{"title":"Heart Rate Estimation by PCA with LSTM from Video-based Plethysmography Under Periodic Noise","authors":"Chetsadaporn Traivinidsreesuk, Nutcha Yodrabum, Irin Chaikangwan, Taravichet Titijaroonroj","doi":"10.1109/ICSEC56337.2022.10049315","DOIUrl":"https://doi.org/10.1109/ICSEC56337.2022.10049315","url":null,"abstract":"A remote photoplethysmography (rPPG) analysis can extract vital signs from the source video, including heart rate estimation. One of the problems of heart rate estimation is periodic noise embedded in the source video. It is difficult for an rPPG analysis to discriminate between vital signal information and noise, increasing prediction error. To alleviate this problem, this paper used principal component analysis (PCA) to extract rPPG signals from the input video before forwarding the signal to Long Short Term Memory (LSTM) to estimate heart rate. The experimental results show that, among discrete Fourier Transform method, neural networks, and neural network with LSTM, the proposed method accomplished a much lower MAEP at 15.05, 13.90, and 17.90 in the cases of overall, with no periodic noise, and with periodic noise, respectively.","PeriodicalId":430850,"journal":{"name":"2022 26th International Computer Science and Engineering Conference (ICSEC)","volume":"610 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123041969","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tamal Ahmed, Shawly Folia Mukta, Tamim Al Mahmud, S. Hasan, Md Gulzar Hussain
{"title":"Bangla Text Emotion Classification using LR, MNB and MLP with TF-IDF & CountVectorizer","authors":"Tamal Ahmed, Shawly Folia Mukta, Tamim Al Mahmud, S. Hasan, Md Gulzar Hussain","doi":"10.1109/ICSEC56337.2022.10049341","DOIUrl":"https://doi.org/10.1109/ICSEC56337.2022.10049341","url":null,"abstract":"Emotions have a significant role in human contact. Written material, vocal discourse, and facial expressions can all be used to convey emotion. The habit of showing emotion on digital platforms or blogs has grown considerably in recent years. Bangla is a widely spoken language throughout the globe, with billions of people speaking it. Bangla is used by these folks to express their emotions. It will be wonderful to have a means to identify these emotions outside of the text. In order to achieve this goal, we tested three algorithms for detecting emotion in Bangla texts. Logistic Regression, Multinomial Naive Bayes, and Multi-layer Perceptron have all been used to determine six identical emotion-related categories. TF-IDF, count vectorizer and their combination is used as features on two blended datasets to evaluate the performance of these three algorithms. It is found that he LR with TF-IDF approach gives the best overall accuracy, precision, recall, and F1-measure score among all of the results.","PeriodicalId":430850,"journal":{"name":"2022 26th International Computer Science and Engineering Conference (ICSEC)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125174570","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Cancelable Face Biometric Verfication Algorithm Built on GoogLeNet and Characteristic Arbitrary Projection","authors":"H. B. Alwan, Ahmed Hamid Ahmed, K. Ku-Mahamud","doi":"10.1109/ICSEC56337.2022.10049360","DOIUrl":"https://doi.org/10.1109/ICSEC56337.2022.10049360","url":null,"abstract":"Biometric pattern information securing is necessary for avoiding individual confidentiality and identity loss. Arbitrary projection built on cancelable face biometrics is an effective and efficient approach to accomplish biometric pattern securing. Nevertheless, standard arbitrary projection-built cancelable pattern design can be easily attacked by attackers. To resolve this problem, in this paper, a characteristic arbitrary projection built on a cancelable face biometric algorithm is proposed, in which the projection arrays are created from one fundamental array in integration with face biometric information. The created projection arrays are deleted after utilization which makes it impossible for the hacker to attack information. The proposed algorithm is tested on two known benchmarks, FEI and Georgia Tech face datasets. Experimental results illustrate the robustness of the proposed algorithm.","PeriodicalId":430850,"journal":{"name":"2022 26th International Computer Science and Engineering Conference (ICSEC)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130953335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Isarn Dialect Word Segmentation using Bi-directional Gated Recurrent Unit with transfer learning approach","authors":"Sawetsit Aim-Nang, Pusadee Seresangtakul, Pongsathon Janyoi","doi":"10.1109/ICSEC56337.2022.10049346","DOIUrl":"https://doi.org/10.1109/ICSEC56337.2022.10049346","url":null,"abstract":"This paper presents an Isarn dialect word segmentation based on a recurrent neural network. In this study, the Isarn text written in Thai script is taken as input. We explored the effectiveness of the types of recurrent layers; recurrent neural networks (RNN), gated recurrent units (GRU), and long short-term memory (LSTM). The F1-scores of RNN, GRU, and LSTM are 95.36, 96.05, and 95.70, respectively. The experiment results showed that using GRU as the recurrent layer achieved the best performance. To deal with borrowed words from Thai, transfer learning was applied to improve the performance of the model by fine-tuning the pre-trained model given the limited size of the Isarn corpus. The model trained through the transfer learning approach outperformed the model trained from the Isarn dataset alone.","PeriodicalId":430850,"journal":{"name":"2022 26th International Computer Science and Engineering Conference (ICSEC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130984576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Contextual Data Modeling for Recommender System in Building and Construction Materials Business","authors":"Sutthirat Kliangklao, N. Suvonvorn","doi":"10.1109/ICSEC56337.2022.10049329","DOIUrl":"https://doi.org/10.1109/ICSEC56337.2022.10049329","url":null,"abstract":"The recommendation system is one of the most important supported technologies to e-commerce that aims for recommending products or services to increase customer’s satisfaction. In this paper, we propose the method for Contextual Data Modeling as an improved version of Hybrid Filtering to introduce the context-awareness in the building and construction materials business. The recommendation along with e-commerce system are built, deployed, and tested in the real situation. The evaluation score is up to 97.8 compared to baseline.","PeriodicalId":430850,"journal":{"name":"2022 26th International Computer Science and Engineering Conference (ICSEC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124338537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Orawan Chunhapran, C. Phromsuthirak, Maposee Hama, Maleerat Maliyaem
