2022 26th International Computer Science and Engineering Conference (ICSEC)最新文献

{"title":"Python Code Smell Detection Using Machine Learning","authors":"Natthida Vatanapakorn, Chitsutha Soomlek, Pusadee Seresangtakul","doi":"10.1109/ICSEC56337.2022.10049330","DOIUrl":"https://doi.org/10.1109/ICSEC56337.2022.10049330","url":null,"abstract":"Python is an increasingly popular programming language used in various software projects and domains. Code smells in Python significantly influences the maintainability, understandability, testability issues. This paper proposes a machine learning-based code smell detection for Python programs. We trained eight machine learning models with a dataset based on 115 open-source Python projects, 39 class-level software metrics, and 22 function-level software metrics. We intended to identify five code smell types in both class and function levels, i.e., long method, long parameter list, large class long scope chaining, and long based class list. Correlation-based feature selection (CFS) and logistic regression-forward stepwise (conditional) selection were employed to improve the performance of the model. This research concluded with an empirical evaluation of the performance of the machine learning approaches against the tuning machine method. The results show that the machine learning method achieved 99.72% accuracy when identifying long method and long base class list. The machine learning-based code smell detection also outperformed the tuning machine method. Moreover, we also found a set of high-impact features that contributed most when identifying each type of code smell.","PeriodicalId":430850,"journal":{"name":"2022 26th International Computer Science and Engineering Conference (ICSEC)","volume":"5 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":"114957031","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":"Adaptive Learning Rate For Neural Network Classification Model","authors":"Rujira Jullapak, A. Thammano, Boonprasert Surakratanasakul","doi":"10.1109/ICSEC56337.2022.10049365","DOIUrl":"https://doi.org/10.1109/ICSEC56337.2022.10049365","url":null,"abstract":"Imbalanced data cause prediction inaccuracy of the classification model. Two types of techniques have been devised to address this problem: pre-processing data before training a classification model and adjusting the classification algorithm. This study, which introduced the adaptive learning rate into a backpropagation neural network algorithm, is of the latter type. The learning rate was adjusted in each iterative learning cycle: the learning rate is increased for the data class with fewer samples and decreased for the data class with more samples. K-fold cross-validation was used to test the effectiveness of the prediction model on 10 datasets. The results showed that the proposed ZMP algorithm outperformed the original backpropagation neural network on 6 datasets; the improvement ranged from 2.24% to 20.22%. Moreover, on the other 4 datasets, even though the proposed technique provided less accurate predictions, the differences were very slight.","PeriodicalId":430850,"journal":{"name":"2022 26th International Computer Science and Engineering Conference (ICSEC)","volume":"49 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":"122781229","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":"Monitoring System of Wearable Sensor Signal in Rehabilitation Using Efficient Deep Learning Approaches","authors":"Ponnipa Jantawong, S. Mekruksavanich, A. Jitpattanakul","doi":"10.1109/ICSEC56337.2022.10049326","DOIUrl":"https://doi.org/10.1109/ICSEC56337.2022.10049326","url":null,"abstract":"Recognition of human activity has utilized inputs from wearable sensors, which has significant implications for rehabilitative medicine and cognitive neuroscience. Unfortunately, some crucial dynamic data on upper-limb movements need to be included in the feature extraction procedure for wearable sensor data. The issue is that only a few rehabilitative motions can be recognized, and classification precision is readily compromised. We study several convolution neural networks to extract valuable characteristics from multichannel wearable sensor inputs automatically and precisely identify rehabilitation operations. We gathered wearable sensor signal data for six physiotherapy exercises to assess identification effectiveness using the SPARS9x standard rehabilitation dataset. Experiments showed that the PyramidNet18 model had the highest F1-score on the benchmark dataset, 99.15%.","PeriodicalId":430850,"journal":{"name":"2022 26th International Computer Science and Engineering Conference (ICSEC)","volume":"98 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":"114301399","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":"The Improvement Process for The Software Development and Requirements Management to Achieve Capability Level 3 of CMMI","authors":"Pitiphat Joembunthanaphong, Gridaphat Sriharee","doi":"10.1109/ICSEC56337.2022.10049356","DOIUrl":"https://doi.org/10.1109/ICSEC56337.2022.10049356","url":null,"abstract":"This research proposes the improvement process for software development and requirements management for a small and medium company to achieve capability level 3 of CMMI 2.0. The process was proposed to be executed by the waterfall process model and scrum-based agile. The authors developed the improvement process and support tool. The proposed process was applied to use in the home-loan service software development 2 projects. The evaluation of the proposed process was analyzed by comparing it to past project two projects. The result showed that the projects that applied the proposed improvement process had a better outcome 34.34%. The SCAMPI