Publication Search

This research aims to ensure accuracy, ease of use, and effectiveness in the learning module development process which aims to increase understanding of the content of the 1945 Constitution of the Republic of Indonesia (UUD 1945). In this research, research and development (R&D) methods are used using the ADDIE development model, namely analysis, design, development, implementation, and evaluation. In the research results, it is known that the results of expert validation of teaching materials obtained a score of 96% and validation of material experts obtained a score of 91%. In the practicality results obtained from the response questionnaire to teachers and students after using the teaching modules used, the practicality results for teachers were 94% and students were 98%. In the results of its effectiveness by giving evaluation questions to class X students, an average of 83.7 was obtained, while the KKM for class The results of this research show that the learning module that has been created meets the third evaluation standard, namely validity, ease of use, and effectiveness.

The reality shows that there are still teachers who do not have role models, especially in terms of pedagogy. Teachers often start lessons late for various reasons. This problem was discovered by researchers at SMP Negeri 1 Juwiring. After the questionnaire is distributed to respondents (students), the names of teachers who are often late will be collected. One way to overcome this problem is to provide training to increase teacher motivation to come to class on time. In this training, the Reward and Punishment method was applied with a positive work culture. When teachers (participants) have achieved the specified indicators, they will receive a reward, while teachers who have achieved the indicators will receive a punishment. The indicator of success in this research is that 100% of participants always arrive on time when starting lessons. This research uses the spiral method from Kemmis and Taggart. Kemmis and Mc model action research design. According to Taggart, there are four stages of action research, namely planning, action, observation and reflection. The data collection instruments were in the form of observation sheets for researchers and assessment sheets for participant attendance levels. The results of the research were that after carrying out positive culture training at SMP Negeri 1 Juwiring in cycle I, none of the participants had completed it. There is no participant who has succeeded 100% in not being late, but there is 1 participant whose accuracy level has reached 93%, this means that the participant has experienced improvement. Meanwhile, the accuracy rates for the other 4 participants ranged between 55%, 58%, 2% and 77%. After carrying out cycle II while continuing to use Reward and Punishment with a positive culture, 5 participants completed it.

The purpose of this study is to discuss and find out about the concept of accountability in contemporary educational institutions. This research method uses literature review, by studying from literary sources that are relevant to the material discussed. Accountability is the obligation to provide accountability for a mandate or responsibility assigned to related parties, especially the party providing the mandate. The application of accountability in educational institutions is a must to increase public trust in educational institutions. Forms of implementing accountability in contemporary educational institutions include: Decisions must be made in writing and available to every citizen who needs them, accuracy and completeness of information, explanation of policy objectives taken and communicated, feasibility and consistency, and dissemination of information regarding a decision. One of the accountability models applied in contemporary educational institutions is administrative accountability, which includes traditional accountability, managerial accountability, program accountability and process accountability.

The research was centred on a demographic comprising individuals who were consumers of Implora lipstick within the local community. This research employed quantitative research methods to examine two primary objectives: (1) to evaluate the impact of product quality on the intention to repurchase implora lipsticks in Kolaka Regency, and (2) to analyse the influence of brand experience on the intention to repurchase implora lipsticks in Kolaka Regency. To evaluate the dependability and accuracy of the research instrument, a battery of tests was administered by the researchers utilising the statistical software SPSS 25.0. The evaluation of the measurement model, also known as the outer model, and the structural model, referred to as the inner model, is performed through the utilisation of Structural Equation Modelling (SEM) with the application of Partial Least Squares (PLS) methodology. The findings of the research demonstrate a significant and favourable association between the attributes of product quality and the degree of inclination towards engaging in subsequent purchases. The assertion is substantiated by empirical evidence, as indicated by a t-statistic of 5.648 and a corresponding P-value of 0.000. Moreover, recent studies have unveiled that characteristics linked to the brand encounter demonstrate a positive and statistically significant impact on the level of propensity to engage in repeat purchasing behaviour. The assertion provided is supported by a t-statistic value of 3.543, which is accompanied by a P-Value of 0.000.

The advent of the Internet as an effective means for resource sharing has consequently, led to proliferation of adversaries, with unauthorized access to network resources. Adversaries achieved fraudulent activities via carefully crafted attacks of large magnitude targeted at personal gains and rewards. With the cost of over $1.3Trillion lost globally to financial crimes and the rise in such fraudulent activities vis the use of credit-cards, financial institutions and major stakeholders must begin to explore and exploit better and improved means to secure client data and funds. Banks and financial services must harness the creative mode rendered by machine learning schemes to help effectively manage such fraud attacks and threats. We propose HyGAMoNNE – a hybrid modular genetic algorithm trained neural network ensemble to detect fraud activities. The hybrid, equipped with knowledge to altruistically detect fraud on credit card transactions. Results show that the hybrid effectively differentiates, the benign class attacks/threats from genuine credit card transaction(s) with model accuracy of 92%.

