Science in Information Technology Letters最新文献

{"title":"Vision-based chicken meat freshness recognition system using RGB color moment features and support vector machine","authors":"S. Sutarman, Donny Avianto, Adityo Permana Wibowo","doi":"10.31763/sitech.v4i2.1230","DOIUrl":"https://doi.org/10.31763/sitech.v4i2.1230","url":null,"abstract":"Chicken meat is a highly sought-after food product among various segments of the general population, known for its high nutritional value and easy accessibility. Presently, meat identification is primarily conducted manually, relying on visual inspection or tactile assessment of the meat's color and texture. However, this approach presents several limitations, particularly when consumers lack the discernment to differentiate the quality of chicken meat freshness. This research aims to identify the freshness level of chicken meat using the Support Vector Machine method, employing the extraction of RGB color moment features to determine the freshness of the meat. The feature extraction process involves calculating the percentage of intensity values for R (Red), G (Green), and B (Blue) in each chicken meat image. Based on the image processing results, the percentage of intensity values, particularly in the R and B parameters, can be used as determining factors. The study involves software testing using fresh and non-fresh chicken meat. The developed system can identify the freshness level of fresh chicken meat with an accuracy rate of 71.6% using the linear kernel SVM and 60.5% using the RBF kernel SVM.  This research represents a significant step toward the automation of chicken meat freshness assessment, potentially reducing food waste and enhancing food safety in the food industry. Further research and development could improve the system's accuracy and expand its applications in various food quality control settings.Chicken meat is a highly sought-after food product among various segments of the general population, known for its high nutritional value and easy accessibility. Presently, meat identification is primarily conducted manually, relying on visual inspection or tactile assessment of the meat's color and texture. However, this approach presents several limitations, particularly when consumers lack the discernment to differentiate the quality of chicken meat freshness. This research aims to identify the freshness level of chicken meat using the Support Vector Machine method, employing the extraction of RGB color moment features to determine the freshness of the meat. The feature extraction process involves calculating the percentage of intensity values for R (Red), G (Green), and B (Blue) in each chicken meat image. Based on the image processing results, the percentage of intensity values, particularly in the R and B parameters, can be used as determining factors. The study involves software testing using fresh and non-fresh chicken meat. The developed system can identify the freshness level of fresh chicken meat with an accuracy rate of 71.6% using the linear kernel SVM and 60.5% using the RBF kernel SVM.  This research represents a significant step toward the automation of chicken meat freshness assessment, potentially reducing food waste and enhancing food safety in the food industry. Further research and development could improve the s","PeriodicalId":123344,"journal":{"name":"Science in Information Technology Letters","volume":"63 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139242959","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":"Improving sentiment analysis on PeduliLindungi comments: a comparative study with CNN-Word2Vec and integrated negation handling","authors":"H. Jayadianti, Berliana Andra Arianti, Nurheri Cahyana, S. Saifullah, Rafał Dreżewski","doi":"10.31763/sitech.v4i2.1184","DOIUrl":"https://doi.org/10.31763/sitech.v4i2.1184","url":null,"abstract":"This study investigates sentiment analysis in Google Play reviews of the PeduliLindungi application, focusing on the integration of negation handling into text preprocessing and comparing the effectiveness of two prominent methods: CNN-Word2Vec CBOW and CNN-Word2Vec SkipGram. Through a meticulous methodology, negation handling is incorporated into the preprocessing phase to enhance sentiment analysis. The results demonstrate a noteworthy improvement in accuracy for both methods with the inclusion of negation handling, with CNN-Word2Vec SkipGram emerging as the superior performer, achieving an impressive 76.2% accuracy rate. Leveraging a dataset comprising 13,567 comments, this research introduces a novel approach by emphasizing the significance of negation handling in sentiment analysis. The study not only contributes valuable insights into the optimization of sentiment analysis processes but also provides practical considerations for refining methodologies, particularly in the context of mobile application reviews.","PeriodicalId":123344,"journal":{"name":"Science in Information Technology Letters","volume":"31 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139242947","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":"Forging a learner-centric blended-learning framework via an adaptive content-based architecture","authors":"Arnold