E-Journal Politeknik Negeri Cilacap
Not a member yet
919 research outputs found
Sort by
Natural Language Processing-Based Financial Time Series Forecasting: Utilizing Sentiment Analysis for Improved Stock Price Prediction
Full text linkThis study explores the application of natural language processing (NLP) techniques in financial time series forecasting, specifically in predicting stock prices. Historical stock price data and textual data from financial news articles and social media sources were collected, and TextBlob was used to obtain sentiment indices from the textual data. A hybrid model combining NLP techniques with LSTM (Long Short-Term Memory) neural networks was developed, and the methodology involved preprocessing and analyzing textual data using sentiment analysis with TextBlob and integrating the sentiment indices with historical stock price data for forecasting with LSTM. The LSTM model achieved a performance of 89.6 percent precision and outperformed traditional time series forecasting models in terms of accuracy and reliability. The results demonstrate that incorporating sentiment indices obtained through NLP significantly enhances the predictive performance of stock price forecasting models, and the study highlights the potential of NLP techniques, particularly sentiment analysis with TextBlob, in conjunction with LSTM neural networks, to improve the accuracy of financial time series forecasting, specifically in predicting stock prices.
Â
Studi ini mengeksplorasi penerapan teknik pemrosesan bahasa alami (Natural Language Processing/NLP) dalam peramalan deret waktu keuangan, khususnya untuk memprediksi harga saham. Data harga saham historis dan data tekstual dari artikel berita keuangan serta sumber media sosial dikumpulkan, dan TextBlob digunakan untuk memperoleh indeks sentimen dari data tekstual tersebut. Sebuah model hibrida yang menggabungkan teknik NLP dengan jaringan saraf LSTM (Long Short-Term Memory) dikembangkan, dan metodologinya melibatkan praproses dan analisis data tekstual menggunakan analisis sentimen dengan TextBlob, serta integrasi indeks sentimen dengan data harga saham historis untuk peramalan menggunakan LSTM. Model LSTM ini mencapai kinerja dengan tingkat ketepatan (precision) sebesar 89,6 persen dan mengungguli model peramalan deret waktu tradisional dalam hal akurasi dan keandalan. Hasilnya menunjukkan bahwa penggabungan indeks sentimen yang diperoleh melalui NLP secara signifikan meningkatkan kinerja prediktif model peramalan harga saham, dan studi ini menekankan potensi teknik NLP, khususnya analisis sentimen dengan TextBlob, dalam kombinasi dengan jaringan saraf LSTM, untuk meningkatkan akurasi peramalan deret waktu keuangan, khususnya dalam memprediksi harga saham
A Risk Management Guide for Information System Infrastructure in Digital Banking
Full text linkDigital banks rely heavily on IT infrastructure to support digital services, data management, and transaction processing, making them vulnerable to risks such as system failures, cybersecurity threats, and regulatory compliance. The implementation of Information Systems Risk Management (ISRM) is crucial to ensure data security and regulatory compliance. This study integrates ISO-31000: 2018, NIST SP 800-30, COBIT 2019, and Risk IT Framework to design a comprehensive risk management guide for banks, especially digital banks. ISO-31000: 2018 is used to define the objectives, scope, stakeholders, risk tolerance, and boundaries of risk management., NIST SP 800-30 is used for risk identification and assessment, Risk IT Framework is used to determine risk responses, and COBIT 2019 provides principles and practices that can be implemented to address risks. The research approach includes risk identification, assessment of likelihood and impact, selection of risk response options (Avoid, Reduce/Mitigate, Share/Transfer, Accept), and implementation of action plans. The study shows that the integration of this framework enables the bank to effectively address high-priority risks. After implementing the COBIT 2019-based mitigation plan, the risk score can be significantly lowered, putting the risk in an acceptable position. In addition, this approach enables the bank to comprehensively identify information technology and systems risks and implement action plans to reduce risks to an acceptable level
PENGEMBANGAN ALAT PENGERING GABAH DENGAN FITUR KENDALI OTOMATIS BERAT DAN KADAR AIR
