Jurnal Politeknik Negeri Batam (PoliBatam)
Not a member yet
3001 research outputs found
Sort by
Automatic License Plate Recognition (ALPRON) Using Optical Character Recognition Method
No full textManual parking systems are prone to inefficiencies and human error, especially with increasing vehicle density. This study proposes ALPRON, an automatic license plate recognition system using Optical Character Recognition (OCR) to automate motorcycle parking management. The system integrates Raspberry Pi 4, USB cameras, and Tesseract OCR to detect and recognize license plates in real-time. Performance testing was conducted under varying distances, lighting intensities, and camera angles. The results show that the system achieves a peak recognition accuracy of 98.75% at 70 cm, in bright lighting, and a 0° camera angle. These findings suggest that ALPRON is a potentially cost-effective and efficient solution for smart parking applications, particularly in controlled campus environments. While current limitations include daylight dependency and difficulty recognizing skewed angles plates, future improvements will address these through infrared support and deep learning enhancements
Generation Z Entrepreneurial Intentions in the Agricultural Sector in Batam Industrial City
No full textThis study aims to analyze the factors of generation Z entrepreneurial intentions in the agricultural sector in the industrial city of Batam. The population in this study is management students from 4 universities in Batam City with a total of 200 respondents. This research is a quantitative research. The method used to analyze the data is factor analysis. In this study, there are 19 variables that can be reduced to several factors with the results of the study showing that there are 5 new factors, namely economic improvement, decision-making, interest, entrepreneurship education and entrepreneurial confidence
PERAN KUALITAS AUDIT DALAM MEMODERASI PENGARUH PENGUNGKAPAN ESG TERHADAP NILAI PERUSAHAAN
No full textThis research seeks to analyze the role of audit quality in strengthening or weakening the impact of ESG disclosure on firm value (a case study of companies included in the ESG list on the Indonesia Stock Exchange (IDX) during the 2020-2022 period). The disclosures of environmental, social, and governance aspects are regarded as independent variables. Audit quality plays the role of a moderating variable. The dependent variable in this study is firm value. Agency theory and signaling theory underpin this research. The secondary data used in this study comes from the IDX, covering the years 2020 to 2022. The sample selection in this study was carried out through a targeted sampling approach, resulting in 102 observations. A moderated regression technique was applied to assess the hypotheses. The findings suggest that transparency in environmental, social, and governance aspects does substantially impact corporate value. Furthermore, audit quality as a moderating factor meaningfully affect the corporate valuation.Penelitian ini berusaha untuk menganalisis peran kualitas audit dalam memperkuat atau memperlemah dampak pengungkapan ESG terhadap nilai perusahaan (studi kasus pada perusahaan yang masuk dalam daftar ESG di Bursa Efek Indonesia (BEI) selama periode 2020-2022). Pengungkapan aspek lingkungan, sosial, dan tata kelola dianggap sebagai variabel independen. Kualitas audit berperan sebagai variabel moderasi. Variabel dependen dalam penelitian ini adalah nilai perusahaan. Teori keagenan dan teori sinyal mendukung penelitian ini. Data sekunder yang digunakan dalam penelitian ini berasal dari BEI, mencakup tahun 2020 hingga 2022. Pemilihan sampel dalam penelitian ini dilakukan melalui pendekatan targeted sampling, sehingga menghasilkan 102 observasi. Teknik regresi moderasi digunakan untuk menguji hipotesis. Hasil penelitian menunjukkan bahwa transparansi dalam aspek lingkungan, sosial, dan tata kelola secara substansial mempengaruhi nilai perusahaan. Lebih lanjut, kualitas audit sebagai faktor moderasi tidak secara signifikan mempengaruhi hubungan dengan nilai perusahaan
ANTESEDEN DAN KONSEKUENSI DIGITALISASI PELAPORAN KEUANGAN PADA UKM BIDANG REAL ESTATE DAN KONSTRUKSI DI JAWA TENGAH
