E-Journal Politeknik Negeri Cilacap
Not a member yet
919 research outputs found
Sort by
Deteksi Dini Gangguan Kesehatan Mental dengan Model Bert dan Algoritma Xgboost
Get PDFMental health disorders are severe conditions that affect a person\u27s thoughts, feelings, behavior, and well-being. Data from the World Health Organization (WHO) shows that more than 264 million people worldwide experience depression, one of the most common forms of mental health disorders. However, limited access to psychological services, such as lack of professionals and high costs, are major challenges in providing adequate support. Therefore, innovative technology-based solutions are needed for efficient and affordable psychological support. Efforts to improve research results to develop a mental health chatbot model by combining BERT (Bidirectional Encoder Representations from Transformers) and XGBoost (Extreme Gradient Boosting) models. The BERT model is used to understand the context of the conversation, while the XGBoost algorithm is used for text classification. The dataset used comes from Kaggle, which consists of 312 question patterns with several patterns or classes, namely 79 classes. The results of the program implementation test produced a percentage of 93.05% and output in the form of a program in the execution of the model on Google Colab..
 
Enhanching User Experience in E-Commerce Website Design Through the User Centered Design Approach: A Case Study
Get PDFMany small-scale businesses in Indonesia rely on manual customer interaction workflows, leading to delays, inefficiencies, and missed opportunities in digital transactions. This study proposes designing and implementing a user-centered e-commerce website to streamline order processing, improve user autonomy, and reduce the operational burden on the business owner. Addressing management issues in small businesses requires creating a website that meets user needs. The User-Centered Design (UCD) methodology includes iterative stages of user research, requirements specification, interface design, and usability evaluation. A high-fidelity prototype was tested by 65 participants, resulting in 56 valid responses after data cleaning. Usability was evaluated through ISO/IEC 25022-based metrics, achieving a 67.86% completion rate, an average task time of 91.66 seconds, and an overall relative efficiency of 66.96%. Using the User Experience Questionnaire (UEQ), we measured user satisfaction, with five out of six dimensions rated as “Excellent”. The final system was implemented using Laravel and Filament, integrated with Midtrans for payment automation, Mailtrap for email testing, and a management dashboard for order tracking and status updates. This study demonstrates the practical application of UCD in the digital transformation of SMEs by delivering a fully functional, user-validated interface that enhances transactional clarity and customer experience. Compared to prior methods, the approach enables self-service ordering with reduced reliance on real-time manual responses. The findings offer a replicable reference for similar businesses seeking to implement user-focused digital solutions efficiently
The Effect of Light Intensity, Camera Pixel Quality, Camera Distance, and Object Altitude on Detection Accuracy in a Real-Time Drone Surveillance System Using YOLOv5
Get PDFThis research evaluates the performance of the drone detection system based on YOLOv5 in a variety of environmental conditions. The four main variables under test were drone height, camera type, light intensity, and camera-to-object distance. Thirty-six different scenarios were used with three different camera types (1080p, 2K, and Canon 600D). The height of the drones varied from 1 to 14 meters, and the variations in illumination ranged from 0 to 46 lux. Results showed consistent YOLOv5 performance with an average accuracy of 60%, precision of 62%, recall of 58%, F1-score of 60%, and IoU of 75%. ANOVA revealed that light intensity, camera distance, and drone height all had a significant impact on detection accuracy (p < 0.05), but camera type was not statistically significant. The best results were obtained under the following conditions: high light levels (>40 lux), camera distances <10 m, and drone altitudes between 6 and 9 m. These findings demonstrate the importance of environmental setup in improving the performance of object detection systems based on deep learning. This research helps design a more reliable and adaptable drone detection system for real-world applications. This work provides practical guidelines for implementing deep learning-based aerial surveillance and highlights optimal operational parameters for YOLOv5 systems