Data mining is a technology that plays an important role in supporting data-driven decision making, especially in complex and dynamic higher education environments. In the context of education management, the ability to predict student graduation is an essential aspect because it can help institutions plan strategic steps, intervene earlier, and optimize academic resources. This study aims to apply the C4.5 decision tree algorithm to build a student graduation prediction model based on academic data. The research dataset includes key variables such as Grade Point Average (GPA), total Semester Credit Units (SKS) taken, and student attendance rates during lectures. The analysis was conducted using the C4.5 algorithm, which is known for its high level of interpretability, making the model results easy to understand by policy makers. The test results showed an accuracy of 84.6%, indicating that this method has the potential to support data-based academic management systems. These findings are expected to serve as a basis for educational institutions to improve the effectiveness of monitoring and evaluating the student learning process.

One mathematical model in the form of a system of nonlinear ordinary differential equations is the predator-prey model. The predator-prey model explains population changes of one prey population and one predator population due to changes in time. The radial basis function network method is used to find a numerical solution to the predator-prey model. The radial basis function network method can directly approximate the function and derivative of the prey-prey model using a basis function. The basis function used is a multiquadric basis function. Numerical solutions using the radial basis function network method obtained from this research show high accuracy and low error. The absolute error obtained from the two simulations with Δt = 0.01 each is 0.0066 in the first simulation and 0.022 in the second simulation. The errors obtained are relatively small because each only represents 0.66% of the initial value of the first type and 0.5% of the initial value of the second type. This shows that the radial basis function network method is efficient in calculating the predator-prey model solution.

The purpose of this study was to determine the effect of ROA, ROE, and DER on profit growth in insurance sub-sector companies listed on the Indonesia Stock Exchange (BEI) in 2018-2022. The technique used for sampling is purposive sampling method with data from 7 insurance companies. This research is quantitative, which is research presented in the form of numbers and statistics. In determining the accuracy of the model that needs to be done is analyzing financial data, then testing several classical assumptions underlying the regression model. The analysis technique used is multiple linear regression analysis.Data analysis and hypothesis testing in this study using Eviews software version 12.0. The results of this study indicate that ROA has a simultaneous positive effect on earnings growth, while ROE and DER have no significant effect simultaneously on earnings growth. The suggestion in this study is that there is a need to improve the company's financial performance in order to increase company profits so that company prices can increase.

Convolutional neural network (CNN) is a deep learning (DL) model that has significantly contributed to medical systems because it is very useful in digital image processing. However, CNN has several limitations, such as being prone to overfitting, not being properly trained if there is data duplication, and can cause unwanted results if there is an imbalance in the amount of data in each class. Data augmentation techniques are used to overcome overfitting, eliminate data duplication, and random under sampling methods to balance the amount of data in each class, to overcome these problems. In addition, if the CNN model is not designed properly, the computation is less efficient. Research has proved that data augmentation can prevent or overcome overfitting, eliminating duplicate data can make the model more stable, and balancing the amount of data makes the model unbiased and easy to learn new data as evidenced through model evaluation and testing. The results also show that the custom convolutional neural network model is the best model compared to ResNet50 and VGG19 in terms of accuracy, precision, recall, F1-score, loss performance, and computation time efficiency

Plant disease is one of the problems in the world of agriculture. Early identification of plant diseases can reduce the risk of loss, so automation is needed to speed up identification. This study proposes a custom-designed convolutional neural network (CNN) model for plant disease recognition. The proposed CNN model is not complex and lightweight, so it can be implemented in model applications. The proposed CNN model consists of 12 CNN layers, which consist of eight layers for feature extraction and four layers as classifiers. Based on the experimental results of a plant disease dataset consisting of 38 classes with a total of 87,867 image records. The proposed model can get high performance and not overfitting, with 97%, 98%, 97% and 97%, respectively, for accuracy, precision, recall and f1-score. The performance of the proposed model is also better than some popular pre-trained models, such as InceptionV3 and MobileNetV2. The proposed model can also work well when implemented in mobile applications.

