UIN (Universitas Islam Negeri) Sunan Kalijaga, Yogyakarta: E-Journal Fakultas Sains dan Teknologi
Not a member yet
1440 research outputs found
Sort by
Integrating Retrieval-Augmented Generation with Large Language Model Mistral 7b for Indonesian Medical Herb
No full textLarge Language Models (LLMs) are advanced artificial intelligence systems that use deep learning, particularly transformer architectures, to process and generate text. One such model, Mistral 7b, featuring 7 billion parameters, is optimized for high performance and efficiency in natural language processing tasks. It outperforms similar models, such as LLaMa2 7b and LLaMa 1, across various benchmarks, especially in reasoning, mathematics, and coding. LLMs have also demonstrated significant advancements in addressing medical queries. This research leverages Indonesia’s rich biodiversity, which includes approximately 9,600 medicinal plant species out of the 30,000 known species. The study is motivated by the observation that LLMs, like ChatGPT and Gemini, often rely on internet data of uncertain validity and frequently provide generic answers without mentioning specific herbal plants found in Indonesia. To address this, the dataset for pre-training the model is derived from academic journals focusing on Indonesian medicinal herbal plants. The research process involves collecting these journals, preprocessing them using Langchain, embedding models with sentence transformers, and employing Faiss CPU for efficient searching and similarity matching. Subsequently, the Retrieval-Augmented Generation (RAG) process is applied to Mistral 7b, allowing it to provide accurate, dataset-driven responses to user queries. The model\u27s performance is evaluated using both human evaluation and ROUGE metrics, which assess recall, precision, F1 measure, and METEOR scores. The results show that the RAG Mistral 7b model achieved a METEOR score of 0.22%, outperforming the LLaMa2 7b model, which scored 0.14%
Microtremor Microzonation Based on Seismic Vulnerability Index (Kg) Using HVSR (Horizontal To Vertical Spectral Ratio) Method in Kapanewon Berbah, Sleman, D.I.Yogyakarta: Mikrozonasi Mikrotremor Berdasarkan Indeks Kerentanan Seismik (Kg) Menggunakan Metode HVSR (Horizontal To Vertical Spectral Ratio) di Kapanewon Berbah, Sleman, D.I.Yogyakarta
No full textThe 2006 Bantul Earthquake centered on the Opak River Fault has caused many casualties and damage to buildings, including in Kapanewon Berbah, Sleman. Kapanewon Berbah is the most affected area in Sleman Regency, because it is located in the red zone near the Opak Fault line. This study uses the HVSR (Horizontal to Vertical Spectral Ratio) method which aims to determine the soil conditions in Kapanewon Berbah based on the dominant frequency and dominant period microzonation, as well as to determine the level of damage based on the dominant amplification value and the seismic vulnerability index. The microtremor data measured at 17 points are processed in geopsy software so that the dominant frequency and amplification values are obtained. Furthermore, the calculation is carried out on Microsoft Excel in order to obtain the value of the dominant period and the seismic vulnerability index. The dominant period is inversely proportional to the dominant frequency value, while the seismic vulnerability index value is obtained from squaring the amplification divided by the dominant frequency. These parameters are processed in surfer12 software in order to obtain a microzonation map based on each parameter. Based on the Kapanewon Berbah microzonation map, a low dominant frequency value is obtained in the range 0.65 - 2.02 hz which shows soft soil conditions in the form of thick sediment; high dominant period values in the range 0.88-1.46 s which indicates very soft soil conditions; high amplification values at the range 4.9-6.1 includes a high level of damage; and the high seismic vulnerability index value is in the range 18.9 to 41.5. The most stable location is at the TA4 measurement point in Tegaltirto Village and the most prone location to experience damage is at the TA2 measurement point in Kalitirto Village
Sentiment Analysis of PeduliLindungi User Using Naïve Bayes Classifier Algorithm and Support Vector Machine
No full textThe Indonesian government is attempting to track the spread of the virus by creating an application named “PeduliLindungi” to deal with the coronavirus\u27s exponential increase in cases across the country. Because it has a feature to disclose the user\u27s location immediately, it is envisaged that this program can reduce the transmission of viruses in monitoring. Indonesians have used the PeduliLindungi, and there are user reviews of both positive and negative experiences. Therefore, to enhance these services, an assessment is required. The text mining method can extract information from users\u27 reviews to collect this data. This method\u27s application additionally uses the Naive Bayes Classifier and Support Vector Machine algorithms, which analyze word associations and do a classification evaluation of the data\u27s accuracy. Based on the two methods\u27 calculations, the NBC algorithm\u27s average classification accuracy was 83.81%, and the SVM algorithm was 93.84%. Following that, discoveries on words that frequently exist or are used by people are obtained through word associations in the sentiment analysis of positive or negative reviews
The Halal Tourism Preferences: The Role of Brand Awareness, Attitudes, and Social Norms Among Muslim and Non-Muslim Travelers
