by GSV. However, the most difficulty is the great image volumes. Moreover, for the reality, the map of interactive system ought to like with the physical place. This research proposed the management system created by the simple concept of database and designed by the simple color menu concept. Additionally, the map is constructed by the adjacent in the directed graph theory. This concept will demonstrate with the interactive system of the small pagoda in Thailand. The administrator management is easy and simple to manage this system, and the user or visitor feels like stay in the physical place and attracts to go to that place with more satisfied contentment.
<br>Citations: 0
<br>Aggregation Type: Book Series
<br>-------------------
<br><br><br>Title: Performance comparison of the diskless technology
<br>Cover Date: 2013-09-09
<br>Cover Display Date: 2013
<br>DOI: 10.1109/JCSSE.2013.6567327
<br>Description: Currently, the traditional disk-full technology will be replaced by the diskless technology because of its advantage such as controlling from the Central Control System, managing large number of computer systems, reducing the redundancy of computer system, reducing the energy consumption and costs. However, the disadvantage of diskless technology is slow speed when lot of client machines boot to ready state. This research is proposed with the architectural and structural design of the diskless technology on Ethernet topology and tested the efficiency algorithm with the boot up time. From the result, we found that the link aggregation structural connections shows the high performance in term of the minimum average of times. © 2013 IEEE.
<br>Citations: 0
<br>Aggregation Type: Conference Proceeding
<br>-------------------
<br><br><br>Title: Generation of optimal binarisation output from ancient Thai manuscripts on palm leaves
<br>Cover Date: 2013-01-01
<br>Cover Display Date: 2013
<br>DOI: 10.1109/ICMLC.2013.6890862
<br>Description: Recently, several binarisation techniques have been proposed to process different kinds of ancient document images. While many well-known binarisation techniques are particularly suitable for certain types of document images, there is no specific guidelines on the determination of the appropriate type of image degradation, or characteristics of the image. In this paper, a novel method has been proposed to generate the optimal binary image from different binarised outputs from a document image. This approach is based on weight majority vote, and uncertain pixels are then determined based on local areas of the binarised images, by applying iteration of weight majority vote. Experiment over benchmark data set of the Document Image Binarization Contest (DIBCO) 2011 shows that the proposed method provided better performance than most well-known techniques. The proposed method has also been applied to ancient manuscripts on palm leaves from Thailand and this approach provided better results than binarised outputs from original binarisation techniques.
<br>Citations: 5
<br>Aggregation Type: Conference Proceeding
<br>-------------------
<br><br><br>Title: Automatic nipple detection based on face detection and ideal proportion female using random forest
<br>Cover Date: 2013-01-01
<br>Cover Display Date: 2013
<br>DOI: 10.1109/CyberneticsCom.2013.6865772
<br>Description: Currently pornographic image on the online world, teenagers and kids can visit easily. Which stimulate sexual desire. Resulting behavior of sexual abuse, enticing a child under the age of 15 years increased, cause problems getting pregnant and sexually transmitted diseases. Pornographic detection is essential to prevent to access through analyzing image content. Many researchers are interested in pornographic detection of nipple using extended Haar-like for extracting the features, color, texture and shape that are used for classification using various algorithms cascaded AdaBoost. However, this disadvantage is the templates for nipple which require a lot of training set and it consumes the time to detect a multiple possible position similar to nipples such as eyes and navel. This research proposed the novel algorithm without using templates for detecting the nipple. Our proposed creates the novel model based on ideal proportion detection. The result of this algorithm shows the high accuracy and reducing the computational time when compares with the existing method. © 2013 IEEE.
<br>Citations: 9
<br>Aggregation Type: Conference Proceeding
<br>-------------------
<br><br><br>Title: Shape control of a hyper-redundant arm for planar object manipulation
<br>Cover Date: 2011-06-29
<br>Cover Display Date: 2011
<br>DOI: 10.1163/016918611X574669
<br>Description: This paper discusses a method for controlling a hyper-redundant arm to manipulate an object on a plane. The hyper-redundant arm can perform simple whole-arm manipulation by coiling or wrapping around the object and then pulling the object toward the goal position. The process of object manipulation can be separated into two steps: encircling the object and transporting the object. In the process of encircling the object, the arm is controlled by a set of virtual constraints that guide the arm to reach around the object and encircle it, keeping the arm within a specified bound to ensure the circular shape around the object. In the process of transporting the object, a simplified desired shape is generated from a Bézier curve according to a given goal position and the arm geometry. Then, the gradient descent method is used to update the joint angles of the arm at each step to move the arm toward the desired shape until the object reaches its target position. The proposed method has been tested in both simulation and real experiments. © 2011 Koninklijke Brill NV, Leiden.
<br>Citations: 3
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Comparison of image analysis for thai handwritten character recognition
<br>Cover Date: 2006-12-01
<br>Cover Display Date: 2006
<br>DOI: N/A
<br>Description: This paper is proposing the method for Thai handwritten character recognition. The methods are Robust C- Prototype and Back-Propagation Neural Network. The objective of experimental is recognition on Thai handwritten character. This is the result of both methods to be appearing accuracy more than 85%.
<br>Citations: 0
<br>Aggregation Type: Conference Proceeding
<br>-------------------
<br><br><br>Title: Comparison of image analysis for Thai handwritten character recognition
<br>Cover Date: 2006-12-01
<br>Cover Display Date: 2006
<br>DOI: N/A
<br>Description: This paper is proposing the method for Thai handwritten character recognition. The methods are Robust C-Prototype and Back-Propagation Neural Network. The objective of experimental is recognition on Thai handwritten character. This is the result of both methods to be appearing accuracy more than 85%.
<br>Citations: 2
<br>Aggregation Type: Book Series
<br>-------------------
<br><br><br>Title: An adaptive RBF network optimised using a genetic algorithm applied to rainfall forecasting
<br>Cover Date: 2004-12-01
<br>Cover Display Date: 2004
<br>DOI: N/A
<br>Description: Rainfall prediction is a challenging task especially in a modern world facing the major environmental problem of global warming. The proposed method uses an Adaptive Radial Basis Function neural network mode with a specially designed genetic algorithm (GA) to obtain the optimal model parameters. A significant feature of the Adaptive Radial Basis Function network is that it is able create new hidden units and solve the spread factor problem using a genetic algorithm. It is shown that the evolved parameter values improved performance.
<br>Citations: 15
<br>Aggregation Type: Conference Proceeding
<br>-------------------
<br><br><br>