E-Journal Politeknik Negeri Cilacap
Not a member yet
919 research outputs found
Sort by
Pelatihan Pengolahan Produk Berbasis Nanas Melalui Pemberdayaan Wanita Desa Margoluwih Kabupaten Sleman
The community in Margoluwih Village is currently developing pineapple cultivation. While pineapple marketing is still limited to fresh form when the harvest season comes, pineapple production will be abundant so that prices can fall. Therefore, there needs to be a follow-up to overcome this by making other derivative products such as pineapple jam and syrup. The Community Partnership Empowerment Program (PKM), has provided a positive perception to partners regarding the diversification of pineapple processing into products with economic value, and as a solution to overcome the peak harvest in addition to increasing competitiveness and capturing market opportunities. The products offered from pineapple processing received a good response from partners, namely through pineapple syrup and jam processing. The PKM program was carried out through several stages starting from preliminary surveys, socialization, counseling, and training. The PKM method used during the activity was Participatory Rural Appraisal (PRA). This technique involves the active role of all partners in the activity. The PKM program succeeded in increasing the knowledge, skills, and abilities of partners in processing pineapple into products with economic value as a whole by 97%. In addition, PKM activities have had positive impacts on partners, especially in utilizing free time for productive activities that can generate income and economic resources for families. 
Pendampingan dan Pelatihan Digital Marketing UMKM Toeng Kitchen melalui Instagram
UMKM Toeng Kitchen is a small and medium enterprise engaged in traditional culinary located in Menganti District, Gresik Regency, East Java. UMKM Toeng Kitchen offers a variety of traditional snacks, ranging from wet cakes such as klepon, onde-onde, and layered cakes, to other sweet treats that pamper the tongue. With selected raw materials and a manufacturing process that maintains quality and taste, Toeng Kitchen MSME is committed to providing delicious, healthy, and safe products for customers. However, marketing constraints are a challenge for UMKMToeng Kitchen. Amid the rapid development of technology, UMKM do not have tech-savvy workers. This situation makes UMKM Toeng Kitchen owners concerned about the growth and sustainability of their businesses. Therefore, this community service activity focuses on mentoring the creation of digital marketing and operational training for the Management Team. This activity has had a positive impact on UMKM Toeng Kitchen sales revenue. The results obtained from this activity include marketing effectiveness. By uploading product photos, videos, and reels that attract attention, UMKM Toeng Kitchen can reach a wider customer base
KOPAJA: Edukasi Pencegahan Obesitas dan Gizi Seimbang bagi Pekerja Dewasa di Kota Serang
Obesity is a growing public health concern in Indonesia. Adult workers form a vulnerable group due to their sedentary lifestyles and time constraints. This community service activity aimed to provide education on obesity prevention and balanced nutrition for adult workers in Serang City. The implementation method included the preparation of educational materials, online dissemination through videos and interactive discussions via WhatsApp, and offline dissemination by distributing posters and stickers. Knowledge evaluation was conducted using pre- and post-tests on 12 workers. The results demonstrated a significant increase in knowledge after education (average pre-test score of 40.00 to 91.67 on the post-test, p < 0.001). This activity concludes that structured health education is effective in improving workers\u27 knowledge about obesity, which is expected to encourage behavioral changes towards a healthier lifestyle
Analisis Perancangan Utilitas dan Iluminasi Hotel Citra Dua Pangandaran
Perencanaan sistem utilitas dan iluminasi pada bangunan hotel memiliki peran penting dalam menunjang kenyamanan, keamanan, dan efisiensi energi. Penelitian ini membahas perencanaan sistem utilitas dan iluminasi pada Hotel Citra Dua yang mencakup lima aspek utama, yaitu sistem pencahayaan (iluminasi), penghawaan (HVAC), keamanan (CCTV), jaringan data (Wi-Fi), serta keselamatan kebakaran (fire alarm). Tujuan penelitian ini untuk menganalisis efisiensi energi, kenyamanan pengguna, dan keandalan sistem utilitas yang diterapkan pada bangunan hotel. Metode perancangan dilakukan dengan pendekatan Lumen Method untuk sistem pencahayaan, metode Cooling Load Temperature Difference (CLTD) untuk sistem penghawaan, serta perhitungan rasio efisiensi energi sistem (ηₛ) untuk keseluruhan utilitas. Hasil perhitungan menunjukkan total daya pencahayaan sebesar 6.573 W dan kebutuhan beban pendingin sebesar 12,8 TR. Sistem CCTV mampu mencakup 98% area publik, sistem Wi-Fi menjangkau 97% area hotel, dan sistem fire alarm konvensional memiliki waktu respon 3,1 detik, sesuai SNI 03-3989-2000. Rasio efisiensi energi total bangunan mencapai 0,87, melampaui standar ASEAN Energy Management Standard (AEMS) sebesar 0,8. Secara keseluruhan, rancangan sistem utilitas ini dinilai efisien, aman, dan layak diterapkan sebagai acuan perencanaan hotel berskala menengah
Design and Implementation of Intelligent Traffic Lights for One-Way Open and Close Roads Based on Reinforcement Learning
