SHM Publisher Journals
Not a member yet
315 research outputs found
Sort by
Optimization of breast cancer classification using feature selection on neural network
Get PDFCancer is currently one of the leading causes of death worldwide. One of the most common cancers, especially among women, is breast cancer. There is a major problem for cancer experts in accurately predicting the survival of cancer patients. The presence of machine learning to further study it has attracted a lot of attention in the hope of obtaining accurate results, but its modeling methods and predictive performance remain controversial. Some Methods of machine learning that are widely used to overcome this case of breast cancer prediction are Backpropagation. Backpropagation has an advantage over other Neural Networks, namely Backpropagation using supervised training. The weakness of Backpropagation is that it handles classification with high-dimensional datasets so that the accuracy is low. This study aims to build a classification system for detecting breasts using the Backpropagation method, by adding a method of forward selection for feature selection from the many features that exist in the breast cancer dataset, because not all features can be used in the classification process. The results of combining the Backpropagation method and the method of forward selection can increase the detection accuracy of breast cancer patients by 98.3%
Implementation of signature-based intrusion detection system using SNORT to prevent threats in network servers
Get PDFSecurity is an important factor in today's digital era. In a network, implementing a security system is the focus of a network developer. One of the most basic network securities is in the form of access. To manage the security of a system must be known in advance who is involved in the system and what activities are carried out. Just like a security alarm, which monitors work conditions, this is the function of the Intrusion Detection System (IDS). IDS has several effective methods for detecting threats, one of which is the Signature-based method. IDS can be implemented through the open-source SNORT application, and the method works with rules which are commands to IDS to recognize various attacks. IDS rules will be included in the signature matching process, which means matching between rules and incoming attacks and views of both protocols, then the IDS will generate alerts that contain notifications. This study conducted a reading of the MIT-DARPA 1999 dataset on 1,252,412 packages and tested alerting with Network Scanning and DoS attacks. Analyze Package Data runs at a speed of 83,494 packets /second and gets a true positive percentage reaching 100% and an accuracy of 98.10%
Implementation of the data encryption using caesar cipher and vernam cipher methods based on CrypTool2
Get PDFInformation has become precious and essential for all fields, so it is crucial to carry out information security. The principle of information security is to protect and safeguard information with the aim that the information is not entitled to be read, modified, or deleted by anyone who does not have rights to it. The purpose of our research is to analyze how the caesar cipher and vernam cipher methods are jointly used in the cryptographic process and are expected to produce a high level of data encryption so that it can increase the security of data or messages. The research applies the combination of the caesar cipher and vernam cipher methods to encrypt text data or messages. Using the secret key value will convert the input message into an encrypted message that is difficult to crack and cannot be decrypted again. The input text and the encrypted data have no resemblance to maintain the confidentiality of the information or data contents
Prediction of hospital intensive patients using neural network algorithm
Get PDFThis study aims to predict whether the patient deserves to be inpatient or outpatient by comparing several machine learning techniques, namely, logistic regression, decision tree, neural network, random forest, gradient boosting. The research method uses three stages of research, namely data collection, data preprocessing, and data modeling. Implementation of program code using google colab and python programming language. The dataset used as the research sample is Electronic Health Record Predicting data. Based on the accuracy results generated in this study, the use of the Neural Network machine learning algorithm to predict hospitalization decisions for patients has proven to be a machine learning algorithm that has the highest accuracy rate reaching 74, 47% compared to other comparison machine learning algorithms, namely logistic regression, decision tree, neural network, random forest, gradient boosting
Application of TOPSIS method in assessment of the best learning comunication media for elementary school students
Get PDFThe spread of the Covid-19 virus that occurred so quickly and occurred almost all over the world caused the implementation of activities to be carried out online, including learning activities. The main thing that can help the online learning process is technology, especially communication technology. Commonly used communication media to assist the online learning process include Whatsapp, school e-learning Web, Youtube, Zoom, and Google Meet. Of course, every communication media used has advantages and disadvantages. This study aims to determine the best learning communication media using the TOPSIS method to assist users in choosing the best communication media for elementary school students based on the criteria for easy use and maintenance, completeness of features, quota requirements, understanding obtained, and the ability to re-access information. The results of this study indicate that the best communication media for elementary school student learning is the Whatsapp application. In addition, this research also produces a simple excel-based TOPSIS program that can be used by educators to determine what application is right for use in the learning process because many criteria are considered by an educator to determine the applicatio
