Telematika最新文献_第2页

Implementation of Mel-Frequency Cepstral Coefficient as Feature Extraction using K-Nearest Neighbor for Emotion Detection Based on Voice Intonation 基于k近邻的mel频率倒谱系数特征提取在语音语调情感检测中的实现

Telematika Pub Date : 2023-03-01 DOI: 10.31315/telematika.v20i1.9518

Revanto Alif Nawasta, Nurheri Cahyana, H. Heriyanto

{"title":"Implementation of Mel-Frequency Cepstral Coefficient as Feature Extraction using K-Nearest Neighbor for Emotion Detection Based on Voice Intonation","authors":"Revanto Alif Nawasta, Nurheri Cahyana, H. Heriyanto","doi":"10.31315/telematika.v20i1.9518","DOIUrl":"https://doi.org/10.31315/telematika.v20i1.9518","url":null,"abstract":"Purpose: To determine emotions based on voice intonation by implementing MFCC as a feature extraction method and KNN as an emotion detection method.Design/methodology/approach: In this study, the data used was downloaded from several video podcasts on YouTube. Some of the methods used in this study are pitch shifting for data augmentation, MFCC for feature extraction on audio data, basic statistics for taking the mean, median, min, max, standard deviation for each coefficient, Min max scaler for the normalization process and KNN for the method classification.Findings/result: Because testing is carried out separately for each gender, there are two classification models. In the male model, the highest accuracy was obtained at 88.8% and is included in the good fit model. In the female model, the highest accuracy was obtained at 92.5%, but the model was unable to correctly classify emotions in the new data. This condition is called overfitting. After testing, the cause of this condition was because the pitch shifting augmentation process of one tone in women was unable to solve the problem of the training data size being too small and not containing enough data samples to accurately represent all possible input data values.Originality/value/state of the art: The research data used in this study has never been used in previous studies because the research data is obtained by downloading from Youtube and then processed until the data is ready to be used for research.","PeriodicalId":31716,"journal":{"name":"Telematika","volume":"14 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82279145","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

Autoregressive Integrated Moving Average (ARIMA) Models For Forecasting Sales Of Jeans Products 基于自回归综合移动平均(ARIMA)模型的牛仔裤销售预测

Telematika Pub Date : 2023-03-01 DOI: 10.31315/telematika.v20i1.7868

Jenny Meilila Azani Cahya Permata, Muhammad Shyamsi Habibi

{"title":"Autoregressive Integrated Moving Average (ARIMA) Models For Forecasting Sales Of Jeans Products","authors":"Jenny Meilila Azani Cahya Permata, Muhammad Shyamsi Habibi","doi":"10.31315/telematika.v20i1.7868","DOIUrl":"https://doi.org/10.31315/telematika.v20i1.7868","url":null,"abstract":"Purpose: To be able to compete with other companies, it is necessary to estimate and forecast jeans products that will be ordered according to consumer demand every month, so that there is no excess inventory and product shortage. If there is a shortage of goods, the consumer will be disappointed with the seller, and vice versa if the goods are overstocked, the quality will continue to decline to the detriment of the seller and the buyer, resulting in a shortage of materials.Methodology: To overcome the problem of selling jeans products, the ARIMA method is suitable to overcome the problem of forecasting the stock of jeans sales. ARIMA model is a model that completely ignores the independent variables in making forecasts. ARIMA uses past and present values of the dependent variable to produce accurate short-term forecasting.Results: The built forecasting has a MAPE accuracy rate of 17.05% so it can be said that predicting has good results according to the criteria. Forecasting results in the following year show that sales tend to increase from the previous year.Originality: This research was conducted using sales data of jeans products at company XYZ and using the ARIMA method which previous researchers have never done.","PeriodicalId":31716,"journal":{"name":"Telematika","volume":"5 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88765922","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

Performance Analysis of XGBoost Algorithm to Determine the Most Optimal Parameters and Features in Predicting Stock Price Movement XGBoost算法在股票价格走势预测中的性能分析