This study aims to determine the effect of CAR, NPL, BOPO, and LDR on ROA in National Private Commercial Bank companies listed on the Indonesia Stock Exchange (IDX) in 2018-2022. The technique used for sampling is purposive sampling method with data from 5 banking companies. This type of research is quantitative research, namely research presented in the form of numbers and statistics. In determining the accuracy of the model that needs to be done is financial data analysis, then testing some of the classical assumptions that underlie the regression model. The analysis technique used is multiple linear regression analysis.Data analysis and hypothesis testing in this study used Eviews software version 12.0. The results of this study indicate that CAR, NPL, BOPO and LDR partially have a positive effect on ROA. The results of this study also show that CAR, NPL, BOPO and LDR simultaneously have an effect on ROA. The ability of several independent variables to influence the dependent variable is 98.2% and the other 2.8% is influenced by other factors outside of this study.  

This data mining association processes 1224 Gamefantasia ticket redemption transaction data. The goal is to find a pattern of association between goods as a recommendation for structuring the display of goods at the cashier counter and increasing ticket exchange transactions. Modeling uses a comparison of two algorithms, namely the Apriori algorithm and FP-Growth. The data analysis method with the CRISMP-DM method is then processed by RStudio software. The results of the study with the same parameters support 0.02 and confidence 0.1 FP-Growth algorithm formed 53 rules, the strength of the association rule 6.2%, the accuracy was1245%. Whereas the Apriori algorithm forms only 12 rules, the strength of the association rules is 2.1% and the accuracy is 7.8%. Thus, it can be concluded that the use of the FP-Growth algorithm has better results than the Apriori algorithm because it has the highest accuracy in finding transaction patterns.

The “Covid-19” pandemic that occurred from 2019-2022 had an impact on the restaurant, hotel and tourism sub-sector businesses, resulting in a loss of revenue. Early warning of bankruptcy can be obtained by conducting a bankruptcy analysis. The goal of this research is to find out how likely it is that businesses in the tourism, hotel, and restaurant subsector will be in financial distress between 2017-2021 period using the Altman model, internal growth rate, and Springate and to determine the most appropriate and accurate model among the three models. The quantitative descriptive analysis method is used in this study. The population used is the restaurant, hotel and tourism sub-sector companies listed on the IDX. Sampling using purposive sampling method. The analysis tool uses Altman model analysis, internal growth rate, and Springate, as well as testing the level of accuracy. This study's findings show that the Altman model, the internal growth rate model, and the Springate model can predict financial distress in restaurant, hotel and tourism subsector companies listed on the IDX for the 2017-2021 period, and the most accurate model is the Altman model with a high degree of accuracy. the highest was 77.1% and the type error was 22.9%.

Diseases of the heart and blood vessels, such as coronary artery disease (heart attack), cerebrovascular disease (stroke), heart failure (HF), and other pathologies, are collectively referred to as cardiovascular disease (CVD). Globally, around 17 million people a year die from cardiovascular disease, with mortality increasing significantly for the first time in 50 years. Has performed an analysis of the performance of the selection algorithm with case studies predicting the determination of the customer's risk profile. Data mining is the extraction of previously unknown or previously hidden patterns from large databases or data warehouses. This study compares data mining classification models Nave Bayes, Decision Tree, Random Forest, KNN, and SVM to find the most effective model for classifying customer profile data. Later, the most accurate model will be proposed as a replacement model for forecasting the customer's risk profile. As a result, the accuracy value obtained is 82.93% and AUC is 0.896. Then accuracy testing is carried out using the rapidminer application. Testing on rapidminer was carried out with the highest accuracy obtained with an accuracy value of 86.64% and an AUC of 0.880.  

  This study aims to determine the implementation of SISKEUDES in improving the quality of village financial accountability in Karangrejo Village, Selomerto District. This research uses descriptive method with qualitative analysis using the implementation model. Data collection was carried out by library research, observation, and in-depth interviews. The research location is in Karangrejo Village, Selomerto District, Wonosobo Regency. Data analysis uses data reduction, data presentation, and data verification or conclusions. The results showed that the management of the SISKEUDES application in Karangrejo Village, Selomerto District, Wonosobo Regency had been carried out in an accountable manner. performance indicators. With the SISKEUDES application, the village government is greatly assisted in managing village finances and budgets and also provides accuracy in reports that have been made and upholds reporting transparency and accountability.