This study aims to design and implement an intelligent traffic light system for one-way open and close road conditions, commonly encountered during road repair projects. These situations often cause congestion due to alternating vehicle flow in a single lane. To address this issue, the system utilizes a Reinforcement Learning (RL) algorithm to dynamically adjust the traffic light timing based on real-time traffic conditions. The research was conducted in three main stages: (1) designing the network topology and IoT devices using Raspberry Pi, ESP modules, and Access Points (APs), (2) implementing the intelligent traffic light system, and (3) conducting a functional evaluation. A key performance metric evaluated was the response time of the system. Experimental results showed that the traffic light system achieved an average response time of 0.51 seconds, indicating that it is responsive and suitable for real-time operation. The successful integration of RL and MQTT-based communication also demonstrates the feasibility of deploying this system in dynamic traffic environments. Further research is recommended for field testing with additional sensor integration and advanced RL models to enhance system accuracy and efficienc
Kendali Kecepatan Motor BLDC dengan metode Mesin Sinkron dan Variasi PWM berbasis IoT
This study investigates speed control of brushless DC (BLDC) motors using a synchronous machine method and Pulse Width Modulation (PWM) variations based on IoT. A three-phase inverter controlled by an STM32 microcontroller was used to drive the BLDC motor. Speed control was implemented by adjusting the inverter frequency based on the synchronous machine principle, while PWM duty cycle was varied to regulate the input voltage. An IoT-based system using a smartphone app allowed remote speed settings. Experimental results showed that the synchronous machine method could effectively control BLDC motor speed, with frequency changes linearly affecting inverter output voltage. Varying PWM duty cycles impacted the voltage required to achieve target speeds, with higher duty cycles requiring lower voltages. The control system achieved speed accuracies within 3% of setpoints across different duty cycles. This approach demonstrates the feasibility of applying synchronous machine principles for BLDC motor control with IoT integration
Analisis Kinerja Ensemble Learning dan Algoritma Tunggal dalam Klasifikasi Sindrom Ovarium Polikistik Menggunakan Random Forest, Logistic Regression, dan XGBoost
Polycystic ovary syndrome (PCOS) is a hormonal disorder that is the most common cause of anovulation and infertility in women of reproductive age, affecting approximately 5-10% of the population, with up to 70% of cases undiagnosed. This highlights the need for early detection methods with high accuracy for timely treatment. Previous research utilized a classification method based on the K-Nearest Neighbor (KNN) algorithm, which demonstrated good performance with an accuracy of 93%, precision of 100%, recall of 82%, and F1-Score of 90%. This study proposes using an ensemble learning method with a voting classifier technique that combines several classification models: Random Forest Classifier, Logistic Regression, and XGBoost Classifier. The results show that the proposed method performs better with an accuracy of 95%, precision of 100%, recall of 85%, F1-Score of 92%, and an AUC (Area Under Curve) value of 94.34%Sindrom ovarium polikistik atau polycystic ovary syndrome (PCOS) adalah kelainan hormonal yang menjadi penyebab paling umum anovulasi dan infertilitas pada wanita usia reproduksi, memengaruhi sekitar 5-10% populasi, namun hingga 70% kasus tidak terdiagnosis. Hal ini menunjukkan perlunya metode deteksi dini dengan tingkat akurasi tinggi untuk penanganan tepat waktu. Penelitian sebelumnya menggunakan metode klasifikasi berbasis algoritma K-Nearest Neighbor (KNN) dan menunjukkan kinerja yang cukup baik dengan hasil akurasi sebesar 93%, precision 100%, recall 82%, dan F1-Score 90%. Penelitian ini mengusulkan penggunaan metode ensemble learning dengan teknik voting classifier yang menggabungkan beberapa model klasifikasi, yaitu Random Forest Classifier, Logistic Regression, dan XGBoost Classifier. Hasil penelitian menunjukkan bahwa metode yang diusulkan memberikan kinerja yang lebih baik dengan akurasi sebesar 95%, precision 100%, recall 85%, F1-Score 92%, dan nilai AUC (Area Under Curve) sebesar 94,34%
Optimasi Efisiensi Perawatan Air Conditioning Tipe Split dengan Penerapan Pembersih Filter Otomatis Berbasis Condition-Base Maintenance
The increasing use of split air conditioners (AC) in various sectors demands efficient maintenance solutions to ensure optimal performance and improve energy efficiency. Time-based maintenance (TBM), the commonly used method, often leads to premature or delayed maintenance, reducing system efficiency and increasing operational costs. Previous studies have not fully explored the application of condition-based maintenance (CBM) for AC filter maintenance, especially in developing automated systems. A significant research gap exists due to the lack of real-time solutions for accurately detecting filter conditions and enabling maintenance without manual intervention. This study aims to develop an automated AC filter cleaner prototype based on CBM by integrating sensors, microcontrollers, and actuators. The results show the system reduces energy consumption by up to 58%, shortens cleaning time by 75%, and eliminates water use. In conclusion, the proposed prototype offers an innovative and efficient solution for enhancing operational performance and reducing costs.
