SHM Publisher Journals
Not a member yet
315 research outputs found
Sort by
Accuracy of Malaysia Public Response to Economic Factors During the Covid-19 Pandemic Using Vader and Random Forest
Get PDFThis study conducted a sentiment analysis of the impact of the Covid-19 pandemic in the economic sector on people's lives through social media Twitter. The analysis was carried out on 23,777 tweet data collected from 13 states in Malaysia from 1 December 2019 to 17 June 2020. The research process went through 3 stages, namely pre-processing, labeling, and modeling. The pre-processing stage is collecting and cleaning data. Labeling in this study uses Vader sentiment polarity detection to provide an assessment of the sentiment of tweet data which is used as training data. The modeling stage means to test the sentiment data using the random forest algorithm plus the extraction count vectorizer and TF-IDF features as well as the N-gram selection feature. The test results show that the polarity of public sentiment in Malaysia is predominantly positive, which is 11,323 positive, 4105 neutral, and 8349 negative based on Vader labeling. The accuracy rate from the random forest modeling results was obtained 93.5 percent with TF-IDF and 1 gram
Business process re-engineering to support cake shop business sustainability
Get PDFBusiness Process Re-engineering is usually carried out to increase satisfaction with goods or services so that customers tend to choose goods or services from certain companies rather than choosing goods or services from competing companies. This cake shop has been around since 2000, but previously in 1999 they had tried to process the cake shop's recipe so that they found a concoction that suited the local people's tongue. However, this business did not last long because the shop they owned had experienced a fire incident which caused the cake shop business to be evicted and eventually moved to another place so that they also received business threats, namely the emergence of many competitors selling similar products. The purpose of our research is that we will conduct a re-engineering analysis to optimize the business processes in the cake shop. The research method used in our research is descriptive. The descriptive research method is carried out by seeking information related to existing symptoms, clearly explaining what goals will be achieved in the research conducted. In this new model, we add a promotion method, namely by using advertising services on social media so that it can reach people who are still not familiar with the product. In the new model, we also added a process, namely a research process to add innovation to new product cake variants that will give a new impression to the shop's customers
Evaluation of business process in convention production companies using business process improvement (BPI)
Get PDFThis research aims to choose the best business process model for a convection company during the COVID-19 pandemic. This study applies an analytical framework of business process improvement (BPI), including five whys analysis (organizing for improvement, understanding the process, streamlining, measurement and controls, continuous improvement). Model business process modeling and notation (BPMN). The results of this study are an analysis of business processes that occur in convection companies, and the results are that the business processes in convection companies are still less effective. In addition, the author also provides recommendations, namely the use of a database on the ordering system used evaluation of business processes in convection production companies using BPI and BPMN
Increasing package delivery efficiency through the application of the prim algorithm to find the shortest route on the expedition route
No full textOne of the changes is in terms of shopping. Previously, people shopped through physical stores, but since the emergence of online shopping platforms, people have started to switch to using the marketplace as a place to make buying and selling transactions. This platform utilizes expedition services to send packages in the form of ordered goods from sellers to buyers. This activity presents a new problem, which is related to the efficiency of package delivery by courier services so that goods can arrive as quickly as possible in the hands of buyers. Graph modeling to solve a problem related to the shortest path and the fastest path is adapted in this paper. The algorithm used is Prim's Algorithm, which is an algorithm to determine the minimum spanning tree of a connected weighted graph. The test results show that the algorithm is suitable for increasing packet delivery efficiency by determining the shortest path based on the minimum spanning tree concept. By taking a sample of travel routes on the island of Java, the best route was obtained with a total distance of 1,771 kilometers connecting cities from the city of Jakarta to the city of Banyuwangi
Multi-objective optimization for multi-satellite scheduling task
Get PDFThe satellites scheduling mission play an effective role in enhancing the role of ground station control and monitoring systems. In this search, SGSEO is re-formulated into a multi-objective optimization task. Therefore, the Gravitational Search Algorithm GSA is exploited to attain several essential objectives for generating tight scheduling. Moreover, particle swarm optimization model PSO is consolidated with GSA in a novel form for strengthening its ability of local search and slow the speed of convergence. On the other side, to make the most of the satellite resources in the right direction, we have observed targets that have fewer observational opportunities to keep them from being lost. The PageRank algorithm is used to fulfil this issue by ranking the candidate's strips. Finally, the effect of different parameters of the proposed approach was studied by experimental outcomes and compared with previous methods. It has shown that the performance of the proposed approach is superior to its peers from other methods
