Abstract:Abstract: Understanding students’ emotional conditions is important for evaluating engagement and learning atmosphere in classroom environments. However, conventional evaluation methods are often subjective and difficult…
lt to apply in real time. Therefore, this study proposes a real-time multi-face emotion detection system designed for classroom learning environments. The system integrates a CNN-based Tiny Face Detector for multi-scale face localization with a convolutional neural network to classify seven facial emotions: angry, disgust, fear, happy, sad, surprise, and neutral. Experimental evaluation was conducted using classroom video data under varying lighting conditions, face orientations, partial occlusions, and different numbers of detected faces per frame. The proposed system achieves stable real-time performance with processing speeds ranging from 10–20 FPS, depending on face density. The results show higher recognition performance for expressive emotions, while subtle emotions remain more challenging. Overall classification accuracy reaches above 80% when emotion predictions are aggregated across multiple faces and time windows. These results indicate that the proposed system is suitable for objective analysis of emotional dynamics in classroom environments and supports the deployment of lightweight emotion-aware monitoring systems for educational applications.
Keywords: classroom monitoring; convolutional neural network; facial emotion recognition; multi-face detection; tiny face detector.
Abstrak: Pemahaman terhadap kondisi emosional mahasiswa penting untuk mengevaluasi keterlibatan dan suasana pembelajaran di kelas. Namun, metode evaluasi konvensional umumnya bersifat subjektif dan sulit diterapkan secara real-time. Oleh karena itu, penelitian ini mengusulkan sistem deteksi emosi multi-wajah secara real-time yang dirancang untuk lingkungan pembelajaran di kelas. Sistem mengintegrasikan Tiny Face Detector berbasis CNN untuk pelokalan wajah multi-skala dengan jaringan saraf konvolusional untuk mengklasifikasikan tujuh emosi wajah, yaitu marah, jijik, takut, senang, sedih, terkejut, dan netral. Evaluasi eksperimen dilakukan menggunakan data video kelas dengan variasi kondisi pencahayaan, orientasi wajah, oklusi parsial, serta jumlah wajah yang berbeda dalam satu frame. Sistem menunjukkan kinerja real-time yang stabil dengan kecepatan pemrosesan antara 10–20 FPS, bergantung pada kepadatan wajah. Hasil pengujian menunjukkan kinerja yang lebih baik pada emosi ekspresif, sementara emosi dengan ciri halus lebih menantang untuk dikenali. Akurasi klasifikasi keseluruhan mencapai di atas 80% ketika hasil emosi diagregasi berdasarkan banyak wajah dan interval waktu. Hasil ini menunjukkan bahwa sistem yang diusulkan berpotensi digunakan untuk analisis objektif dinamika emosi di kelas serta mendukung pemantauan lingkungan pembelajaran berbasis kecerdasan buatan.
Kata kunci: pengenalan emosi wajah; deteksi multi-wajah; Tiny Face Detector; jaringan saraf konvolusional; pemantauan kelas.
Abstract:Abstract: Ms Glow Kisaran Original Store is one of the beauty companies that sells skincare products that are useful for maintaining healthy facial and body skin. However, the Original Ms. Glow series currently faces challenges…
hallenges such as tight competition and ineffective inventory management in terms of sales figures. This company sells ± 1500 products a month, but also often faces shortages and stockpiles of product, which can reduce customer confidence and cause Ms. Glow Kisaran Original to experience financial losses, among others. Conversely, if the demand for skincare increases but the skincare supply cannot be prepared, this is a loss for the store and customers. The purpose of this study is to improve the accuracy of the forecast, the use of the Single Exponential Smoothing Method is proposed. This method smoothes past values with exponential weights, placing greater emphasis on the latest data. The use of data from the last 12 months as reference data for past recording for forecasting experiments for the next 1 (one) month. The results of the study at Ms Glow Kisaran show the flexibility of the method in adapting to different sales dynamics. Overall, this research helps in predicting skincare sales predictions at the Ms Glow Kisaran Original Kisaran Store using the Single Exponentian Smoothing method, so that it can overcome the challenges in predicting sales figures.
