Publication Search

This research discusses the implementation and evaluation of the Convolutional Neural Network (CNN) convolutional neural network model for classification of fruit types, specifically to differentiate between Banana and Papaya. The CNN model used consists of several convolutional, pooling, and fully connected (dense) layers designed to extract features and perform binary classification. Data augmentation is applied to the training set to increase data variation and prevent overfitting. The image data used is normalized to speed up training convergence. The model was trained using the Adam optimizer and the binary crossentropy loss function for 20 epochs. Performance evaluation was carried out using the validation set. The results show that the model is able to effectively classify fruit images with a high level of accuracy. Predictions are made by uploading images, resizing them, and normalizing them before using the model for predictions. The classification threshold was set at 0.4, where a predicted probability greater than or equal to 0.4 was classified as Banana and a probability less than 0.4 was classified as Papaya. This research shows that the CNN model can be used effectively for binary image classification tasks and can be extended to classify more types of fruit with appropriate data adjustments and model architecture.

Stunting is a condition of failure to thrive in children, in Indonesia it is still a serious problem with a fairly high prevalence. The government is trying to reduce stunting rates with various health programs, and early detection through routine measurements is very important. This research uses the Extreme Gradient Boosting (XGBoost) algorithm to classify stunting status in children under five years. This study uses a relevant dataset containing anthropometric information on children, such as gender, age, birth weight and length, current weight and length, and breastfeeding status. The research stages include dataset search, preprocessing, classification, evaluation, and implementation in a local web-based prediction program. The XGBoost algorithm was chosen because of its advantages in speed, scalability, and efficiency. After preprocessing and data sharing, the model was trained and tested, resulting in 86% accuracy, 89% precision, 95% recall, and 92% F1-score. Evaluation using the confusion matrix and classification report shows that this model is quite effective in classifying stunting status.  

. Sex role classification in adolescents can have a significant impact on their development and well-being. While this classification can provide a framework for understanding gender identity, it can also limit possibilities for exploration and result in high conformity pressure. Adolescents may feel bound to narrow gender stereotypes, causing restrictions in self-expression and opportunities available to them. Impacts include increased risk of mental disorders, discrimination and stigma. To facilitate positive growth, it is important for society to recognize and support the diversity of gender identities, and provide space for adolescents to explore their interests, talents and aspirations without the restrictions imposed by gender stereotypes.

The objective of this research is to find out whether character education in the "English for Nusantara" textbook for seventh-grade students is in accordance with the current curriculum. This research analyzed character education contained in the reading and conversational texts of the textbook. The research methodology used a descriptive qualitative approach and content analysis technique. The characters found in the textbook were classified into six dimensions of the Pancasila Student Profile. The results showed that the six dimensions of the Pancasila Student Profile were found. The dimension of having faith, fear of God Almighty, having a noble character 33.2%, global diversity 12.9%, mutual cooperation 16.7%, independent 20.4%, critical reasoning 7.5%, and creative 9.3%. In the six dimensions of the Pancasila Student Profile, which have 20 elements, only 19 were found, while one element that was not found was intercultural communication and interaction. The characters in this book are mostly integrated implicitly. The primary focus dimension of the “English for the Nusantara” textbook was having faith, fear of God Almighty, and having noble character. In addition, the main focus element in this textbook was the manner towards others. Based on the classification of character education stated by Prismarani (2014), this textbook scored 95% and was classified as ‘very high’ quality.

Research This study aims to determine the application of accountability accounting as a tool for production cost control and performance appraisal at UPT. production cost control and performance appraisal at Sikka Innovation Center. innovation center. In the application of responsibility accounting there are several indicators, namely, organizational structure, budget, separation of controllable and uncontrollable costs, account code classification, account reporting, and performance appraisal at UPT. controlled and uncontrolled, account code classification, accountability report. accountability report. Implementation of accountability accounting as a performance appraisal tool There are several indicators, namely, identification of the center of responsibility center, standards are set as benchmarks for manager performance on certain responsibility center, manager performance is measured by comparing the budget and realization between budget and realization, managers are individually rewarded or punished by higher management. or punishment from higher management.  This research uses a qualitative descriptive method. Techniques data collection techniques using literature study, observation, interviews, and documentation. documentation. The data analysis technique is done by comparing the existing theories that already exist with the data obtained from the case study.  The research results obtained from the application of accountability accounting as a means of controlling production costs and performance appraisal has not been effective because the and performance appraisal has not been effective because there is no separation between controlled and uncontrolled costs. controlled and uncontrolled costs.

