Publication Search

Batik culture is very strong in Indonesia, this is the reason that batik can be found throughout the archipelago, with unique characteristics that distinguish it in each region. However, people are often confused and find it difficult to recognize one type of batik from another. One of the famous types of batik motif is Batik Parang. This research aims to establish a Convolutional Neural Network (CNN) model to classify Batik Parang and help people distinguish it from other batik motifs. Deep learning, particularly CNN, was chosen because it has a high accuracy rate in image classification. A quantitative Experimental design is used, using a dataset of 100 batik images evenly divided into two classes, namely Batik Parang and not Batik Parang. The dataset is divided into two categories, namely training data and testing data, with a data ratio of 80:20. Thus, by using Convolutional Neural Network (CNN), the classification between Batik Parang and not Batik Parang produces an accuracy of 95%, with the use of epoch = 118 and batch_size = 100.

This research aims to evaluate the effectiveness of linear regression as a forecasting tool to estimate the Provincial Minimum Wage (UMP) in Indonesia. Utilizing UMP data from various provinces during the period 2002-2022, this study employs linear regression to analyze the factors influencing UMP determination. The predicted UMP for North Sumatra in 2023 demonstrates a high level of accuracy (R-squared = 0.9678), affirming the potential of linear regression as an effective tool to understand regional economic dynamics. The research provides a crucial foundation for policymakers in regional economic planning and suggests avenues for further investigation, including exploring alternative prediction methods and analyzing the impact of UMP regulation policies.

The use of standard language is used in writing news. This research aims to identify and analyze writing errors made by journalists in writing news on internet media, especially on CNBC Indonesia. The research method used is descriptive qualitative, focusing on Indonesian writing errors from the aspects of spelling and diction. The research results show that there are several errors that often occur in news writing on CNBC Indonesia, such as inappropriate use of punctuation, letter writing errors, and word writing errors. These errors can confuse readers and create ambiguity in understanding. Recommendations that can be given are to increase accuracy in the use of punctuation marks, letters and words. Journalists need to pay attention to correct writing rules and double-check before publishing news. Apart from that, the editorial team also needs to provide training and guidance to journalists to improve the quality of news writing. It is hoped that the results of this research can contribute to improving the quality of CNBC Indonesia's online news writing and reducing ambiguity in reader understanding. This is important to maintain media professionalism and provide clear and accurate information to readers. In this way, it is hoped that CNBC Indonesia's online news can become a reliable source of information that is easy for readers to understand.

This research allows an automated system for detecting classified means of transportation in Medan City traffic using the YOLOv8 algorithm. The YOLOv8 algorithm is used to detect transportation objects with accuracy that is many times better than other object detection algorithms and with good accuracy after training with various data sets. The use of this algorithm provides an effective solution for handling congestion in the form of increasing the number of vehicles and less orderly traffic users in the city of Medan. The placement of each transportation object in the image to be tested by the system has an influence on the shape accuracy of the object detection results by the algorithm.

This community service was conducted on Jalan Jembatan Merah I and Jalan Wisata Babarsari. The purpose of this community service is to improve the quality of financial record-keeping, ensuring accuracy and correctness, to provide an accurate overview of the financial condition of UMKM Siomay Indul and Gudeg Jogya Mak Karti. This community service is focused on enhancing the quality of the financial reports of these UMKMs through understanding and implementing proper accounting practices in financial record-keeping. With the provision of training and mentoring, it is expected that the stakeholders of traditional culinary UMKMs can optimize their business potential. The results of the community service indicate that improvements in transaction recording systems and a better understanding of accounting standards can significantly enhance the quality of financial reports, providing the clarity needed for better decision-making in business management.

Parkinson's disease (PD) is a neurodegenerative disorder causing a decline in dopamine levels, impacting the peripheral nervous system and motor functions. Current detection methods often identify PD at advanced stages. This study addresses early-stage detection using handwriting analysis, specifically exploring the PaHaW dataset for pen pressure and stroke movement data. Evaluating online and offline features, the research employs pre-trained CNN models (VGG 19 and AlexNet) for offline datasets, achieving an overall accuracy of 0.53. For online datasets, velocity, and acceleration features are extracted and classified using Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), and recurrent neural networks (RNN), with GRU yielding the highest accuracy at 0.57. Notably, the convolution-based model C-Bi-GRU surpasses other architectures with a remarkable 0.75 accuracy, emphasizing its efficacy in early PD detection. These findings underscore the potential of handwriting analysis as a diagnostic tool for PD, contributing valuable insights for further research and development in medical diagnostics.