No full textAdoption of digital-based accounting technology will help SMEs to produce quality financial information so that it can be a reference for business strategy decisions to improve business performance. The purpose of this study is to analyze the influence of antecedent variables, namely accounting knowledge, business experience, business strategy on the digitalization of financial reporting, and the consequences of digitalization of financial reporting on company performance in SMEs in the Real Estate and Construction Sector in Central Java. This study analyzes data using a variant-based Structural Equation Model (SEM) statistical method approach, with an alternative Partial Least Square (PLS) approach. The results of this study reveal that accounting knowledge and business strategy have a significant impact on the digitalization of financial reporting. In addition, the digitalization of financial reporting contributes significantly to company performance. However, business experience does not show a significant influence on the digitalization of financial reporting in SMEs.Penggunaan teknologi akuntansi berbasis digital dapat membantu UKM dalam menghasilkan informasi keuangan yang berkualitas, yang selanjutnya dapat menjadi dasar untuk pengambilan keputusan strategi bisnis guna meningkatkan kinerja usaha. Penelitian ini bertujuan untuk menganalisis pengaruh variabel anteseden, seperti pengetahuan akuntansi, pengalaman bisnis, dan strategi bisnis terhadap digitalisasi pelaporan keuangan. Selain itu, penelitian ini juga akan mengeksplorasi dampak digitalisasi pelaporan keuangan terhadap kinerja perusahaan pada UKM di sektor Real Estate dan Konstruksi di wilayah Jawa Tengah. Penelitian ini menganalisis data menggunakan pendekatan metode statistika Structural Equation Model (SEM) berbasis varian, dengan alternatif pendekatan Partial Least Square (PLS). Hasil penelitian ini mengungkapkan bahwa pengetahuan akuntansi dan strategi bisnis memiliki dampak signifikan terhadap digitalisasi pelaporan keuangan. Selain itu, digitalisasi pelaporan keuangan berkontribusi secara signifikan terhadap kinerja perusahaan. Namun, pengalaman bisnis tidak menunjukkan pengaruh yang signifikan terhadap digitalisasi pelaporan keuangan pada UKM
Usability Analysis of Online Travel Agent Applications Using System Usability Scale and Electroencephalography
Get PDFIn the digital era, technology has transformed the travel and tourism industry, with Online Travel Agents (OTAs) like Traveloka, Tiket.com, and Agoda offering convenient trip planning through digital platforms. Despite their popularity, issues such as navigation difficulties and unclear information still affect user satisfaction. This study aims to evaluate the usability of OTA applications using the System Usability Scale (SUS) based on the ISO 9241-11 standard and Electroencephalography (EEG) to analyze user physiological responses. The test involved 10 respondents and 4 task scenarios. The results showed that Traveloka achieved a SUS score of 85, with 95% effectiveness and 0.023 goals per second efficiency. Tiket.com scored 79 with 92.5% effectiveness and 0.026 goals per second efficiency, while Agoda scored 70 with 87.5% effectiveness and 0.016 goals per second efficiency. EEG data revealed that Traveloka and Tiket.com had the highest average alpha wave values, indicating respondents felt nervous or anxious, whereas Agoda showed higher beta wave values, suggesting respondents were calm and aware without full concentration. This study highlights that the usability of OTA applications is influenced by user experience, which can be measured subjectively through SUS and more deeply using EEG data to understand physiological responses when interacting with the application
Indonesian Food Classification Using Deep Feature Extraction and Ensemble Learning for Dietary Assessment
Get PDFFood is a cornerstone of culture, shaping traditions and reflecting regional identities. However, understanding the nutritional content of diverse cuisines can be challenging due to the vast array of ingredients and the similarities in appearance across different dishes. While food provides essential nutrients for the body, excessive and unbalanced consumption can harm health. Overeating, particularly high-calorie and fatty foods, can lead to an accumulation of excess calories and fat, increasing the risk of obesity and related health issues such as diabetes and heart disease. This paper introduces a novel ensemble learning approach with a dictionary that contains food nutrition content for addressing this challenge, specifically on Padang cuisine, a rich culinary tradition from West Sumatera, Indonesia. By leveraging