International Journal of Computing Sciences Research最新文献_第5页

An Enhancement of Long-Short Term Memory for the Implementation of Virtual Assistant for Pamantasan ng Lungsod ng Maynila Students 使用虚拟助手对帕曼塔桑、隆隆索和梅尼拉学生长短期记忆的增强

International Journal of Computing Sciences Research Pub Date : 2023-01-01 DOI: 10.25147/ijcsr.2017.001.1.91

Draillim Xaviery Valonzo, Jose Ramon Jasa, Mark Christopher R. Blanco, Khatalyn E. Mata, Dan Michael A. Cortez

{"title":"An Enhancement of Long-Short Term Memory for the Implementation of Virtual Assistant for Pamantasan ng Lungsod ng Maynila Students","authors":"Draillim Xaviery Valonzo, Jose Ramon Jasa, Mark Christopher R. Blanco, Khatalyn E. Mata, Dan Michael A. Cortez","doi":"10.25147/ijcsr.2017.001.1.91","DOIUrl":"https://doi.org/10.25147/ijcsr.2017.001.1.91","url":null,"abstract":"Purpose – Natural Language Processing is an aspect of Artificial Intelligence that focuses on how technology can understand words, derive meaning from them, and return a meaningful and correct output. Therefore, it is used in the making of Virtual Assistants today. Training virtual assistants require long temporal dependencies and sequence-to-sequence classification. This study will be used to create a possible algorithm that will enhance the performance of a possible virtual assistant designed for PLM students and faculty members. Method – LSTM will be used to train the model to address these concerns. However. The LSTM algorithm faces the problem of slow computing speed and high computation costs. To address this the researchers implemented TensorFlow XLA to the model to optimize the computation costs in the problem. Results – Though the number of matrices exploded from 934 to 30000, the training can show slight improvement both in memory, CPU (Central Processing Unit) utilization, and time reduction. At 50 epochs, training the model with XLA has shown a time decrease of 8 minutes and can save at most 500 megabytes of memory. Conclusion – XLA has proven that it has helped the LSTM algorithm in terms of its usage in memory, utilization of CPU, and overall speed of training, especially in longer processes. Recommendations – The researchers recommend using XLA in the context of pruning and the effect of pruning paired with XLA to maximize the performance of the model. Practical Implication – This would allow a much more efficient and cost-friendly training of the model when feeding it new data to be used for virtual assistant designed for PLM students and faculty members.","PeriodicalId":33870,"journal":{"name":"International Journal of Computing Sciences Research","volume":"157 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79954415","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}

引用次数: 0

Insights and Trends of Capstone Project of CS/IT Department of Bicol University from 2011 to 2019 2011 - 2019年比科尔大学CS/IT系顶点项目的洞察与趋势

International Journal of Computing Sciences Research Pub Date : 2023-01-01 DOI: 10.25147/ijcsr.2017.001.1.99

Benedicto Balilo Jr., Ryan K. Rodriguez, Jonathan Jaime Guerrero

引用次数: 0

Artificial Intelligence (AI) in the Hospitality Industry: A Review Article 人工智能(AI)在酒店业:综述文章

International Journal of Computing Sciences Research Pub Date : 2023-01-01 DOI: 10.25147/ijcsr.2017.001.1.103

Pongsakorn Limna

引用次数: 12

Role of IoTs and Analytics in Efficient Sustainable Manufacturing of Consumer Electronics 物联网和分析在消费电子产品高效可持续制造中的作用

International Journal of Computing Sciences Research Pub Date : 2023-01-01 DOI: 10.25147/ijcsr.2017.001.1.105

S. Jahan, M. Sazu

引用次数: 29

RAMY Greeting Feature using HAAR cascade classifier and HOG Algorithm for Asia Pacific College 亚太学院使用HAAR级联分类器和HOG算法的RAMY问候特征

International Journal of Computing Sciences Research Pub Date : 2023-01-01 DOI: 10.25147/ijcsr.2017.001.1.133

Einstein D. Yong, Luigi Carlo De Jesus, S. G. Brucal, Leonardo Samaniego Jr., Sergio Peruda Jr., Paulo Cosio, Juan Miguel Villarroel, Kimberly Novilla, Esther Anne Cacalda, Clarisha Lacar, Andrea Calibara

引用次数: 0

Optimizing the University Student Advising Process through Weighted Minimum Spanning Tree Algorithm 基于加权最小生成树算法的大学生建议过程优化

International Journal of Computing Sciences Research Pub Date : 2023-01-01 DOI: 10.25147/ijcsr.2017.001.1.128

Danilo Sabado

引用次数: 0

Behavioral Analysis and Evaluation of Online Shoppers in the Philippines using the Proposed Online Shopping Website 使用拟议的网上购物网站的菲律宾网上购物者的行为分析和评价

International Journal of Computing Sciences Research Pub Date : 2023-01-01 DOI: 10.25147/ijcsr.2017.001.1.153

Nelson C. Rodelas, Alexis John Rubio, Jherold John Valdoz, Kathleen Dimaano, Amelia A. Pasilan, Edie Boy Dela Cruz

