10023 research outputs found
Sort by
Comparative study of ultrasonic and maceration extraction in enhancing antioxidant and SPF properties of green coffee beans serum
No full textThis study investigates the efficiency of maceration and ultrasonic extraction methods for
obtaining antioxidants from Arabica, Robusta, and Liberica green coffee beans. Ultrasonic
extraction demonstrated higher yields and enhanced antioxidant activity, with Liberica
exhibiting the most potent radical scavenging potential (lowest IC50 values), followed by
Robusta and Arabica in 45.3706 ppm, 46.6647 ppm, 49.4257 ppm. Formulated serums derived
from these extracts were evaluated for compliance with SNI 16-4399-1996 standards. Both
methods produced serums with acceptable texture, homogeneity, pH levels, and active
ingredient retention. However, ultrasonic-derived serums displayed superior microbial safety
profiles, with significantly lower total plate counts. Viscosity analysis revealed higher values
for maceration-derived serums, while Sun Protection Factor (SPF) evaluation indicated that
serum of Liberica extract provided the highest UV protection. These findings emphasize the
potential of ultrasonic extraction and Liberica green coffee beans in developing high-value
cosmetic and pharmaceutical products, paving the way for further research into optimized
extraction techniques and broader applications
Formula Misteri dalam Webtoon Kemala Karya Sweta Kartika, Dedy Koerniawan dan Pierre Rangga: Kajian Genre John G. Cawelti
Full text linkPenelitian ini bertujuan mengungkapkan formula misteri dan invensi yang terdapat
pada Webtoon Kemala karya Sweta Kartika, Dedy Koerniawan dan Pierre Rangga.
Webtoon ini merupakan cerita misteri horor. Teori yang digunakan adalah teori
formula dari John G. Cawelti. Jenis penelitian ini adalah penelitian deskriptif
kualitatif. Metode pengumpulan data yang dipakai melibatkan studi pustaka, baca,
simak,dan catat dari sumber-sumber pustaka yang relevan. Analisis data dilakukan
dengan menganalisis formula, invensi dalam Webtoon tersebut. Hasil analisis
menunjukkan bahwa formula misteri dalam Webtoon terdiri dari (1) pengenalan
detektif, (2) kejahatan dan petunjuk, (3) penyelidikan, (4) pengumuman solusi, (5)
penjelasan solusi, dan (6) akhir dari cerita. Bentuk invensi yang terdapat pada pola
cerita yaitu terdapat pengubahan alur atau struktur naratif yaitu pengenalan
detektif/tokoh utama. Penambahan alur atau struktur naratif yaitu menceritakan
asal muasal kehidupan tokoh utama sebelum meninggal
Aspek Nilai Pendidikan Karakter Islam dalam Novel Tanah Para Bandit Karya Tere Liye
No full textMuhammad Lutfi Nur Fauzi (1900031145) Program Studi Pendidikan Agama Islam, Fakultas Agama Islam, Universitas Ahmad Dahlan
Latar belakang ini adalah adanya karakter yang tidak berakhlak terpuji dan tidak adanya keadilan, maka penulis berusaha menganalisis novel Tanah Para Bandit, supaya bisa mengambil hikmah dari novel dan bisa diterapkan di kehidupan sehari-hari. Tujuan penelitian ini yaitu: (1) mengetahui nilai Pendidikan karakter Islam di dalam Novel Tanah Para Bandit, dan (2) untuk mengetahui relevansi Aspek Nilai Karakter Islam Dalam Novel Tanah Para Bandit dengan Pendidikan Agama Islam.
Di dalam skripsi ini menggunakan metode penelitian kualitatif deskriptif kajian pustaka (Library Research). Beberapa sumber data yang digunakan adalah primer dan skunder salah satunya adalah Novel dan referensi yang diambil dari literatur sesuai dengan penelitian.
