Sentiment Analysis Using Naive Bayes Algorithm with Feature Selection Particle Swarm Optimization (PSO) and Genetic Algorithm

This study analyzes Sentiment to see opinions, points of view, judgments, attitudes, and emotions towards creatures and aspects expressed through texts. One of Social Media is like Twitter is one of the most widely used means of communication as a research topic. The main problem with sentiment analysis is voting and using the best feature options for maximum results. Either, the most widely known classification method is Naive Bayes. However, Naive Bayes is very sensitive to significant features. That way, in this test, a comparison of feature selection is carried out using Particle Swarm Optimization and Genetic Algorithm to improve the accuracy performance of the Naive Bayes algorithm. Analyses are performed by comparing before and after testing using feature selection. Validation uses a cross-validation technique, while the confusion matrix ??is appealed to measure accuracy. The results showed the highest increase for Naïve Bayes algorithm accuracy when using the feature selection of the Particle Swarm Optimization Algorithm from 60.26% to 77.50%, while the genetic algorithm from 60.26% to 70.71%. Therefore, the choice of the best characteristics is Particle Swarm Optimization which is superior with an increase in accuracy of 17.24%.

A Comparative Analysis of C4.5 Classification Algorithm, Naïve Bayes and Support Vector Machine Based on Particle Swarm Optimization (PSO) for Heart Disease Prediction

Heart disease is a general term for all of types of the disorders which is affects the heart. This research aims to compare several classification algorithms known as the C4.5 algorithm, Naïve Bayes, and Support Vector Machine. The algorithm is about to optimize of the heart disease predicting by applying Particle Swarm Optimization (PSO). Based on the test results, the accuracy value of the C4.5 algorithm is about 74.12% and Naïve Bayes algorithm accuracy value is about 85.26% and the last the Support Vector Machine algorithm is about 85.26%. From the three of algorithms above then continue to do an optimization by using Particle Swarm Optimization. The data is shown that Naïve Bayes algorithm with Particle Swarm Optimization has the highest value based on accuracy value of 86.30%, AUC of 0.895 and precision of 87.01%, while the highest recall value is Support Vector Machine algorithm with Particle Swarm Optimization of 96.00%. Based on the results of the research has been done, the algorithm is expected can be applied as an alternative for problem solving, especially in predicting of the heart disease.

The Implementation and Testing of Online Self-Diagnose Covid19 Application Using CBR and UAT

Nowadays, at Bali Province (Indonesia), one of the public services that are still lacking related to the Covid19 pandemic is online self-diagnosis, so there are still many people who do not know whether they are exposed or not, based on general symptoms, unusual symptoms, or serious symptoms so that they can be treated immediately. In this research, Covid19CBR as a prototype of an online Covid19 self-diagnose application using the CBR (Case-Based Reasoning) method was developed, which can be run online via a web browser. Users simply input their personal data, choose the symptoms experienced or felt, then the system will provide diagnostic results online. This research use Design Science Research Methodology (DSRM) with the case study qualitative research methods, literature study data collection methods, with prototype design using Use Case Diagrams and Sequence Diagrams. The application was tested using User Acceptance Testing (UAT) with the results of 95% that mean user can use this application easily.

Use Ordinary Expressions to Learn How to Extract Code Feedback From the Software Program Upkeep Process

Software engineering is the manner of making use of engineering studies and alertness packages to the design, improvement and renovation of software program. For software program builders or college students majoring in data engineering, the software program renovation manner is a totally complicated activity. Software renovation manner charges account for 40% to 80% of the whole software program engineering manner. The software program renovation manner is resulting from based programming, inadequate understanding domains, and application documentation. In this study, researchers attempted to apply the Java programming language and c / c ++ to deal with supply code truncation. After finishing this manner, this system code may be divided into code and remarks. This report could be used to gain data approximately the manner of knowledge this system from the software program renovation manner. For supply code slicing, the writer makes use of normal expressions, specifically textual content processing strategies or patterns. Using normal expressions can accelerate the manner of locating remarks to your application. The end result of this study is to construct software primarily based totally on open supply code (loose license) so that scholars and trendy programmers can use it to assist apprehend this system. According to the effects of the researchers' testing, the recuperation price is 100% and the accuracy is 100%.

Implementing Data Privacy of Cloud Data on a Remote Server using Symmetric Cryptographic Algorithms

Cloud Computing is an excellent technology for Micro Medium and Small Enterprises, which operate under budget shortage for setting up their own Information Technology infrastructure that requires capital investment on resources such as computers, storage and networking devices. Now-a-days, major Cloud Providers like Google and Amazon provide cloud services to its customers for managing their email, contact list, calendar, documents, and their own websites. MSME can take advantage of the cloud-based solutions offered by various Cloud Service Providers for equipping their own employees in doing their day to day activities more effectively and on the cloud. Though cloud computing promotes less expensive and collaborative work environment among a group of employees, it involves risks in keeping the resources such as computing and data secured. Different mechanisms are available for securing the data on the cloud among which encryption of data using cryptographic algorithm is the widely used one. Among various encryption symmetric algorithms, Advanced Encryption Standard is the more secured symmetric encryption algorithm for implementing data privacy on the cloud. In this paper, the authors have discussed some of the issues involved in adopting the cloud in an organization and proposed solutions that will benefit an organization while uploading and managing data in files and databases on the cloud.

