IKADO E-Journal (Institut Informatika Indonesia)
Not a member yet
470 research outputs found
Sort by
Inovasi Pengolahan Limbah Kotoran Ayam Menjadi Pupuk Kompos Organik di Desa Rombasan, Sumenep
No full textDesa Rombasan merupakan salah satu desa di Kecamatan Pragaan, Kabupaten Sumenep yang sebagian besar masyarakatnya memiliki usaha peternakan ayam petelur. Hasil dari peternakan tersebut berupa telur ayam yang selama ini menjadi penunjang perekonomian masyarakat. Akan tetapi, masyarakat tidak menyadari bahwa limbah kotoran ayam juga dapat dimanfaatkan sebagai penunjang perekonomian. Oleh karena itu, diperlukan terobosan produk yang berasal dari limbah kotoran ayam menjadi pupuk kompos dengan metode fermentasi. Proses pelaksanaan program pembuatan pupuk kompos melalui tiga tahapan yaitu uji coba pembuatan pupuk kompos, penyuluhan tentang pertanian organik dan pelatihan pembuatan produk pupuk kompos yang dilaksanakan di Balai Desa Rombasan Kecamatan Pragaan Kabupaten Sumenep. Adapun hasil dari tahapan uji coba pembuatan menghasilkan produk pupuk kompos padat dan proses penyuluhan dan pelatihan pembuatan pupuk kompos dihadiri oleh Aparat Desa, ibu Kepala Desa, Ibu-ibu PKK, Ibu-ibu anggota Fatayat NU dan masyarakat Desa Rombasan. Tujuan dari program pembuatan produk pupuk kompos yaitu agar masyarakat dapat mengolah limbah kotoran ayam yang selama ini menjadi pencemar lingkungan sehingga kesehatan masyarakat dapat terjaga dan bebas dari bakteri yang terkandung dalam limbah kotoran ayam dan dapat membantu perekonomian masyarakat dengan melalui pengolahan limbah kotoran ayam menjadi produk yang bernilai ekonomi dan memberikan inovasi dan kreatifitas produk sebagai media pembangunan di Desa Rombasan, Kecamatan Pragaan, Kabupaten Sumenep
LyFy: Enhancing Batik E-Commerce Live Streaming Through Real-Time Chat Filtering and Product Recommendation
Full text linkLive streaming has emerged as an essential tool for e-commerce, allowing sellers to engage with potential customers in real-time. However, the massive influx of comments during these sessions often includes a mix of useful product-related queries and irrelevant or distracting messages, which can overwhelm the presenter and reduce the effectiveness of the stream. In this paper, we propose LyFy, a browser-based extension designed to filter live chat messages and provide personalized product recommendations in real-time, specifically applied in Batik e-commerce to support the preservation and promotion of this unique cultural heritage of Indonesia. Our system uses a combination of natural language processing (NLP) and machine learning models to identify relevant comments, group similar queries, and offer product suggestions based on viewers\u27 interests. We demonstrate the effectiveness of this system through a prototype implementation and evaluate its performance with qualitative feedback from streamers and users. The evaluation results indicate high user satisfaction, with over 51% of respondents rating LyFy as highly effective and 52% as highly efficient, making it a valuable tool for enhancing e-commerce live streaming interactions
Implementation and Analysis of Container Image Optimization Using Alpine Linux and Multi-Stage Builds
Full text linkContainerization enables isolation within a host, with Docker being a popular tool for packaging applications and their dependencies in container images. However, challenges like slow build processes and bloated image sizes can consume resources, slow down builds, and pose security risks. This study optimizes Docker images by combining the Alpine base image with multi-stage builds, analyzing size, build speed, and security across different combinations and environments to identify and propose the most efficient combination solution. The approach used is a quantitative quasi-experiment with a within-subject design. The sample used was a JavaScript framework, with the main experimental group being the combination of Alpine and multi-stage builds, while the comparison group included combinations of Node and Node-Alpine, both in single-stage and multi-stage configurations, as well as single-stage Alpine. Data was obtained from CI/CD, container registry, and Trivy reports. Analyzed by descriptive analysis, One-Way ANOVA or Kruskal Wallis test, and post-hoc test. The results show that combining multi-stage builds with Alpine is considered best practice because it produces the smallest image size, reducing it by up to 94% compared to single-stage Node. It also achieves the shortest build times across all environments and presents low vulnerability issues. However, it is important to note that while the Alpine multi-stage combination offers the most efficient build times, it experiences a 1.3x increase in duration in low-spec environments
Implementation of Blockchain Technology for Image Plagiarism Detection Using DCT, AES128, and SHA-1 Algorithms