No full textThis research focuses on the influence of brand awareness, attitudes, and social norms on the intentions of Muslim and non-Muslim tourists to visit Lombok as a Halal tourism destination. Lombok has been designated by the Indonesian government as a center for Islamic tourism, providing a complementary option to Bali’s Hindu cultural tourism. The study utilized the Theory of Planned Behavior and gathered data via an online survey involving 123 participants, 56 non-Muslims and 67 Muslims. The results indicated that Halal brand awareness and social norms did not significantly impact non-Muslim tourists\u27 intentions to visit Lombok. At the same time, brand awareness also did not affect Muslim tourists. Attitudes were identified as the main factor influencing their willingness to visit. Interestingly, the R-squared values differed notably between the two groups, with the variables accounting for 58.1% of non-Muslim tourists\u27 decisions but only 39.9% for Muslim tourists. This research offers new insights into Halal tourism from both Muslim and non-Muslim perspectives
K-Means Clustering of Social Studies Performance at Junior High School
No full textThis study aims to optimize the use of technology in evaluating student performance by grouping students based on their abilities. The main issues include the underutilization of technology, the absence of an appropriate evaluation system for different levels of student ability, and ineffective methods for grouping students. The K-Means Clustering algorithm was chosen because it has proven effective in grouping academic data in various studies. The data used includes Daily Knowledge Scores (DKS), Daily skill scores (DSS), Mid-term Summative Scores (MSS), End-of-Year Summative Scores (ESS), and Grade Report (GR). The data was analyzed using the CRISP-DM methodology with the help of RapidMiner. The results showed that 28.63% of students were classified as having excellent performance, 50.21% as having good performance, and 21.16% as having moderate performance. The Davies-Bouldin Index score of 1.713 for K=3 was considered sufficient for distinguishing the different student performance groups. The results of this study are expected to help schools provide learning support that better aligns with student needs. Future research is recommended to focus on optimizing the number of clusters (K), applying this method to other subjects, and integrating it with e-learning platforms for real-time student performance monitoring
Keanekaragaman Kupu-Kupu (Lepidoptera: Rhopalocera) di Kawasan Ekowisata Dusun Kaliurang Timur, Yogyakarta
No full textButterflies act as bioindicators and pollinators of the environment. Ecotourism development poses a threat to butterfly life due to high human activity and land degradation. This study aims to determine the diversity of butterflies (Rhopalocera), diversity index, evenness index, dominance index, similarity index, and abiotic parameters at each sampling location. The data was collected at Tlogo Putri, settlements, and Tankaman Natural Park, whose location selection was based on purposive sampling and using the point count method. Based on the research obtained 55 species with a total of 294 individuals, diversity index (TP: 2.88; P: 2.51; TNP: 2.66), evenness index (TP: 0.86; P: 0.75; TNP: 0.84), dominance index (TP: 0.08; P: 0.14; TNP: 0.09), species similarity index (TP & P: 46.42; TP & TNP: 27.45). Abiotic parameters in the ecotourism area of Kaliurang Timur Hamlet are altitude of 814-889 meters above sea level, temperature of 26-28°C, air humidity of 10-45%, light intensity of 7571-4877x10 lux, wind speed of 0-1 m/s, and rainfall of 0-20. The conclusion of this study is that 55 species of Rhopalocera order were found, the diversity index is moderate, the evenness index is high, the dominance index and the similarity index are low at each sampling location. Abiotic parameters measured were in the normal range for Rhopalocera life in the ecotourism area of Kaliurang Timur Hamlet
Klasifikasi Buah dan Sayuran Segar atau Busuk Menggunakan Convolutional Neural Network
No full textFresh fruits and vegetables contain many nutrients, such as minerals, vitamins, antioxidants, and beneficial fiber, superior to those found in rotten or almost rotten produce. On the other hand, fruits and vegetables that are nearly spoiled or already rotten have significantly lost their nutritional value. Rotten produce also harbors bacteria and fungi that can lead to infections and food poisoning when consumed. Convolutional Neural Network (CNN) offers a programmable solution for classifying fresh and rotten fruits and vegetables. Image processing using the TensorFlow library is employed in this classification process. During testing on the training data, the CNN achieved an accuracy of 90.42%. In comparison, the validation accuracy reached 94.21% when using the SGD optimizer, 20 epochs, a batch size 16, and a learning rate of 0.01. For the testing data, the accuracy obtained was 80.83%
Pelabelan Sentimen Berbasis Semi-Supervised Learning menggunakan Algoritma LSTM dan GRU
No full textIn the sentiment analysis research process, there are problems when still using manual labeling methods by humans (expert annotation), which are related to subjectivity, long time, and expensive costs. Another way is to use computer assistance (machine annotator). However, the use of machine annotators also has the research problem of not being able to detect sarcastic sentences. Thus, the researcher proposed a sentiment labeling method using Semi-Supervised Learning. Semi-supervised learning is a labeling method that combines human labeling techniques (expert annotation) and machine labeling (machine annotation). This research uses machine annotators in the form of Deep Learning algorithms, namely the Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) algorithms. The word weighting method used in this research is Word2Vec Continuous Bag of Word (CBoW). The results showed that the GRU algorithm tends to have a better accuracy rate than the LSTM algorithm. The average accuracy of the training results of the LSTM and GRU algorithm models is 0.904 and 0.913. In contrast, the average accuracy of labeling by LSTM and GRU is 0.569 and 0.592, respectively
