SHM Publisher Journals
Not a member yet
315 research outputs found
Sort by
Room occupancy classification using multilayer perceptron
Get PDFA room that should be comfortable for humans can create a sense of absence and appear diseases and other health problems. These rooms can be from boarding rooms, hotels, office rooms, even hospital rooms. Room occupancy prediction is expected to help humans in choosing the right room. Occupancy prediction has been evaluted with various statistical classification models such as Linier Discriminat Analysis LDA, Classification And Regresion Trees (CART), and Random Forest (RF). This study proposed learning approach to classification of room occupancy with multi layer perceptron (MLP). The result shows that a proper MLP tuning paramaters was able estimate the occupancy with 88.2% of accurac
Accuracy of classification poisonous or edible of mushroom using naïve bayes and k-nearest neighbors
Get PDFMushrooms are plants that are widely consumed by the general public, but not all mushrooms can be consumed directly, because the types of mushrooms are feasible and it is still too difficult to distinguish, then there are several ways to identify fungi, namely by means of morphology. The morphology referred to in this paper is the morphology of fungi which includes color, habitat, class, and others. We got the morphology of this mushroom from a datasets we get from UCI Machine Learning with the 23 atribut that we use in the program. In determining the classification of this fungus we use the Naive Bayes algorithm which produces an accuracy of around 90,2% which we then improve again so that it reaches 100% accuracy using the K-Nearest Neighbors algorithm. Furthermore, in this case to prove accuracy that we had before, we use calculation accuracy with confusion matrix to show it the accuracy of classification poisonous or edible mushroom
Analysis of twitter sentiment in COVID-19 era using fuzzy logic method
Get PDFThe sentiment is an assessment of attitudes towards certain events or things. Collecting opinion is known as a sentiment from existing data. This technique can also help analyze the opinions given by people in assessing certain objects. The best available source for gathering sentiment is the internet. In the era of the Covid-19 pandemic, many people access social media, especially Twitter to give their opinion on certain objects. Twitter is known as the social media that is accessed by users to post their opinions online. By using soft computing, especially fuzzy logic, it is possible to design, create and build bots that can analyze user opinions on Twitter. This model is used for data sentiment analysis on Twitter
Comparation analysis of naïve bayes and decision tree C4.5 for caesarean section prediction
Get PDFThe development of technology can be used to facilitate many matters. One of them is childbirth in the medical fields. Maternal mortality rate (MMR) is the number of maternal deaths during pregnancy to postpartum caused by pregnancy, childbirth or its management. There are several methods of labors that can be done. The determination of the labor is based on many factors and must be in accordance with the conditions of pregnant patient. Caesarean birth is the last alternative in labor, due to high risk factors. The objective of this research is to predicte and analyse caesarean section using C4.5 and Naïve Bayes classifier models. For experimentation the dataset is collected from UCI Machine Learning Repository and the main attributes represented in this dataset are age, delivery number, delivery time, blood of pressure, and heart problem. The accuracy using C4.5 by 80 training cases is 45% And the accuracy using Naïve Bayes is 50%
Simulations of text encryption and decryption by applying vertical bit rotation algorithm
Get PDFCryptography is the study of hiding text and numbers in the form of codes. Vertical Bit Rotation (VBR) is one of the most widely implemented cryptographic algorithms as a one-way hash function that simplifies the encryption process with a high degree of difficulty in decryption. The purpose of this study is to apply VBR hash algorithm modeling to binary value characters with bit rotation keys 10, 11, 7, 3, 2, 7, 5, and 4. Thus, generating a passcode. The results of the encryption simulation show the code in the form of letters and characters, then the result of the decryption with the opposite rotation to the encryption process returns the value from ciphertext to plaintext based on ASCII characters. Cryptographic algorithms are applied to avoid cryptanalytic experiments in opening encryption codes
The forecasting of palm oil based on fuzzy time series-two factor
