Proceedings of the 1st International Conference on Advanced Information Science and System最新文献_第3页

Integrated model for smartwatch adoption 智能手表采用的集成模型

Proceedings of the 1st International Conference on Advanced Information Science and System Pub Date : 2019-11-15 DOI: 10.1145/3373477.3373485

N. M. Dawi, N. Jalil

引用次数: 2

Prediction of employee performance using machine learning techniques 使用机器学习技术预测员工绩效

Proceedings of the 1st International Conference on Advanced Information Science and System Pub Date : 2019-11-15 DOI: 10.1145/3373477.3373696

A. S. Lather, R. Malhotra, P. Saloni, Prabhjot Singh, Sarthak Mittal

{"title":"Prediction of employee performance using machine learning techniques","authors":"A. S. Lather, R. Malhotra, P. Saloni, Prabhjot Singh, Sarthak Mittal","doi":"10.1145/3373477.3373696","DOIUrl":"https://doi.org/10.1145/3373477.3373696","url":null,"abstract":"Any business's success depends on its employees. Businesses that realize this are concerned about employee output and productivity. Productivity has a compounding effect at the different levels in the workplace, meaning that high productivity at a lower level of organization paves way for higher productivity at the higher levels of the organization. Hence, analysis of performance of employees in any organization is the need of the hour. Performance of an employee cannot be attributed to any fixed quality. Different people have different skill sets and different behavioral characteristics. Thus, performance analysis requires data to be gathered from all walks of life. The purpose of this paper is to analyze and predict the performance of employees in an organization on the basis of various factors, including, but not limited to, individual and domain specific characteristics, nature and level of schooling, socioeconomic status and different psychological factors. This research paper uses Supervised learning techniques namely Support Vector Machines, Random Forest, Naive Bayes, Neural Networks and Logistic Regression which considers these factors and provides insights into the performance and commitment of employees. The employees are classified into 3 output classes indicating the level of their performance from low to high. In this research paper, 10-fold validation technique is used to ensure the correctness of the prediction by the above-mentioned techniques. Support Vector Machines prove to be the most efficient in terms of accuracy. The result is accentuated by the high validation score obtained by the same. Also, Employee's Creativity stands out as the most impactful feature.","PeriodicalId":300431,"journal":{"name":"Proceedings of the 1st International Conference on Advanced Information Science and System","volume":"194 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114539383","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: 5

Generating images with desired properties using the DiscoGAN model enhanced with repeated property construction 使用重复属性构造增强的DiscoGAN模型生成具有所需属性的图像

Proceedings of the 1st International Conference on Advanced Information Science and System Pub Date : 2019-11-15 DOI: 10.1145/3373477.3373705

Thanatwit Angsarawanee, B. Kijsirikul

{"title":"Generating images with desired properties using the DiscoGAN model enhanced with repeated property construction","authors":"Thanatwit Angsarawanee, B. Kijsirikul","doi":"10.1145/3373477.3373705","DOIUrl":"https://doi.org/10.1145/3373477.3373705","url":null,"abstract":"The idea of image-to-image translation is to take advantage in certain areas such as adding the sharpness to images and improving the semantic segmentation. The most popular models for solving problems are generative adversarial network (GAN) [1] models such as DiscoGAN [2] and CycleGAN [3]. In training process, input images with no desired properties, and output images with the desired properties are fed into the generative model to train the model. After training, the model can synthesize the desired properties from the input images without those properties. However, in practical usage, an input image may be different from the training process because the input image may be the image with or without the desired properties. This research proposes the method of training the generative model by giving input images with and without desired properties in the same way as when the model is used. Our proposed model enhances DiscoGAN with repeated property construction to generate images with desired properties. The model can use unpaired data as the training data, which makes data preparation more efficiently and more comprehensive than paired data. The proposed model obtained approximately 8% better Fréchet Inception Distance (FID) [4] score compared to the DiscoGAN model.","PeriodicalId":300431,"journal":{"name":"Proceedings of the 1st International Conference on Advanced Information Science and System","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121044991","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

T-series analysis for predicting apple prices in indonesian market using the SARIMA method 运用SARIMA方法预测印尼市场苹果价格的t系列分析

Proceedings of the 1st International Conference on Advanced Information Science and System Pub Date : 2019-11-15 DOI: 10.1145/3373477.3373496

Yosua Alvin Adi Soetrisno, E. Handoyo, Muhammad Haikal Ilyasa, Denis, E. W. Sinuraya