Keywords: ms glow kisaran; skincare sales; ses.
Abstrak: Toko Ms Glow Kisaran Original merupakan salah satu perusahaan di bidang kecantikan yang menjual produk-produk skincare yang bermanfaat untuk menjaga kesehatan kulit wajah dan tubuh. Namun rangkaian Original Ms. Glow saat ini menghadapi tantangan seperti persaingan yang ketat dan pengelolaan inventaris yang kurang efektif dalam hal angka penjualan. Perusahaan ini menjual ±1500 produk dalam sebulan, namun juga sering menghadapi kekurangan dan penumpukan stok produk, yang dapat menurunkan kepercayaan pelanggan dan menyebabkan Ms. Glow Kisaran Original mengalami kerugian finansial. Sebaliknya jika permintaan akan skincare meningkat namun persediaan skincare tidak dapat disiapkan maka ini menjadi kerugian bagi pihak toko dan pelanggan. Tujuan penelitian ini adalah untuk meningkatkan ketepatan perkiraan, penggunaan Metode Single Exponential Smoothing diusulkan. Metode ini menghaluskan nilai masa lalu dengan bobot eksponensial, memberikan penekanan lebih besar pada data terbaru. Penggunaan data 12 bulan terakhir sebagai data acuan pencatatan masa lalu untuk percobaan peramalan untuk 1 (satu) bulan kedepan. Hasil penelitian pada Ms Glow Kisaran menunjukkan fleksibilitas metode dalam menyesuaikan diri dengan dinamika penjualan yang berbeda. Secara keseluruhan, Penelitian ini membantu dalam meramalkan prediksi penjualan skincare di Toko Ms glow Kisaran Original Kisaran menggunakan metode Single Exponentian Smoothing, sehingga dapat mengatasi tantangan dalam memprediksi angka penjualan.
Kata kunci: ms glow kisaran; penjualan skincare; ses.
Abstract:Abstract: Unemployment is a global economic issue that directly impacts human life in both developed and developing countries, especially in Indonesia, which, if ignored, will severely impact society's social dynamics. To…
o overcome this problem, forecasts are made so that later, the government can take policies to control and suppress the unemployment growth rate. This research aims to predict unemployment in Indonesia in 2023 using the Weighted Moving Average method, widely used to determine the trend of a time series, which is part of one of the Time Series methods that gives different weights. The dataset used was obtained from the Central Statistics Agency (BPS) relating to unemployment data from 2000 to 2022 (23 years). To analyze the level of accuracy of the results of this unemployment forecast using the MAD, MSE, and MAPE methods. This research concludes that the Weighted Moving Average method can be applied in predicting unemployment in Indonesia in 2023. The results of this research are a prediction of the number of unemployed in Indonesia, as many as 8,874,942 people at a weight value of 3 (three) where the accuracy of the MAD value is 745786.1833, the MSE value is 948402050986.3 and MAPE is 8.28%.
Keywords: forecasting; unemployment; weigth moving average; indonesia
Abstrak: Pengangguran menjadi isu ekonomi global yang berdampak secara langsung terhadap tingkat kehidupan manusia di negara-negara yang sudah maju maupun yang sedang berkembang khususnya di negara Indonesia, yang jika diabaikan akan berdampak serius terhadap dinamika sosial masyarakat. Untuk mengatasi permasalahan tersebut dibuatlah peramalan agar nantinya pemerinta dapat mengambil kebijakan dalam mengendalikan dan menekan angka pertumbuhan pengangguran tersebut. Penelitian ini bertujuan untuk memprediksi pengangguran di Indonesia pada tahun 2023 menggunakan metode Weighted Moving Average dimana metode ini banyak digunakan untuk menentukan trend dari suatu deret waktu yang merupakan bagian dari salah satu metode Time Series yang memberikan bobot yang berbeda-beda. Adapun dataset yang digunakan diperoleh dari Badan Pusat Satatistik (BPS) berkaitan dengan data pengangguran dari tahun 2000 sampai dengan tahun 2022 (selama 23 tahun). Untuk menganalisa tingkat akurasi dari hasil peramalan pengangguran ini memakai metode MAD, MSE, dan MAPE. Kesimpulan dari penelitian ini yaitu dapat diterapkannya metode Weighted Moving Average dalam memprediksi pengangguran di Indonesia pada tahun 2023. hasil dari penelitian ini berupa prediksi jumlah pengangguran di Indonesia sebanyak 8.874.942 orang pada nilai bobot 3 (tiga) dimana akurasi nilai MAD sebesar 745786,1833, nilai MSE sebesar 948402050986,3 dan MAPE sebesar 8,28 %.