Analisis Malware Hummingbad Dan Copycat Pada Android Menggunakan Metode Hybrid
No full textPerkembangan teknologi yang terus berlanjut dapat menjadi ancaman di dunia maya, terutama dalam hal kejahatan cyber. Kemudian tingkat popularitas smartphone serta jumlah penggunanya meningkat dari tahun ke tahun. Sementara itu, smartphone dengan platform android masih menduduki peringkat pertama dalam persentase pengguna tertinggi di dunia. Karena itu, jumlah malware dan serangan berbahaya di platform android semakin meningkat. Pengembang aplikasi penipuan ini mengeksploitasi kekurangan platform android dengan menyuntikkan malware sebagai kode sumber ke dalam aplikasi android dan menyebarkannya melalui blog atau pasar aplikasi android. Teknik yang digunakan dalam penelitian ini adalah teknik hybrid yang menggabungkan metode statis dan dinamis. Penelitian ini menggunakan contoh malware HummingBad dan CopyCat. Penelitian ini memiliki tujuan untuk melakukan identifikasi dan analisis pada malware HummingBad dan CopyCat menggunakan metode hybrid menggunakan mobile security framework. Analisis yang dilakukan pada sampel malware HummingBad dan CopyCat menunjukkan bahwa sampel malware HummingBad memiliki tingkat keamanan 27/100 sedangkan untuk sempel malware CopyCat memiliki tingkat keamanan 38/100.
Kata kunci: android, static, dynamic, analysis hybrid, malware
----------------------------------------------------------
The continued development of technology can become a threat in cyberspace, especially in terms of cyber crime. Then the level of popularity of smartphones and the number of users increases from year to year. Meanwhile, smartphones with the android platform are still ranked first in the highest percentage of users in the world. Because of this, the number of malware and malicious attacks on the android platform is increasing. Developers of these deceptive apps exploit the flaws of the android platform by injecting malware as source code into Android apps and spreading it via blogs or android app marketplaces. The technique used in this study is a hybrid technique that combines static and dynamic methods. This study uses the examples of HummingBad and CopyCat malware. This study aims to identify and analyze the hummingbad and copycat malware using a hybrid method using the mobile security framework. The analysis conducted on the HummingBad and CopyCat malware samples shows that the HummingBad malware samples have a security level of 27/100 while the CopyCat malware samples have a security level of 38/100.
Keywords: android, static, dynamic, analysis hybrid, malwar
Analisis Dan Pengukuran Quality Of Service (Qos) Jaringan 4G (Operator Telkomsel, Xl, Dan Indosat)
No full textTeknologi jaringan komunikasi merupakan serangkaian komponen teknologi yang saling berhubungan antara satu dengan yang lainnya. Salah satu di antaranya yang banyak di gunakan dalam kehidupan sehari-hari yaitu teknologi jaringan 4G. Dengan adanya jaringan tersebut akan mempermudah kebutuhan akan internet sehari-harinya. Namun perbedaan kecepatan dalam mengakses perlu akan adannya pengujian dan pembahasan suatu jaringan dalam layanan yang baik dan juga perlu adanya layanan Quality Of Service(QOS) yang baik pula. Dalam pengujian Teknologi jaringan 4G ini berfokus hanya pada lima parameter QOS saja yaitu : Throughput, Delay, Jitter, Packet loss dan Bandwidth. Dalam pengukuran performa teknologi jaringan 4G menggunakan layanan Quality Of Service (QOS), analisa dan pengujian yang di lakukan untuk mengetahui reperentasi pada kondisi jaringan pada saat ini. Dari hasil penelitian ini, didapatkan perbedaan yang tidak begitu signifikan antara masing-masing operator jaringan. Meski tidak begitu signifikan operator jaringan TELKOMSEL memiliki hasil yang lebih baik di banding operator XL maupun INDOSAT. Dari hasil penelitian ini dari ketiga operator jaringan tersebut dapan di gunakan sebagai pertimbangan bagi user dalam memilih penggunaan internet sesuai dengan kebutuhan masing-masing.
Kata kunci: QOS, jaringan 4G, Telkomsel, Xl, Indosat
--------------------------------------------------------
Communication network technology is a series of technological components that are interconnected with one another. One of them that is widely used in everyday life is 4G network technology. With this network, it will facilitate the need for daily internet. However, the difference in speed in accessing the need for testing and discussing a network in good service and also the need for good Quality Of Service (QOS) services as well. In testing 4G network technology, it focuses only on five QOS parameters, namely: Throughput, Delay, Jitter, Packet loss and Bandwidth. In measuring the performance of 4G network technology using Quality Of Service (QOS) services, analysis and testing are carried out to determine the representation of current network conditions. From the results of this study, it was found that the difference between each network operator was not so significant. Although not so significant, TELKOMSEL network operators have better results than XL and INDOSAT operators. From the results of this study of the three network operators can be used as a consideration for users in choosing internet usage according to their individual needs.
Keywords: QOS, 4G Network, Telkomsel, Xl, Indosa