This research use the Naive Bayes algorithm to classification of user reviews of the Sky Childern Of The Light application from the Google Play Store. The Sky Childern Of The Light application is a popular online game, because it offers a unique and immersive playing experience. This method was chosen because of its simplicity, speed, ease of interpretation, and suitability for high-dimensional data. The advantages of Naive Bayes are the accuracy and efficiency of calculations, fast results and presentation. The data collected was 1500 data with a classification ratio of 8:2 with an accuracy value of 87% using the Naïve Bayes algorithm. This method is very good at analyzing the sentiment of the Sky Children Of The Light application.      

This research aims to describe the use of language in community interactions at the Motabuik terminal, Atambua City. The use of language in question is the form and function of code switching and code mixing in the interaction of the Motabuik Terminal Community, Atambua City. The data referred to in this research is code switching and code mixing in the interactions of the Atambua City Terminal Community, in the form of speech between the Motabuik Terminal Community. The speech in question is in the form of a conversation containing words, phrases, clauses and sentences that have elements of code switching and code mixing. Data collection was carried out using listening, note-taking and introspection techniques. Data analysis techniques were carried out with all utterances that showed the occurrence of code switching and code mixing in interactions at the Motabuik Terminal, Atambua City which contained elements of code switching and code mixing. Data collection was carried out by listening, taking notes and introspection. Data analysis techniques were carried out with all utterances that showed the occurrence of code switching and code mixing in the interaction of the Motabuik Terminal community, Atambua City, identified and carded complete with their construction. Next, classification and categories of the overall data are carried out. The data was analyzed by selecting and sorting out the forms and functions of code switching and code mixing in the interactions of the Motabuik Terminal Community, Atambua City. After being analyzed and classified, the data is described and explained to find out the form and function of code switching and code mixing in the interaction of the Motabuik Terminal Community, Atambua City. The results of the research show that there are two types of code switching in the interaction discourse at the Motabuik Terminal, namely in the form of language transfer, includes code switching from Atambua language to Indonesian and code switching from Indonesian to Atambua language at the Motabuik terminal, namely internal code mixing in the form of Atambua language words and phrases and connecting Indonesian as a unifying language communication tool at the terminal, the code mixing function has aspects speech, to explain, provide information and respect passengers.

Understanding the concept of Justification by Faith is crucial for Christians, as it enables them to gauge their comprehension and application of this doctrine in their lives. Many Christians have yet to fully grasp this foundational aspect of their faith. This study aims to elucidate the true significance of Justification by Faith by comparing the perspectives of Paul and James, which at first glance, seem contradictory. This research employs a literature review approach, involving the identification, classification, and analysis of relevant literature on the topic of Justification by Faith according to Paul, James, and Calvin. The study involves a hermeneutical analysis of biblical texts, a comparison of theological perspectives, and a systematic organization of findings. Paul asserts that justification occurs through faith, independent of works, as an act of God's grace (Romans 3:28, 4:5). The law reveals human sinfulness and the need for divine justification through faith in Christ. James emphasizes that genuine faith is demonstrated through works (James 2:24). He argues that faith without works is dead and insists on the necessity of works as evidence of true faith. Calvin integrates both perspectives, emphasizing that justification by faith is inseparable from the process of regeneration by the Holy Spirit. He views faith as a gift from God that leads to good works, the fruit of genuine faith. Justification by Faith is an act of God that can only be achieved through His grace and the sacrifice of Jesus Christ (Romans 4:5; 5:6). Faith is rooted in the truth of God's revelation in Christ, culminating in belief in His crucifixion and resurrection. Both Paul and James agree that faith and works are essential in a genuine response to God, with good works being the inevitable result of true faith. This study underscores the interconnectedness of faith and works, aligning with Martin Luther's assertion that good works are the fruit of righteousness. The comprehensive understanding of Justification by Faith involves recognizing it as a divine act that provides hope for salvation through faith, a gift from God facilitated by the Holy Spirit (Ephesians 2:8; Galatians 5:22).  

This study analyzes the use of deep learning, primarily Convolutional Neural Networks (CNN), to categorize various types of citrus fruits. The study attempts to create an automated system that can accurately categorize citrus fruit kinds using image processing techniques. The collection contains 40 photos of four different citrus fruit types: pomelo, mandarin orange, kaffir lime, and lime. The methodology entails gathering photos, preprocessing them to improve quality, and then training a CNN model to classify the fruit varieties. The results show a high accuracy rate of 95% in classifying fruit types, demonstrating that the CNN model is effective for this task. The findings indicate that increasing the dataset and including other fruit species could significantly boost the system's accuracy.

Land cover is defined as the physical and biological cover of the earth's surface, both those formed naturally such as swamps, hills and rivers and those formed by man-made means such as rice fields, gardens, forests and buildings. As technology develops, conventional methods of satellite image processing are starting to be abandoned. This is because conventional methods require quite a long time to process satellite image data. The presence of Google Earth Engine (GEE), which is a cloud computing-based platform, makes it easier for users to process satellite image data boldly and for free. This research aims to classify satellite image land cover in the Trenggalek Regency area, East Java. The level of accuracy in this study uses a confusion matrix. The accuracy test results show a value of 90.23%.