Full text linkPlagiarism encompasses the act of appropriating high-quality user-generated content as if it were one\u27s own intellectual property. Image plagiarism can be conceptualized as a broader category that encompasses the challenges of detecting copied images. Identifying instances of plagiarism is of paramount importance not only for graphic designers, professional photographers, and bloggers but also for publishing entities and legal practitioners seeking to uncover unauthorized reproductions of their creations. In addressing this issue, the implementation of blockchain technology presents a viable solution. Fundamentally more than just a collection of interconnected blocks, blockchain is characterized by the systematic recording of digital signatures or hashes of each block. Blockchain is essentially more than just a collection of interconnected blocks; it is characterized by the systematic recording of a digital signature or hash of each block. To generate the hash, cryptographic methods can be applied. This study aims to develop a web-based application that is adept at detecting image plagiarism through the application of blockchain technology. Images submitted by users will undergo plagiarism detection by an application that uses blockchain methodology. This study applies the DCT method to extract features from images, then uses the AES-128 and SHA-1 methods to generate blockchain. The results of this study are in the form of a website that can be used to detect image plagiarism. From the results of the tests carried out, it was obtained that the combination of the DCT, AES-128 and SHA-1 methods can detect image plagiarism with an accuracy of 100%. This means that the combination of these methods can be applied to carry out the process of detecting image plagiarism with a very high level of accuracy
Development of a Modified CycleGAN Model with Residual Blocks and Perceptual Loss for Image Dehazing
No full textFog reduces image contrast and clarity, creating challenges for applications such as autonomous driving and remote sensing. This study proposes a series of CycleGAN modifications for single image dehazing using unpaired data, integrating residual blocks, attention mechanisms, VGG19-based perceptual loss, and haze-aware loss. Among ten architectural variants, Modification 10 combining perceptual and haze-aware loss achieved the best overall performance. Quantitatively, it showed stable generator losses (0.91 for Gen G, 0.57 for Gen F), with improved discriminator performance (Disc X: 0.59, Disc Y: 0.47), indicating better training stability and image realism. Additionally, it offered competitive PSNR (7.99), strong SSIM (0.4202), and low LPIPS (0.6577), confirming its effectiveness in both pixel-level accuracy and perceptual quality. Qualitatively, this model generated clearer, more natural images with improved edge sharpness and detail preservation. These findings demonstrate that the modified CycleGAN significantly enhances dehazing performance and presents a valuable contribution to deep learning-based image restoration
Optimization of Village Grouping Using Comparison of K-Means and K-Medoids Methods
No full textSumenep Regency is the largest agricultural area in Madura and a major producer of food crops such as rice, corn, and vegetables. However, agricultural productivity in some areas has declined due to uneven fertilizer distribution and limited knowledge about plant diseases and their treatment. To address this, a village clustering system is needed to help the Agriculture Office identify areas with high and low productivity, enabling more targeted assistance and resource allocation. This study aims to classify villages based on agricultural productivity to support better decision-making in agricultural development. Two clustering methods, K-Means and K-Medoids, were applied and compared. K-Means determines cluster centers based on the average of data points, while K-Medoids selects the most representative data point within each cluster. The data used in this research is 690 datasets in 2023. Before clustering is carried out, the data is preprocessed first. Data Pre-processing steps include data transformation, label encoding, imputation, and Min-Max normalization. Cluster optimization was performed using the Sum of Squared Errors (SSE) method. The results show that K-Medoids offers more stable clustering, especially in the presence of outliers, while K-Means is more efficient in computation. The best clustering result was achieved using K-Means with five clusters (K = 5), producing the lowest SSE value of 29.8. These findings can assist local governments in prioritizing agricultural support based on village productivity profiles
Application of the Simple Additive Weighting Method in the Selection Process for Recipients of the 1000 Anak Negeri Scholarship at Nusa Putra University
Full text linkThe 1000 Anak Negeri Scholarship at Nusa Putra University supports outstanding students from underprivileged families, yet its manual selection process is inefficient, subjective, and lacks transparency, leading to delays and potential misjudgments. This study aims to develop a Decision Support System (DSS) using the Simple Additive Weighting (SAW) method to enhance the accuracy, efficiency, and fairness of scholarship selection. The system evaluates applicants based on eight criteria: poverty status, parental occupation, income, family dependents, parental status, academic achievement, non-academic achievement, and Quran recitation ability, with assigned weights ensuring objective ranking. The SAW method normalizes decision matrices and calculates final scores to determine recipients, significantly improving efficiency and transparency compared to manual selection. The top-ranked recipient achieved a final score of 0.7765, followed by scores of 0.743, 0.625, 0.6105, and 0.584, demonstrating a more structured and reliable selection process. The automated approach reduces processing time, minimizes human errors, and ensures systematic selection based on predefined criteria. This research confirms that the SAW method provides a more accurate and reliable decision-making process, making scholarship distribution fairer and more targeted. The implementation of this system at Nusa Putra University serves as a model for other educational institutions to optimize their scholarship selection processes, ensuring that financial aid reaches students who need it most while improving transparency, efficiency, and decision-making accuracy
