Jurnal Ilmiah Universitas Islam Balitar
Not a member yet
2054 research outputs found
Sort by
Implementasi Metode Naïve Bayes dan Certainty Factor pada Sistem Pakar Untuk Diagnosa Awal Penyakit Gigi dan Mulut
Get PDFGigi dan mulut merupakan bagian tubuh yang sering kurang dijaga kesehatannya. Penyakit gigi dan mulut sendiri sering dianggap sepele oleh masyarakat, padahal jika tidak segera ditangani maka dapat menyebabkan penyakit jantung dan stroke. Jumlah penyebaran dokter gigi dan mulut yang tidak merata menyebabkan masyarakat sulit untuk dapat memeriksakan kesehatan gigi dan mulut. Oleh karena itu, diharapkan dengan adanya penelitian ini dapat membantu masyarakat khusunya yang tidak terjangkau oleh seorang pakar gigi dan mulut untuk dapat mengetahui diagnosa awal penyakit gigi dan mulut yang diderita serta saran yang dapat diberikan. Pada sistem ini digunakan metode dalam proses diagnosanya, yaitu metode naïve bayes – certainty factor. Naïve Bayes sendiri diterapkan untuk mencari nilai probabilitas tiap gejala terhadap suatu penyakit sedangkan metode certainty factor digunakan untuk menentukan nilai keyakinan dari penyakit yang telah diketahui dari hasil nilai bobot yang diberikan oleh pakar dan bobot oleh pengguna. Data yang digunakan pada sistem ini terdapat 10 jenis penyakit dan 44 gejala penyakit gigi dan mulut. Proses Pengujian sistem ini dilakukan 2 tahap yaitu blackbox testing dan uji akurasi sistem. Hasil dari uji akurasi sistem diperoleh akurasi sebesar 95% dari 20 data uji manual yang dilakukan oleh pakar
PERBEDAAN FEEDER SPACE TERHADAP PERTAMBAHAN BOBOT BADAN DAN KESERAGAMAN AYAM PETELUR
Get PDFThis study aims to determine the differences in feeder space on weight gain and uniformity of laying hens in the grower phase of the closed house system. The study was conducted in a closed house owned by PT Jatinom Indah Farm with 180 Isa brown chicken strains in Slorok Village, Doko District, Blitar Regency, which began on February 25, 2024 and ended on April 28, 2024. The experiment was conducted using the Posttest-Only Control Design method where the treatment was only in the experimental class and the control class was used for comparison objects. Observations were made after the chickens were 7 weeks to 16 weeks old. The observation parameters included weight gain and uniformity. The results showed that the treatment using different feeder spaces did not show a significant value on the weight gain of laying hens in the grower phase (P> 0.05). With the average result of weight gain of the control class of 82.76 gr and in the experimental class of 82.39 gr. However, the treatment with different feeder space showed a significant value on the uniformity of laying hens in the grower phase (P <0.05). With the average result of uniformity of the control class of 86.94% and in the experimental class of 93.47%
UJI ORGANOLEPTIK YOGHURT DARI SUSU KAMBING PE (PERANAKAN ETAWA) DENGAN SUBSTITUSI KAYU MANIS (CINNAMOMUM VERUM)
Get PDFThis study evaluates the effect of adding cinnamon on the organoleptic quality of yogurt made from Peranakan Etawa (PE) goat milk. A Completely Randomized Design (CRD) method was used to manage variations between samples, and Analysis of Variance (ANOVA) was employed to determine significant differences between treatments. The findings revealed no statistically significant differences in organoleptic aspects such as visual appearance, aroma, color, and texture. However, panelists preferred yogurt with 2.5% cinnamon, indicating that this concentration may enhance the sensory appeal of yogurt by imparting a warm aroma and sweet flavor. The results suggest that while no significant differences were observed, the addition of cinnamon at this level can improve the overall sensory experience. Future research is recommended to explore a wider range of cinnamon concentrations and different types of cinnamon, as well as using a larger and more diverse panel to obtain more representative data
KARAKTERISTIK ORGANOLEPTIK KOMPOS BERBAHAN DASAR LIMBAH BAGLOG JAMUR TIRAM DAN KOHE KAMBING
Get PDFThe purpose of this research is to explore the production of compost from goat manure with the addition of oyster mushroom substrate (baglog) and EM4. Composting is an effective method of recycling organic waste and improving soil fertility, making it a vital aspect of sustainable agriculture. This study focuses on determining the best mixture of goat manure and baglog in producing high-quality compost, which could serve as an alternative to chemical fertilizers. The research method utilized involved distributing questionnaires to 47 panelists who were tasked with evaluating the quality of the compost based on three sensory attributes: texture, color, and odor. These attributes are critical indicators of compost maturity and usability in agricultural applications. Each treatment was repeated three times to ensure consistent and reliable results. The organoleptic (sensory) test results indicated that the best treatment was P2, which contained 50% goat manure and 50% baglog. This mixture produced compost with the most favorable characteristics in terms of texture, color, and odor compared to other treatments. The combination of organic materials appeared to complement each other well, creating a balanced compost suitable for improving soil quality and plant growth. It is recommended that future research include laboratory tests to analyze the nutrient composition of the compost more precisely. Additionally, field trials should be conducted to test the compost\u27s effectiveness in various agricultural settings and crops, ensuring its practicality as a sustainable alternative to synthetic fertilizer
