Publication Search

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.

The author of this final report aims to analyze the calculation of the cost of production based on orders for January 2023 at CV Rantau Bayur Permai. The company is located at Jln. Palembang – Jambi, Sukamoro, Kel. Tanah Mas Kec. Talang Kelapa KM.14 sukajadi, Banyuasin Regency, South Sumatra 30961. And is a company engaged in convection. From the data obtained by the author through interviews and observations. Based on data from the company, the authors found several problems, namely the company had not classified the cost of raw materials and auxiliary materials, the company had not taken into account the cost of depreciation of equipment and electricity into the calculation of the cost of production, so that the calculation of the cost of production was not correct as a whole. Based on the existing problems, the author suggests grouping raw material costs and supporting material costs and calculating depreciation costs and electricity costs into factory overhead so that the cost of production can be calculated correctly.

The air transportation business in Indonesia has experienced a rapid increase seen from the number of airlines established in Indonesia. The increasing number of airlines makes the competition increasingly fierce in building a company. So the company can experience financial difficulties that can lead to bankruptcy. One of the airline companies experiencing financial distress is PT. Indonesia Transport and Infrastructure Tbk. This research aims to analyze and predict the bankruptcy of the company PT. Indonesia Transport and Infrastructure Tbk. This research uses the Altman Z-Score and Springate methods. The data collection technique used in the research is secondary data in the form of PT's annual financial report. Indonesia Transport and Infrastructure Tbk for the 2017-2021 period.       The results of this research state that in 2017 the company experienced distress with a z-score classification of -2.2920 and Springate -0.5127. In 2018 the company experienced distress with a classification of -2.9939 and Springate -0.4330. In 2019 the company experienced distress with a z-score classification of -4.0886 and Springate -0.5974. In 2020 the company experienced distress with a z-score classification of -6.8293 and Springate -0.7776. In 2021 the company experienced distress with a z-score classification of -8.0491 and Springate -0.5821.

Freedom of speech is the right for every human being or individual to speak freely for his or her opinion, and is included in the classification of personal rights in human rights. So the right to freedom of opinion is part of one of the human rights that relates to a person's personality. The purpose of this research is to find out the existence of the right to freedom of speech in criticizing government policies which in reality are limited by the ITE Law. The method used in this research is normative law by collecting primary and secondary data from regulations, books, journals, and documents related to the research. The results of this study found several cases related to the right to freedom of speech that is restricted by Law Number 19 of 2016 concerning Electronic Information and Transactions Law.

This study aims to determine the effect of product quality, price and service quality on customer loyalty camping equipment rental. the method used is a case study, data obtained through questionnaires to Astrajingga Adventure customers. Withdrawal of samples using purposive sampling technique and the method of analysis used is multiple linear regression analysis method. The results of the research show that product quality, price, service quality and customer loyalty are included in the good classification. Simultaneously product quality, price and service quality have a significant effect on customer loyalty for Astrajingga Adventure camping equipment rental. Partially the product quality variable has no significant effect on camping equipment rental customer loyalty, the price perception variable has a significant effect on camping equipment rental customer loyalty, similarly the service quality variable has a significant effect on camping equipment rental customer loyalty Astrajingga Adventure.

The aim of this research is to analyze the simultaneous significant influence of salary and incentives on employee work productivity in the Promotions Division of CV. Lentera Galuh R Tasikmalaya. Salary has a significant partial influence on employee work productivity in the Promotions Division of CV. Lentera Galuh R Tasikmalaya, while Incentives also have a significant partial influence on employee work productivity in the same division. The research method used in this study is a quantitative method with a causal associative analysis approach. The research sample consists of 39 employees of CV. Lentera Galuh R Tasikmalaya. Data were collected through questionnaires distributed to employees in the division. The analytical tool used in this research is multiple regression analysis conducted using SPSS 25.0. The research results indicate that Salary has a classification of Very Strong, Incentives have a classification of Very Strong, while Employee Work Productivity also has a Very Strong classification. The findings of this study are expected to provide a better understanding of the influence of salary and incentives on employee work productivity in CV. Lentera Galuh R Tasikmalaya and offer recommendations to the management for enhancing employee performance and productivity.