This study aims to explore the diversity of syllable types and develop a comprehensive classification framework. Analysis was conducted on the syllable structures of various languages to understand both common patterns and language-specific variations in syllable formation. Linguistic data from diverse languages were collected and analyzed to identify phonotactic patterns, morphological interactions, prosodic features, and phonetic realizations of syllables. Findings indicate a wide range of syllable structures, ranging from simple CV to complex structures with multiple consonants and vowels. There are also significant interactions between syllable structure and morphological processes, as well as prosodic features. The results of this study are integrated into a comprehensive classification framework that encompasses various phonological, morphological, and phonetic dimensions of syllables. Theoretical and practical implications of the research are discussed, along with recommendations for future research.

Inheritance is wealth which can be a collection of assets and liabilities from the heir which is transferred to the heirs. In inheritance law, a principle applies, namely that if an heir dies then by law his rights and obligations immediately pass to his heirs. The division of inherited assets can have legal impacts in society which occurred in the Sikka Krowe Tribe community, specifically in Klotong Hamlet, Bura Bekor Village, Bola District, Sikka Regency between disputed heirs. The problem formulation of this research is 1. What are the reasons for the struggle between heirs? 2. What is the process for resolving property disputes between heirs? And 3. How is the distribution of assets resulting from struggles between heirs viewed from the customary law of the Sikka Krowe tribe, Bola District, Sikka Regency? This research is empirical legal research. The data sources in this research are primary and secondary data sources. Data management and analysis techniques are editing, classification and description, then the data obtained, both primary and secondary data, will be processed and analyzed by researchers based on the problem formulation. Based on the research results, the reason why there is a struggle between heirs in inherited land disputes is that the family does not know the exact status of ownership of the inherited land and the factor of poor communication between the two parties. Settlement of disputes or disputes Done through utun omok (gathering to find a way out) includes: presenting family parties, deliberation or mediation (kula babong), decision making, settlement and returning decisions to the parties in dispute. Distribution of land inheritance using a patrilineal kinship system, namely distribution that is directly given to sons as the main heirs and gets more inheritance.

Attention to spices and flavorings among the younger generation is still low. The strategy that can be used to overcome this problem is a programmed and computerized arrangement of spices and flavorings using Convolutional Neural Network (CNN) calculations. In this exploration there are 300 images of spices and flavors which will be characterized into 3 classifications. Namely ginseng, ginger and galangal. Information in each classification is divided into two, namely preparation information and testing information with a proportion of 80%: 20%. The CNN model used in computerized grouping of spice and flavor images is a model with 2 convolutional layers, where the first convolutional layer has 10 channels and the second convolutional layer has 20 channels. Each channel has a 3x3 portion frame. The channel size in the pooling layer is 3x3 and the number of neurons in the secret layer is 10. The actuation capability in the convolutional layer and secret layer is tanh, and the actuation capability in the result layer is softmax. In this model, the accuracy of preparation information is 0.9875 and the loss value is 0.0769. The precision of the test data is 0.85 and the loss value is 0.4773. Meanwhile, testing new information with 3 images for each classification resulted in an accuracy of 88.89%.

Chronic diseases in humans are very difficult to detect visually, for example glaucoma, hypertension, diabetes, and others. So it takes a lot of time for further medical examination by visiting a health center or hospital. Therefore, this research aims to find a solution combining medical and computer science to classify quickly and precisely. Classifying eye images requires good features and characteristics so that disease images can be classified. This research uses the Deep Learning method, namely Convolutional Neural Network with MobileNet-V3 architecture which can extract features from large resolution images very well. This research resulted in accurate classification of images of chronic diseases Normal, Diabetes, Glucoma, Cataract, Age related macular degeneration, Hypertension, Pathalogical Myopia. uses the MobileNet-V3 architecture, with transfer learning reaching 81%, and loss only 0.4913.

On August 14, 2023, Indonesia had approximately 228 million social media users, a number that is expected to continue growing to reach 267 million by 2028. Social media can be used to spread both positive and negative information, and one of the various negative effects is cyberbullying. Consequently, much research is conducted in the field of machine learning to develop sentiment analysis. One crucial step in sentiment analysis is word weighting. The two most common word weighting methods are TF-IDF and Word2Vec. These methods can be compared to determine which one produces better classification results, allowing cyberbullying sentiments on social media to be detected more accurately. Based on nine test scenarios, the final results showed that TF-IDF performed better than Word2Vec in this study, with an accuracy of 84%.    