Facial Image-Based Autism Detection Using ConvNeXt Tiny: A Lightweight Deep Learning Approach for Early Screening
Get PDFThis study proposes a deep learning model using the ConvNeXt Tiny architecture to detect autism spectrum disorder (ASD) from facial images, addressing the need for an early, efficient, and accessible diagnostic tool. The model integrates facial image preprocessing techniques like Contrast Limited Adaptive Histogram Equalization (CLAHE) and data augmentation, with facial segmentation performed by MTCNN. The ConvNeXt Tiny model is trained using transfer learning and evaluated through metrics such as accuracy, precision, recall, and F1-score, and compared with traditional CNN models like ResNet50 and EfficientNet-B0. The results demonstrate that the proposed model outperforms ResNet50 and EfficientNet in all evaluation metrics, achieving a classification accuracy of 84%. It also demonstrates a balanced performance across both classes (autistic and non-autistic), with high precision and recall for both, leading to a high F1-score. Furthermore, the model\u27s computational efficiency makes it suitable for web and mobile applications, enabling scalable and real-time screening for ASD in children. The study\u27s contributions include the development of a novel, lightweight ASD classification system, a comparative analysis of ConvNeXt with other CNN models, and the creation of a prototype for early ASD detection. This approach not only provides a promising alternative to conventional diagnostic methods but also sets the groundwork for further research and practical implementation in clinical settings
Implementasi Maintenance Robot Palletizer Di Motor Servo Untuk Meningkatkan Keamanan Dan Mengurangi Kerusakan Pada Robot Palletizer
Get PDFRobot palletizer sering menghadapi masalah terkait kontrol pergerakan yang tidak optimal, yang dapat menyebabkan kecelakaan kerja dan kerusakan mekanis. Dengan menambahkan clutch brake pada motor servo, diharapkan kontrol pergerakan robot dapat lebih presisi, sehingga risiko kecelakaan dan kerusakan dapat diminimalisir. Penelitian ini mengevaluasi efektivitas penambahan clutch brake pada motor servo dalam meningkatkan keamanan dan mengurangi kerusakan pada robot paletizer. Metode yang digunakan adalah metode eksperimen untuk mengukur parameter keamanan dan kerusakan sebelum dan sesudah penambahan clutch brake. Tujuan implementasi penambahan clutch brake pada motor servo diharapkan dapat memberikan kontrol lebih baik terhadap pergerakan robot dan menahan lengan agar tidak jatuh, mengurangi risiko kecelakaan kerja, serta memperpanjang umur operasional komponen mekanis. Penelitian ini diharapkan dapat memberikan kontribusi dalam peningkatan keandalan dan efisiensi operasi robot paletizer di industri
A Analisis Tempat Penampungan Sementara (TPS) Menggunakan Sistem Informasi Geografis Untuk Pengelolaan Sampah Berkelanjutan di Kota Lhokseumawe
No full textLhokseumawe City is the center of government and economy has a dense population, with a population density index of 1,082.6 people / km2. Good waste management must be done to maintain environmental health, including the management of Temporary Shelters (TPS). Waste that is disposed of carelessly creates illegal Waste Disposal Sites (LPS) that can trigger various diseases and reduce environmental aesthetics. The focus of the research is to map the location of TPS and LPS using Geographic Information System (GIS), analyze the distribution pattern of TPS and LPS using nearest neighbor analysis on image processing software, and analyze the suitability of TPS capacity with the volume of waste from the people of Lhokseumawe City. The results of the study obtained that the TPS facilities in Lhokseumawe City are 18 TPS while there are 36 illegal LPS. The distribution pattern of TPS includes a clustered pattern with a distribution index of 0.69. The distribution pattern of LPS includes a clustered pattern with a distribution index of 0.51 and the highest LPS is found in the Muara Satu District area. The results of the analysis of the suitability of TPS capacity obtained the availability of TPS in each sub-district is still lacking to accommodate waste generation, Banda Sakti sub-district still lacks 34 TPS, Muara Dua sub-district 23 TPS, Muara Satu sub-district 15 TPS, and Blang Mangat sub-district 8 TPS..