Application of pest detection on vegetable crops using the cnn algorithm as a smart farm innovation to realize food security in the 4.0 era
Get PDFPests and diseases are one of the factors that become obstacles in the cultivation of vegetables because they can cause a decrease in the quality and quantity of production. The more varied types of pests have different impacts on crops, so if farmers incorrectly identify the class of pests, the treatment will be ineffective. Therefore, we need a technology that can classify the types of pests on vegetable crops to maintain the quality and quality of the product as well as the abundant harvest. The classification model of pests on vegetables using the deep learning method using the Convolutional Neural Network (CNN) algorithm with a high level of accuracy is the solution to this problem. The application of artificial intelligence in the agricultural sector also supports smart agriculture in Indonesia. Based on the research that has been carried out, the application of pest classification on vegetable crops made by applying the CNN model using the Inception V3 - k-fold cross-validation method has a test accuracy rate of 99%, meaning that the application can perform pest classification correctly
Techniques of Applied Machine Learning Being Utilized for the Purpose of Selecting and Placing Human Resources within the Public Sector
Get PDFIn strategic human resource management, one of the most critical issues to focus on is the correct selection and placement of people. Within the confines of this framework, the reason for the study that was conducted was to explore the machine learning approaches that proved to be the most effective in assisting with the recruitment of personnel and the assessment of their positions. To accomplish this goal, a in a series of tests involving workers in the public sector, categorization algorithms were used. The purpose of these tests was to determine which employees would be the ideal fit in which workstations and to determine how workers should be distributed. For supporting the decision support system, an algorithm model was created. Used in the process of recruiting and evaluating potential workers based on the results of the tests that were given. The most important results of this study support the idea that using the People's Evaluation for Recruitment and Promotion Algorithm Model (EERPAM) would make hiring and promoting people in a company fairer
Analysis and recommendations for business process improvement for retail companies using the business process improvement (BPI) method
No full textRetail companies are businesses that involve direct interaction between sellers of goods or services and consumers, meaning that retail businesses do not have a processing process from raw materials to finished products. In the process of editing and recapping goods data, there are 2 main businesses, namely editing data, sending copies of goods data, and storing new data in the cashier’s GIS database. After the evaluation, it was found that simplification could be made to make it more efficient. Based on the results of the evaluation of the business process, it was found that the root cause of the editing time and recap of goods data was long. Business process recommendations are made and the results are obtained, eliminating the process of providing a copy of new item data to the warehouse clerk and storing new item data in the cashier’s GIS database
Optimize naïve bayes classifier using chi square and term frequency inverse document frequency for amazon review sentiment analysis
Get PDFThe rapid development of the internet has made information flow rapidly wich has an impact on the world of commerce. Some people who have bought a product will write their opinion on social media or other online site. Long-text buyer reviews need a machine to recognize opinions. Sentiment analysis applies the text mining method. One of the methods applied in sentiment analysis is classification. One of the classification algorithms is the naïve bayes classifier. Naïve bayes classifier is a classification method with good efficiency and performance. However, it is very sensitive with too many features, wich makes the accuracy low. To improve the accuracy of the naïve bayes classifier algorithm it can be done by selecting features. One of the feature selection is chi square. The selection of features with chi square calculation based on the top-K value that has been determined, namely 450. In addition, weighting features can also improve the accuracy of the naïve bayes classifier algorithm. One of the feature weighting techniques is term frequency inverse document frequency (TF-IDF). In this study, using sentiment labelled dataset (field amazon_labelled) obtained from UCI Machine Learning. This dataset has 500 positive reviews and 500 negative reviews. The accuracy of the naïve bayes classifier in the amazon review sentiment analysis was 82%. Meanwhile, the accuracy of the naïve bayes classifier by applying chi square and TF-IDF is 83%
The Effect of Modern Strategy Implementation on Smart Infrastructure on Increasing Employee Performance at University in Indonesia
Get PDFThe design of strategies to increase the potential benefits of an organization is very important for renewal by implementing modern strategies. Smart infrastructure is a digital system that functions to improve performance, welfare, and increase cost efficiency and resource consumption. Previous research shows a significant increase in smart infrastructure which is influenced by the ability of the community. This study aims to analyze the success of implementing a renewal strategy for Smart Infrastructure for employees at university which we can assess from the performance of the university employees. Primary data was collected through questionnaires with a sample of 40 respondents which was then processed quantitatively by ANOVA test and LSD test using the Statistical Package for the Social Sciences (SPSS). The results showed that the percentage rate accepted was 78%, so that the implementation of a smart infrastructure system could increase employee productivity in university