The aim of this research is to determine and analyze the accounting treatment of fixed assets based on SAK-ETAP at Puskopdit Swadaya Utama 2020-2021. The research method used is descriptive qualitative. The data sources used in this research are primary data and secondary data. Data collection techniques in this research used observation, interviews and documentation methods. The data analysis technique used is qualitative analysis, namely data collection and analysis, data reduction, data presentation, and verification or drawing conclusions. The results of this research show that the classification of fixed assets, acquisition and recognition of fixed assets, measurement of fixed assets, depreciation of fixed assets, and presentation of fixed assets in the balance sheet are in accordance with SAK-ETAP. Meanwhile, the termination and disposal of fixed assets is not in accordance with SAK-ETAP.

The purpose of this study was to determine the description of Relationship Marketing and Customer Loyalty at Da'o Screen Printing company and to determine the effect of Relationship Marketing on Customer Loyalty at Da'o Screen Printing company. The research method used by researchers is to use descriptive analysis. This research uses a quantitative approach. The type of research used in this research is causal. In this study, the authors conducted direct research on all Da'o Screen Printing customers to obtain data. The sample in this study was 50 people, this is based on saturated sampling technique where the population in this study was 50 people. Researchers will conduct tests using SPSS version 25. Relationship Marketing at Da'o Screen Printing company is currently in a very good classification. Da'o Screen Printing's customer loyalty is currently in a good classification because many customers maintain loyalty at Da'o Screen Printing. Relationship Marketing has a significant effect on Customer Loyalty because if the implementation of Relationship Marketing will increase customers who are loyal to the products provided by Da'o Screen Printing.

In this research, the Science Laboratory in SMP Negeri 3 Kota Langsa has demonstrated good standardization in supporting the implementation of the independent curriculum. The research findings indicate that the infrastructure support for the science laboratory has an average rating of 87.5% with a classification of very good, while the facility support reaches an average percentage of 90.15% with a classification of very good. The standardization of laboratory personnel has achieved a percentage of 66.66% which falls into the good category, while the standardization of the science laboratory management based on the competencies of the laboratory head has a percentage of 85.16% which is classified as very good. The implementation of the independent curriculum in terms of the principles of learning and assessment is considered good, with a percentage of 72.6%.Overall, the Science Laboratory in SMP Negeri 3 Kota Langsa meets the standards effectively. The laboratory management has adopted a future-oriented approach by implementing digital information technology. Consequently, the Science Laboratory in SMP Negeri 3 Langsa is ready to support the implementation of the independent curriculum.

This study aims to analyze the communication of marine mammals, especially whales and dolphins, through a bioacoustic approach combined with computational science as an effort to support conservation in the Tropical Ocean region. The focus of the location is on the Banda Sea, the Seram Sea, and the tropical Pacific region which are important migration routes for marine mammals. Data were obtained from underwater sound recordings using hydrophones, accompanied by visual observations to validate the behavior and existence of species. The analysis is carried out through several stages, including signal pre-processing with noise filtering and sound segmentation, spectral analysis using Fast Fourier Transform (FFT), as well as the creation of a spectrogram to visualize vocalization patterns. Machine learning algorithms such as Support Vector Machine (SVM) are used to classify interspecies voices, while deep learning approaches are applied to identify more complex communication patterns, including dialect variations. The results showed that whales produced low-frequency vocalizations (20–200 Hz) for long-distance communication, while dolphins used high-frequency clicks and whistles (5–20 kHz) for echolocation and social interaction. The integration of bioacoustics and artificial intelligence improves the accuracy of sound classification by more than 90%. These findings confirm the effectiveness of computational-based non-invasive methods in monitoring the presence and behavior of marine mammals and provide a scientific basis for sustainable conservation.

