Publication Search

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.

The study aimed to investigate the alkaloid content in cinnamon (Cinnamomum burmannii) powder using the Soxhlet extraction method. Alkaloids are organic chemical compounds widely found in nature as secondary metabolites in both plants and animals. They possess a cyclic structure containing one or more basic nitrogen atoms, conferring unique basic properties. The research was conducted to provide a deeper understanding of the potential utilization of plant-derived alkaloids, particularly from cinnamon, in drug development. The study sought to determine the color of the precipitate formed in the extraction solution after the addition of Mayer's reagent and to investigate the effect of the number of Soxhlet extraction cycles on the color of the ethanol used in the research with cinnamon samples. The findings from this study contribute to the exploration of the alkaloid content in cinnamon and its potential applications in pharmaceutical development.

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.

Introduction: Banana peel is an organic waste which is known to have various benefits, especially as an antidepressant for mental health. It inspired to conduct a research on various type of banana peels in Indonesia, particularly on Kepok banana which has been widely studied. This research aimed to prove the effect of Kepok banana peel extract (Musa paradisiaca L.) as an antidepressant in mice (Mus musculus) with acute restraint stress.Method: This research used a laboratory experimental design. The male mice were acclimatized for 3 days. Twenty-four mice were then divided evenly into 4 groups. The first group was given banana peel extract (Musa paradisiaca L.) at a dose of 200 mg / kgBW, the second group was given a dose of 400 mg / kgBB, the third group was given a dose of 800 mg / kgBW and the fourth group was given water as control. Each group was given a dose orally for 14 days and ARS depressed induction for 7 hours. Subsequently, mice were treated to assess depression behavior using the tail suspension test (TST) and forced-swim test (FST) to determine the duration of immobility.Result: The result showed that there was a significant difference (p<0.01) between the control group and the experimental group, at TST there was a significant difference (p<0.01) between two doses of 400 mg / kgBW and 800 mg / kgBW, as well as on the forced-swim test (FST). In addition, there was a significant difference (p<0.01) between two doses of 200 mg / kgBW and 800 mg / kgBW, and between two doses of 400 mg / kgBW and 800 mg / kgBW. Conclusion: These result confirmed that Kepok banana peel extract (Musa paradisiaca L.) was an effective antidepressant in reducing immobility duration with acute restraint stress.

Kemiri Village is one of the villages located in Sidoarjo Regency. Most of the people in Kemiri Village work in the agricultural sector and small MSMEs. One of the plants that is often found is the betel plant which grows in people's yards and has not been utilized optimally. The community service program carried out by National Defense Thematic Community Service (KKN) Group 5 Batch 2 UPN Veteran East Java students is a socialization and training program for making dishwashing soap made from betel leaves which is economically valuable. The method used in this service It goes through several stages, namely the preparation stage, implementation stage and evaluation stage. This activity was attended by PKK women from Kemiri Village who were enthusiastic and enthusiastic. The result of this activity is to provide knowledge and skills to residents to be able to utilize existing natural resources optimally so that the potential of betel leaves can be utilized more effectively. This does not rule out the possibility of producing products that have attractive sales potential, thereby creating new economic opportunities and increasing the welfare of the community in Kemiri Village, Sidoarjo.

Creativity is a human potential that does not come from outside the individual. Data collection techniques carried out in the form of documentation and extracting information about innovative methods and utilization of used goods. The results of this service activity are based on observations that have been made in Aman Damai Village Hamlet 3 Sirapit District, namely some of the results show positive because the manufacturing process does not take much time, in making bookshelves from cardboard children show enthusiasm for the directions delivered by the service team, positive reactions shown by children to interest in making bookshelves where almost all participants are able to make and decorate bookshelves well, children follow the mechanism of making products and are quite good at working with the team and children's creativity develops quite well. With used goods can increase income and can help the family economy.

Introduction: Knowledge of oral health is a person's ability to know everything about oral health. Actions that can be taken in oral and dental care, one of which is tooth extraction. Anxiety is most often experienced by some patients when performing dental treatment, especially when performing tooth extraction. Anxiety itself is characterized by negative feelings or emotions accompanied by body tension. In the field of dentistry, anxiety is referred to as dental anxiety. Objective of the study: To determine whether there is a relationship between the level of knowledge about tooth extraction and the patient's anxiety level. Materials and Methods: This study was conducted at the Specialized Dental Hospital (RSKDGM) in Makassar City. The method used was analytic observation with a cross sectional design. The measuring instrument used was a questionnaire designed to measure the level of knowledge and anxiety related to the tooth extraction procedure. Results: Based on the results of the Spearman correlation test, it shows a relationship value of 0.228 with a p-value of 0.038 which is smaller than 0.05 (p-value <0.05), these results indicate that there is a significant positive relationship between knowledge and anxiety. Conclusion: Based on the results of this study, it shows that the level of knowledge about tooth extraction has a significant relationship with the patient's anxiety level.