Full text linkIndonesia sebagai negara agraris, memiliki sektor pertanian yang memiliki dampak yang signifikan terhadap perekonomian nasional. Salah satu komoditas pertanian yang mendominasi di Indonesia adalah padi. Padi, setelah diolah menjadi beras, menjadi sumber makanan utama di sebagian besar wilayah di Indonesia. Namun, proses produksi beras di Indonesia menghadapi sejumlah kendala, terutama yang disebabkan oleh faktor alam, seperti perubahan iklim yang semakin sulit diprediksi dan tidak menentu. Padi setelah proses panen, umumnya memiliki tingkat kadar air yang bervariasi, berkisar antara 20 hingga 27% basis basah, yang sangat dipengaruhi oleh kondisi musim saat panen dilakukan. Dengan mengurangi kadar air padi menjadi sekitar 13%-14% basis basah, yang merupakan tingkat kadar air yang aman untuk penyimpanan jangka panjang atau sebelum dipasarkan, risiko kerusakan akibat kelembaban tinggi dapat diminimalkan. Penelitian ini melakukan penelitian dengan pendekatan penelitian dan pengembangan (R&D). Dalam pembuatan alat ini, ESP32 digunakan sebagai kontrol dari seluruh sistem kendali alat. Kendali alat ini diatur oleh setting point dari gabah kering, yaitu berat 40 Kg dan kadar air 13% untuk memberhentikan proses pengeringan dari alat ini. Hal ini mencakup seluruh proses kontrol yang terdapat pada alat yang akan dibuat. Hasil penelitian menunjukan alat pengering gabah otomatis dengan menggunakan sensor soil moisture dan load cell sebagai kendali setting point pada alat dapat bekerja sesuai yang direncanakan. Sensor soil moisture untuk mengukur kadar air pada gabah. Sementara sensor load cell berfungsi untuk mengukur berat gabah. ESP32 dapat mengkontrol sistem pengeringan pada alat dengan baik. Proses pengeringan dapat selesai sesuai setting point sensor loadcell yang membaca parameter dari berat, yakni 40 kg. Proses pengeringan dapat selesai sesuai setting point dari sensor soil moisture yang membaca parameter kadar air, yakni 13%. Penggunaan sensor soil moisture kurang efektif untuk membaca parameter kadar air pada gabah. Menambahkan pemanfaatan sumber energi alternatif, untuk mengurangi biaya oprasional dari alat pengering padi. Pembuatan kapasitas alat yang lebih besar. Monitoring dan pengkajian beban daya listrk yang diperlukan
Pengembangan Bakpao Ikan Tenggiri sebagai Potensi Intervensi Pencegahan Stunting pada Anak Usia Dini dan Ibu Hamil: Study of the Acceptance Level of Mackerel Fish Buns as an Effort to Prevent Stunting
No full textStunting is a problem related to brain development, resulting in slow motor and mental growth. The issue of stunting is influenced by low access to food, both in quantity and nutritional quality. Mackerel can be used as an alternative food to prevent stunting because of the content it contains. In this study, mackerel was used as a filling in bakpao. Bakpao is one of the traditional Chinese foods that is often used as a snack. This study aims to determine the level of panelist acceptance of mackerel fish bakpao. The contents of mackerel fish bakpao include 76.5% water, 21.4% protein, 0.56% fat, 0.61% carbohydrates and 0.93% ash content. Based on the hedonic test of the parameters of taste, aroma, texture, and color, mackerel fish bakpao was liked by the panelists. Based on these results, bakpao with mackerel fish filling can be used as a food to prevent stunting.
Keywords: stunting, bakpao, mackerel fish
 
Perbandingan Arsitektur VGG16, MobileNetV2, InceptionV3, ResNet50, dan CNN Kustom untuk Klasifikasi Gambar Furnitur
No full textThe rapid development of technology in the current digital era is driving increased demand across various sectors, including the furniture industry. Classifying furniture images is one of the critical challenges in image processing and computer vision, mainly due to the diversity of types. This research aims to understand how pre-trained models can affect image classification accuracy using furniture dataset results. This study uses five CNN architectures and focuses on comparing the performance of a custom architecture with four pre-trained architectures, namely VGG-16, MobileNetV2, InceptionV3, and ResNet-50, using furniture images that have five classes such as chairs, tables, cabinets, sofas, and mattresses. The research results show that the models produced by the pre-trained architectures provide higher accuracy and performance, with VGG-16 reaching 97%, MobileNetV2 at 96%, and InceptionV3 and ResNet-50 at 98%. Meanwhile, the custom model only achieved an accuracy of 85%. This research shows that using pre-trained model algorithms significantly improves performance in image classification.Perkembangan teknologi yang pesat di era digital saat ini memicu peningkatan kebutuhan di berbagai sektor, termasuk industri furnitur. Klasifikasi gambar furnitur menjadi salah satu tantangan penting dalam pengolahan citra dan visi komputer, terutama karena adanya keberagaman jenisnya. Penelitian ini bertujuan untuk memahami bagaimana model pra-latih dapat mempengaruhi hasil akurasi klasifikasi gambar menggunakan dataset furnitur. Studi ini menggunakan lima arsitektur CNN dan berfokus kepada perbandingan kinerja arsitektur kustom dengan empat arsitektur pra-latih, yaitu VGG-16, MobileNetV2, InceptionV3, dan ResNet-50 menggunakan citra furnitur yang memiliki lima kelas seperti kursi, meja, lemari, sofa, dan kasur. Hasil penelitian menunjukkan bahwa model yang dihasilkan oleh arsitektur pra-latih memberikan akurasi dan performa yang lebih tinggi, dengan VGG-16 mencapai 97%, MobileNetV2 96%, InceptionV3 dan ResNet-50 98%. Sementara model kustom hanya mencapai akurasi sebesar 85% saja. Penelitian ini menunjukkan bahwa penggunaan algoritma model pra-latih secara signifikan meningkatkan kinerja dalam klasifikasi gambar