{"title":"Movie Recommendation System Using Director-Based","authors":"Orawan Chunhapran, C. Phromsuthirak, Maposee Hama, Maleerat Maliyaem","doi":"10.1109/ICSEC56337.2022.10049347","DOIUrl":"https://doi.org/10.1109/ICSEC56337.2022.10049347","url":null,"abstract":"A recommendation system saves the user the time and effort of searching for information by analyzing their profile and recommending the most appropriate content. To perform recommendations, a variety of techniques have been proposed, including content-based, collaborative, and hybrid filtering. Recommendation systems are used to suggest content such as books, music, and movies. The film business, in particular, makes movie recommendations using collaborative filtering that is based on genres and is frequently utilized in film recommendation systems. When customers first come across movie suggestion services or have certain movie interests, such as preferences for directors, this method may not work as well. This inspired us to propose a director-based recommendation system that uses content-based filtering and takes into account the genres of 5,000 records of Kaggle movie data as well as information on the filmographies of the directors. The cosine similarity function is used to assess the effectiveness and performance of the recommended system, and the results are very satisfactory.","PeriodicalId":430850,"journal":{"name":"2022 26th International Computer Science and Engineering Conference (ICSEC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128736633","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"AI-Based Suspicious Identification System for Agency Security Monitoring using Big Data Fusion","authors":"S. Vorapatratorn","doi":"10.1109/ICSEC56337.2022.10049352","DOIUrl":"https://doi.org/10.1109/ICSEC56337.2022.10049352","url":null,"abstract":"Terrorism is now a global issue, particularly the use of objects, car bombs, and even human suicide attacks. However, these issues can be avoided by reporting any anomalies that occur in the area. Unfortunately, it is not possible to use people to inspect the entire area. This study presents an AI-based suspicious identification system for agency security monitoring based on big data fusion, which employs specific data from an agency’s person, thing, and vehicle that appear at various times and locations. The best machine learning algorithm was used to train this data, and the results were displayed in real-time on the web application. In our experiment, we used ANN, SVM, k-NN, decision tree, and Naive Bayes to train the suspicious model with Scikit-learn on Python. The decision tree algorithm has the highest classification accuracy of 98.867% and the fastest prediction speed of 0.005 milliseconds per sample, according to the experiment results.","PeriodicalId":430850,"journal":{"name":"2022 26th International Computer Science and Engineering Conference (ICSEC)","volume":"151 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114108250","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Aphichaya Kruakuanphet, P. Phongwisit, W. Yindeesuk, S. Kamoldilok, K. Srinuanjan
{"title":"Multi-range Ammonia Gas Sensor Control and Monitor via IoT System","authors":"Aphichaya Kruakuanphet, P. Phongwisit, W. Yindeesuk, S. Kamoldilok, K. Srinuanjan","doi":"10.1109/ICSEC56337.2022.10049351","DOIUrl":"https://doi.org/10.1109/ICSEC56337.2022.10049351","url":null,"abstract":"In this paper, we present a multi-range of ammonia gas concentration control and monitoring via IoT system. We can select the ammonia gas concentration measurement range by adjusting load resistance within the voltage divider circuit. The appropriate measurement range, which corresponds to the concentration of ammonia gas produced by agricultural and industrial activities, can control and monitor via Blynk application. The MQ-137 gas sensor is selected as the main sensor, and each load resistance condition within the voltage divider circuit is calibrated with known ammonia gas concentration inside a calibration box. The calibration data is input into computer programming and processed by ESP8266 microprocessor. After calibration, we obtained a multi-range ammonia gas sensor suitable for measuring the ammonia gas concentration for each concentration range. The experiment showed that load resistance affects the measurement accuracy of ammonia gas concentration. We can select the load resistance suitable for the ammonia gas concentration and display on a smartphone via IoT system.","PeriodicalId":430850,"journal":{"name":"2022 26th International Computer Science and Engineering Conference (ICSEC)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123720929","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Thai Covid-19 Wave Breaks Analysis Based on Fourier Transform","authors":"A. Heednacram, Phatcharee Thepnimit","doi":"10.1109/ICSEC56337.2022.10049349","DOIUrl":"https://doi.org/10.1109/ICSEC56337.2022.10049349","url":null,"abstract":"Around the beginning of April 2021, the Thai Covid-19 Alpha-Delta wave began to spread. After approximately 37 weeks, the Omicron wave emerged in mid-December 2021. This paper proposes a Fourier transform approach for examining the exact wave breaks and reveals the hidden information in the power spectrum of the pandemic by converting the number of infected cases, death cases, and recovered cases caused by Covid-19 in Thailand from the time domain to the frequency domain. Analyses are conducted on wave intensity, pattern, and cycle duration. Two validation procedures are proposed to ensure the correct identification of wave breaks. The first strategy employs cross-correlation, whereas the second technique utilizes matching peak frequencies. Our results mathematically determined the Alpha-Delta wave’s end date and the Omicron wave’s beginning date. The matched peak frequency between the waves was discovered at frequency 5.286, corresponding to a cycle length of 7.027 days. The outcome enables policymakers to comprehend the pandemic’s trend and determine if the policy should be strengthened or relaxed.","PeriodicalId":430850,"journal":{"name":"2022 26th International Computer Science and Engineering Conference (ICSEC)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131796627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}