Illegal mining itself is a mining activity or extracting agricultural products carried out by the community or a business entity or we can call it a company where this activity does not have a business permit and also does not use the principles regarding how to mine in accordance with existing regulations or not. use mining methods properly and correctly. The basic mining laws that apply in Indonesia are stated in the Mining UlUl Number 3 of 2020 concerning amendments to UlUl Number 4 of 2009 concerning Mineral and Coal Mining, mining excavation itself consists of several types. Starting from strategic minerals or group a minerals, vital minerals or group c, and finally, group c minerals. In Indonesia itself we can certainly find cases of illegal mining in various regions, that is why enforcement efforts should be carried out as best as possible in order to reduce the growth rate of existing illegal mining which of course is to guarantee or increase state income through existing mining businesses. certainly legal in the eyes of the law.

To effectively comprehend human actions, we have developed a Deep Neural Network (DNN) that utilizes inner spatiotemporal non-locality to capture meaningful semantic context for efficient action identification. This work introduces the Top-Heavy CapsNet as a novel approach for video analysis, incorporating a 3D Convolutional Neural Network (3DCNN) to apply the thematic actions of local classifiers for effective classification based on motion from the spatiotemporal context in videos. This DNN comprises multiple layers, including 3D Convolutional Neural Network (3DCNN), Spatial Depth-Based Non-Local (SBN) layer, and Deep Capsule (DCapsNet). Firstly, the 3DCNN extracts structured and semantic information from RGB and optical flow streams. Secondly, the SBN layer processes feature blocks with spatial depth to emphasize visually advantageous cues, potentially aiding in action differentiation. Finally, DCapsNet is more effective in exploiting vectorized prominent features to represent objects and various action features for the ultimate label determination. Experimental results demonstrate that the proposed DNN achieves an average accuracy of 97.6%, surpassing conventional DNNs on the traffic police dataset. Furthermore, the proposed DNN attains average accuracies of 98.3% and 80.7% on the UCF101 and HMDB51 datasets, respectively. This underscores the applicability of the proposed DNN for effectively recognizing diverse actions performed by subjects in videos.

Nutrient Agar is a universal medium containing agar, meat extract, yeast extract and peptone. NA media is often made in large quantities, stored under sterile conditions, and then reheated when needed. Repeated heating can reduce the number of bacterial colonies that grow because the components that make up the media become damaged. This study aimed to determine the effect of repeated heating of NA (Nutrient Agar) media 4 times on the Total Plate Count (TPC) test results for Staphylococcus aureus and Escherichia coli bacteria. The number of bacteria that grew on the media with varying amounts of heating was calculated, and the results showed that repeated heating 4 times caused a decrease in the number of bacterial colonies that grew on the NA media. The ANOVA test gave a value of p = 0.000 for the two types of bacteria separately, which showed that there is a significant difference between the number of bacteria in varying amounts of media heating. This research concluded that repeated heating of NA (Nutrient Agar) media affects the TPC test results for Staphylococcus aureus and Escherichia coli.

During the period of compulsory education in Indonesia, which is 12 years, the government requires mathematics as the main learning subject for extracts which will continue to have an impact on people’s lives. The level of ability in a field of science must be measured to obtain valid data for the development of education in Indonesia. The use of Geogebra Mathematics Software in schools in Indonesia is not surprising at this time, technological developments have made the use of Geogebra mathematics software commonplace. This research is a Systematic Literature Review, in this research the author analyzes and compares several articles obtained from the internet or digital databases, for example Semantic Scholar or Sprinter Link. The articles that have been found are then selected according to the title researched, so that several reference articles are obtained. The research results show that the use of Geogebra mathematics software in learning has a great influence on students’ computing abilities. Geogebra is a media with a visual, analytical and numerical approach that can be solved using algorithms that require computational capabilities to operate. There is empathy in computational thinking, namely algorithmic thinking problem solving, pattern recognition, and abstraction and generalization.