 
Improving Cervical Cancer Classification Using ADASYN and Random Forest with GridSearchCV Optimization
Cervical cancer is a leading cause of death among women, with over 300,000 deaths recorded in 2020. This study aims to improve the accuracy of cervical cancer diagnosis classification through a combination of Adaptive Synthetic Sampling (ADASYN) and Random Forest algorithm. The research data was obtained from the Cervical Cancer dataset in the UCI Machine Learning Repository with an imbalanced data distribution of 95% negative class and 5% positive class. ADASYN method was chosen for its ability to handle imbalanced data by focusing on minority data points that are difficult to classify. The Random Forest algorithm was optimized using GridSearchCV to achieve maximum performance. Results show that this combination improved accuracy from 96.5% to 96.8% and recall from 93.7% to 94.3%. Feature importance analysis identified key risk factors such as number of pregnancies, age at first sexual intercourse, and hormonal contraceptive use that significantly influence diagnosis. This research demonstrates the effectiveness of combining ADASYN and Random Forest in enhancing classification performance for early cervical cancer detection.Kanker serviks merupakan salah satu penyebab utama kematian pada wanita, dengan lebih dari 300.000 kematian tercatat pada tahun 2020. Penelitian ini bertujuan meningkatkan akurasi klasifikasi diagnosis kanker serviks melalui kombinasi metode Adaptive Synthetic Sampling (ADASYN) dan algoritma Random Forest. Data penelitian diambil dari dataset Cervical Cancer pada UCI Machine Learning Repository dengan distribusi data tidak seimbang 95% kelas negatif dan 5% kelas positif. Metode ADASYN dipilih karena kemampuannya dalam menangani data tidak seimbang dengan fokus pada titik data minoritas yang sulit diklasifikasikan. Algoritma Random Forest dioptimasi menggunakan GridSearchCV untuk menghasilkan performa maksimal. Hasil penelitian menunjukkan kombinasi metode ini meningkatkan akurasi dari 96,5% menjadi 96,8% dan recall dari 93,7% menjadi 94,3%. Analisis feature importance mengidentifikasi faktor risiko utama seperti jumlah kehamilan, usia pertama melakukan hubungan seksual, dan penggunaan kontrasepsi hormonal yang berpengaruh signifikan terhadap diagnosis. Penelitian ini membuktikan efektivitas kombinasi ADASYN dan Random Forest dalam meningkatkan performa klasifikasi untuk deteksi dini kanker serviks
Bahasa Indonesia
Technology Acceptance of the Pasar Banjarwaru Platform Using the Technology Acceptance Model 3 (TAM 3). With the increasing reliance on digital platforms, understanding the factors influencing technology adoption in online buying and selling activities is crucial. This study explores variables such as perceived usefulness, ease of use, social influence, and user intention. Data were collected through an online questionnaire survey of 362 respondents and analyzed using the PLS-SEM method. The findings indicate that user intention significantly impacts the level of platform usage. Additionally, factors such as computer self-efficacy, enjoyment in using the platform, and platform image enhance users\u27 perceptions of its usefulness and ease of use. Social norms, particularly the influence of the surrounding environment, are identified as the most significant determinants of user intention and perceived benefits. Technology acceptance is shaped by an interplay of social, psychological, and technical factors. Based on these insights, recommendations for developers include adopting user-friendly designs and leveraging community-based promotional strategies to enhance technology acceptance