Uji Performa Sistem Hidrolik Alat Peraga Mini Excavator Zhugimada
Full text linkPractical learning activities on heavy equipment units are important because they increase understanding of work systems and provide an actual picture. The need for excavators for practicum activities in vocational education is currently hampered by price issues when commercial units are used as learning tools, therefore learning media in a more concise form are needed without ignoring important aspects. The manufacture of mini excavator props has been carried out but research related to work system testing is still rare, so performance testing of the work system is needed to ensure the performance of the props. The aim of this research is to test cylinder speed, cylinder pressure and cylinder drift using quantitative observation methods with variations in zero capacity, struck capacity and heaped capacity transport. From the test results, it was found that the cylinder speed values ​​were between 0.028–0.081 m/sec, the cylinder pressure was 17–20 bar for the boom, 65–72 bar for the arm, 24–34 bar for the bucket and the increase in length in the cylinder drift test was 0 mm
 
Model Sistem Dinamik Timbulan Sampah, Perancangan, dan Keberterimaan Sosial Masyarakat terhadap Pembangunan Tempat Pengelolaan Sampah Reuse, Reduce, dan Recycle (TPS 3R)
Full text linkAn increase in population leads to an increase in waste generation, which has the potential to cause negative impacts on health and the environment. Waste management in rural areas is important to reduce air pollution due to waste burning and soil pollution, while providing economic value through the development of Reduce, Reuse, Recycle Waste Processing Site (3R WPS). This study aims to estimate waste generation using a dynamic system approach, design an environmentally based 3R WPS design, and evaluate the perception of social acceptance of the community in Pesue Village, Konawe Islands Regency, Southeast Sulawesi. The dynamic system approach was used to project the amount of waste, while the design of 3R WPS was designed using AutoCAD. The community\u27s perception of the acceptability of 3R WPS was evaluated through a questionnaire survey. The simulation results show that the population growth of Pesue Village follows a sigmoid graph pattern in the 2021-2050 projection, and a linear pattern in the 2021-2030 period. The increase in population is in line with the increase in waste generation, which is depicted in a linear graph pattern. Simulation of waste management with 3R WPS shows that this facility can significantly reduce waste generation. The survey results show that the community supports the development of 3R WPS with the hope that waste management is carried out properly and sustainably. Implementation of the 3R principles (Reduce, Reuse, Recycle) is recommended to ensure environmentally friendly waste management, thus supporting the creation of a clean and healthy environment.
Keywords: Waste, 3R WPS, Dynamical System, Population, AcceptabilityPeningkatan jumlah penduduk berdampak pada meningkatnya timbulan sampah, yang berpotensi menimbulkan dampak negatif terhadap kesehatan dan lingkungan. Pengelolaan sampah di wilayah pedesaan menjadi penting untuk mengurangi polusi udara akibat pembakaran sampah dan pencemaran tanah, sekaligus memberikan nilai ekonomis melalui pembangunan Tempat Pengolahan Sampah Reduce, Reuse, Recycle (TPS 3R). Penelitian ini bertujuan untuk mengestimasi timbulan sampah menggunakan pendekatan sistem dinamik, merancang desain TPS 3R berbasis lingkungan, serta mengevaluasi persepsi keberterimaan sosial masyarakat di Desa Pesue, Kabupaten Konawe Kepulauan, Sulawesi Tenggara. Pendekatan sistem dinamik digunakan untuk memproyeksikan jumlah sampah, sementara desain TPS 3R dirancang menggunakan AutoCAD. Persepsi masyarakat terhadap keberterimaan TPS 3R dievaluasi melalui survei kuesioner. Hasil simulasi menunjukkan bahwa pertumbuhan penduduk Desa Pesue mengikuti pola grafik sigmoid pada proyeksi 2021–2050, dan pola linear pada periode 2021–2030. Peningkatan jumlah penduduk sejalan dengan bertambahnya timbulan sampah, yang digambarkan dalam pola grafik linear. Simulasi pengelolaan sampah dengan TPS 3R menunjukkan bahwa fasilitas ini mampu mengurangi timbulan sampah secara signifikan. Hasil survei menunjukkan bahwa masyarakat mendukung pembangunan TPS 3R dengan harapan pengelolaan sampah dilakukan secara baik dan berkelanjutan. Implementasi prinsip 3R (Reduce, Reuse, Recycle) direkomendasikan untuk memastikan pengelolaan sampah yang ramah lingkungan, sehingga mendukung terciptanya lingkungan yang bersih dan sehat.