Adimabua Ojugo, Christopher Chukwufunaya Odiakaose, Frances Uche Emordi, Patrick O. Ejeh, Winifred Adigwe, Kizito Eluemonor Anazia, Blessing Nwozor","doi":"10.31763/sitech.v4i1.1186","DOIUrl":"https://doi.org/10.31763/sitech.v4i1.1186","url":null,"abstract":"The covid-19 pandemic was reported with significant negative impact on global education with shocks that disrupted the learning processes via the closure of traditional classrooms/schools from 2020 to March 2022. These effects have continued to ripple across even with advances in media literacy. The Nigerian frontier has also witnessed a paradigm shift in the adoption/integration of the information and communication tech as tools for both digital revolution and advancement of alternative education delivery. Today’s education which aspires for growth and progressive development is assured of positive changes if priority for educational values and ICT is harnessed. Past educational theories seem not to cope with the ever-changing, information society. Nigeria must develop strategies to address education reforms with frameworks to bridge these gaps vid post covid-19 era. Our study implements a hybrid a(synchronous) learning framework for Nigerian Tertiary education. Result shows improved learner cognition, engaged qualitative learning, and a learning scenario that ensures a power shift in the educational structure that will further equip learners to become knowledge producer, help teachers to emancipate students academically, in a framework that measures quality of engaged student’s learning","PeriodicalId":123344,"journal":{"name":"Science in Information Technology Letters","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135692905","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":"Optimizing CNN hyperparameters with genetic algorithms for face mask usage classification","authors":"Awang Hendrianto Pratomo, Nur Heri Cahyana, Septi Nur Indrawati","doi":"10.31763/sitech.v4i1.1182","DOIUrl":"https://doi.org/10.31763/sitech.v4i1.1182","url":null,"abstract":"Convolutional Neural Networks (CNNs) have gained significant traction in the field of image categorization, particularly in the domains of health and safety. This study aims to categorize the utilization of face masks, which is a vital determinant of respiratory health. Convolutional neural networks (CNNs) possess a high level of complexity, making it crucial to execute hyperparameter adjustment in order to optimize the performance of the model. The conventional approach of trial-and-error hyperparameter configuration often yields suboptimal outcomes and is time-consuming. Genetic Algorithms (GA), an optimization technique grounded in the principles of natural selection, were employed to identify the optimal hyperparameters for Convolutional Neural Networks (CNNs). The objective was to enhance the performance of the model, namely in the classification of photographs into two categories: those with face masks and those without face masks. The convolutional neural network (CNN) model, which was enhanced by the utilization of hyperparameters adjusted by a genetic algorithm (GA), demonstrated a commendable accuracy rate of 94.82% following rigorous testing and validation procedures. The observed outcome exhibited a 2.04% improvement compared to models that employed a trial and error approach for hyperparameter tuning. Our research exhibits exceptional quality in the domain of investigations utilizing Convolutional Neural Networks (CNNs). Our research integrates the resilience of Genetic Algorithms (GA), in contrast to previous studies that employed Convolutional Neural Networks (CNN) or conventional machine learning models without adjusting hyperparameters. This unique approach enhances the accuracy and methodology of hyperparameter tuning in Convolutional Neural Networks (CNNs).","PeriodicalId":123344,"journal":{"name":"Science in Information Technology Letters","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135692908","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":"YOLOv3 and YOLOv5-based automated facial mask detection and recognition systems to prevent COVID-19 outbreaks","authors":"Md Asifuzzaman Jishan, Ananna Islam Bedushe, Md Ataullah Khan Rifat, Bijan Paul, Khan Raqib Mahmud","doi":"10.31763/sitech.v4i1.1199","DOIUrl":"https://doi.org/10.31763/sitech.v4i1.1199","url":null,"abstract":"Object detection system in light of deep learning have been monstrously effective in complex item identification task images and have shown likely in an extensive variety of genuine applications counting the Coronavirus pandemic. Ensuring and enforcing the proper use of face masks is one of the main obstacles in containing and reducing the spread of the infection among the population. This paper aims to find out how the urban population of a megacity uses facial masks correctly. Using YOLOv3 and YOLOv5, we trained and validated a brand-new dataset to identify images as \"with mask\", \"without mask\", and \"mask not in position\". In the YOLOv3 we carried out three pre-trained models which are: YOLOv3, YOLOv3-tiny, and SPP-YOLOv3. In addition, we utilized five pre-trained models in the YOLOv5: YOLOv5n, YOLOv5s, YOLOv5m, YOLOv5l, and