This research explores the use of Text Mining Methods as an innovative approach to extract important information from research report text. With a strong conceptual foundation from the literature review, this research details the key concepts of Text Mining, such as tokenization techniques, sentiment analysis, and entity extraction. The steps of applying Text Mining Methods to research reports are explained in depth, with a focus on using such techniques to improve the efficiency and accuracy of information extraction. Through the evaluation of the method's performance, the research demonstrates a significant improvement in analysis speed and information extraction accuracy compared to conventional methods. The research conclusions provide a holistic picture of the potential of Text Mining Methods in improving the effectiveness of the research report text analysis process. The implications of this research stimulate thoughts on the applicability of this technology in various disciplines that rely on research reports as a primary source of information. Thus, this research makes a positive contribution to the understanding and development of text analysis techniques to support more efficient decision making.

Following the journey of mathematics at the elementary school level, students often hear complaints when they have to explore concepts such as addition, subtraction, multiplication, and division. In such a dilemma, the need for innovation becomes even more pressing, as a way to carve out a vibrant next generation. The author sees that in learning mathematics, grade 3 students at SD Negeri 4 Citeureup lack enthusiasm for mathematics because this subject is often considered difficult. Overall, the process of implementing community service with a focus on education uses the jarimatics method to increase enthusiasm or motivation in studying mathematics for Citeureup 4 public elementary school students. The results of community service activities include the following: (a) achievement of the target number of participants. (b) the accuracy and skill of students working on multiplication problems. (c) achievement of activity objectives. After a series of training activities were carried out, finally we provided feedback questions from students. Do they feel happy and more motivated in learning mathematics? They all agree that they are happy and feel more motivated. To increase students' interest and motivation in learning mathematics, teachers should use good and effective methods to move and motivate students to be active in learning mathematics.

This study aims to improve students' learning outcomes regarding the material of faith in angels through the use of audiovisual media. This media refers to a learning strategy that utilizes sound and image elements, so that in the process of absorbing the material, students can involve their senses of sight and hearing. This Classroom Action Research (CAR) was carried out in two cycles, each consisting of the planning, implementation, observation, and reflection stages. Data were collected through observation, practical tests, and interviews, then analyzed descriptively. The results of the study showed a significant increase in students' understanding of the material of faith in angels after the application of audiovisual media. In the first cycle, many students still had difficulty understanding the material. However, in the second cycle, a significant increase in the accuracy of their understanding was observed. Thus, the application of the audiovisual method has proven effective in improving students' skills in understanding the meaning of faith in angels.

This study explores the implementation of the SiskeuDes application in financial management in Pijot Utara Village. SiskeuDes, as a village financial information system, aims to improve the efficiency, transparency, and accountability of village financial management. This study identifies and analyzes the stages of SiskeuDes use, namely planning, implementation, administration, and reporting, and evaluates the advantages and disadvantages of the system in the village context. At the planning stage, SiskeuDes assists in the preparation of planning documents such as RKPDes and APBDes through village deliberations involving village officials and the community. This system supports the accuracy and efficiency of budget planning despite challenges such as network disruptions and HR skills. At the implementation stage, SiskeuDes facilitates verification and budget preparation and reporting, with the active role of the Village Secretary and the Village Financial Management Unit (UPKD). Financial administration has also progressed thanks to this system, which reduces the risk of manipulation and increases transparency. The reporting and accountability process is carried out in a structured and integrated manner with SiskeuDes, although there are obstacles in conveying information to the community. The advantages of using SiskeuDes include increased efficiency of financial recording and reporting, real-time transparency, and support for community participation. However, disadvantages include limited infrastructure, suboptimal HR skills, and challenges in delivering information to the community. Improvement efforts such as increasing training and improving infrastructure are being made to address these shortcomings. Overall, SiskeuDes has made a positive contribution to village financial management, but still requires adjustments to address the various challenges that exist.  

As many as 7.3 million people worldwide die from heart disease. This indicates that heart disease is one of the diseases that cause the most deaths. As a preventive effort in handling heart disease, it is necessary to predict heart disease in patients. The classification process to predict heart disease is done using a decision tree. This decision tree is interesting because it is more flexible in providing the advantage of visualizing the advice so that the prediction can be observed. This study uses Heart Disease Prediction Dataset data with a total of 303 data. Then predictions are made using Decision tree so that the accuracy results are 83.60%, precision 89.28%, recall 78.12% and F1 score of 83.33%.

Mushrooms are very diverse with characteristics of each type, there are 1,433,800 types of mushrooms that have not been recognized. In this study, researchers used the Neural Network and Deep Learning Inception V3 methods as a feature extraction process in images to classify mushroom images based on genus with the Orange Data Mining application. There are 9 genera of mushrooms used in this study, namely Agaricus, Amanita, Boletus, Cortinarius, Entoloma, Hygrocybe, Lactarius, Russula, and Suillus. The total dataset used is 2,700, with 300 images for each genus. The test uses the cross-validation method which is applied to the confusion matrix to get precision, recall, F1-score, and accuracy values. In this study, the final classification results were obtained with an accuracy of 82.5% and the genus Boletus mushroom obtained the best results with an accuracy of 98.9%.