Kata kunci: Sampah, TPS 3R, Sistem Dinamik, Penduduk, Keberterimaa
Urgensi Pelarangan Penggunaan Air Mineral dalam Kemasan Plastik Sekali Pakai pada Seluruh Lingkungan Kantor Pemerintahan di Indonesia
Full text linkSampah merupakan masalah yang tiada habisnya. Salah satu penyumbang sampah adalah kemasan air mineral plastik. Pemerintah memiliki komitmen untuk mengurangi sampah plastik di Indonesia. Alangkah baiknya apabila tindakan yang diambil dalam mewujudkan komitmen tersebut dimulai dari internal pemerintah itu sendiri. Penulisan ini bertujuan untuk mengkaji urgensi pelarangan penggunaan air mineral dalam kemasan plastik sekali pakai di lingkungan kantor pemerintahan. Metode yang digunakan adalah metode kualitatif dengan memanfaatkan data sekunder dari berbagai literatur yang tersedia. Melihat urgensinya, pemerintah sangat perlu menerapkan kebijakan pelarangan penggunaan air mineral dalam kemasan plastik sekali pakai ini sebagai wujud nyata komitmen pemerintah dalam menanggulangi permasalahan sampah di Indonesia. Selain itu, penerapan kebijakan ini juga dilakukan dalam rangka mendukung Tujuan Pembangunan Keberlanjutan yaitu tujuan ke-12 konsumsi dan produksi yang bertanggung jawab serta tujuan ke-14 ekosistem lautan. Dalam penerapannya, pemerintah berpotensi akan menemui tantangan antara lain keengganan pegawai pemerintah sendiri untuk tidak mengonsumsi air mineral dalam kemasan plastik sekali pakai dan sulitnya pengawasan pemenuhan aturan
Penerapan Sistem Pembangkit Listrik Tenaga Surya Pada Alat Pembuat Pupuk Organik Cair di Desa Banjarwaru
Full text linkThe majority of the population of Banjarwaru Village are farmers. The price of fertilizer is getting higher from time to time while farmers need fertilizer for their plants. Problems arise when fertilizer shortages often occur. In addition, the type of fertilizer used is generally a type of chemical fertilizer that is not good for the human body because the substance can be carried into the food consumed. Organic fertilizer is one option to overcome this problem. This type of fertilizer is now starting to be widely available on the market, although the price is relatively expensive. The solution to this problem is that it can be done by making organic fertilizer independently. Another factor is that there is a lot of organic waste that can be processed into liquid organic fertilizer (POC). Therefore, to create a village that is independent in fertilizer, the PKM Team aims to create an organic fertilizer maker based on a PLTS electricity source and provide training in operating the tool. The method used is by making an organic liquid fertilizer maker, socializing it to residents of Banjarwaru Village, and training and demonstrating how to operate the tool. 
Pemodelan dan Simulasi Perbaikan Harmonisa Menggunakan Double Tuned Filter di Laboratorium Teknik Elektro Universitas Negeri Medan
Full text linkThe Basic Electrical Engineering Laboratory of Medan State University uses many nonlinear loads such as computers, laptops, printers, scanners, projectors, inverters, converters and others that can cause harmonics. The method used to overcome harmonics is by using a double tuned passive filter, the use of a double tuned filter has an effect on reducing current harmonics and overcoming the increase in cos phi values ​​in the electrical system. A double tuned filter can be a broader strategy in managing power factors by reducing certain harmonic orders, but it cannot directly improve the overall power factor without carefully considering the system conditions and existing problems. By inputting the filter requirement values ​​F,,, , Ω the simulation results obtained are a decrease in harmonic levels, where the third order harmonic which was originally 28.3% fell to 19.77% and the fifth order harmonic which was originally 13.27% fell to 9.27%. The reliability of using a double tuned filter to increase the desired power factor of 0.95 by compensating for the known reactive power of Qc = 794.206846 Var. The use of passive filters is very feasible to be used in reducing harmonic disturbances that occur in the electric power system.