Features Selection for Entity Resolution in Prostitution on Twitter

Entity resolution is the process of determining whether two references to real-world objects refer to the same or different purposes. This study applies entity resolution on Twitter prostitution dataset based on features with the Regularized Logistic Regression training and determination of Active Learning on Dedupe and based on graphs using Neo4j and Node2Vec. This study found that maximum similarity is 1 when the number of features (personal, location and bio specifications) is complete. The minimum similarity is 0.025662627 when the amount of harmful training data. The most influencing similarity feature is the cellphone number with the lowest starting range from 0.997678459 to 0.999993523. The parameter - length of walk per source has the effect of achieving the best similarity accuracy reaching 71.4% (prediction 14 and yield 10).

Greedy, A-Star, and Dijkstra’s Algorithms in Finding Shortest Path

The problem of finding the shortest path from a path or graph has been quite widely discussed. There are also many algorithms that are the solution to this problem. The purpose of this study is to analyze the Greedy, A-Star, and Dijkstra algorithms in the process of finding the shortest path. The author wants to compare the effectiveness of the three algorithms in the process of finding the shortest path in a path or graph. From the results of the research conducted, the author can conclude that the Greedy, A-Star, and Dijkstra algorithms can be a solution in determining the shortest path in a path or graph with different results. The Greedy algorithm is fast in finding solutions but tends not to find the optimal solution. While the A-Star algorithm tends to be better than the Greedy algorithm, but the path or graph must have complex data. Meanwhile, Dijkstra's algorithm in this case is better than the other two algorithms because it always gets optimal results.

Text Detection Based on Faster R-CNN Algorithm with Skip Pooling and Fusion of Hindi Handwritten Characters

Significant learning is at present the standard system for object disclosure. Speedier territory based convolutional neural association (Faster R-CNN) has a basic circumstance in significant learning. It has stunning area impacts in standard scenes. Regardless, under unprecedented conditions, there can even now be inadmissible acknowledgment execution, for instance, the thing having issues like hindrance, contorting, or little size. This paper proposes a novel and improved estimation reliant on the Faster R-CNN framework got together with the Faster R-CNN figuring with skip pooling and mix of consistent information. This computation can improve the revelation execution under uncommon conditions dependent on Faster R-CNN. The improvement basically has three segments: The underlying portion adds a setting information incorporate extraction model after the conv5_3 of the convolutional layer; the resulting part adds skip pooling so the past can totally secure the coherent information of the article, especially for conditions where the thing is hindered and distorted; and the third part replaces the area recommendation association (RPN) with a more capable guided anchor RPN (GA-RPN), which can keep up the survey rate while improving the revelation execution. The last can get more positive information from different segment layers of the significant neural association figuring, and is especially centered around scenes with little articles. Differentiated and Faster R-CNN, you simply look once plan, (for instance, YOLOv3), single shot pointer, (for instance, SSD512), and other article revelation computations, the estimation proposed in this paper has an ordinary improvement of 6.857% on the mean typical precision (mAP) appraisal list while keeping up a particular audit rate. This unequivocally exhibits that the proposed methodology has higher ID rate and disclosure efficiency for this circumstance.

Multi-Attribute Decision Making using Hybrid Approach based on Benefit-Cost Model for Sustainable Fashion

Multi-Attribute Decision Making (MADM) is used to select the best alternative from multi-alternatives based on multi-attribute (fashion material) and multi-criteria (sustainable fashion). Multi-alternatives are cotton, linen, silk, wool, acrylic, nylon, polyester, rayon, spandex, and mixed. Multi-attributes are material, texture, color, characteristic, comfort, and wearability. Multi-criteria are material fiber, smooth texture, faded color, elastic clothing, useful long, chilly and comfortable. Hybrid approaches and optimal solutions are needed to determine the best choice in decision making for both producers and consumers. The hybrid approach in MADM used is Simple Multi-Attribute Rating (SMART), Multi-Factor Evaluation Process (MFEP), Multi-Object Optimization based on Ratio Analysis (MOORA), Simple Additive Weighting (SAW), and Weighted Product (WP). SMART and MFEP are based on the Non-Benefit Cost Model while MOORA, SAW, and WP are based on a Benefit-Cost Model. The experimental results show that the SMART model with the best alternative is the rayon with the highest value (2.8333). The selection of the MFEP Model with the best alternative is rayon with the highest value (2.8330). The choice of MOORA model with the best alternative is rayon with the highest value (0.2595). The selection of the SAW Model with the best alternative is rayon with the highest value (0.8932). The selection of the WP Model with the best alternative is rayon with the highest value (0.1285). MADM using SMART, MFEP, MOORA, SAW, and WP for sustainable fashion yields the best alternative for consumption and production for the middle-class population in Indonesia.

Self-Diagnosis of Web-Based Pregnancy and Childbirth Disorders Using Forward Chaining Methods

The high mortality rate for pregnant women and childbirth in Bali, Indonesia, is caused by a lack of initial diagnosis of the diseases and complaints experienced by pregnant women during pregnancy, as well as a lack of health medical personnel scattered throughout Bali, to be able to provide optimal health services. It is necessary to have an online information system that helps pregnant women to be able to independently and online diagnose diseases, complaints, and symptoms experienced during pregnancy. The system must be able to be accessed anytime and anywhere, with high reliability and availability, and provide fast diagnostic results. Focus of this research is design and implementation of an Information System for Diagnosis of Pregnancy Disorders Based on Cloud Computing based on Forward Chaining Method, using Design Science Research Methodology (DSRM) and tested using the Technology Acceptance Model (TAM) method. The application is placed on the Hybrid Cloud. The results of this research, can help pregnant women in diagnosing diseases and complaints online, to reduce the mortality rate for pregnant women and giving birth.