Hasil penelitian ini menunjukkan bahwa: (1) Nilai Pendidikan karakter yang tertanam dalam novel Tanah Para Bandit seperti Didalam novel ini memberikan pembelajaran yang sangat berharga seperti: Sidik adalah orang yang jujur, Amanah artinya dapat dipercaya, fathonah berarti orang yang pandai atau cerdas, (2) Relevansi Aspek Nilai Karakter Islam Dalam Novel Tanah Para Bandit dengan Pendidikan Agama Islam, memiliki kesesuaian serta dapat membantu dalam pembelajaran karakter, dengan adanya penelitian ini para pembaca dan para guru bisa mengimplementasikan ke dalam kehidupan sehari-hari
Factors Influencing 5G Adoption in Java: A Theory of Consumption Value and Stimulus-Organism-Response Approach
Full text linkThe rapid advancement of information and communication technology has led to a significant transformation in telecommunication networks, particularly with the introduction of 5G technology, which offers high speed, low latency, and extensive device connectivity. However, the adoption of 5G in Indonesia, particularly in Java, remains challenging due to unequal network distribution and disparities in purchasing power between urban and rural areas. This study examines the key factors influencing consumer acceptance of 5G services in Java using the Theory of Consumption Value (TCV) and Stimulus-Organism-Response (SOR) framework. A descriptive quantitative approach was applied, collecting primary data from 200 respondents through purposive sampling. Data were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). The findings reveal that Safety Affordance and Facilitation Conditions significantly influence consumption value, whereas Visibility Affordance and Guidance Affordance do not. These results highlight the importance of security perceptions and supporting infrastructure in 5G adoption. This study contributes to the theoretical understanding of technology adoption by integrating TCV and SOR in the context of 5G and provides practical recommendations for policymakers and service providers to enhance 5G implementation, particularly by addressing infrastructure gaps in rural areas
Impact of Image Quality Enhancement Using Homomorphic Filtering on the Performance of Deep Learning-Based Facial Emotion Recognition Systems
Full text linkFacial emotion recognition technology is crucial in understanding human expressions from images or videos by analyzing distinct facial features. A common challenge in this technology is accurately detecting a person's facial expression, which can be hindered by unclear facial lines, often due to poor lighting conditions. To address these challenges, it is essential to improve image quality. This study investigates how enhancing image quality through homomorphic filtering and sharpening techniques can boost the accuracy and performance of deep learning-based facial emotion recognition systems. Improved image quality allows the classification model to focus on relevant expression features better. Therefore, this research contributes to in facilitating more intuitive and responsive communications by enabling system to interpret and respond to human emotions effectively. The testing used three different architectures: MobileNet, InceptionV3, and DenseNet121. Evaluasi kinerja dilakukan menggunakan metrik akurasi, presisi, recall, dan F1-score. Experimental results indicated that image enhancement positively impacts the accuracy of the facial emotion recognition system. Specifically, the average accuracy increased by 1-2% for the MobileNet architecture, by 5-7% for InceptionV3, and by 1-3% for DenseNet121
Optimizing Machine Learning-Based Network Intrusion Detection System with Oversampling, Feature Selection and Extraction
Full text linkNetwork security is a global challenge that requires intelligent and efficient solutions. Machine Learning (ML)-based Network Intrusion Detection Systems (NIDS) have been proven to enhance accuracy in detecting cyberattacks. However, the main challenges in implementing ML-based IDS are dataset imbalance and large dataset size. This research addresses these challenges by applying oversampling techniques to balance the dataset, feature selection using random forest to identify the most relevant features, and feature extraction using Principal Component Analysis (PCA) to further reduce the selected important features. Additionally, K-fold cross-validation is used to test the features to minimize bias and ensure the model does not suffer from overfitting, while Optuna is implemented to automatically optimize model parameters for maximum accuracy. Since IDS performance deteriorates with high-dimensional features, the combination of methods used is evaluated based on feature selection applied to the model using datasets wtih 45 features selected from UNSW-NB15, 78 features from CIC-IDS-2017, and 80 features from CIC-IDS-2018 using various ML algorithms. The results demonstrate that the combination technique with feature selection, along with maximum optimization for each model significantly improves performance on large and imbalanced datasets reaching 99% accuracy compared to conventional methods in network traffic analysis
Optimizing K-Nearest Neighbors with Particle Swarm Optimization for Improved Classification Accuracy