evaluation of the proposed process was taken by three experts and the result showed that the capability of the proposed process was 91.63% and the user satisfaction was at the good level with score of 4.37. From the experimentation that was conducted with two software companies, it was obvious that the proposed improvement process had significance to enhance the software development process to achieve capability level 3.","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":"128755759","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":"Tag Recommendation for Movie and Music Contents","authors":"Oluwatimilehin Adekunle Ileladewa, Yen-Min Jasmina Khaw, Gunavathi Duraisamy","doi":"10.1109/ICSEC56337.2022.10049338","DOIUrl":"https://doi.org/10.1109/ICSEC56337.2022.10049338","url":null,"abstract":"Tag recommendations are popular for labelling online web content. It usually involves the process of content classification, organization, and information retrieval. With the increase in the consumption of online content, recommender systems have been developed to study the behavioural patterns of users and use these results to recommend content. The cold start problem is an issue being faced in developing recommender systems due to insufficient data regarding recommended items. In this paper, we propose a hybrid approach of a Media Convolutional Neural Network with a Latent Dirichlet Allocation topic modelling (MCNN-LDA) algorithm for recommending tags for movie and music contents in trying to address the multi-label classification issue of the cold start problem. The final model is evaluated on the Internet Movie Database (IMDB) movie dataset and GTZAN audio dataset. The high accuracy results of the developed model achieved at a threshold of 0.90 indicate a high performance on the quality of tags recommended which is confirmed by the evaluation metrics performed.","PeriodicalId":430850,"journal":{"name":"2022 26th International Computer Science and Engineering Conference (ICSEC)","volume":"45 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":"129342386","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":"PIRSE: Plant Identification and Repository for the Smart Environment","authors":"Kanyarat Wannaphat, Aneesa Museh, Terapat Jinasa, U. Prasatsap, P. Thanarak, C. Termritthikun","doi":"10.1109/ICSEC56337.2022.10049317","DOIUrl":"https://doi.org/10.1109/ICSEC56337.2022.10049317","url":null,"abstract":"The purpose of this study was to apply smartphone technology to environmental programs to reduce CO2 emissions. A large plant database was developed that could be accessed via a smartphone application that was developed in this research project. The study was conducted in the School of Renewable Energy and Smart Grid Technology (SGtech), Naresuan University on an area of 13.79 acres planted with 460 trees of 45 different species. Data that was collected for each species, included height, circumference, carbon sequestration, CO2 absorption pinpointing, and photographs of leaves and bark. Using the Plant Identification and Repository for the Smart Environment (PIRSE) application, a plant database was developed that could be accessed via smartphone. From the carbon sequestration and CO2 absorption data in the database, the total CO2 absorption of the growing area was calculated as 1340.85-ton CO2e per year, which is equivalent to the CO2 emissions of one vehicle over five years. This smartphone technology can be applied to assist in decision-making on environmental issues such as forest clearing or forest rejuvenation and reforestation by planting programs, and the selection of appropriate species.","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":"130410377","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":"Comparative Analysis of Clustering Methodologies in DNA Storage","authors":"Subhasiny Sankar, Yixin Wang, Zhang Jiayu, Nur Sabrina, E. Gunawan, Y. L. Guan, Noor-A-Rahim Md., C. Poh","doi":"10.1109/ICSEC56337.2022.10049327","DOIUrl":"https://doi.org/10.1109/ICSEC56337.2022.10049327","url":null,"abstract":"Owing to the significance of DNA storage technology in meeting exponential storage demands and longevity, the challenges caused by bio-molecular errors while reading/sequencing data from DNA molecules must be addressed. By reading redundant copies, data can be reconstructed but with associated cost of sequencing and decoding complexities. Hence, solutions for dealing with both errors and complexities are sought after. The main objective of this work is to study data reconstruction methods for processing sequence readouts at downstream stage of DNA data storage. We investigated applicability of three clustering tools -Starcode, Slidesort, MeShClust, and two algorithms - Majority Nucleotide Selection (MNS), Cooperative Sequence Clustering (CSC) by transforming them into suitable tools for storage application. We observed that for fixed redundancy of 6.3x to 8.6x based on the nature of the dataset, Starcode outperforms other tools with 1% to 40% higher recovery rate. However, it costs the highest decoding complexity whereas MNS and CSC provides the lowest decoding complexity. Moreover, the distribution of the cluster and clustering speed of each tool/method are compared. This is the first comparative analysis study of tools/methods for data reconstruction in DNA data storage.","PeriodicalId":430850,"journal":{"name":"2022 26th International Computer Science and Engineering Conference (ICSEC)","volume":"142 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":"123913521","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":"To Dev or to Doc?: Predicting College IT Students’ Prominent Functions in Software Teams Using LMS Activities and