Telematika Pub Date : 2023-03-01 DOI: 10.31315/telematika.v20i1.9329

Affan Ardana

{"title":"Performance Analysis of XGBoost Algorithm to Determine the Most Optimal Parameters and Features in Predicting Stock Price Movement","authors":"Affan Ardana","doi":"10.31315/telematika.v20i1.9329","DOIUrl":"https://doi.org/10.31315/telematika.v20i1.9329","url":null,"abstract":"Purpose: The research aims to find the best parameters and features for predicting stock price movement using the XGBoost algorithm. The parameters are searched using the RMSE value, and the features are searched using the importance value.Design/methodology/approach: The research data is the stock data of Amazon.com company (AMZN). The dataset contains the Date, Low, Open, Volume, High, Close, and Adjusted Close features. The dataset is ensured to have no missing data by handling missing values. The input feature is selected using the Pearson Correlation feature selection method. To prevent the difference between the highest and lowest stock price from being too far apart, the data is scaled using the scaling method. To avoid bias that may appear in the prediction result, cross-validation is used with the Min Max Scaling method, which will devide the dataset into training data and testing data within a range of 30 days after the training data. The parameters to be tested include n_estimator = 500, early stopping round = 3, learning rate = 0.01, 0.05, 0.1, and max_depth (tree depth) = 3, 4, 5.Findings/result: The result of the research that a learning rate of 0.05 and a tree depth of 5 obtained the lowest RMSE result compared to other models, with an RMSE of 0.009437. The Low feature obtained the highest importance value among all the models built.Originality/value/state of the art: This study used testing data within a range of 30 days after the training data and used a combination of parameters, including n_estimator = 500, early stopping round = 3, learning rate = 0.01, 0.05, 0.1, amd max_depth (tree depth) = 3, 4, 5. ","PeriodicalId":31716,"journal":{"name":"Telematika","volume":"469 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85568555","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

Sentiment Analysis of Cryptocurrency Exchange Application on Twitter Using Naïve Bayes Classifier Method 基于Naïve贝叶斯分类器的Twitter加密货币交易应用情感分析

Telematika Pub Date : 2023-03-01 DOI: 10.31315/telematika.v20i1.9044

Andhika Octa Indarso, H. N. Irmanda, Ria Astriatma

{"title":"Sentiment Analysis of Cryptocurrency Exchange Application on Twitter Using Naïve Bayes Classifier Method","authors":"Andhika Octa Indarso, H. N. Irmanda, Ria Astriatma","doi":"10.31315/telematika.v20i1.9044","DOIUrl":"https://doi.org/10.31315/telematika.v20i1.9044","url":null,"abstract":"Purpose: The growth and development of the digital currency industry also presents a variety of applications for conducting transactions using these currencies, including utilizing cryptocurrency exchanges to make investments. InI ndonesia, there are two applications that fall into the category of the largest cryptocurrency exchange and are recognized by Bappebti (Commodity Futures Trading Regulatory Agency), namely TokoCrypto and Indodax. Both applications are analyzed based on the sentiments of their users on Twitter.Design/methodology/approach: In this study the data collected is data originating from social media Twitter and has the keywords \"indodax\" or \"#indodax\" and \"tokocrypto\" or \"#tokocrypto\". The data used is between January 2021 – January 2022. The data collected from Twitter is processed using the Naïve Bayes Classifier algorithm.Findings/result: From the results of the analysis, it was found that the Indodax application has a higher positive sentiment percentage value of 9% compared to TokoCrypto.Originality/value/state of the art: The use of the Naïve Bayes algorithm in this study supports sentiment analysis of cryptocurrency exchange application users to consider which application has better positive sentiment for investing in digital currency or cryptocurrency.","PeriodicalId":31716,"journal":{"name":"Telematika","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89475354","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

Retinal Vessel Segmentation to Support Foveal Avascular Zone Detection 视网膜血管分割支持中央凹无血管区检测

Telematika Pub Date : 2023-03-01 DOI: 10.31315/telematika.v20i1.9645

Dhimas Arief Dharmawan

引用次数: 0

Study of The Effect Stuart and Prandtl Numbers on Diamond Nano Fluid Flowing Through Cylindrical Surface Stuart和Prandtl数对金刚石纳米流体在圆柱表面流动影响的研究

Telematika Pub Date : 2023-02-24 DOI: 10.35671/telematika.v16i1.2103

Yolanda Norasia

引用次数: 1

Smart Farming System for Monitoring and Optimizing Paddy Field with Internet of Things Technology 基于物联网技术的水田监测优化智能农业系统

Telematika Pub Date : 2023-02-24 DOI: 10.35671/telematika.v16i1.2183

Bagus Kusuma

引用次数: 0

Use of Hybrid Methods in Making E-commerce Product Recommendation Systems to Overcome Cold Start Problems 利用混合方法在电子商务产品推荐系统中克服冷启动问题

