SHM Publisher Journals
Not a member yet
315 research outputs found
Sort by
Performance comparison of support vector machine and gaussian naive bayes classifier for youtube spam comment detection
Get PDFYoutube is a video sharing site that was begun back in 2005. Youtube produces over 400 hours of substance each moment and more than 1 billion hours of substance are devoured by clients every day. In this work, we present a new approach by comparing the analysis results using a support vector machine and the Gaussian Naive Bayes classificatio. Our proposed methodology We used the dataset from UCI especially Youtube-Shakira for training and testing. The transformed dataset is split into training and testing subsets and fed into Naive Bayes and Support Vector Machin. In all cases, the F1 score was used to evaluate the classifier's performance. The results of the experiment are displayed in Gaussian Naive Bayes with an F1 score of 84.38% and a Support Vector Machine (SVM) with an F1 score of 88.00%. Naive Bayes is consistently the worst performer than SVM
New fuzzy transportation algorithm without converting fuzzy numbers
Get PDFThe ranking function is widely used to convert fuzzy numbers to be crisp on solving fuzzy transportation problems. The converting process can indeed make it easier to play the fuzzy transportation method, but from the convenience, it causes failed in interpreting the results of converting fuzzy numbers. This is because the converting process of fuzzy numbers still has subjectivity values, so it cannot be eliminated, moreover, the ordering can cause incompatible input and output fuzzy numbers resulted. Therefore, the new fuzzy transportation method is proposed by fuzzy Analytical Hierarchy Process to order fuzzy parameters on fuzzy transportation problem without converting fuzzy numbers to crisp numbers, then Algorithm 2 until 6 is used to obtain a fuzzy optimal solution. The advantages of the new proposed method can improve the shortcomings of the existing methods, as well as relevant to solve fuzzy transportation problems in real lif
Recommendation of Yogyakarta tourism based on simple additive weighting under fuzziness
Get PDFFor tourists who do not understand the situation or the desired tourist attraction, they can choose tour and travel services. Tour and travel provides a choice of tour packages with various variations. Determining the right tour and travel package and agency can benefit tourists, both in terms of financial and vacation quality. The data used in this study were obtained from several Tour and Travel agents. There are several variables used, namely the price of the package, the number of participants, and the number of facilities obtained. The method used in this study combines the Triangular Fuzzy Number (TFN) and the Simple Additive Weighting (SAW) method. The purpose of this study is to help tourists determine the most profitable or best packages. The results of this study obtained the best 2 packages recommended for tourists to choose
Irrigation management of agricultural reservoir with correlation feature selection based binary particle swarm optimization
Get PDFThe requirement for the applied innovation to farming water system is especially required for supplies, as rural water system focuses. Supplies as one of horticulture water system asset focus that are regularly constraints identified with the conveyance of repository water stream, this brought about lopsided dissemination of rural water system and the term of control of agrarian water system that streams from water system asset focuses. At the point when ranchers need to change the water system way, it will take a long effort to make another water system way. From these troubles to convey rural water systems simpler, it is important to plan a specialist framework to decide rural water system choices. A few researchers focused on improved quality of plant. There have been limited studies concerned with irrigation management Therefore, this research intends to design The objectives of this research are optimization irrigation management of agricultural reservoirs with CFS-BPSO. The consequences of this investigation demonstrate that the exactness of the utilization of the SVM calculation is 62.32%, while after utilizing the CFS calculation precision of 84.12% is acquired and exactness of ten SVM calculations by applying a blend of CFS highlight choice. also, BPSO 91.84%
Implementation of fuzzy tsukamoto in employee performance assessment
Get PDFEmployees are one of the important things for the sustainability of a company, because employees are company assets. In addition, employee performance is also something that cannot be ignored because it determines the achievement of company goals. So it is important to monitor employee performance and conduct performance appraisals. With the addition of performance appraisal, the company can determine the provision of rewards, promotions, and punishments. It can be used as a work evaluation stage to improve the quality of work. Employee performance appraisal is based on several predetermined criteria, including responsibility, discipline, and attitude which in the end results in between two linguistic values, namely good or bad. One method for evaluating employee performance is the Tsukamoto fuzzy method. With the Tsukamoto fuzzy method, it is hoped that the assessment can be carried out fairly and measurably
Improve the Accuracy of C4.5 Algorithm Using Particle Swarm Optimization (PSO) Feature Selection and Bagging Technique in Breast Cancer Diagnosis
Get PDFBreast cancer is the second leading cause of death due to cancer in women currently. It has become the most common cancer in recent years. In early detection of cancer, data mining can be used to diagnose breast cancer. Data mining consists of several research models, one of which is classification. The most commonly used method in classification is the decision tree. C4.5 is an algorithm in the decision tree that is often used in the classification process. In this study, the data used was the Breast Cancer Wisconsin (Original) Data Set (1992) obtained from the UCI Machine Learning Repository. The purpose of this study was to select features that will be used and overcome class imbalances that occur, so that the performance of the C4.5 algorithm worked more optimal in the classification process. The methods used as feature selection are PSO and bagging to overcome class imbalances. Classification was tested using the confusion matrix to determine the accuracy that was generated. From the results of this study, the application of PSO as a feature selection and bagging to overcome class imbalances with the C4.5 algorithm succeeded in increasing accuracy by 5.11% with an initial accuracy of 93.43% to 98.54%