YOLOv5x. The dataset is included 6550 pictures with three classes. On mAP, the dataset achieved a commendable 95% performance accuracy. This research can be used to monitor the proper use of face masks in various public spaces through automated scanning.","PeriodicalId":123344,"journal":{"name":"Science in Information Technology Letters","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135692907","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":"Suicide and self-harm prediction based on social media data using machine learning algorithms","authors":"Abdulrazak Yahya Saleh, Fadzlyn Nasrini Binti Mostapa","doi":"10.31763/sitech.v4i1.1181","DOIUrl":"https://doi.org/10.31763/sitech.v4i1.1181","url":null,"abstract":"Online social networking (SN) data is a context and time rich data stream that has showed potential for predicting suicidal ideation and behaviour. Despite the obvious benefits of this digital media, predictive modelling of acute suicidal ideation (SI) remains underdeveloped at now. In combined with robust machine learning algorithms, social networking data may provide a potential path ahead. Researchers applied a machine learning models to a previously published Instagram dataset of youths. Using predictors that reflect language use and activity inside this social networking, researchers compared the performance of the out-of-sample, cross-validated model to that of earlier efforts and used a model explanation to further investigate relative predictor relevance and subject-level phenomenology. The application of ensemble learning approaches to SN data for the prediction of acute SI may reduce the complications and modelling issues associated with acute SI at these time scales. Future research is required on bigger, more diversified populations to refine digital biomarkers and assess their external validity with more rigor","PeriodicalId":123344,"journal":{"name":"Science in Information Technology Letters","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135563581","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":"Placement model for students into appropriate academic class using machine learning","authors":"Khalid Haruna, Anadi Stella Uju, Ibrahim Alhaji Lawal, Raliya Abubakar","doi":"10.31763/sitech.v4i1.1024","DOIUrl":"https://doi.org/10.31763/sitech.v4i1.1024","url":null,"abstract":"Choosing the right academic major for junior secondary students into senior secondary school will assist both students and their teachers toward achieving the academic goal. Traditionally, students seeking admission into senior classes (Gambia, Sierra-leone, Ghana, Liberia and Nigeria) must have passed stipulated examinations like Basic Education Certificate Examination (BECE) and/or West Africa Junior Certificate Examination, which are done at the end of year three (at a sitting). They must pass the exam(s) satisfactorily with no emphasis on any of Science, Art or Commercial related subjects. Some schools use “Mock exam” or “Placement exam” as the basis for their placement of students but all are done at a sitting (end of year three). Though this method is to an extent valid but associated with some challenges (bias) as it does not carry along the student’s academic history in making decision for placement into appropriate class. However, we proposed a model that predicts appropriate academic class of Science, Art or Commercial for Junior students based on their progressive academic performances (history) of their predecessors on related subjects using ten supervised machine learning techniques. Two evaluation techniques were applied (70/30 splitting and 10-fold cross validation). The highest results of this research showed accuracy of 93% with Random forest, 98% precision with random forest, 99% recall with Decision tree and 94% f1 score with Random forest and KNN (cross validation). The correlation coefficient of the proposed model recorded 0.3 higher than that of the existing method. This research will benefit all stakeholders in education and students in particular because their academic performances over time stands a better chance for appropriate placement.","PeriodicalId":123344,"journal":{"name":"Science in Information Technology Letters","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135563582","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":"Design of an FTTH (Fiber To The Home) Network for the Improvement of Voice, Broadband, and Television Services in Hard-to-Reach Areas. The Colombian Case","authors":"Leonel Hernandez, J. Albás, Jair Camargo, César De La Hoz, Fachrul Kurniawan","doi":"10.31763/sitech.v3i2.1001","DOIUrl":"https://doi.org/10.31763/sitech.v3i2.1001","url":null,"abstract":"This project establishes the process of designing a fiber optic Ftth network that reaches the homes of each end customer, which allows providing voice services, broadband internet, and television, the above using GPON technology, based on the tree architecture through passive elements, where the node or central is connected to other nodes through a common link, which is shared by all the nodes (ONTs) of the network. This network will be designed in two levels, the first level that starts from the OLT to the level one splitter and