Telematika Pub Date : 2023-02-24 DOI: 10.35671/telematika.v16i1.2080

Budi Santosa

{"title":"Use of Hybrid Methods in Making E-commerce Product Recommendation Systems to Overcome Cold Start Problems","authors":"Budi Santosa","doi":"10.35671/telematika.v16i1.2080","DOIUrl":"https://doi.org/10.35671/telematika.v16i1.2080","url":null,"abstract":"The large number of users and the items offered in e-commerce make it difficult for buyers to choose the right items and sellers to offer their items to the right buyers. To overcome this problem, a system that can offer and recommend goods automatically, namely a recommendation system is needed. One of the most popular methods used to create a recommendation system is collaborative filtering, the recommendations are created based on similarities in user behavior. Unfortunately, this method has a weakness, namely cold start, where the recommendations will be inaccurate on data that has a lot of new users and items due to minimal historical data regarding user behavior. This problem will be tried to be solved in this study using a hybrid method, where this method combines more than 1 method to create a list of recommendations so that it will cover the shortcomings of each method. This study uses Amazon's e-commerce product and transaction data. The use of the hybrid method in this study can overcome the cold start problem by using switching and mixed methods, by not using the collaborative filtering model on new user recommendations or users who have little interaction. New users will receive recommendations based on the combination of popularity-based and content-based filtering models. This can be seen from the Mean Absolute Error (MAE) value of the model, where the MAE value for the data with a minimum user has at least 3 times rating is 0.566883, for the minimum 7 times, the MAE value is smaller, 0.487553.","PeriodicalId":31716,"journal":{"name":"Telematika","volume":"506 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136165974","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

Dynamical Analysis of the Spread of COVID-19 model and its Simulation with Vaccination and Social Distancing COVID-19传播模型的动态分析及其在疫苗接种和社会距离下的模拟

Telematika Pub Date : 2023-02-24 DOI: 10.35671/telematika.v16i1.2373

Ummu Habibah

{"title":"Dynamical Analysis of the Spread of COVID-19 model and its Simulation with Vaccination and Social Distancing","authors":"Ummu Habibah","doi":"10.35671/telematika.v16i1.2373","DOIUrl":"https://doi.org/10.35671/telematika.v16i1.2373","url":null,"abstract":"The model's creation and dynamical analysis were covered in this paper, SEIRS on the effects of vaccination and social isolation on the transmission of COVID-19. The susceptible individual subpopulation (S), the exposed individual subpopulation (E), the infected individual subpopulation (I), and the recovered individual subpopulation (R) are the four subpopulations that make up the human population in this model. This concept is founded on the notion that someone who has recovered from the illness is nonetheless vulnerable to reinfection. The carried out dynamical analysis includes the determination of the equilibrium point, the fundamental reproduction number (R_0), and evaluation of the local stability of the equilibrium point. The outcomes of the dynamical analysis show that there are two equilibrium points in the model: the endemic equilibrium point and the disease-free equilibrium point. Mathematical R_0>1 indicates the presence of an endemic equilibrium point, whereas a disease-free equilibrium point is always present. If the Routh-Hurwitz conditions are met, the endemic equilibrium point is locally asymptotically stable, but the disease-free equilibrium point is locally asymptotically stable if R_0<1. The numerical simulation results are consistent with the analyses' findings.","PeriodicalId":31716,"journal":{"name":"Telematika","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136165975","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

Smart Solar Tracker and Energy Control Based on Internet of Things (IoT) 基于物联网(IoT)的智能太阳能跟踪器和能量控制

Telematika Pub Date : 2023-02-24 DOI: 10.35671/telematika.v16i1.2576

Budi Artono

{"title":"Smart Solar Tracker and Energy Control Based on Internet of Things (IoT)","authors":"Budi Artono","doi":"10.35671/telematika.v16i1.2576","DOIUrl":"https://doi.org/10.35671/telematika.v16i1.2576","url":null,"abstract":"ndonesia's electricity consumption per capita in 2022 will reach 1,173 kWh/capita sourced from the Ministry of Energy and Mineral Resources. This consumption rate increased by around 4% compared to 2021, as well as a new record high in the last five decades. This must be accompanied by the availability of energy from power plants, especially renewable energy, namely solar energy because this solar power plant is considered safer for the environment and has a minimal maintenance schedule. In addition, it requires maximum utilization of solar panels and a monitoring system in real time so that the reliability of the power plant is maintained, the Smart Solar Tracker and Energy Control Based on Internet Of Things (IoT) are the answer to this problem. This research uses PV (Photovoltaic) as a power source in the system accompanied by a tracker drive in the form of actuators and servo motors that move in the direction of the sun. This IoT is integrated with a database server so officers can monitor and control if the device is damaged. The IoT module in this research uses the ESP8266 which functions for device control and relay. In addition to reading the voltage and current, both incoming and outgoing, use the ACS 712 voltage sensor and current sensor, not only that, there is also an LDR sensor to read the position of the sun.","PeriodicalId":31716,"journal":{"name":"Telematika","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136165976","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