Abstract:ANNs have the ability to learn from data and recognize unstructured patterns. In face detection, ANNs can be used to recognize faces from images or videos. However, selecting the right ANN method is crucial for achieving…
optimal face detection performance. The results of this study are the highest classification accuracy value of the backpropagation artificial neural network system in recognizing student facial images with a comparison of the Learning Vector Quantization method is 96.25% (detection error = 0) with a classification architecture of the test data comparison - training data 70: 30, 20,000 iterations, calculation error tolerance 0.00001 and the number of hidden layer neurons = 5 while the lowest classification accuracy value of the backpropagation artificial neural network system in recognizing student facial images based on LVQ features is 85.42% (detection error = 34) with a classification architecture of the test data comparison - training data 70: 30, 10,000 iterations, calculation error tolerance 0.01 and the number of hidden layer neurons = 15
Abstract:Today's consumers not only fulfill basic needs but also prioritize physical appearance, especially facial care, which is a priority to look better. Having healthy, clean and bright facial skin is the dream of every Indonesian…
esian woman. Cosmetics companies certainly carry out strategies to provide benefits and benefits to their consumers to produce an increase in Brand Loyalty. The aim of this research is to determine the relationship between Brand Love, Self-Esteem, Brand Attitude and Brand Loyalty among users of facial care products. This research was conducted on 250 female respondents who used Scarlett, Emina and Whitelab products aged 15 - 40 years in the JABODETABEK area. Data collection was obtained through distributing questionnaires online which was carried out from January to February 2023. This research used the Lisrel Structural Equation Model (SEM) to test the research model. The results of this research show that the four hypotheses proposed are acceptable and one hypothesis is unacceptable. Then, the brand attitude variable has the greatest influence on brand love. Meanwhile, the results show that the proposed research hypothesis does not support the existing hypothesis, namely that the brand attitude variable has no influence on brand loyalty. Therefore, this research implies that brand loyalty is an important factor for a business to be able to maintain its business.
Abstract:This study aims to analyze the influence of packing machine automation on operator productivity in the facial tissue industry by considering the role of moderation, technical competence and operator workload perception.…
The method used is Systematic Literature Review (SLR) by reviewing scientific articles published in the 2020–2026 range from reputable databases such as Scopus. The selection process was carried out using the PRISMA approach through the identification, screening, eligibility, and inclusion stages, resulting in a number of articles relevant to the topics of industrial automation, labor productivity, technical competence, and workload. The results of the study show that the implementation of packing machine automation in general has a positive impact on increasing operator productivity through time efficiency, quality consistency, and reduction of manual errors. Nevertheless, the effectiveness of automation is highly dependent on the level of technical competence of the operator, especially in the operation, maintenance and troubleshooting of the machine. In addition, workload perception has also been shown to moderate the relationship, where automation can lower physical workloads but potentially increase mental workloads due to the demands of automated system supervision. Other findings suggest that an imbalance between automation levels and human resource readiness can hinder productivity optimization. Conceptually, this study confirms that the relationship between packing machine automation and operator productivity is not linear, but is influenced by individual and psychological factors. The practical implications of this study are the importance of technical competency-based training as well as adaptive workload management in supporting the successful implementation of automation in the manufacturing industry. This research contributes to the development of an integrative model that connects technology, people, and operational performance in the context of the tissue processing industry.
Abstract:The rise of social media platforms like TikTok has created new avenues for informal language learning. This study employs a qualitative content analysis to investigate the pedagogical strategies within the popular Indonesian…
sian TikTok hashtag #learningenglishwithmrfaisal. The research aims to identify the types of English language content, teaching strategies, and pedagogical approaches used by the creator, Mr. Faisal. A systematic analysis was conducted on a purposive sample of 10 public TikTok videos from the hashtag. Data collection involved video observation, transcription, and documentation of multimodal elements, followed by a thematic analysis. Key findings reveal a primary focus on pronunciation drills and practical vocabulary, delivered through highly repetitive and multimodal techniques. Mr. Faisal effectively combines verbal repetition, visual cues (on-screen text, mouth close-ups), exaggerated facial expressions, and motivational speaking to facilitate learning and maintain engagement. The study concludes that TikTok serves as a significant platform for informal digital language learning, particularly for micro-learning and confidence-building. These findings suggest that formal educators can adopt similar engaging, bite-sized techniques, while content creators can leverage multimodal design to enhance instructional video effectiveness.