Kata kunci: peramalan; pengangguran; weigth moving average; indonesia
Abstract:This study examines how employees perceive and trust Algorithmic Performance Appraisal (APA) in digital-native and technology-driven companies. Adopting Organizational Justice Theory, the Trust in Technology Framework, and…
nd Cognitive Appraisal Theory, the research explores both the direct and indirect effects of APA on employee trust, with Perceived Procedural Fairness (PPF) as a mediating variable. The study uses a quantitative, cross-sectional approach, collecting data from 200 employees in technology-based organizations and analyzing the data with Partial Least Squares Structural Equation Modeling (PLS-SEM). Results show that APA significantly enhances both procedural fairness and employee trust, with PPF playing a partial mediating role in this relationship. These findings underscore the importance of transparency, procedural legitimacy, and avenues for employee voice in cultivating trust in algorithmic systems. The study’s theoretical contribution lies in its integration of multiple perspectives on trust and fairness within algorithmic HR management. The practical implication calls for the careful design and implementation of APA systems that employees perceive as fair and trustworthy. Future research should investigate these relationships in longitudinal and multi-contextual settings to deepen the understanding of trust dynamics in evolving AI-mediated work environments.
Abstract:The rapid advancement of digital technology and artificial intelligence (AI) in the twenty-first century has fundamentally transformed the structure of modern constitutional governance. Digitalization has reshaped the interactions…
teractions between governments and citizens, altered the patterns of political participation, and presented major challenges to constitutional principles. This study aims to analyze the implications of technological development for constitutional law and propose the concept of a digital constitution as an adaptive framework in the AI era. This study employs a normative legal method, using both conceptual and statutory approaches. Legal materials consist of primary, secondary, and tertiary sources, which are analyzed qualitatively and descriptively. The findings reveal that, while digital transformation enhances governmental efficiency and public transparency, it also generates serious risks, including data misuse, digital surveillance, and political disinformation. These dynamics demand a reinterpretation of constitutional norms to protect citizens' digital rights in cyberspace. The concept of a digital constitution is proposed as a normative response that integrates digital rights into constitutional rights and reaffirms the principle of the rule of law within technological governance. To achieve a democratic and just constitutional order, it is crucial to strengthen regulatory frameworks, ensure algorithmic accountability, and foster collaboration among state institutions, civil society, and the private sector. Ultimately, constitutional law must evolve into an adaptive, transparent, and fair system that can address the profound challenges of the digital and AI-driven era.