{"title":"T-series analysis for predicting apple prices in indonesian market using the SARIMA method","authors":"Yosua Alvin Adi Soetrisno, E. Handoyo, Muhammad Haikal Ilyasa, Denis, E. W. Sinuraya","doi":"10.1145/3373477.3373496","DOIUrl":"https://doi.org/10.1145/3373477.3373496","url":null,"abstract":"Autoregressive Integrated Moving Average, or ARIMA, is one example of method that widely used to forecast price or stock exchange in the form of univariate time-series data. Although ARIMA could handle data with trend, it does not support time series analysis for seasonal goods like apple. SARIMA needed for time series analysis, which is seasonally changed. Apple price prediction using SARIMA could help to monitor the stock safety level of apple, which is rotten quickly. Dataset of average apple data in Indonesia captured from PIHPS (Pusat Informasi Harga Pangan Strategis Nasional), published by Bank of Indonesia in collaboration with Gamatechno. The objective of this research is to generate predictive stock information about apple's price habit by means of the time series analysis. Data was taken until 109 month from year 2018. The best Sarima model for Indonesian market is SARIMA(1,0,0)x(0,0,0,12) with AIC (Akaike Information Criterion) point about -126,89658390969188. Although best model is selected, MAPE indicator show that the error was 99.47, which show that model is not good enough for predict the apple price only using univariate analysis.","PeriodicalId":300431,"journal":{"name":"Proceedings of the 1st International Conference on Advanced Information Science and System","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129665136","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

A critical review on state-of-the-art EEG-based emotion datasets 对最先进的基于脑电图的情感数据集的重要回顾

Proceedings of the 1st International Conference on Advanced Information Science and System Pub Date : 2019-11-15 DOI: 10.1145/3373477.3373707

Jasper Hwong Yu Chen, Raja Majid Mehmood

引用次数: 3

Multi-channel LSTM with different time scales for foreign exchange rate prediction 基于多通道不同时间尺度LSTM的外汇汇率预测

Proceedings of the 1st International Conference on Advanced Information Science and System Pub Date : 2019-11-15 DOI: 10.1145/3373477.3373693

Wenyu Wei, Pengfei Li

引用次数: 4

Applications of tf-idf concept to improve monolingual and cross-language information retrieval based on word embeddings 应用tf-idf概念改进基于词嵌入的单语和跨语言信息检索

Proceedings of the 1st International Conference on Advanced Information Science and System Pub Date : 2019-11-15 DOI: 10.1145/3373477.3373493

Syandra Sari, M. Adriani

引用次数: 1

OCR-based aircraft maintenance report data structuring 基于ocr的飞机维修报告数据结构

Proceedings of the 1st International Conference on Advanced Information Science and System Pub Date : 2019-11-15 DOI: 10.1145/3373477.3373490

Jiong Zhang, Yuxin Yao, Dawei Wang

引用次数: 0

Comparative analysis of time-series forecasting algorithms for stock price prediction 股票价格预测的时间序列预测算法比较分析

Proceedings of the 1st International Conference on Advanced Information Science and System Pub Date : 2019-11-15 DOI: 10.1145/3373477.3373699

Baleshwarsingh Joosery, G. Deepa

引用次数: 0

Recognizing fingerspelling in SIBI (sistem isyarat bahasa Indonesia) using OpenPose and elliptical fourier descriptor 使用OpenPose和椭圆傅立叶描述符识别SIBI(印尼语系统)的手指拼写

Proceedings of the 1st International Conference on Advanced Information Science and System Pub Date : 2019-11-15 DOI: 10.1145/3373477.3373491

Nanda Maulina Firdaus, Erdefi Rakun

{"title":"Recognizing fingerspelling in SIBI (sistem isyarat bahasa Indonesia) using OpenPose and elliptical fourier descriptor","authors":"Nanda Maulina Firdaus, Erdefi Rakun","doi":"10.1145/3373477.3373491","DOIUrl":"https://doi.org/10.1145/3373477.3373491","url":null,"abstract":"Humans are social beings; they communicate with other humans to coexist. In general, humans use verbal methods to communicate. However, the limited of verbal communication in people with hearing loss causes them to use non-verbal communication through sign language. It is challenging for nondisabled to grasp sign language quickly because it takes a long time to learn and understand. Therefore, a system that can recognize SIBI is needed. This research focused on fingerspelling gesture in SIBI, concentrating on finger and hand movements. The accuracy results by using OpenPose as feature extraction achieved a 61.49% accuracy. To improve accuracy, by using OpenPose as hand tracking, image masking as pre-processing, and Elliptical Fourier Descriptor as feature extraction, this method achieved a 64.05% accuracy. We investigated whether feature extraction with EFD and OpenPose for hand tracking can improve accuracy; however, some labels still could not be detected correctly. To improve accuracy, image masking and delete similarity frames are used as preprocessing; OpenPose uses as hand tracking, and EFD uses as feature extraction. This method achieved 67.23% accuracy.","PeriodicalId":300431,"journal":{"name":"Proceedings of the 1st International Conference on Advanced Information Science and System","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115242091","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: 4