Abstract:The growth of the cosmetics industry in Indonesia is influenced by the increasing demand for beauty products. One of the contributing factors to this trend is a common issue faced by women, especially Gen Z, which is dull…
l skin. One of the most purchased beauty products by Gen Z is facial serum. The aim of this research is to examine the influence of Negative EWOM (Electronic Word of Mouth) and variety seeking on brand switching behavior, with customer engagement as an intervening variable for Scarlett facial serum among Gen Z consumers. This study employs a quantitative approach with descriptive and causal research methods. Data collection is done through a questionnaire survey with 300 respondents who use Scarlett facial serum in Indonesia. The data analysis technique used is Structural Equation Modeling (SEM) using SmartPLS for research data analysis. The research findings indicate that Negative EWOM have a positive influence on brand switching behavior, Negative EWOM have a negative influence on customer engagement, variety seeking have a negative influence on customer engagement, variety seeking have a positive influence on brand switching behavior, customer engagement have a negative influence on brand switching behavior, Variety seeking on brand switching behavior through customer engagement as an intervening variable have a positive influence, Negative E-WOM on brand switching behavior through customer engagement as an intervening variable also have a positive influence.This research has implications for companies, including the need for companies to enhance product quality and their brand image in response to Negative E-WOM. Companies should also continue to innovate by improving product quality and uniqueness. Additionally, understanding customer preferences and market trends is crucial for competing in a market with many similar products. Maintaining customer interactions can also keep the company top of mind among customers, preventing them from switching to other brands. These actions are necessary to retain customers and prevent brand switching. Referring to several previous studies, research on negative word of mouth, brand switching behavior, variety seeking, and customer engagement has never been conducted simultaneously with the same variables and object.
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: Face recognition based on deep learning has become an important technology in many areas. However, these systems often face challenges in real-world conditions, such as when the face is partially covered by accessories…
essories such as masks or glasses. This study aims to evaluate the effect of data augmentation by adding facial accessories (masks, glasses, and a combination of both) and geometric augmentation on the accuracy of face recognition systems. There are three types of datasets used in this method: the original dataset (category 1), the dataset with facial accessories augmentation (category 2), and the dataset with geometric augmentation (category 3). Data augmentation was performed on the training dataset to increase diversity, followed by the face detection process using SCRFD and feature extraction with ArcFace. The model was then trained using Multi-Layer Perceptron (MLP). Based on the results, adding face accessories (category 2) made the model a lot more accurate, hitting 99% accuracy. In category 3, adding geometric features improved accuracy to 91%. Other evaluation metrics, such as precision, recall, and F1-score, also showed improvement after augmentation. This study concludes that facial accessories augmentation is more effective in improving the accuracy and robustness of face recognition models compared to geometric augmentation.
Keywords: augmentation; deep learning; face recognition; glasses.
Abstrak: Pengenalan wajah berbasis deep learning telah menjadi salah satu teknologi penting dalam berbagai aplikasi. Namun, sistem ini sering kali menghadapi tantangan dalam kondisi dunia nyata, seperti saat wajah tertutup sebagian oleh aksesori seperti masker atau kacamata. Penelitian ini bertujuan untuk mengevaluasi pengaruh augmentasi data dengan menambahkan aksesori wajah (masker, kacamata, dan kombinasi keduanya) serta augmentasi geometris terhadap akurasi sistem pengenalan wajah. Metode yang digunakan melibatkan tiga kategori dataset: dataset asli tanpa augmentasi (kategori 1), dataset dengan augmentasi aksesoris wajah (kategori 2), dan dataset dengan augmentasi geometris (kategori 3). Augmentasi data dilakukan pada dataset pelatihan untuk meningkatkan keberagaman, diikuti dengan proses deteksi wajah menggunakan SCRFD dan ekstraksi fitur dengan ArcFace. Model kemudian dilatih menggunakan Multi-Layer Perceptron (MLP). Hasil penelitian menunjukkan bahwa augmentasi aksesoris wajah (kategori 2) memberikan peningkatan signifikan pada akurasi model, mencapai 99%, sedangkan kategori 3 dengan augmentasi geometris mencapai akurasi 91%. Metrik evaluasi lainnya, seperti precision, recall, dan F1-score, juga menunjukkan peningkatan setelah augmentasi. Penelitian ini menyimpulkan bahwa augmentasi aksesoris wajah lebih efektif dalam meningkatkan akurasi dan ketahanan model pengenalan wajah dibandingkan dengan augmentasi geometris.