Sentiment Analysis On Tripadvisor Travel Agent Using Random Forest, Support Vector Machines, and Naïve Bayes Methods
Full text linkTripAdvisor faces problems in improving the quality of service on its application, namely the presence of unexpected or non-functional features, which can affect the user experience and reduce trust in the application. This research aims to develop an application capable of performing sentiment analysis on TripAdvisor application user reviews on the Google Play Store with negative, positive, and neutral classifications using the Random Forest (RF), Support Vector Machine (SVM), and Naïve Bayes (NB). The RF method was chosen in this study because of its ability to handle large and complex data very accurately, while SVM is able to classify data on a large scale and is resistant to overfitting, while NB is able to classify text with clear probabilities. The Lexicon-based method as data labelling. The results of sentiment analysis from 1500 reviews with web scrapping show the classification of positive, negative, and neutral sentiments of 48, 726, and 646 data, respectively. Model performance in RF, SVM, and NB testing gets an accuracy value of 94%, 93.6%, and 77.8%, respectively. The RF model produces the best accuracy compared to other methods. The RF model produces the best accuracy compared to other methods. The results of sentiment analysis from 1500 user reviews allow developers to identify features that are often criticized or do not function properly in their application services
Enhancing Consumer Decision-Making in Skincare: Implementation of the VIKOR Method for Product Recommendation Systems
No full textThe challenge of selecting the most suitable skincare products, particularly sunscreens, has become increasingly complex due to the overwhelming variety of choices available on the market. Consumers are often confronted with a plethora of products, making it difficult to discern which one best suits their needs. This study seeks to address this issue by employing the VIKOR multi-criteria decision-making (MCDM) method, which offers a structured approach to product selection based on various factors that are highly relevant to consumers. The VIKOR method, which focuses on minimizing regret and finding the closest compromise solution, is especially suited for handling decisions that involve conflicting criteria. In this study, five key criteria—skin type, brand origin, price, SPF rating, and UVA protection grade—were identified as being of particular importance to consumers. A dataset of 175 sunscreens formulated for oily skin and produced locally was systematically analyzed using the VIKOR algorithm. This method enabled the normalization and aggregation of diverse criteria, allowing for an objective, data-driven comparison of the products. The VIKOR-based approach efficiently ranked the sunscreens and identified AZARINE Hydramax-C Sunscreen Serum as the optimal product. This sunscreen achieved the lowest Q value of 0.07, signifying that it represented the best compromise solution across all criteria. The study’s findings not only highlight the practical value of advanced decision-making tools in the context of consumer product selection but also contribute to broader discussions on consumer behavior and decision-making frameworks. By demonstrating the efficacy of the VIKOR method, this research paves the way for its future application in various industries, offering a replicable and adaptable model for improving decision processes in consumer goods selection across diverse markets
Memperkuat Kreativitas Generasi Muda “Capcut: Inovasi Media Visual Kreatif”
No full textMemasuki tahun 2024, media digital menjadi nomor satu diantara media lainnya. Dengan adanya media digital berbagai kalangan masyarakat ingin menjadi bagian dari perkembangan digital tidak terkecuali siswa sekolah menengah kejuruan (SMK). Siswa SMK dituntut memiliki skill yang mumpuni sebelum masuk kedunia kerja ataupun perguruan tinggi. Skill editing vidio menjadi salah satu skill yang paling dibutuhkan karena tingginya permintaan konten berkualitas hampir untuk semua jenis bisnis ataupun usaha. Kebutuhan akan pembuatan konten berkualitas membuat siswa SMK yang nantinya harus siap bekerja ataupun ingin memulai usaha membutuhkan kemampuan untuk memenuhi permintaan pembuatan konten tersebut. Saat ini skill editing vidio siswa SMK diwilayah medan belum sebaik para konten creator yang berada di daerah jawa. Konten-konten yang diproduksi biasanya masih hanya sebatas daily vlog sederhana, ASMR, ataupun konten hiburan mengikuti tren Tiktok, sedangkan kebutuhan saat ini lebih kepada konten kreatif untuk pemasaran produk ataupun jasa, konten edukasi, sampai personal branding. Karena kebutuhan tersebut, siswa SMK harus mulai mengembangkan minat dan bakatnya yang bertujuan menjadi portofolio mereka untuk memasuki perguruan tinggi ataupun dunia kerja. Maka dari itu, penulis menawarkan kegiatan pelatihan yang berhubungan dengan peningkatan skill editing siswa SMK. CAPCUT salah satu aplikasi yang mampu menjadi media inovasi visual kreatif, dimana aplikasi CAPCUT dapat digunakan untuk membuat konten kreatif dengan berbagai tools yang ditawarkan sehingga konten yang dihasilkan menjadi lebih variatif. Solusi yang kami tawarkan adalah mengajarkan siswa SMK dalam menggunakan aplikasi CAPCUT serta memberikan tips dan trik penggunaan tools aplikasi tersebut agar dapat menambah skill siswa SMK dalam mengikuti perkembangan media digital