Pronunciation plays an important role in communication. It provides the different meaning of English words when they are pronounced differently especially English diphthongs. Producing errors in pronouncing English diphthongs cause misunderstanding in communication. The research was aimed to know(1) the commonmispronounced diphthongs by the second semester of English Study Program’s students atintermediate speaking class and (2) the causation of errors in pronouncing English diphthongs. The mixed method research was used to get the data. The qualitative data were taken based on the observations, documentations, and interviews, meanwhile the quantitative data were taken based on the errors of the students on the tests. The results of the research were described by the percentages. The students commonly made diphthong errors as follows/uә/= 19.3%, /eә/= 21.3%, /ei/= 20%,/aʊ/= 13.10%, and/ɪә/= 26.2%.The errors happened in the classifications ofsubstitution = 46.9%, insertion = 13.8%, and omission = 39.3%. It happened because of the influence of inter-lingual and intra-lingual factors.

The purpose of this research is to evaluate PT. Batulicin Nusantara Maritim's financial performance between 2018 and 2022 based on its profitability and liquidity ratios. The financial accounts of PT. Batulicin Nusantara Maritim, a coal transportation service provider listed on the investment gallery of the Indonesian Stock Exchange (GIBEI), are the subject of this study. An analysis of the documentation was the method employed to prepare this research. Data is collected through the study, recording, and classification of documentation. This study requires the gathering of data from a corporation in the form of financial reports, which will then be used as research material. The data was then compiled, classified, confidentially handled, and evaluated using quantitative descriptive analysis to offer a summary of the issues encountered or looked into. Results of the study The financial performance of PT. Batulicin Maritime Archipelago is impacted by the profitability ratio and liquidity ratio of PT. Batulicin Nusantara Maritim during the years 2018 to 2022. has an effect on the financial performance of PT. Batulicin Nusantara Maritim.

Background:  Elderly is a condition where a person is 60 years old. Hypertension is a condition of a person who has mixture of salt and lemongrass that can facilitate blood circulation in the body. systolic blood pressure of 140 mmHg and diastolic 80 mmHg. Data from the Kaliwungu Health Center (2023) shows that the number of hypertensive elderly is 18 elderly people. Non-pharmacological therapy that can be done by soaking warm water feet with aObjective: to determine the effect of the application of foot soak therapy using warm water with salt and lemongrass on blood pressure in elderly people with hypertension in Kaliwungu Village, Semarang Regency. Method: this application uses a case study research design with prestest and post-test design. Samples were 2 elderly people who had 2nd degree hypertension. Results: the application of  there was a decrease in blood pressure that was different between respondent 1 and respondent 2 after the application of warm water foot soak with salt and lemongrass for 3 consecutive days for 20 minutes. Both respondents were categorized as grade 2 hypertension decreased to normal-high based on the PDHI classification (2019). Conclusion: Application of warm water foot soak with a mixture of salt and lemongrass can lower blood pressure in elderly people with hypertension.  

Hypertension is  a health problem that is commonly found in the elderly. The number of people with  hypertension  continues to increase every year, it is estimated that by 2025 there will be 1.5 billion people affected by hypertension. Hypertension can occur due to various factors,  namely: unhealthy diet / diet, smoking lifestyle and alcohol consumption, obesity or excessive weight, lack of  exercise / physical activity, excessive salt intake, consumption of saturated fat, use of estrogen, lack of fruit and vegetable intake. Efforts to overcome hypertension can be done with pharmacological  and non-pharmacological therapies  .  Non-pharmacological therapies  can be done by modifying lifestyle, complementary therapies  such as; hydrotherapy (foot bath) and physical exercise. In the Nursing Interventions Classification (NIC) warm water foot soak is one of the interventions of nursing diagnosis, namely peripheral tissue perfusion disorders. Descriptive research using case study design. There was a decrease in  blood pressure in  hypertensive elderly after  hydrotherapy soaked feet warm water. There are differences in  the development of lowering blood  pressure in  hypertensive elderly before and after  hydrotherapy soak feet warm water.    