Kata kunci: augmentasi; deep learning; kacamata; pengenalan wajah.
Abstract:Face recognition has become a common thing used in the field of surveillance and security in computer technology and image devices. This study aims to identify the usefulness of a person's face on 3 test images. This study…
dy examines the methods of cropping techniques, image enhancement through intensity measurement, and histogram analysis to improve the contrast and distribution of image intensity. In addition, the Viola-Jones algorithm is used to detect key facial features such as eyes, nose, and mouth. The results of the analysis are then applied in the feature evaluation stage, where usually between facial features are applied to measure the ratio of facial proportions. Furthermore, the comparison of proportional ratios of several images was analyzed using bar graphs and line graphs to evaluate the trend and stability of facial proportions. The results showed the best ratio stability with a smaller variation of the on-off ratio of image 2 which is 0.4762 pixels to 0.4983 pixels. Image 2 is the most ideal for face measurement systems based on geometric ratios because it provides more consistent and visible results.
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: Face detection remains a challenging task in computer vision due to real-world factors such as uneven lighting, varying viewpoints, distance, and occlusion. This study aims to develop and evaluate a real-time facial…
acial feature detection application (detecting face, eyes, nose, and mouth) using MATLAB and a webcam. Detection is performed using the Viola-Jones Cascade Classifier method through the vision.CascadeObjectDetector function. Key parameters that were adjusted include the MergeThreshold (ranging from 4 to 50 depending on the feature) and MinSize (based on estimated feature size within the frame). However, this study does not include tuning of other parameters such as FalseAlarmRate, which constitutes a limitation of the employed method. The adjustment of these parameters proved significant in improving detection accuracy and robustness under varying lighting conditions. Nevertheless, the system still encounters difficulties in detecting facial features in the presence of occlusion. This study also has the potential to serve as a foundation for further developments in face recognition, emotion detection, or biometric authentication.
Keywords: computer vision; haar cascade; MATLAB
Abstrak: Deteksi wajah merupakan tantangan dalam visi komputer karena dipengaruhi oleh kondisi nyata seperti pencahayaan tidak merata, sudut pandang, jarak, dan obstruksi. Penelitian ini bertujuan untuk mengembangkan dan menguji aplikasi deteksi fitur wajah secara real-time (wajah, mata, hidung, dan mulut) menggunakan MATLAB dan kamera webcam. Deteksi dilakukan dengan metode Viola-Jones Cascade Classifier melalui fungsi vision.CascadeObjectDetector. Parameter penting yang disesuaikan adalah MergeThreshold (antara 4 hingga 50 tergantung fitur), MinSize (mengikuti estimasi ukuran fitur dalam frame). Namun, penelitian ini tidak mencakup penyesuaian parameter lain seperti FalseAlarmRate, yang menjadi salah satu keterbatasan metode yang digunakan. Penyesuaian parameter ini terbukti signifikan dalam meningkatkan akurasi deteksi dan ketahanan terhadap variasi kondisi pencahayaan. Namun, sistem masih mengalami kesulitan mendeteksi fitur wajah jika terjadi obstruksi. Penelitian ini juga berpotensi menjadi dasar untuk pengembangan lebih lanjut dalam face recognition, emotion detection, atau biometric authentication.
Kata kunci: visi computer; haar cascade; MATLAB