The part of the basil plant is the leaves which have various types of benefits if studied further. With the introduction of secondary metabolites, it can be said that basil leaves contain eugenol compounds. The eugenol compound can be used as a reducing agent in the synthesis of TiO2 nanoparticles. The precursor used in the synthesis of TiO2 is titanium isopropoxide which has an oxidation state of +4. By utilizing the green synthesis method, TiO2 was reacted with basil leaf extract and then characterized using XRD and FTIR. The resulting particle size is 10.86 nm. And FTIR shows a wave number of 874.59 which represents the Ti-O functional group. Photocatalytic activity can take advantage of the synthesis of TiO2 nanoparticles by placing the nanoparticles in a methylene blue solution which has a concentration of 20 ppm and varies based on contact time and adsorbent mass. Photocatalytic activity testing obtained a degradation percentage of 79%-84% which varied based on adsorbant mass and contact time. Varying the adsorbant mass and time results in a degradation percentage that increases with each additional mass but will not increase again if it has reached the optimum phase and can reduce the degradation percentage.

This study proposes an approach for human fall classification utilizing a combination of Weighted Moving Average (WMA) and Convolutional Neural Networks (CNN) on the SisFall dataset. Falls among elderly individuals pose a significant public health concern, necessitating effective automated detection systems for timely intervention and assistance. The SisFall dataset, comprising accelerometer data collected during simulated falls and activities of daily living, serves as the basis for training and evaluating the proposed classification system. The proposed method begins by preprocessing accelerometer data using a WMA technique to enhance signal quality and reduce noise. Subsequently, the preprocessed data are fed into a CNN architecture optimized for feature extraction and fall classification. The CNN leverages its ability to automatically learn discriminative features from raw sensor data, enabling robust and accurate classification of fall and non-fall events. Experimental results demonstrate the efficacy of the proposed approach in accurately distinguishing between fall and non-fall activities, achieving high classification performance metrics such as accuracy, precision, recall, and F1-score. Comparative analysis with existing methods showcases the WMA-CNN hybrid approach's superiority in classification accuracy and robustness. Overall, the proposed methodology presents a promising framework for real-time human fall classification using sensor data, offering potential applications in wearable devices, ambient assisted living systems, and healthcare monitoring technologies to enhance safety and well-being among elderly individuals.

The lime plant with the Latin name Citrus Aurantifolia is a plant that grows widely in Indonesia. Lime can also be used as a cough medicine, phlegm buster, influenza medicine, acne medicine and many more. Apart from using natural materials, we also use fish scale waste. Milkfish scales contain 0.3% collagen. The collagen content can be used as anti-aging for the skin. To find out the stability test of the peel off gel mask, a combination of milkfish scales and lime, meets the criteria parameters for cosmetic preparations. The formulation of the peel off gel mask was carried out by modifying the formula into 3 (three) formulas with different concentrations of the extract to be used, namely F1 (1%), F2 (3%) and F3 (5%). This research began with collecting simplicia, extraction, making a peel-off gel mask and stability testing. The stability tests carried out were organoleptic, pH, dry preparation time and spreadability. In accordance with SNI masks 16-6070-1999. The stability test of the preparation was determined by storing the preparation for 21 days at different temperatures. The stability test is based on looking at the changes that occur starting from day 1 to day 21 of storage. The test results of the three peel-off gel mask formulations showed that the three temperatures on day 21 experienced changes in test parameters. The research results were analyzed using the SPSS Anova method.

The aim of this Systematic Literature Review research is to find a way that can help overcome the problems faced and identify different points of view regarding the problem being researched and reveal theories that are relevant to the problems in the research. The research method used is literature study. Electronic databases used by researchers include Google Scholar, Garuda. Next, all articles are extracted and only articles that are relevant and meet the inclusion criteria will be analyzed. The results of the research suggest that the main type of error in mathematical proof is conceptualization error. Students do not understand the meaning of the questions due to a lack of basic understanding and lack of literacy to understand the meaning of the questions given. This must be explored further to strengthen understanding of concepts and mastery of techniques and strategies in mathematical proof.

Sabu woven fabric is one of the cultural heritages of Sabu Island. In addition to being a cultural heritage, Sabu woven fabric is one of the handicrafts that still exist today which is preserved by Sabu women. Based on its manufacture, the classification process of Sabu woven fabric is based on color or motif identification. However, the classification process is not an easy process, because the classification process requires time and experts in the field of Sabu woven fabric. In addition to the classification process, the wider community also does not get much information about Sabu woven fabric clearly, because it is necessary to introduce the type of Sabu woven fabric, so that people can know or recognize the type of Sabu ikat woven fabric based on its type. Digital image processing techniques are utilized to build a system that can overcome the problems faced. Furthermore, image feature extraction will be carried out using gray level co-occurrence matrix (GLCM) with 4 features namely contrast, correlation, energy, and homogeneity with angles of 0°, 45°, 90°, and 135°. Each GLCM feature shows the same value even though the original image is rotated. After image feature extraction, the extracted data will be classified using the TensorFlow library. From these results it can be concluded that the program succeeded in selecting the type of Sabu ikat woven fabric class.