Diabetes Mellitus is a hazardous disease, and according to the World Health Organization (WHO), diabetes will be one of the main causes of death by 2030. One of the most popular diabetes datasets is PIMA Indians, and this dataset has been widely tested on various machine learning (ML) methods, even deep learning (DL). But on average, ML methods are not able to produce good accuracy. The quality of the dataset and features is the most influential thing in this case, so deeper investment is needed to examine this dataset. This research will analyze and compare the PIMA Indians and Abelvikas datasets using the Random Forest (RF) method. The two datasets are imbalanced, in fact, the Abelvikas dataset is more imbalanced and has a larger number of classes so it is be more complex. The RF was chosen because it is one of the ML methods that has the best results on various diabetes datasets. Based on the test results, very contrasting results were obtained on the two datasets. Abelvikas had accuracy, precision, and recall, reaching 100%, and PIMA Indians only achieved 75% for accuracy, 87% for precision, and 80% for the best recall. Testing was done with 3, 5, 7, 10, and 15 tree number parameters. Apart from that, it was also tested with k-fold validation to get valid results. This determines that the features in the Abelvikas dataset are much better because more complete glucose features support them.

Research on the Identification of Drug Related Problems (DRPS) has been carried out in Congestive Heart Failure (CHF) patients at the Outpatient Installation of RSUD dr. Soekardjo City of Tasikmalaya used a descriptive method of medical record data of CHF patients retrospectively. This study aims to determine the frequency and categories of DRPs that occur based on the Pharmaceutical Care Network Europe V9.0 classification. The results showed that out of 80 patients, 288 DRPs were found consisting of 4 symptoms (indications) that were not treated (1.4%), adverse drug events may occur as much as 1 event (0.3%), inappropriate drug combinations or drug interactions as many as 279 events (96.9%), and the dose was too high in 4 incidents (1.4%), so that it can be concluded that the categories of causes and problems of DRPs that most often occur in RSUD dr. Soekardjo City of Tasikmalaya in 2022, namely drug interactions.

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.

Phishing is a crime that uses social engineering techniques, both in deceptive statements and technically, to steal consumers' personal identification data and financial account credentials. With the new Phishing machine learning approach, websites can be recognized in real-time. K-Nearest Neighbor(KNN) and Naïve Bayes (NB) are popular machine learning approaches. KNN and NB have their own strengths and weaknesses. By combining the two, deficiencies can be covered. So this study proposes to combine K-Nearest Neighbor with Naïve Bayes to classify phishing websites. Based on the results of the accuracy test of the combination of KNN with k=8 and Naïve Bayes, a maximum accuracy of 93.44% is produced. This result is 6.25% superior compared to using only one classifier.

Skin is the largest organ in humans, it functions as the outermost protector of the organs inside. Therefore, the skin is often attacked by various diseases, especially cancer. Skin cancer is divided into two, namely benign and malignant. Malignant has the potential to spread and increase the risk of death. Skin cancer detection traditionally involves time-consuming laboratory tests to determine malignancy or benignity. Therefore, there is a demand for computer-assisted diagnosis through image analysis to expedite disease identification and classification. This study proposes to use the K-nearest neighbor (KNN) classifier and Gray Level Co-occurrence Matrix (GLCM) to classify these two types of skin cancer. Apart from that, the average filter is also used for preprocessing. The analysis was carried out comprehensively by carrying out 480 experiments on the ISIC dataset. Dataset variations were also carried out using random sampling techniques to test on smaller datasets, where experiments were carried out on 3297, 1649, 825, and 210 images. Several KNN parameters, namely the number of neighbors (k)=1 and distance (d)=1 to 3 were tested at angles 0, 45, 90, and 135. Maximum accuracy results were 79.24%, 79.39%, 83.63%, and 100% for respectively 3297, 1649, 825, and 210. These findings show that the KNN method is more effective in working on smaller datasets, besides that the use of the average filter also has a significant contribution in increasing the accuracy.

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