Center for Scientific Publication
Not a member yet
4029 research outputs found
Sort by
Comparison of Supervised Learning Algorithms for Cigarette and Vape Smoke Classification Using Electronic Nose
Get PDFThis research discusses applying the Supervised Learning method using Electronic Nose to classify the types of cigarette and vape smoke in the air. Electronic Nose is used as a scent detector that can identify the characteristics of smoke from both sources. Three Supervised Learning algorithms, namely KNN, SVM, and Decision Tree, were applied to compare the performance in classifying smoke types. The data comprised reference air samples, air contaminated by manufactured cigarette smoke, rolled cigarettes, and vape. The results showed that all three Supervised Learning algorithms successfully provided an excellent classification for cigarette and vape smoke types using data from Electronic Nose. The best accuracy result was achieved by SVM, with an accuracy rate of 96.55%. This research contributes to identifying sources of air pollution that have the potential to endanger human healt
Modulus of Rupture and Modulus of Elasticity in Recycling FRP
Get PDFFiber Reinforced Plastic (FRP) material has been widely used as a ship construction alternative to wood. FRP has many advantages such as lightweight material, easy maintenance, weather resistance, economical price, and shorter production time. FRP ship production is weak from the waste factor produced, such as production residue during shipbuilding, ship molds, and FRP shipwrecks. FRP waste can impact the environment, economy, and human health. These impacts include soil pollution, microplastics, skin diseases, and human respiratory disorders. FRP material tends to be burned by many shipyards but still leaves waste in the form of dust. FRP material is difficult to decompose and takes a long time to melt. One strategic effort to minimize the impact of FRP is to recycle FRP. This study aims to reduce FRP waste by making composite boards from FRP waste. The method used was experimental, involving the making of 12 specimens and testing the density, MOR, and MOE. Based on the results of the density value test, the average value obtained follows the JIS A 5905-2003 reference. The MOR and MOE values for each specimen do not comply with the Indonesian Classification Bureau (BKI) standards. In the ANOVA test calculation, no significant differences were obtained for MOR and MOE
Transforming Tofu Waste into a Growth Medium: Boosting Biomass and Proximate Content of Microalgae
Get PDFThis study explores the potential of tofu waste as a cost-effective alternative growth medium for cultivating Spirulina sp. and Nannochloropsis oculata, addressing the high costs of traditional nutrient media that limit large-scale applications. Despite the nutrient richness of tofu waste, its use as a sustainable growth substrate remains underexplored. This research aims to fill this gap by evaluating the growth performance and nutritional suitability of these microalgae in tofu-based media compared to standard controls. The cultivation process was conducted in a closed photobioreactor system, with harvesting methods including flocculation, centrifugation, and filtration. Results showed that tofu waste media supported biomass production comparable to standard cultivation media, with the highest biomass concentrations recorded at the 20% tofu waste treatment, yielding 0.23 ± 0.05 g L-1 for Spirulina sp. and 0.53 ± 0.2 g L-1 for Nannochloropsis oculata. At this concentration, the final COD levels were 840.84 mg L-1and 825.90 mg L-1, respectively. The lipid and protein contents were 2.44% and 1.71% for Spirulina sp., and 1.21% and 1.50% for Nannochloropsis oculata, respectively. These findings demonstrate that tofu waste can serve as an effective and low-cost growth substrate for Spirulina sp. and Nannochloropsis oculata, promoting circular economy principles within many sectors such as energy, food, and agriculture. This study underscores the potential of waste utilization to enhance the sustainability and economic viability of microalgae cultivation
Hybrid CNN-SVM with Borderline SMOTE for Imbalance Class Cabbage Plants
Get PDFCabbage farming is highly vulnerable to diseases and pests, leading to substantial yield losses if not properly managed. Traditional diagnostic methods, reliant on manual assessment, are often time-consuming and inaccurate. This study introduces a hybrid approach combining Convolutional Neural Networks (CNN) and Support Vector Machines (SVM) to address these challenges, specifically focusing on improving classification accuracy in imbalanced cabbage image datasets. CNNs are leveraged for their powerful feature extraction, while SVM, optimized using a One-vs-All strategy, enhances multi-class classification. To handle data imbalance, Borderline SMOTE (Synthetic Minority Over-sampling Technique) is applied, generating synthetic samples to balance underrepresented classes. The SqueezeNet architecture is employed for feature extraction, with SVM hyperparameters fine-tuned via grid search. Results demonstrate that the integration of CNN, SVM, and Borderline SMOTE significantly improves classification performance, particularly for minority classes, achieving an accuracy of 99%. This approach offers a more reliable and efficient tool for early detection of cabbage diseases and pests, contributing to better agricultural management and reduced crop losses