Academic Profiles","authors":"Varit Rungbanapan, Tipajin Thaipisutikul, Siripen Pongpaichet, A. Supratak, Chih-Yang Lin, Suppawong Tuarob","doi":"10.1109/ICSEC56337.2022.10049348","DOIUrl":"https://doi.org/10.1109/ICSEC56337.2022.10049348","url":null,"abstract":"A software team comprises software practitioners with diverse backgrounds and responsibilities, such as programmers, reviewers, testers, and documentation experts. Whether developing the architecture, implementing new features, creating test cases, or providing documentation for users and the development team, each of these jobs is essential to the accomplishment of software tasks. Current methods for determining a student’s software development skill include sending questionnaires and monitoring students while they work. Not only are these techniques restricted in coverage, but they also rely on intervention strategies, which may result in social desirability bias and student exhaustion. In this research, we offer a multivariate time-series classification strategy for automatically identifying students’ expertise in software development based on information passively accessible via LMS logs and course grades. Several machine learning and deep learning models, including XGBoost, Random Forest, SVM, Stochastic Gradient Descent, Multi-layer Perceptron, Gaussian Naive Baye, Complement Naive Bayes, Long Short-Term Memory (LSTM), and XceptionTime, are examined for their ability to model students’ LMS activities and academic performance at various degrees of granularity, namely semester and daily levels. A case study of 33 IT-majoring college students is utilized to validate the effectiveness of the proposed strategy. The experimental findings demonstrate that our best models yield F1 values of 79.52% and 75.68% for the developer and documenter identification tasks, utilizing Multilayer Perceptron with daily features and LSTM with semester features, respectively. We are the first to attempt to determine the roles of students in software development using passively accessible data. The findings not only shed light on the ability to create personalized education tailored to each student’s needs but also pave the way for numerous intelligent education technology applications that aim to automatically evaluate certain student characteristics in order to optimize student learning outcomes.","PeriodicalId":430850,"journal":{"name":"2022 26th International Computer Science and Engineering Conference (ICSEC)","volume":"10 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":"123955593","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":"Selecting an open-source home automation system using the AHP Methodology","authors":"P. Sookavatana","doi":"10.1109/ICSEC56337.2022.10049344","DOIUrl":"https://doi.org/10.1109/ICSEC56337.2022.10049344","url":null,"abstract":"Smart homes are one of the most growing areas of the emerging Internet of Thing technology. Homes become an ecosystem of smart devices and applications from various manufacturers. To avoid the frustration of using multiple applications to control different smart devices from different commercial bands, users opt to implement a single control system and use only one application to rule all smart devices in their home automation system. Open-source home automation systems offer affordable and allow third-party support for devices and services that are unsupported by commercials. Each system comes with its own set of functionalities and restrictions. Choosing a suitable system is a challenge, as a wrong decision may be costly. In this paper, we present a method using Analytic Hierarchy Process to choose a home automation system based on different user criteria. Finally, an example is used to prove the method effectiveness.","PeriodicalId":430850,"journal":{"name":"2022 26th International Computer Science and Engineering Conference (ICSEC)","volume":"69 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":"125617142","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":"Time Series Classification Using Deep Learning for HAR Based on Smart Wearable Sensors","authors":"Ponnipa Jantawong, Narit Hnoohom, A. Jitpattanakul, S. Mekruksavanich","doi":"10.1109/ICSEC56337.2022.10049357","DOIUrl":"https://doi.org/10.1109/ICSEC56337.2022.10049357","url":null,"abstract":"In the last decades, time series classification (TSC) has emerged as one of the most challenging issues in data mining, and extensive studies have been done on various methods, including algorithm-based and learning-based techniques. Sensor-based human activity recognition (HAR) is a TSC issue that has become one of the most sought-after fields among business and academia specialists because of the proliferation of smartphone technology and wearable movement sensors. Conventional approaches to feature extraction provide a significant challenge in feature selection. Deep learning is an efficient strategy in the HAR scientific field and has solved the issue of feature selection. Nevertheless, several obstacles remain to study topics, including classifier interpretation. This article integrates well-known deep learning methods, namely convolutional neural networks and RNN-based models. The new approach proved to be more effective than the existing state-of-the-art approach. We assessed our network on the multivariant time-series benchmark (UCI-HAR) and revealed that our model surpasses other models in terms of training time and overall accuracy.","PeriodicalId":430850,"journal":{"name":"2022 26th International Computer Science and Engineering Conference (ICSEC)","volume":"148 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":"122282109","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}