Abstract:The increasing complexity and dynamics of the business environment at local, regional, and global levels have driven PT PLN (Persero)’s Internal Audit Unit (SPI) to adopt a Purpose-Driven Internal Audit approach, positioning…
ioning the audit function as a strategic partner for long-term organizational success. However, the Internal Stakeholder Satisfaction Index for assurance services in the Construction, Generation, and New Renewable Energy Audit Division (AKP) fell short of its targets in 2023 and 2024. This study aims to analyze the impact of audit service quality—comprising tangibles, reliability, responsiveness, assurance, and empathy—on auditee satisfaction. Using a quantitative approach with PLS-SEM and Importance–Performance Map Analysis (IPMA), data were collected from AKP Division auditees in 2024. The results show that all dimensions of audit service quality positively and significantly influence satisfaction, with responsiveness and empathy being the most dominant factors. The findings offer practical insights for SPI PLN in prioritizing service improvements based on user perceptions and provide theoretical support for the SERVQUAL model as a key psychological mechanism in fostering satisfaction within trust-based professional services
Abstract:Nasi tutug oncom is a traditional Sundanese dish, which is not only a food but also reflects the rich culture and life of the Sundanese people. The purpose of this study examines the uniqueness of nasi tutug oncom and how…
w this dish acts as a tool to express the values, identity, and social dynamics of Sundanese society that continues to evolve in the midst of globalization. The method used is descriptive qualitative method with data acquisition through literature study, interviews with culinary experts and the community, and analysis of how tutug oncom rice is presented in various media, this research tries to reveal the deep meaning behind tutug oncom rice. The research sample is tutug oncom rice. The results show that nasi tutug oncom is more than just food; it symbolizes the hospitality, local wisdom and food security of the Sundanese people. The process of making it, serving it, and eating it, is full of meanings that reflect the values of mutual cooperation, simplicity, and respect for nature. In this era of globalization, nasi tutug oncom faces both challenges and opportunities. On the one hand, this dish can become an Indonesian culinary icon that can be recognized worldwide. However, on the other hand, nasi tutug oncom is vulnerable to changes that can eliminate its uniqueness and original characteristics. This research suggests the importance of preserving and developing nasi tutug oncom without sacrificing its cultural and philosophical significance. Overall, this research shows that food is not just a daily necessity. Through nasi tutug oncom, we can see that food has deep social and cultural aspects, which are important for preserving local cultural diversity.
Abstract:Tax avoidance represents a strategic maneuver by taxpayers to minimize their tax burden by capitalizing on the intricacies of tax legislation. This complex phenomenon encompasses a range of tactics, including leveraging…
exemptions, deductions, tax incentives, non-taxable income, deferring tax liabilities, and, regrettably, engaging in unethical practices such as bribery and forgery. This study seeks to unravel the intricate relationships between profitability, solvency, capital intensity, and company size regarding tax avoidance within the manufacturing sector, specifically targeting food and beverage firms listed on the Indonesia Stock Exchange from 2017 to 2022. Employing the Cash Effective Tax Rate (CETR) as a proxy for tax avoidance, we meticulously selected a sample of 70 companies through purposive sampling based on rigorous criteria. Our analysis, conducted via multiple linear regression using SPSS 25, reveals compelling insights: profitability, solvency, and capital intensity significantly bolster tax avoidance strategies, while larger company size appears to dampen these efforts. Collectively, these factors create a multifaceted influence on tax avoidance behaviors, highlighting the intricate dynamics at play within the corporate landscape.
Abstract:This study aims to investigate the dynamics of tax avoidance in energy sector companies listed on the Indonesia Stock Exchange during the 2018 to 2022 period, with a focus on the influence of profitability, company size,…
earnings management, and sales growth. Using a quantitative method, hypothesis testing was conducted based on secondary data collected from the financial statements of energy companies. Through a purposive sampling approach, the analysis included 20 companies, resulting in a dataset consisting of 73 observations. The analysis revealed several interesting findings: profitability did not show a significant effect on tax avoidance, while company size was found to have a significantly positive impact. Meanwhile, earnings management did not significantly contribute to tax avoidance, and sales growth demonstrated a significantly negative relationship with tax avoidance. These findings enrich the understanding of the factors influencing tax strategies in Indonesia's energy
Abstract:This study aims to explore the ability of Cellular Automata-Markov (CA-Markov) model in predicting the expansion of urban growth rate in Ambon, Indonesia, and Gaza Strip, Palestine. Using a literature study approach, this…
s research collected and analyzed secondary data on land use change, population growth, and factors affecting urbanization in both regions. The results of the analysis show that the CA-Markov model has high accuracy in predicting land use change, and is able to describe the spatial dynamics of built-up land growth. This research emphasizes the importance of integrating environmental aspects in land use planning to achieve sustainable development. The findings are expected to provide useful recommendations for policy makers in managing urban growth, as well as enrich the literature on the application of the CA-Markov model in different contexts.