The development of image processing technology today can create systems that are able to effectively recognize digital images, one of which is in the field of agriculture for plant disease identification. Citrus plants experience a decrease in productivity due to pathogen attacks on leaves such as Black Spot, Cancer, and CVDP so that disease identification is needed. The classification method that can be used to classify images is the K-Nearest Neighbor (K-NN) algorithm because it is simple and has high accuracy in image management. This study aims to implement and determine the performance of the K-NN algorithm in identifying citrus plant diseases based on leaf images. This research uses a dataset from the Kaggle website of 1,096 images. There are 12 research scenarios using the comparison between test data and training data as much as 4, namely (90% training data + 10% test data, 80% training data + 20% test data, 70% training data + 30% test data, 60% training data + 40% test data) and testing with 3 random state values (42, 32, 22). The results showed that the K-NN algorithm is very effective in identifying citrus plant diseases with the highest accuracy value in the 90% training data scenario and 10% test data with a value of K = 2 which is 98.5%.

This research explores the classification of brass instrument sounds using Convolutional Neural Network (CNN) combined with Mel-Frequency Cepstrum Coefficient (MFCC) feature extraction. This research aims to improve the accuracy of brass instrument sound recognition by utilizing CNN's ability to process audio data. Through experiments conducted with different audio durations and variations in CNN model architecture, this study evaluates the impact of dataset separation and model design on classification performance. The results show that dataset duration and CNN model architecture significantly affect classification accuracy, with the highest accuracy achieved in the scenario using 30 seconds of audio duration with an accuracy value of 84%. In addition, experiments varying the number of convolution layers in the CNN model show that the selection of the model architecture plays an important role in classification performance. Overall, this research contributes to advancing the field of audio classification by providing insight into the optimal dataset duration and model architecture for wind instrument speech recognition using CNNs.

Advertising as one of the forms of communication has an important role in introducing a product that is goods or services to the society. And advertising is one of the parts of the discourse, which is called the advertising discourses. This study aims to describe the assumption analysis in the Takaful Ikhlas 2024 publicity discourse. As for the method used in this research, it is qualitative descriptive. The source of the data used is data collected using the technique of logging and logging. The researchers took a video of the Takaful Ikhlas 2024 publicity, and then recorded all the announcements for classification and analysis. The subject of this study is Takaful Ikhlas 2024. Data analysis process using data reduction, data display (data presentation), conclusion withdrawal (verification). The results of the study found that there are six types of assumptions found: 1) factual assumption (following the vocabulary that can be considered as a fact), 2) non-factual (assuming not true), 3) structural (constantly and conventionally that the part of the structure has been assumed to be true), 4) lexical (interpreting not expressed as understood), 5) existential (associating the existence of an existence), and 6) contractual (not just untrue but the opposite of the truth or not of the fact).    

Digital Pathology Image Analysis (DPIA) is one of the areas where deep learning (DL) techniques offer modern, cutting-edge functionality. Convolutional Neural Network (CNN) technology outperforms the competition in classification, segmentation, and detection tasks while being just one of numerous DL techniques. Classification, segmentation, and detection methods can often be used to address DPIA concerns. Some difficulties can also be resolved using pre- and post-processing techniques. However, other CNN models have been investigated for use in addressing DPIA-related issues. Furthermore, the research seeks to explore how susceptible the model is to adversarial attacks and suggest strategies to counteract them. To predict ischemic strokes caused by blood clots, the authors of this study developed CNN with a pixel brightness transformation (PBT) technique for image enhancement and developed several approaches of image augmentation techniques to increase and provide the learning model with more diverse features. Also, adversarial training was integrated into CNN models to train the model with perturbed data in order to assess the impact of adversarial noise at different stages of training. Several metrics, including precision, F1-score, accuracy, and recall, are utilized to assess the experiments' effectiveness. The research findings indicate that employing transfer learning with a deep learning model achieved an accuracy of up to 97% using the ReLU activation function. Also, data augmentation helps improve the accuracy of the model.

Biology learning, particularly the topic of the classification of living organisms, is often considered difficult and boring by some students. To address this challenge, a more engaging and interactive approach is needed. One effective solution is to utilize game-based technology, such as Wordwall, which allows students to actively learn through various educational games. This study aims to enhance student engagement in learning the classification of living organisms using interactive Wordwall games. Through a community service method, this activity involved teachers and students from several schools to integrate Wordwall as a learning tool. The interactive games provided by Wordwall include various types of activities, such as puzzles, quizzes, and matching games, designed to help students better understand the concepts of classification of living organisms. The implementation of this program is expected to improve student motivation, involvement, and understanding of the material. Furthermore, it is hoped that the use of this technology will provide a more enjoyable learning experience and increase the effectiveness of classroom learning. The evaluation conducted shows a significant improvement in student engagement, as well as a better understanding of the material compared to traditional teaching methods.