Keywords: TPS, Geographic Information System, Waste, Nearest Neighbor, MappingKota Lhokseumawe merupakan pusat pemerintahan dan ekonomi memiliki jumlah penduduk yang padat, dengan indeks kepadatan penduduk sebesar 1.082,6 jiwa/km2. Pengelolaan sampah yang baik harus dilakukan untuk menjaga Kesehatan lingkungan, diantaranya pengelolaan Tempat Penampungan Sementara (TPS). Sampah yang dibuang secara sembarangan menimbulkan Lokasi Pembuangan Sampah (LPS) ilegal yang bisa memicu berbagai penyakit dan menurunkan estetika lingkungan. Fokus dari penelitian adalah memetakan lokasi TPS serta LPS memanfaatkan Sistem Informasi Geografi (SIG), menganalisa pola persebaran TPS dan LPS menggunakan analisis nearest neighbour pada Software pengolahan citra, serta menganalisa kesesuaian kapasitas daya tampung TPS dengan volume sampah dari masyarakat Kota Lhokseumawe. Hasil penelitian diperoleh fasilitas TPS yang terdapat di Kota Lhokseumawe adalah 18 TPS sedangkan LPS ilegal sebanyak 36 LPS. Pola persebaran TPS termasuk pola clustered dengan indeks penyebaran 0,69. Pola persebaran LPS termasuk pola clustered dengan indeks penyebaran 0,51 dan LPS tertinggi terdapat pada wilayah Kecamatan Muara Satu. Hasil analisa kesesuaian kapasitas TPS didapatkan ketersediaan TPS disetiap Kecamatan masih kurang untuk menampung timbulan sampah, Kecamatan Banda Sakti masih kekurangan 34 TPS, Kecamatan Muara Dua 23 TPS, Kecamatan Muara Satu 15 TPS, dan Kecamatan Blang Mangat 8 TPS.
Kata kunci: TPS, Sistem Informasi Geografis, Sampah, Nearest Neighbor, Pemetaa
Pengaruh Variasi Jenis Sampah dan Jumlah Larva BSF (Black Soldier Fly) pada Penguraian Sampah Organik Rumah Tangga
Get PDFThe increase in population and household consumption can lead to an increase in the volume of household waste. The increase in the volume of household waste will become a serious problem if no processing efforts are made. If household-scale waste processing is not carried out, it can result in the accumulation of the volume of organic waste in the Integrated Waste Management Site (TPST). One of the efforts that can be made to process waste at the household scale is by decomposing it using BSF larvae (maggot). Household waste generally consists of vegetable scraps and fruit peels. Vegetable and fruit waste is classified as organic waste which contains many nutrients that are utilized by BSF larvae as a food source in their breeding. The ability of BSF larvae to eat organic waste makes them widely used as one of the biodecomposter agents. This study aims to determine the effect of waste type and variation in the number of maggot on feed conversion efficiency, waste reduction index and characteristics of maggot produced. This study was conducted with a complete randomized design method with two independent variables and two repetitions. The physical characteristics of maggot which include, digested feed conversion efficiency (ECD), waste reduction index (WRI), and protein content in dried maggot. The type of garbage has no significant effect on the value of feed conversion efficiency (ECD), has a significant effect on the value of the waste reduction index (WRI) and has a very significant effect on protein content. The variation in the number of maggot has a very significant effect on the value of feed conversion efficiency (ECD) and waste reduction index (WRI) and has a significant effect on protein content.Bertambahnya jumlah penduduk dan konsumsi rumah tangga mengakibatkan peningkatan volume sampah rumah tangga. Peningkatan volume sampah rumah tangga akan menjadi masalah yang serius jika tidak dilakukan upaya pengolahan. Bertambahnya volume sampah dengan proses pengolahan yang tidak optimal akan mengakibatkan terjadinya penumpukan volume sampah organik di Tempat Pengolahan Sampah Terpadu (TPST). Salah satu upaya yang dapat dilakukan untuk mengolah sampah pada skala rumah tangga adalah dengan cara penguraian menggunakan larva BSF (Black Soldier Fly). Sampah rumah tangga pada umumnya terdiri dari sisa-sisa sayuran dan kulit buah. Sisa sayuran dan buah-buahan termasuk dalam sampah organik yang memiliki banyak kandungan unsur hara. Kandungan unsur hara ini dapat dimanfaatkan oleh larva BSF sebagai sumber makanan untuk perkembangbiakannya. Kemampuan larva BSF dalam memakan sampah organik menjadikan larva BSF sebagai salah satu agen biodekomposter. Penelitian ini bertujuan untuk mengetahui pengaruh jenis sampah dan variasi jumlah maggot terhadap efisiensi konversi pakan, indeks pengurangan limbah dan karakteristik maggot yang dihasilkan. Pada penelitian ini dilakukan dengan metode rancangan acak lengkap dengan dua variabel bebas dan dua kali pengulangan. Karakteristik fisik maggot yang meliputi, efisiensi konversi pakan yang dicerna (ECD/Efficiency of Conversion of Digested Feed) Indeks pengurangan limbah (WRI/Waste Reduction Index), dan kadar protein pada maggot kering. Hasil penelitian dianalisis dengan metode sidik ragam dimana memberikan hasil bahwa jenis sampah tidak berpengaruh terhadap nilai efisiensi konversi pakan (ECD), berpengaruh nyata terhadap nilai indeks pengurangan limbah (WRI) dan berpengaruh sangat nyata terhadap kadar protein.Kata kunci: Larva BSF, Maggot, Sampah Organi