The use of the Decision Tree method in smartphone price classification is the focus of this study. By using the 10 most relevant features and data normalization to achieve scale consistency, the Decision Tree algorithm delivers an average accuracy of 81%. Although some false positives and false negatives occur, the model is able to classify smartphone prices well, especially in identifying low and high prices. These results provide important insights into the features that affect smartphone prices. While there is still room for improvement, this model provides a solid foundation for the smartphone industry to determine prices based on certain specifications. The importance of relevant feature selection and data normalization was revealed in this study. Despite the accuracy reaching 81%, improvements in the classification of medium and high price classes are still possible to reduce prediction errors. This method provides an important basis for the smartphone industry to set prices based on specifications, and data mining techniques such as Decision Tree can be improved to improve the accuracy of future price predictions.

Scholarships are a form of assistance in the form of educational expenses provided by the government or foundations to students or students who are categorized as from underprivileged families. However, in datermining scholarship recipients, there are still many scholarship recipients who come from wealthy families, while those from less fortunate families do not receive this assistance. This may be due to calculations and data processing that still use manual methods, causing scholarship recipients to not be on target. The purpose of this research is to simplify and minimize calculation errors in determining scholarship recipients for the Smart Indonesia Program (PIP) at SMK Karya Medika. Therefore, for calculating and processing PIP scholarship recipients data, data mining techniques can use the calssification method using the K-NN algprithm. K-Nearest Neighbor is a data classification method that will be used for data objects based on learning data that is closer to the object. In this study using the Confusion Matrix test so as to obtain an accuracy value of 80.00%.     

This thesis is a study that examines the influence of People's Business Credit (KUR) on the development of Jelutung micro, small and medium enterprises (MSMEs) at Bank BSI Kc Gatot Subroto, Jambi City. The purpose of this thesis is to be able to find out the effect of people's business credit (KUR) on the development of MSME businesses and to be able to find out the amount of contributions made by KUR to the business development of customers of Bank Syariah Indonesia Kc Gatot Subroto Jambi City.In this study using quantitative methods with data collection techniques namely observation, questionnaires and documentation. Which is the questionnaire itself as an instrument in collecting data. Then a validity test and reliability test were carried out to ensure the accuracy of each question item in the questionnaire to be used in collecting data. After that, a classic assumption test was carried out to ensure the soundness of the data and a hypothesis test in the form of a (t) test, simple linear regression test and test for the coefficient of determination (R2).The results of this study are as follows: (1) People's Business Credit (KUR) has a significant and positive effect on customer business development as evidenced by the significance of KUR of 1.68107 > 0.05 and also the value of the simple regression results which obtains a value of 0.554 which indicates a positive number so that the influence that KUR has is good or positive on the development of the customer's business. (2) The contribution made by KUR to the development of the customer's business is 0.47.8 or 47.8% and the remaining is 0.552. Or 52.2% is influenced by variables or other factors not mentioned in this study.

An audit is a systematic, independent examination of financial statements, accounting records, and supporting documents prepared by management, the purpose of which is to form an opinion on the accuracy of financial statements. Financial statements must have relevant characteristics (reliability) and reliability (reliability). Without the services of auditors, management cannot convince outsiders that the financial statements presented by management contain reliable and reliable information. Independence is the auditor's attitude to impartiality. The experience of the examiner contributes to high-quality inspection. The purpose of this study is to analyze the influence of auditor behavior, time pressure, audit experience, and independence on audit quality.   The research was conducted at a Public Accounting Firm (KAP) in Medan City. The number of research samples of 80 people was selected by the nonprobability sampling method. Data collection was carried out by questionnaire through Google form and literature studies that supported this study. The method used in this study is to use the Structural Equation Model (SEM) equation using the Partial Least Square (PLS) tool version 3.0. PLS consists of external relationships (outer model) and internal relationships (inner model), cross-loading> 0.7, Composite Reliability, Convergent Validity, Exploratory Factor Analysis (EFA), and Confirmatory Factor Analysis (CFA). Based on the results of the analysis, it was found that the first, second, fourth, and seventh hypotheses were rejected where each variable such as auditor behavior, and time pressure,  did not affect audit quality and independence could not moderate the influence between auditor behavior on audit quality,  independence could not moderate audit quality. The third, fifth, and sixth hypotheses are accepted where each variable such as audit experience, independence moderates the effect of time pressure on audit quality, and independence moderates the effect of audit experience on audit quality.