Sentiment Analysis On Evos Esports Team Instagram Social Media Using Convolutional Neural Network (CNN)
Get PDFThe rapid growth of the esports industry in Indonesia presents unique challenges for professional teams such as EVOS Esports, particularly in strengthening fan engagement and loyalty in the digital era. This study aims to analyze fan sentiment toward the official Instagram posts of EVOS Esports using a deep learning approach with a Convolutional Neural Network (CNN). The research process involved data collection through web scraping, followed by preprocessing stages such as cleaning, case transformation, normalization, tokenization, stopword removal, and stemming. The dataset was then labeled, split into training and testing sets (90:10), and used for CNN model training and evaluation through a confusion matrix. The results demonstrate that the CNN model successfully classified comments into three sentiment categories—positive, negative, and neutral—with an accuracy of 92%. The model also achieved a precision of 0.92, recall of 0.92, and an F1-score of 0.92, indicating very good classification performance. Sentiment distribution analysis of 11,305 comments showed that neutral sentiment dominated (47.24%), followed by positive (30.12%) and negative (22.64%). These findings provide valuable insights into fan perceptions of esports team performance on social media. For future research, expanding the sentiment lexicon with terms commonly used in online communities is recommended to further enhance classification accuracy
The Implementation of Canva Application to Enhance Students\u27 Creativity in Graphic Design at SMPIT Tenggarong Seberang
No full textThis study examines the effectiveness of the Canva application as an instructional tool to enhance creativity among seventh-grade students in graphic design at SMP IT Tenggarong Seberang. Employing a Classroom Action Research (CAR) methodology, the research was conducted over two cycles involving 44 students. The first cycle revealed that the integration of Canva did not significantly improve student engagement or creativity, with an average participation rate of 56% and an average score of 67.95. Consequently, modifications were made for the second cycle, focusing on clearer instruction and increased student interaction. The results of the second cycle demonstrated substantial improvements, achieving an 84% participation rate and an average score of 83.4, indicating that most students met the mastery criteria. Observations showed enhanced creativity in students’ graphic design projects, highlighting the positive impact of using technology in the classroom. This study underscores the potential of Canva as a versatile educational tool that fosters creativity and engagement, making it beneficial for modern educational practices. Future research may investigate the long-term effects of such applications on student learning outcomes across various subjects and educational levels
Development of Animated Comic Media Containing Local Wisdom "Learning the Culture of Dam Bagong Trenggalek" to Improve Cultural Literacy Students Grade IV Elementary School
Get PDFCultural literacy is an important part of learning to support the Independent Curriculum, especially on the theme of exploring local wisdom. However, the younger generation\u27s attention to local culture is decreasing due to modern developments. This study aims to develop an animated comic media containing local wisdom "Learning the Culture of Dam Bagong Trenggalek" to improve the cultural literacy students grade IV elementary school. The method used is Research and Development (R&D) with the ADDIE development model. The research sample consisted of 90 students from four elementary schools in Trenggalek District, namely SDN 2 Ngantru, SDN 2 Surodakan, SDN 1 Sumbergedong, SDN 3 Tamanan with a purposive sampling technique. Data collection techniques included observation, interviews, questionnaires, tests, and documentation. The validation results showed a score of 93% for media experts, 92.5% for material experts, and 92.5% for language experts, which is classified as very valid. The practitioner\u27s assessment obtained a score of 97.5% and is classified as very practical. The effectiveness test showed an increase in pretest and posttest results of 32.5% on a field scale. The hypothesis test showed a significance value of 0.000 < 0.05. The N-Gain value of 86.12 is included in the high category. Student responses to the media reached 99.34% and were classified as very interesting. The results of the study concluded that the animated comic media containing local wisdom "Learning the Culture of Dam Bagong Trenggalek" is very valid, practical, interesting, and effective in improving the cultural literacy students grade IV elementary school