Pelatihan Branding dan Digital Marketing untuk Meningkatkan Nilai Jual pada UKM Vigaza Farm
Get PDFAs part of the Sleman Millennial Farmers Group, Vigaza Farm SME has great potential in developing quail farming products. However, this business is still hampered by issues related to brand identity management, packaging design quality, and suboptimal digital marketing strategies, which have implications for low sales value and competitiveness. Through community service activities, this program focuses on enhancing branding and digital marketing capabilities for the managers of Vigaza Farm. The training was conducted on June 21, 2025, at Building 2 of Amikom University Yogyakarta, attended by 10 participants comprising owners, staff, and internal members. The implementation methods included socialization, training, technology application, as well as mentoring and evaluation. The materials covered basic branding concepts, visual identity creation (logo, brand colors, typography), packaging design development, and an introduction to simple digital marketing strategies. Evaluation results showed a significant improvement in participants\u27 understanding. Before the training, 75% of participants were in the “understand” category (score 4) and 25% in the “very understand” category (score 5). After the training, 75% of participants were in the very knowledgeable category (score 5) and 25% in the knowledgeable category (score 4). This activity produced two ready-to-use packaging designs, namely “Sambal Telur Puyuh Kencana” and “Puyuh Kencana Frozen,” which met branding principles and were suitable for promotion. These results demonstrate the effectiveness of the training in enhancing branding and digital marketing skills, although further guidance is still needed for optimizing online promotions
Optimisasi Proses Pengupasan dan Pengirisan Bawang Merah dengan Teknologi Terbaru
Get PDFShallots (Allium ascalonicum L.) are essential tuber crops in the food industry, enhancing the aroma and flavour of various dishes. Manual peeling and slicing of shallots are time-consuming and can cause eye irritation. This study aims to develop and test an integrated shallot peeling and slicing machine to improve processing efficiency and reduce discomfort. The machine used in this study has a capacity of 3 kg. Peeling tests were conducted with shallots weighing 1 kg, 2 kg, and 3 kg, recording the time needed for each weight. Slicing tests were conducted with shallots weighing 0,5 kg, 1 kg, 1,5 kg, and 2 kg, measuring the thickness of the slices produced. The results show that the machine takes approximately 6 minutes to peel 1 kg of shallots and 4 minutes for 2 kg and 3 kg, demonstrating 30 times the efficiency of manual peeling. Slicing 0,5 kg of shallots resulted in 0,5 mm thick slices, while for 1 kg and 2 kg, the slice thickness was consistently 0,4 mm. For 1,5 kg, the slice thickness was 0,7 mm, with the machine\u27s slicing performance improving approximately 3 times compared to manual methods. This study concludes that the integrated shallot peeling and slicing machine effectively enhances the efficiency and accuracy of shallot processing, making it viable for implementation in the food industry
Optimalisasi Sistem Informasi Layanan Keuangan dengan Metode First Come First Served (FCFS)
Get PDFOne of the important things in financial management is financial services. Cilacap State Polytechnic (PNC) is a PTN as a Work Unit. Financial management at PNC refers to applicable government regulations, but financial service policies are the authority of the leadership as a strategy to create fast, effective, and accountable financial services. The budget usage policy stipulates that work units must propose budget usage based on the Fund Withdrawal Plan through a down payment form approved by the Financial Management Officer. The current problem is that down payment forms are often scattered or lost, so the response time for payments from finance is slow, and payment queues are often not in sequence. This results in activities being hampered. This research aims to create a prototype or development design for the Financial Services Information System at PNC. The FCFS method is used as a service scheduling algorithm based on arrival time to optimize financial services. In this way, the financial service process will be more organized, the response time for financial services will be faster, and the queue for service requests will be in line