the second level that begins from the level one splitter to the OTB element that the level two Splitters have. The entire design will be subject to standards that must be met to achieve the percentage of attenuation allowed. At the design level, it has two directions: one from left to right, where the nodes insert traffic, and another from right to left, where the nodes only have two functions: read or read and delete traffic. It is nothing more than the convergence of the primary communication services of today, such as fixed telephony, the internet, and television. The FTTH Network is designed for the Municipality of Usiacurí of the Department of Atlántico, using the Top-Down Design methodology, where the requirements are analyzed, the designs are developed, and the tests are carried out. The operation of this network is monitored.","PeriodicalId":123344,"journal":{"name":"Science in Information Technology Letters","volume":"276 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124445175","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":"Motivational aspects of digital games in learning process","authors":"Nabila Musa Abdullahi, Auwal Shehu Ali, Aminu Usman Jibril, Hamidatu Abdulkadir, Ugochukwu O. Matthew, Khalid Haruna","doi":"10.31763/sitech.v3i1.885","DOIUrl":"https://doi.org/10.31763/sitech.v3i1.885","url":null,"abstract":"With the advent of digital games and its rapid evolution, it is almost impossible for a lot of people especially the young children to go a day without coming into contact with them. One of the impacts of these digital games is that it is changing the way these young children think and learn. It is therefore important to carefully examine the influence of digital games on children’s education. The purpose of this research is to identify and examine the factors that motivate children to play digital games and to determine the effect of such games to the children’s learning abilities. Responses from 172 students of ages between 11 and 16 are analysed in this research. A questionnaire is used to capture the children’s motivation towards digital gaming. Also, an intellectual test was carried out to determine the effect of digital games on the children’s learning abilities. The findings have revealed that competitive spirit is the major factor that influences children to play digital games because of the challenge and the competition that comes along with it. Furthermore, a critical view from the results of the intellectual test has shown that the children that play digital games score higher results and were able to finish within a short period of time as against the children that do not play. The outcome of this research could be used to explore the possibilities of using digital games as tools for learning, especially to the young ages.","PeriodicalId":123344,"journal":{"name":"Science in Information Technology Letters","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131828566","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":"Location-Aware Recommender System: A review of Application Domains and Current Developmental Processes","authors":"Khalid Haruna, A. Musa, Zayyanu Yunusa, Yakubu Ibrahim, Fa’iz Ibrahim Jibia, Nur Bala Rabiu","doi":"10.31763/sitech.v2i1.610","DOIUrl":"https://doi.org/10.31763/sitech.v2i1.610","url":null,"abstract":"Recommender systems (RS) have been widely used to extract relevant and meaningful information from a vast body of data, to make appropriate suggestions to users with different preferences in various domains of applications. However, despite the success of the early recommendation systems, they suffer from two major challenges of cold start and data sparsity. Traditional RS consider an interaction between user and item (2D), neglecting contextual information such as location, until fairly recently. The contexts extend traditional RS to multi-dimension interaction and provides a useful information that allow recommendations to be more personalized. Surprisingly, taking these contexts such as location, into consideration eliminates the challenges of traditional RS. Location-Aware Recommender System (LARS) takes user's location into account as an additional context. The combination allows the prediction of spatial items, items closest to the users, to reduce information overload and was proved to be more effective than earlier RS. In this research, we provide a systematic literature of the existing literature in LARS from 2010 to 2021, focusing on the state-of-the-art methodologies, the domain of applications, and trends of publications in LARS. The paper proposed several models of LARS based on the traditional RS methodologies, providing future directions to researchers. Despite numerous reviews available on LARS, a review that proposed several LARS techniques were not found in the literature. The results indicated that the trend of publication in LARS is growing exponentially and that the field is getting attention rapidly with the number of publications on the rise every year.","PeriodicalId":123344,"journal":{"name":"Science in Information Technology Letters","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123865144","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}