Comparison of LSTM, SVM, and naive bayes for classifying sexual harassment tweets
Get PDFTwitter is now a very open and extensive social media; anyone can freely express their opinion on any topic on social media. The content or discussion on Twitter is also quite diverse and unlimited. However, because it is unlimited, many misuse it for negative things. One of them is verbal sexual harassment through Twitter. This research aims to identify sexual harassment in an Indonesian tweet using sentiment analysis using the LSTM, SVM, and naive bayes methods with text normalization. In this study, 2990 tweets in the Indonesian language were tested from 4th to 6th in May 2022. The Twitter data shows that tweets included in sexual harassment are more than those not included in sexual harassment, totaling 2026 data. From the results of the evaluation of tweet data classification using text normalization with LSTM, the accuracy is 84.62%, SVM is 86.54%, and naive bayes is 85.45%. Using the SVM algorithm with text normalization gets the highest accuracy compared to LSTM and naive bayes in classifying Indonesian sexual harassment tweets
Classification of potential customers using C4.5 and k-means algorithms to determine customer service priorities to maintain loyalty
Get PDFThe increasing competition among Middle-Class Micro Enterprises (MSMEs) is a problem because business actors must improve techniques and strategies to maintain customer satisfaction, and the number of customers continues to increase. Customers are an essential asset for the company. To maintain customer loyalty with promising prospects for the company, a strategy is needed to support this. Strategies such as service prioritization can be used to maintain customer loyalty. This research was conducted to classify customers who are estimated to have good prospects for the company so that service priorities are not mistargeted by utilizing 1683 data from store By.SIRR, a fashion store in Semarang, Indonesia contains five attributes, and customers are classified and are estimated to have promising prospects for the company. Data mining methods use the C4.5 and K-Means algorithms to classify the classification process. The research resulted in the grouping of customers into four categories: potential lover, flirting, faithful lover, and spiritual friend. From the validation test conducted using the Confusion Matrix Validation method, the classification results get an Accuracy of 97.70%
Artificial intelligence (AI) imaging for enhancement of parking security
No full textParking is a public facility found in an agency or office that is used to store vehicles. There are lots of vehicles that can enter the parking area. Therefore, we need an area management and parking system. Artificial Intelligence (AI) is the knowledge that makes computers able to imitate human intelligence so that computers can do things that humans do. This research is motivated by crime cases that often occur in parking lots. This is because there is still a lack of security in the place. The purpose of this study is to increase security and ease of scanning on motorcycle license plates to get parking tickets automatically and face scans. That way, if a crime occurs in the monitoring area, the camera can easily recognize the face of the perpetrator, which makes the incident process easy
Application of the greedy algorithm to maximize advantages of cutting steel bars in the factory construction
No full textIndonesia is one of the countries that is currently exuberant with development issues in order to balance the ongoing process of global modernization. In the infrastructure development process, the developer will enter into a contract with the contractor. This study aims to analyze the performance of the greedy algorithm in optimizing steel cutting with maximum profit to construction companies. The methods used include literature studies, program design, and program trials where the algorithm used is a greedy one. From the results obtained, it is evident that the Greedy algorithm can provide optimal steel cutting solutions because it works by calculating and deviating from all available separation settings, so there is no need to recalculate if the program performs that step
Restricted boltzmann machine and softmax regression for acute respiratory infections disease identification
Get PDFRestricted boltzmann machines (RBM) have attracted much attention lately after being proposed as building blocks of deep learning blocks. RBM is an algorithm that belongs to the artificial neural network (ANN) algorithm. Deep learning models can be used in the health field to identify diseases using medical data records. Acute Respiratory Infection (ARI) is a disease that infects the respiratory tract. A patient infected by ARI diseases is high. To identify ARI can use the symptoms that the patient had experienced. Based on this background, this study aims to help identify ARI disease using its symptoms. The method used for identification is the deep learning model, which was built using the RBM and softmax regression. Three steps were used in this research, which are training, testing, and implementation. The trained deep learning model will be implemented to identify ARI disease. This research will use ARI data from Puskemas Warungasem, Indonesia. From the research result, the deep learning model can get an accuracy of 96%. The deep learning configuration used in this research has 4 RBM layers, 1 Softmax layer as the output layer, and a learning rate value of 0.01 and 1000 iterations. This research can be used as a reference so that the next researcher can add other algorithms to Deep learning to improve accuracy