Full text linkThis study aims to improve the performance of the K-Nearest Neighbors (KNN) algorithm in classifying public reviews of Batik Madura through optimizing the K value using the Particle Swarm Optimization (PSO) algorithm. Public reviews collected from the Google Maps platform are used as a dataset, with positive, negative, and neutral sentiment categories. Optimization of the K value is carried out to overcome the constraints of KNN performance, which is highly dependent on the K parameter, with PSO providing a more efficient approach than the grid search method. However, PSO also presents challenges such as sensitivity to parameter tuning and potential computational overhead. This study has succeeded in developing a web-based system using the Python Streamlit framework, which makes it easy for users to access sentiment analysis results. Testing shows that optimizing the K value with PSO increases the accuracy of KNN to 88.5% with an optimal K value of 19. However, this accuracy is not compared to other optimization techniques, leaving its relative advantage unverified. The results are expected to help Batik Madura entrepreneurs in evaluating public perception and guiding strategic innovations. Research outputs include a prototype, intellectual property registration, and journal publication, although the role of deep learning models is only briefly noted without further development
Impact of Cosine Similarity Function on SVM Algorithm for Public Opinion Mining About National Sports Week 2024 on X
Full text linkPublic opinion on PON 2024 (National Sports Week in Indonesia) became a trending topic on X (formerly Twitter), reflecting both positive and negative sentiments. Understanding these sentiments is important for evaluating the event and preparing for the upcoming. However, baseline SVM algorithms using standard kernel functions are not optimized for text similarity and limit performance in sentiment analysis. This research proposes cosine similarity as a substitution for the kernel function on SVM, enhancing the sentiment analyzer's performance on public opinions about PON 2024. The approach leverages cosine similarity's strength in handling text-based data. The key contribution of this research is the integration of cosine similarity into the SVM algorithm as a replacement for kernel functions, improving performance in sentiment analysis. Additionally, this study offers a comprehensive comparison with baseline SVM and provides actionable insights for upcoming PON. The study collected 1,011 tweets related to PON 2024 using web scraping and the Twitter API, followed by labeling sentiments as positive, neutral, or negative. Several preprocessing techniques also were applied to prepare the data. Two models were developed: baseline SVM and another using SVM integrated with cosine similarity, both evaluated through accuracy, precision, recall, and F1-score. The baseline SVM achieved 85.1% accuracy, 85% precision, 83% recall, and 83.3% F1-score, struggling particularly with negative sentiment. Opposite, by integrating cosine similarity on SVM, the performance improved to 88.73% accuracy, 88.3% precision, 89.3% recall, and 88.3% F1-score—a boost of 3.3-6.3%. Additionally, the public opinion revealed that positive sentiments mostly focused on athlete achievements and medal awards, while negative sentiments highlighted issues like referee performance and specific sports (e.g., football). This approach can serve as a valuable tool for event organizers to identify public concerns and maintain positive aspects for the upcoming PON 2028
Depression Detection on Social Media X Using Hybrid Deep Learning CNN-BiGRU with Attention Mechanism and FastText Feature Expansion
Full text linkDepression is a global mental health disorder affecting over 280 million people, with significant challenges in identifying sufferers due to societal stigma. In Indonesia, the National Adolescent Mental Health Survey in 2022 revealed that 17.95 million adolescents experience mental health disorders, with a portion of them suffering from depression. Social media platform X offers an alternative for individuals to share their mental health status anonymously, bypassing societal stigma. This study proposes a hybrid deep learning model combining CNN and BiGRU with an attention mechanism, TF-IDF for feature extraction, and FastText for feature expansion to detect depression in Indonesian tweets. The dataset comprises 50,523 Indonesian tweets, supplemented by a similarity corpus of 151,117 data. To optimize model performance, five experimental scenarios were conducted, focusing on split ratios, n-gram configurations, maximum features, feature expansion, and attention mechanisms. The main contribution of this research is the novel integration of FastText for feature expansion and the attention mechanism within a CNN-BiGRU hybrid model for depression detection. The results demonstrate the effectiveness of this combination, with the BiGRU-ATT-CNN-ATT model achieving an accuracy of 84.40%. However, challenges such as handling noisy, ambiguous social media data and addressing out-of-vocabulary words remain. Future research should explore additional feature expansion techniques, optimization algorithms, and approaches to handle noisy data, improving model robustness for real-world applications in mental health detection