Profiling of corrupt perpetrators is done by looking for information such as office or profession, educational level, employment history and criminal background. Because increased tax receipts are not proportionate to the extraction of benefits to the public, it creates mistrust and reluctance to meet tax obligations. It endangers national security in many aspects, such as social, cultural, moral, political, and legal. Literature Review is an in-depth study of a particular topic with a qualitative approach. The purpose of this writing is to discuss and analyze further about the profiling of perpetrators and the massive impact caused by the case of Rafael Alun Trisambodo PNS class III in the General Directorate of Tax Kemenkeu who served as Head of the General Division of Kanwil DJP South Jakarta. His motive for corruption and money laundering was to enrich himself, his family, or anyone else by abusing office. The conclusion of this writing is that efforts to combat corruption are still not optimal as many sides tempt wealth and take advantage of opportunities.

The rapid advancement of deep learning technologies has significantly transformed healthcare analytics, particularly in medical data prediction and classification. This study proposes a hybrid Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) framework for multi-modal healthcare data analysis, integrating medical imaging, structured electronic health records (EHRs), and IoT-generated time-series physiological signals. The proposed architecture combines spatial feature extraction through CNN with temporal dependency modeling via LSTM to enhance predictive accuracy and clinical decision support. A quantitative experimental design was employed, utilizing multi-source healthcare datasets that underwent preprocessing, normalization, and feature engineering prior to model training. The performance of the hybrid model was evaluated using Accuracy, Precision, Recall, F1-Score, AUC-ROC, and Mean Absolute Error (MAE), and compared with conventional machine learning models and standalone deep learning architectures. Experimental results demonstrate that the proposed CNN–LSTM model achieves superior performance, with improved classification accuracy and reduced prediction error, while maintaining strong generalization capability. The findings indicate that integrating spatial and temporal feature learning significantly enhances disease detection, risk stratification, and personalized treatment planning. This approach supports the development of intelligent clinical decision support systems and scalable smart healthcare environments. The proposed framework offers a reliable and efficient solution for advanced healthcare analytics in IoT-enabled systems.

The rapid growth of social media platforms has generated massive volumes of unstructured textual data containing valuable information about public opinions and sentiments. Extracting meaningful insights from this data has become increasingly important for decision-making in various domains, including business, politics, and social analysis. This study aims to evaluate the effectiveness of deep learning techniques for sentiment analysis of social media data, focusing on Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and a hybrid CNN-LSTM model. A quantitative experimental approach is employed, where datasets are preprocessed through text cleaning, tokenization, and feature representation using word embeddings. The models are trained and evaluated using standard performance metrics, including accuracy, precision, recall, and F1-score. The results indicate that all models perform effectively in sentiment classification tasks, with the hybrid CNN-LSTM model achieving the highest performance due to its ability to capture both local textual features and long-term contextual dependencies. This demonstrates that combining CNN and LSTM architectures enhances classification accuracy compared to individual models. Furthermore, the findings confirm that deep learning approaches are more robust in handling the complexity and noisiness of social media data compared to traditional methods. This study contributes to the development of more adaptive and accurate sentiment analysis models and highlights the potential of hybrid deep learning architectures for real-world applications.

. This research investigates the correlation between mastery of idiomatic expressions and reading comprehension among tenth-grade students at one of high schools in Way Pengubuan during the second semester of the 2022/2023 academic year. Mastery of idiomatic expressions, which improves through childhood and adolescence into adulthood, is essential for accurate comprehension. Reading comprehension is the ability to extract specific information from texts. The study involved 138 students, with a sample of 64 selected through cluster random sampling. Data were collected via tests comprising 20 items each for idiomatic expression and reading comprehension, ensuring the validity of the test items. Analysis was conducted using SPSS 25.0. The findings revealed a high correlation between students' idiomatic expression mastery and their reading comprehension, with a correlation coefficient of 0.986, indicating a strong relationship. This suggests that proficiency in understanding idiomatic expressions significantly enhances reading comprehension.