Accounting pays close attention to aspects of foreign currency transactions and adjustments to the functional currency that impact financial statements. PSAK 10 is the main guideline in regulating changes in foreign exchange rates and affecting businesses. A good understanding of PSAK 10, functional currency, and foreign currency transactions is crucial for business entities, especially those operating in a foreign currency economic environment. The case study used in this research is descriptive qualitative with literature review method. Research that characterizes research subjects based on emerging facts is known as descriptive qualitative research. The results of the research on the case study of PT Dianta Mitrafairindo Internasional highlighted the significant role of foreign exchange transactions in the company's operations, with management seriously implementing proper accounting processes, dealing with foreign exchange differences, and recording them thoroughly. Despite a loss in 2018, the company managed to record a profit in 2019, demonstrating its seriousness and commitment in managing foreign exchange risks. Overall, PT Dianta Mitrafairindo Internasional demonstrated accuracy, vigilance, and a strong commitment to foreign exchange-related accounting aspects in the context of its global business.    

The Effect Of Use Of Lung Mask Fixation On The Accuracy Of Targeted Irradiation In Lung Cancer Intensity Modulated Radiation Therapy (Imrt) Technique In The Department Of Radiation Oncology, Jakarta General Hospital. Lung cancer is the uncontrolled growth of abnormal cells in one or both lungs. While normal cells in the lungs usually develop and reproduce to form healthy lung tissue, these abnormal cells actually reproduce more quickly and are never able to become normal lung tissue. As a result, lumps of cancer cells are formed, which are often referred to as tumors. (4) Radiotherapy is a form of therapy that has been proven to be useful in treating cancer. The aim of radiotherapy is to provide safe, accurate and efficient radiation doses to treat various types of cancer and also non-malignant disorders (7). Carrying out radiotherapy for lung cancer involves the use of immobilization devices, one of which is a thermoplastic mask. This mask functions to reduce the patient's body movements, including movements caused by breathing (9). Verification is a critical stage in the radiotherapy process. The purpose of this verification is to ensure that there are no significant differences in the exposure carried out (14). Giving the right dose of radiotherapy radiation is very necessary to achieve successful therapeutic treatment. The accuracy of dosing and the accuracy of the patient's position influence the dose distribution that will be received by the patient. This verification is based on the International Atomic Energy Agency (IAEA) Human Health Series No. 31 of 2016 with a displacement value of 0.3cm (15). EPID (Electronic Portal Imaging Device) is an additional device connected to the LINAC (Linear Accelerator) radiotherapy device. EPID functions as a verification tool for radiation dose and geometry which is very important in the radiotherapy process (16). The accuracy of the patient's position during radiation treatment greatly influences the accuracy of the IMRT technique. Before irradiation, verification is carried out using an EPID (Electronic Portal Imaging Device) to ensure the correct target position on the tumor. This helps measure the x, y, and z axis coordinates along the radiation area before the radiation procedure begins.

Butterflies’ recognition serves a crucial role as an environmental indicator and a key factor in plant pollination. The automation of this recognition process, facilitated by Convolutional Neural Networks (CNNs), can expedite this task. Several pre-trained CNN models, such as VGG, ResNet, and Inception, have been widely used for this purpose. However, the scope of previous research has been somewhat constrained, focusing only on a maximum of 15 classes. This study proposes to modify the CNN InceptionV3 model and combine it with three data augmentations to recognize up to 100 butterfly species. To curb overfitting, this study employs a series of data augmentation techniques. In parallel, we refine the InceptionV3 model by reducing the number of layers and integrating four new layers. The test results demonstrate that our proposed model achieves an impressive accuracy of 99.43% for 15 classes with only 10 epochs, exceeding prior models by approximately 5%. When extended to 100 classes, the model maintains a high accuracy rate of 98.49% with 50 epochs. The proposed model surpasses the performance of standard pre-trained models, including VGG16, ResNet50, and InceptionV3, illustrating its potential for broader application.

Abstract.Network anomaly detection is a situation that occurs in network traffic that causes conditions to become abnormal. This research aims to analyze the performance of various machine learning algorithms in network anomaly detection and compare the performance of single classifier algorithms with ensemble learning. This ensemble learning technique has advantages such as increased accuracy and performance, can reduce the risk of overfitting and underfitting by using different subsets and features of data, and can turn weak learning into strong learning. However, on the other hand, this ensemble learning technique also has disadvantages in its use, namely that this ensemble method may not work well with high variance models, as the ensemble method may not be optimized for anomaly detection and that this method can be computationally expensive and time consuming due to the need to train and store multiple models. Some of the techniques used are deep learning, eager learning, lazy learning, bagging, feature selection, boosting, and stacking. In addition to this, this machine learning algorithm has weaknesses, including if any of the data used is incomplete, it will result in inaccurate completion data, making the programming process quite time-consuming. This research can help develop a more effective and efficient network anomaly detection system. The results of this research show that using ensemble learning and feature selection techniques can improve anomaly detection performance by reducing the processing time of redundant data and classification, as well as increasing precision values.