Sentiment Analysis Of Mie Gacoan Reviews In Blitar City On The Grab Application Using The Support Vector Machine Method
Get PDFThis study aims to analyze customer review sentiments for Mie Gacoan restaurant in Blitar City through the Grab application using the Support Vector Machine (SVM) algorithm. Customer reviews are categorized into three sentiment classes: positive, negative, and neutral. And the total amount of data used is 991 data. The research process includes manual data collection, text preprocessing, weighting using the TF-IDF method, and classification with the SVM algorithm. Model performance is evaluated using a confusion matrix with precision, recall, and F1-score metrics. And for the testing of the algorithm method using Grid Search and Cross Validation. The results show that the linear kernel achieves the best performance with an F1-score of 0.4649. Positive sentiment dominates the reviews, while negative and neutral sentiments are less prevalent. This study demonstrates that SVM is effective for classifying sentiments in customer reviews and can assist restaurant managers in identifying areas for service improvement
SENTIMENT ANALYSIS MODEL ON ELECTRIC VEHICLES USING INDOBERTWEET AND INDOBERT ALGORITHM
No full textThe increasing adoption of electric vehicles in Indonesia has sparked various public opinions, necessitating sentiment analysis to understand societal perspectives. This study aims to compare the performance of two transformer-based models, IndoBERTweet and IndoBERT, in analyzing sentiments towards electric vehicles in Indonesia. Using a dataset collected from Indonesian language tweets and online comments, the data undergoes preprocessing, sentiment labelling into positive, negative, and neutral sentiments, and subsequent fine-tuning of both models. The models are evaluated based on accuracy, precision, recall, and F1-score. Experimental results demonstrate that IndoBERTweet achieves superior performance compared to IndoBERT in sentiment classification. The best performance recorded for IndoBERTweet was an accuracy of 82,40%, with an F1-score of 82,39%, while IndoBERT achieved an accuracy of 75,98% and an F1-score of 75,46%. These findings highlight the importance of using domain-spesific models for sentiment analysis and contribute to advancements in Indonesia-language natural language processing (NLP).Adopsi kendaraan listrik yang semakin meningkat di Indonesia telah memunculkan berbagai opini publik, sehingga diperlukan analisis sentimen untuk memahami perspektif Masyarakat. Penelitian ini bertujuan untuk membandingkan performa dua model berbasis transformer, yaitu IndoBERTweet dan IndoBERT dalam menganalisis sentimen terhadap kendaraan listrik di Indonesia. Dataset dikumpulkan dari tweet atau komentar online berbahasa Indonesia. Data ini kemudian melalui tahap prapemrosesan, pelabelan sentimen menjadi sentiment positif, netral, dan negative, serta fine-tuning pada kedua model. Model dievaluasi berdasarkan akurasi, presisi, recall, dan F1-score. Hasil eksperimen menunjukkan bahwa IndoBERTweet memiliki performa lebih baik dibandingkan IndoBERT dalam klasifikasi sentimen. Performa terbaik yang dicapai IndoBERTweet adalah akurasi sebesar 82,40% dengan F1-score sebesar 82,39%. Sedangkan, IndoBERT mencapai akurasi sebesar 75,98% dengan F1-score sebesar 75,46%. Penelitian ini menyoroti pentingnya penggunaan model domain spesifik untuk analisis sentiment dan berkontribusi pada kemajuan natural language processing (NLP)
IDENTIFIKASI TEKNIK SAMBUNGAN KAYU PADA ARSITEKTUR VERNAKULAR LAMBAN PESAGI DI LAMPUNG
Get PDFVernacular architecture represents the physical embodiment of local wisdom shaped by adaptation to environmental conditions, cultural practices, and available materials. One example of such architecture in Indonesia is Lamban Pesagi, the traditional house of the Lampung Pepadun ethnic group, which holds significant historical, cultural, and technical value. This study aims to identify and analyze the wooden joinery systems employed in the construction of Lamban Pesagi as part of efforts to preserve traditional building techniques increasingly threatened by modernization. The research adopts a qualitative, descriptive-analytical approach through field observation, visual documentation, technical sketching, and literature review. The object of study is a Lamban Pesagi structure relocated to the Lampung Museum. The findings reveal a variety of joinery techniques, including mortise-and-tenon joints, wooden pegs, ornamental clamped joints, oblique mortise-and-tenon, and lashed joints. Each joint type serves specific structural functions according to its location in the foundation, mid-structure, or roof zone and demonstrates a high level of technical sophistication. These techniques not only ensure structural strength and stability but also provide lateral flexibility and efficient use of local materials. The identified joinery systems exhibit strong potential for integration into contemporary timber construction practices focused on sustainability. The documentation and analysis of these traditional joints contribute significantly to the preservation of Nusantara’s architectural heritage and the development of sustainable construction practices rooted in indigenous knowledge