a dataset of nine Padang dishes, the system employs image enhancement techniques and combines deep feature extraction and machine learning algorithms to classify food items accurately. Then, depending on the classification results, the system evaluates the nutritional content and creates a dietary evaluation report that includes the amount of protein, fat, calories, and carbs. The model is evaluated using different evaluation metrics and achieving a state-of-the-art accuracy of 85.56%, significantly outperforming standard baseline models. Based on the findings, the suggested approach can efficiently classify different Padang dishes and produce dietary assessments, enabling personalised nutritional recommendations to provide clear information on a balanced diet to enhance physical and overall wellness
Optimizing Powertrain Disassembly Efficiency via Machine Learning -Based Lean Six Sigma at PT. TU Surabaya Branch
Get PDFOperational efficiency is vital in mining and construction, were equipment availability drives productivity. This study assesses reconditioning effectiveness for Powertrain components at PT. TU Surabaya, focusing on the Disassembly stage the primary bottleneck in the maintenance cycle. Lean Six Sigma is applied using the DMAIC (Define, Measure, Analyze, Improve, Control) framework to identify, measure, and regulate service duration factors. Machine Learning, via Decision Tree Regression in KNIME, analyzes historical data to predict optimal Disassembly timeframes. Efficiency improvement is implemented using the 5S method, while a Decision Matrix prioritizes solutions to enhance overall system performance. Results from initial implementation show a reduction in average process duration from 26.37 days to 15.33 days. Predictive analysis also reflects an increase in Process Cycle Efficiency (PCE) from 46.49% to 53.20%. These findings affirm the effectiveness of a structured, data-driven operational strategy that combines Lean Six Sigma and predictive analytics to resolve service bottlenecks and improve industrial process outcomes
An Sosialisasi Strategi Pemasaran Digital Pasca Panen Hidroponik Bagi Siswa Ekstrakulikuler Green Be di SMAN 1 Pemali
No full textThe agricultural sector continues to experience a decline in income, largely due to a mismatch between production capacity and the empowerment of farmers in post-harvest product marketing. This issue is exacerbated by the continued reliance on traditional marketing practices, which limit farmers\u27 access to broader consumer markets. Thus, addressing this gap is critical for enhancing farmers\u27 bargaining power by facilitating direct connections between producers and consumers. This community initiative aimed to enhance the capacity of millennial young farmers to digitally market post-harvest hydroponic agricultural products through the TikTok e-commerce platform. The program employed educational seminars and hands-on training focused on digital marketing strategies and the utilization of e-commerce tools. The participants comprised 30 students from SMAN 1 Pemali, all members of the "Green Be" extracurricular group. The result, conducted through semi-structured interview incorporating a combination of structured (closed-ended) and exploratory (open-ended) questions, indicated that 85% of participants demonstrated a significantly improved understanding of digital marketing concepts, including the marketing mix, promotion mix, and content creation. Moreover, participants reported increased proficiency in leveraging TikTok as a marketing platform for hydroponic agricultural products. These findings highlight the critical role of human resource development in advancing post-harvest agricultural marketing through innovative and sustainable digital strategies, contributing meaningfully to the broader objectives of Sustainable Agricultural Development.Pendapatan di sektor pertanian menunjukkan kecenderungan penurunan yang terus berlanjut. Salah satu penyebab utama dari kondisi ini adalah kurangnya upaya pemberdayaan petani dalam hal pemasaran produk pasca panen, meskipun kapasitas produksi mengalami peningkatan. Hal ini terjadi karena sebagian besar petani masih mengandalkan metode pemasaran tradisional, sehingga membatasi petani untuk menjangkau konsumen yang lebih luas. Oleh sebab itu, perlu dilakukan intervensi strategis untuk meningkatkan posisi/harga tawar petani melalui pendekatan yang memungkinkan terjalinnya hubungan