Solar-powered automatic oven machine for chili and ginger drying in the highland
Get PDFChillies and ginger are plantation crops in mountainous areas. One form of processing is by drying. The purpose of drying is to reduce the water content of plantation products. Natural drying requires the sun as a heating source with temperatures around 50˚C-60˚C, which is a problem in the mountains because the temperature is below average so it takes a long time. Natural drying has a dependence on sunlight and also a low level of hygiene. In this Research, a solar-powered Automatic Oven Machine prototype is made for chilli and ginger drying in mountainous areas. The solar-powered system as a supplier of electrical energy uses a solar panel Automatic Transfer Switch system. The selection of the title Automatic Solar Powered Oven Machine for Chilli and Ginger Dryer in Mountainous Areas aims to solve the problem of drying in mountainous areas which can cause a decrease in price and quality due to spoilage. The time used for testing this research tool is 6.53 hours, so the power required is 1506.95 Wh. The results of this study obtained the static characteristics of the temperature sensor have an accuracy of 99.21% and an error of 0.79%, while the weight sensor has an accuracy of 99.36% and an error of 0.64%. Max. overshoot at set point 50OC is 6.44% with a stedy state error of 5.46%
Implementasi Pemberdayaan Masyarakat Desa Mandiri Energi: Studi Kasus Desa Andungbiru Oleh Kelompok PLTMH Tirta Pijar dan Program CSR PT PLN Nusantara Power UP Paiton Kampung Setrum
Get PDFPemberdayaan masyarakat dengan konsep desa mandiri energi merupakan salah satu upaya penyediaan energi alternatif bagi masyarakat desa. Salah satu pemberdayaan dengan konsep desa mandiri energi terdapat di Desa Andungbiru Kecamatan Tiris Kabupaten Probolinggo. Pemberdayaan desa mandiri energi dilakukan melalui unit PLTMH oleh Kelompok PLTMH Tirta Pijar yang berkolaborasi dengan CSR PLN Nusantara Power UP Paiton pada program Kampung Setrum. Penelitian ini bertujuan untuk mengetahui implementasi desa mandiri energi di Desa Andungbiru berdasarkan analisis outcome pemberdayaan masyarakat yang dilakukan oleh Kelompok PLTMH Tirta Pijar berkolaborasi dengan CSR PLN Nusantara Power UP Paiton pada Program Kampung Setrum. Metode yang digunakan dalam penelitian ini adalah kualitatif dengan pendekatan studi kasus. Dalam pengambilan data, data primer diperoleh dari in-depth interview dan focus group discussion kepada informan yang ditentukan dengan metode purposive sampling. Sedangkan data sekunder bersumber dari dokumen CSR PLN Nusantara Power UP Paiton dan dokumen lainnya. Analisis data dilakukan dengan reduksi data, kategorisasi, penyajian data, dan penarikan kesimpulan menggunakan analisis outcome pemberdayaan masyarakat yang kemudian dilakukan uji keabsahan data dengan teknik triangulasi sumber dan validasi ahli. Hasil penelitian ini menggambarkan implementasi pemberdayaan masyarakat desa mandiri energi pada kelompok PLTMH Tirta Pijar; pembuatan keputusan dalam kelompok PLTMH Tirta Pijar, manajemen sumber daya manusia dan sumber daya alam oleh kelompok PLTMH Tirta Pijar, respon kelompok PLTMH Tirta Pijar terhadap permasalahan, dan dampak pemberdayaan masyarakat pada desa mandiri energi oleh kelompok PLTMH Tirta Pijar. Penelitian ini menghasilkan kesimpulan bahwa pemberdayaan masyarakat pada PLTMH Tirta Pijar telah sampai pada tingkatan tertinggi yaitu tingkat power-shift atau peralihan kekuasaan
Effect of Variation of Adsorbent and pH Doses on Boron Adsorption Using DMAPAA-co-DMAPAAQ Hydrogel
Get PDFBoron is very dangerous for living things. The boron concentration allowed for drinking water is less than 1 mg/L. If not standard, boron causes nausea, lethargy, diarrhea, vomiting, dermatitis, and a risk of miscarriage in pregnant women. Thus, this research investigated the effect of variations in adsorbent dosage and pH on boron adsorption using the DMAPAA-co-DMAPAAQ hydrogel. The research began with the hydrogel synthesis process, which continued with the batch-mode sorption study. Based on research results, the higher the adsorbent dosage, the more boron is adsorbed. The highest removal percentage with an adsorbent amount of 0.5 g/L was 19.89% for pH 3, and for an adsorbent dosage of 2 g/L was 19.52% for pH 9. The highest percent removal was at pH 11. The DMAPAA-co-DMAPAAQ hydrogel adsorbent is shown to be environmentally friendly compared to commercial resins because the commercial resins are not biodegradable, making them difficult to recycle, causing more damage to the environment