The Toba Batak tribe has a distinctive fabric known as ulos. Toba Batak ulos have types depending on their uses. But in the modern era, especially among urban communities, very few people know the types and uses. Motivated by the success of Convolutional Neural Network (CNN) algorithm in image classification, this study will conduct a learning-based approach to classify 5 types of Toba Batak ulos (Ragi Hidup, Ragi Hotang, Mangiring, Sadum, and Sibolang). The process starts from data collection, data analysis, model building, model training, and confusion matrix. The dataset used is 1000 images with 80% training data, 10% valid data, and 10% test data. Convolution, maxpooling, dropout, flatten, and fully connected are the 5 layers forming the CNN model. The optimizer used is Adam with a learning rate of 0.001. The model generated in this study can detect Toba Batak ulos images at an accuracy rate of 94.00%.    

The MotoGP One race in West Nusa Tenggara Lombok, Mandalika which was held on March 18 2022, received many responses or reactions from the public on social media, especially Twitter. There are those who agree and disagree about the holding of MotoGP in Mandalika, to find out the responses of the people who agree or disagree is needed that can process tweets data using the sentiment analysis method. The use of BERT (Bidirectional Encoder Representations from Transformers) for sentiment analysis produces a bidirectional language model that can understand the context of all words from a sentence. The dataset used goes through preprocessing stages such as case folding, data cleaning, tokenization, normalization, and removal of stopwords before sentiment analysis is carried out. This study uses several hyperparameters, namely a batch size of 32, the optimizer uses Adam with a learning rate of 3e-6 or 0.000003, and an epoch of 25. The evaluation results of the model obtain an accuracy of 55%. Precision for positive by 56%, neutral by 59%, and negative by 44%. Recall for positive is 74%, neutral is 29%, and negative is 54%. F1-score for positive is 64%, neutral is 38%, and negative is 48%.

HIMS as a series of activities that cover all hospital health services at all administrative levels that can provide information to managers for the management process. In carrying out the hospital management information system process, the HOT FIT method is needed. The HOT FIT method is a complete solution that is most suitable for current difficulties or limitations. The purpose of this literature review is to find out how to analyze the application of a hospital management information system using the HOT FIT method. The literature used in this study is to determine the articles that match the inclusion criteria. The data base used is Google Scholar. The year of publication of literature sources taken is the last 5 years between 2018 and 2023, literature sources use English or Indonesian. The results of 5 articles obtained that the analysis of the application of hospital management information systems using the HOT FIT method is by implementing Human (System use, user satisfaction), Organization (Structure, environment), Technology (system quality, information quality, service quality). It can be concluded that the quality of a management information can be assessed from the level of accuracy and level of relevance of the information data. With the HOT FIT method, information can be more relevant and accurate and this information has benefits for its users. It is also Vnecessary for the hospital to improve the quality of the information management system by paying attention to the stages and models used.

This The speed of information, the accuracy of data, the ease of information services, and accountability are very important reasons for the implementation of the system. Semarang University (USM) is a private university in Semarang that has the most 2 students in Central Java. Based on the 2019 USM tracer data showing horizontal alignment, namely how close the relationship between the field of study and alumni work is, it appears that there is still a discrepancy in the ability of graduates with stakeholders.  The Apriori algorithm is the best-known algorithm for finding high-frequency patterns  Rules that state associations between attributes are often called affinity analysis or market basket analysis. The use of the Apriori Algorithm in data mining calculations using data from the Semarang University tracer that the limit of the minimum support is 50% and the minimum confidence is 100% so that it forms 4 rules. From the four rules produced that modeling using the Apriori Algorithm can produce several rule formations so that it can provide an evaluation to the University for compiling steps, this can be seen because the resulting rules are different because each graduate relationship with the desired desires and different styles.  

Technological developments today make it easy for people to use social media as a means of expressing opinions, including Twitter. The case study taken by the researcher is the sentiment towards the performance of the mayor of Medan. The case was taken because it was widely discussed by Indonesian people, especially the city of Medan on Twitter social media. One of the uses of this research is to find out the trend of Twitter user comments on the performance of the mayor of Medan by conducting a sentiment analysis. Sentiment will be classified as positive, negative and neutral. The algorithm used in sentiment analysis is Naïve Bayes. The stages in conducting sentiment analysis in this study are data preprocessing, data processing, classification, and evaluation. The results of this study are using the SMOTE method, the training and testing ratio is 80:20 because it has the highest accuracy, which is 78% compared to other ratios. The prediction results resulting from the classification turned out to be more dominant towards neutral labels. In addition to classifying for sentiment analysis, this study also measures the performance of the model created. The results showed that the Naïve Bayes algorithm has a precision value of 78%, a recall of 78%, and an f1-score of 77%.