Optimization of Naïve Bayes Classifier By Implemented Unigram, Bigram, Trigram for Sentiment Analysis of Hotel Review
Get PDFThe information needed in its development requires that proper analysis can provide support in making decisions. Sentiment analysis is a data processing technique that can be completed properly. To make it easy to classify hotels based on sentiment analysis using the Naїve Bayes Classifier algorithm. As a classification tool, Naїve Bayes Classifier is considered efficient and simple. In this study consists of 3 stages of sentiment analysis process. The first stage is text pre-processing which consists of transform case, stopword removal, and stemming. The second stage is the implementation of N-Gram features, namely Unigram, Bigram, Trigram. The N-Gram feature is a feature that contains a collection of words that will be referred to in the next process. Next, the last click is the hotel review classification process using Na menggunakanve Bayes Classifier. OpinRank Hotels Review dataset on Naїve Bayes Classifier using N-Gram namely Unigram, Bigram, Trigram with research results that show Unigram can provide better test results than Bigram and Trigram with an average accuracy of 81.30%
SVM Optimization with Correlation Feature Selection Based Binary Particle Swarm Optimization for Diagnosis of Chronic Kidney Disease
Get PDFData mining has been widely used to diagnose diseases from medical data. In this study using chronic kidney disease dataset taken from UCI Machine Learning. The dataset has 25 attributes with 400 samples. With 25 attributes that allow redundant data. Redundant data in datasets can reduce computational efficiency and classification accuracy. To increase accuracy of classification algorithm can be done by reducing dimensions of dataset. Correlation-based Feature Selection (CFS) can quickly identify and filter redundant attributes. However, CFS has disadvantage that selected attribute is not necessarily the best attribute. These weaknesses can be overcome by Binary Particle Swarm Optimization (BPSO). BPSO chooses attributes based on the best fitness value. The purpose of this study is to improve accuracy of Support Vector Machine (SVM) by implementing combination of CFS and BPSO as feature selection. Accuracy of SVM in predicting CKD is 63.75%. Whereas, accuracy of SVM by applying CFS as feature selection is 88.75% and average accuracy of ten execution SVM algorithms by applying a combination of CFS and BPSO as feature selection is 95%. Thus, combination of CFS and BPSO as feature selection on the SVM algorithm can improve results of accuracy in diagnosing CKD by 31.25%
The Implementation of Z-Score Normalization and Boosting Techniques to Increase Accuracy of C4.5 Algorithm in Diagnosing Chronic Kidney Disease
Get PDFIn the health sector, data mining can be used as a recommendation to predict a disease from the collection of patient medical record data or health data. One of the techniques can be applied is classification with the C4.5 algorithm. The increasing accuracy can be conducted in data transformation using zscore normalization method. In addition, the implementation of the ensemble method can also improve accuracy of C4.5 algorithm, namely boosting or adaboost. The purpose of this study was determinin the implementation of zscore normalization in the pre-processing and adaboost stages of the C4.5 algorithm and determing the accuracy of the C4.5 algorithm after applying zscore and adaboost normalization in diagnosing chronic kidney disease. In this study, the mining process used k-fold cross validation with the default value k = 10. The implementation of the C4.5 algorithm obtained an accuracy of 96% while the accuracy of the C4.5 algorithm with the zscore normalization method obtained an accuracy of 96.75%. The highest accuracy was obtained from the addition of the boosting method to the C4.5 algorithm and zscore normalization obtained the accuracy of 97.25%. The increasing accuracy was obtained of 1.25% which compared to the accuracy C4.5 algorithm
Electrical Energy Monitoring System and Automatic Transfer Switch (ATS) Controller with the Internet of Things for Solar Power Plants
Get PDFInternet of Things is a technology that connects communication devices with electronic devices that are used everyday using the internet as a medium to communicate between devices and users. The use of IoT technology can be implemented in solar power generation systems. The IoT technology implemented in this study is to monitor and control the use of batteries in solar power plants. Current technology, battery usage can only be monitored closely to get information about battery capacity and battery usage. When the battery is empty or cannot be used to meet electricity needs, it is not equipped with a diversion of existing electricity sources such as PLN electricity. So, we need a renewable technology to get information about batteries and transfer of electricity sources that can be accessed remotely and can be accessed via the internet. The design of this smart monitoring system has stages, namely planning,design , coding , and test . The results of this study are able to see data in the form of battery capacity, electric current and electric power used in Android applications. The data is obtained from sensors that are on smart monitoring connected to the internet network and stored on a database server. Then the data residing on the database server will be retrieved by the application to be displayed to users in the form of graphics and usage lists. Furthermore, the Automatic Transfer Switch system works if the battery capacity sensor has read less than 11.4V then the relay will automatically transfer electricity to PLN. The Android smartphone application is used as a monitoring tool to view data in realtime