{"title":"Behavioral Analysis and Evaluation of Online Shoppers in the Philippines using the Proposed Online Shopping Website","authors":"Nelson C. Rodelas, Alexis John Rubio, Jherold John Valdoz, Kathleen Dimaano, Amelia A. Pasilan, Edie Boy Dela Cruz","doi":"10.25147/ijcsr.2017.001.1.153","DOIUrl":"https://doi.org/10.25147/ijcsr.2017.001.1.153","url":null,"abstract":"Purpose – Online Shopping is proof that e-commerce is becoming more popular in the Philippines. There are so many online shopping sites and most of them were very popular not only here but also outside the country. The purpose of this study was to determine the behavioral analysis of consumers towards online shopping systems based on the online shopping practices and behavior of the customers. Method – The descriptive quantitative research approach was used in this study, with the questionnaire serving as the primary data collection tool. One hundred (100) respondents were chosen from a pool of business process outsourcing employees at a well-known corporation. Results – The many variables describing the respondents' online purchasing habit are classified into four categories: mall service availability, quality difficulties, and pricing concerns and interests. These practices may reflect respondents' attitudes toward internet buying. According to the findings, there is no significant association between the varied behaviors of the respondents and their demographic profile. This suggests that respondents' online buying behavior is unaffected by their age, gender, or financial level. Conclusion – It may be said that the Online Shopping System satisfies customers with the services, quality of the product, and reliable price offered by the system. Recommendations – This system contributes to the e-commerce popularity in the Philippines in line with the other common online websites. Implications – The inference is that customers' perceptions of a good deal and a worthwhile product or service are likely to impact online customer happiness directly. Then they should think about building methods to keep online clients, which means that the management should create not just a high-quality e-commerce infrastructure, but also excellent items, dependable delivery, and fair pricing.","PeriodicalId":33870,"journal":{"name":"International Journal of Computing Sciences Research","volume":"14 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87580105","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}

引用次数: 0

Development of Crime Reporting System to Identify Patterns of Crime in Laguna 发展犯罪报告系统以识别拉古纳的犯罪模式

International Journal of Computing Sciences Research Pub Date : 2023-01-01 DOI: 10.25147/ijcsr.2017.001.1.110

Mia V. Villarica, Francis F. Balahadia, Jonardo R. Asor, G. Catedrilla

引用次数: 1

Sentiment Analysis of Students’ Perception towards the Implementation of Limited In-Person Learning: A Post-Pandemic Perspective 学生对实施有限面对面学习认知的情绪分析:后流行病视角

International Journal of Computing Sciences Research Pub Date : 2023-01-01 DOI: 10.25147/ijcsr.2017.001.1.126

Erwin L. Cahapin, Cereneo Jr Santiago, B. Malabag, Jocelyn L. Reyes, Gemma S. Legaspi, Marion Joyce Benedicto

引用次数: 0

Development of Tomato Leaf Disease Detection using Single Shot Detector (SSD) Mobilenet V2 利用单次射击检测器(SSD) Mobilenet V2进行番茄叶病检测的开发

International Journal of Computing Sciences Research Pub Date : 2023-01-01 DOI: 10.25147/ijcsr.2017.001.1.136

S. G. Brucal, Luigi Carlo De Jesus, Jex De Los Santos, Mariel Joy Mendoza, Khyrstelle Harion, Guiliane Altaire Reyes, Dominador Nevalasca, Jv Kay Reyes

{"title":"Development of Tomato Leaf Disease Detection using Single Shot Detector (SSD) Mobilenet V2","authors":"S. G. Brucal, Luigi Carlo De Jesus, Jex De Los Santos, Mariel Joy Mendoza, Khyrstelle Harion, Guiliane Altaire Reyes, Dominador Nevalasca, Jv Kay Reyes","doi":"10.25147/ijcsr.2017.001.1.136","DOIUrl":"https://doi.org/10.25147/ijcsr.2017.001.1.136","url":null,"abstract":"Purpose – To create a software prototype for the tomato leaf disease detection model to identify the tomato leaf condition and detect and identify the disease present in it. Methodology – Using the TensorFlow 2 Object Detection API, the object detection model used is the Single Shot Detector (SSD) MobileNetV2 Object Detection model. The feature extractor used is the pre-trained TF2 MobileNetV2 model with the ImageNet dataset providing trained weights that allows feature extraction. Combining the pre-trained TF2 MobileNetV2 and Convolutional Neural Network (CNN) for SSD, the result object localization and image classification with SSD, and feature extractor pre-trained model. Result – When training the model, at the 1300th step out of 6000 steps, the learning rate spiked from 0 to 0.7999. It then stabilized from 0.7999 and gradually decreased to 0.7796. After training, the total loss of the model is 46.95% for evaluation and 45.32% for training results. The average recall of the model is","PeriodicalId":33870,"journal":{"name":"International Journal of Computing Sciences Research","volume":"95 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80659585","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}

引用次数: 1