langsung antara produsen dan konsumen. Kegiatan pengabdian ini dirancang untuk memperkuat kapasitas petani milenial dalam memasarkan produk-produk pertanian hidroponik pasca panen secara digital melalui pemanfaatan platform e-commerce TikTok. Program ini menggunakan metode penyuluhan dan praktik langsung mengenai strategi pemasaran digital serta penggunaan teknologi e-commerce. Program ini melibatkan 30 siswa dari SMAN 1 Pemali yang tergabung dalam ekstrakurikuler Green Be, sebagai representasi generasi muda petani. Berdasarkan hasil evaluasi menggunakan metode close and open-ended semi-structure interview, hasil kegiatan ini menunjukkan bahwa sebesar 85% peserta mengalami peningkatan pengetahuan terhadap konsep pemasaran digital produk pasca panen hidroponik, yang meliputi konsep bauran pemasaran (mix marketing), promosi pemasaran (promotion mix), dan konten digital. Selain itu, adanya peningkatan keterampilan siswa dalam melakukan penjualan produk pasca panen hidroponik melalui platform media digital TikTok. Dengan demikian, pemberdayaan sumber daya manusia dalam memasarkan produk pertanian pasca panen secara luas menggunakan metode-metode pemasaran terbarukan dan modern memiliki dampak yang sangat besar demi mendukung sektor pertanian yang berkelanjutan (Sustainable Agriculture Development) di masa depan
Scientific Paper Recommendation System: Application of Sentence Transformers and Cosine Similarity Using arXiv Data
Get PDFSearching for relevant scientific literature faces complex challenges due to the proliferation of academic publications. This research develops a semantic similarity-based scientific paper recommendation system by utilizing Sentence Transformer (all-MiniLM-L6-v2 model) and cosine similarity algorithm on arXiv dataset (15,504 papers in Computer Science). The system is implemented as a Streamlit-based interactive web application that accepts user queries and recommends related papers based on semantic similarity. Performance evaluation using Precision, Mean Average Precision (MAP), Mean Reciprocal Rank (MRR), and Normalized Discounted Cumulative Gain (NDCG) metrics showed that embedding text from the Introduction section without pre-processing yielded the best performance (NDCG: 0.7590; MAP: 0.6960; MRR: 0.7254), outperforming Abstract-based or text combination approaches. A user test of 45 respondents confirmed the effectiveness of the system: 95.5% expressed satisfaction with the relevance of the recommendations, and 93.3% confirmed a significant reduction in manual search time. The findings prove that retaining the raw text structure in the Introduction is optimal for semantic representation. Development suggestions include multidomain dataset expansion and transformer model optimization for accuracy improvement
Clustering Korean Drama Viewers’ Preferences for Marketing Strategy Optimization Using the K-Means Algorithm on the MyDramaList Platform
Get PDFKorean dramas are highly popular in Indonesia, but it is a challenge for marketers to understand the diverse tastes of the audience. This study aims to identify audience preference segments by applying the K-Means algorithm to perform clustering. The analysis was conducted on 500 Korean dramas from the MyDramaList platform released in the period 2020 to 2023. Features used in the clustering process include rating, number of viewers (no_of_viewers), year of release (year), and genre. To overcome the multi-label genre, this research uses one-hot encoding technique to convert categorical data into numerical format. The optimal number of clusters was determined as four (4) based on analysis using the Elbow Method. The analysis successfully identified four distinct audience segments. Cluster 1 is the largest market segment which includes 323 dramas with a dominant genre of “Drama and Romance” and an average rating of 7.64. In contrast, Cluster 2 is a high-quality niche segment consisting of only 16 dramas but has the highest average rating (8.29) as well as the highest average viewership (25,739), with the dominant genre of “Drama and Mystery”. The other two segments are Cluster 0 (58 dramas) which focuses on the “Thriller” and ‘Mystery’ genres, and Cluster 3 (147 dramas) which features the “Comedy, fantasy and romance” genres. These data-driven findings enable the development of more specific and targeted marketing strategies for each audience profile, thereby improving promotional effectiveness as well as the viewing experience