Get PDFPalm oil is a vegetable oil obtained from the mesocarp fruit of the palm tree, generally, from the species, Elaeis guineensis, and slightly from the species Elaeis oleifera and Attalea maripa. Palm oil is naturally red due to its high alpha and beta-carotenoid content. Palm kernel oil is different from palm kernel oil produced from the same fruit core. Planning for palm oil production is necessary because it greatly affects to the level of the country’s economy. Forecasting can reduce uncertainty in planning. Forecasting used in the palm oil problem is two-factor forecasting using the Kumar method with uama factors in the form of palm oil production and supporting factors in the form of land area. The forecasting is evaluated using AFER and MSE, from the acquisition of AFER value of 1.212% <10%, then the forecasting has very good criteria
Three stages algorithm for finding optimal solution of balanced triangular fuzzy transportation problems
Get PDFIn the literature, the fuzzy optimal solution of balanced triangular fuzzy transportation problem is negative fuzzy number. This is contrary to the constraints that must be non-negative. Therefore, the three stages algorithm is proposed to overcome this problem. The proposed algorithm consist of segregated method with segregating triangular fuzzy parameters into three crisp parameters. This method avoids the ranking technique. Next, total difference method is used to get initial basic feasible solution (IBFS) value based on segregating triangular fuzzy parameters. While, modified distribution algorithm is used to determine optimal solution based on IBFS velue. In order to illustrate the proposed algorithm is given the numerical example and based on the result comparison, the proposed algorithm equality to the two existing algorithms and better then the one existing algorithm. The proposed algorithm can solve in the fuzzy decision-making problems and can also be extended to an unbalanced fuzzy transportation problem
Car insurance segmentation prediction based on the most influential features using random forest and stacking ensemble learning
No full textIn addition to financial transaction services, the Bank also provides insurance services by conducting regular campaigns to attract new customers such as car insurance based on market segmentation, which is one of the main aspects of marketing used in financial services based on demographic data. One way to analyze the market is to predict the likely target market based on the campaign's target demographic data. Therefore, this study aims to find the best classification method for predicting campaign targets using historical data from 4000 customers of a bank in the United States. The market segmentation analysis process uses the best feature selection and ensemble learning. The best feature selection is selected using important features for Random Forest. The ensemble learning used is a stacking model consisting of the basic model of Logistic Regression, Support Vector Classifier, Gradient Boosting, Extra Tree, Bagging, Adaboost, Gaussian Naive Bayes, MLP, XBoost, LGBM, KNeighbors, Decision Tree, and Random Forest. The accuracy results of the stacking model can exceed the accuracy of the basic model with an accuracy rate of 78.80%
Improvement business process model and notation on the drink distribution industries using six core element
Get PDFThe development of distribution and market segmentation has become the company's background in improving business processes. The purpose of this research is to analyze the business processes of beverage companies using Business Process Management (BPM) modeling and improvised based on six core element management. In the analysis process, it is found that there is no stock forecasting system in forecasting sales stock that must be fulfilled. The results of the study show that the Business Process Management model is improved with the addition of a stock forecasting system, so that business processes become more controlled with the presence of a product stock inventory forecasting system in the company
Analysis and development of company business processes using business process model notation (case study of PT Datacomm Diangraha)
Get PDFCompanies in supporting activities that can achieve competitive advantage require a description of the right activities or commonly called business processes. To evaluate existing business processes so as to improve business productivity performance, every company needs to conduct business process analysis so that it is easy to understand the ongoing business processes and can improve them if needed. An important stage of business process analysis is modeling. The purpose of writing this journal is to identify business processes at PT Datacomm Diangraha and make modeling of ongoing business processes (As-Is Model). The Business Process Model Notation (BPMN) method which is a technique or method for understanding, designing and analyzing a business process is used in this research. This study uses observation, interviews and literature review to obtain data. The results obtained are the business processes at PT Datacomm consisting of the contract making process, the work design submission process, the process of paying service fees in stages (30%, 60%, 10%), providing a guarantee period, and customer service and process improvement