Type Deep Learning Model for Multi-Label Waste Classification in Canal Environments: A Comparative Study with CNN Architectures Najirah Umar Journal of Applied Data Sciences, 2026 The escalating environmental degradation caused by waste underscores the necessity of developing intelligent and sustainable management systems. This study introduces a deep learning–based framework with proposed a modified ConvNeXt architecture enhanced by a two-layer non-linear MLP classification, specifically designed for multi-object waste classification in canal environments. Specifically, ConvNeXt-CNN is introduced as the primary backbone for extracting visual features from waste images. Then, a modified Multi-Layer Perceptron (MLP) is employed to transform these features into multi-label predictions. To optimize the model’s generalization capability in recognizing the complexity of waste images, a hybrid data augmentation technique combining SMOTE and MixUp was applied during training. The proposed approach was then compared with ten fine-tuned Convolutional Neural Network (CNN) architectures, ResNet18, ResNet50, VGG16, VGG19, DenseNet121, MobileNet_v2, and EfficientNet (B0, B1, B2, and B3), and evaluated using accuracy, precision, recall, and F1-score metrics. The experimental dataset comprises 855 waste images containing a total of 2,662 annotated objects across 18 categories, including Bamboo, Beverage Carton, Cardboard, Fabric, Glass Bottle, Inorganic Waste, Kite, Leaf, Metal, Organic Waste, Paper, Plastic, Plastic Bottle, Plastic Cup, Residual Waste, Rubber, Small E-waste, Styrofoam, and Wood. The results show that the fine-tuned ConvNeXt achieved the best performance with an F1-score of 0.99, surpassing DenseNet121 (0.95), ResNet18 (0.91), and VGG16 (0.94). The ConvNeXt model demonstrated its robust capability by achieving consistently high identification scores across majority 18 waste categories. When it came to training efficiency, the fine-tuned MobileNetV2 model proved to be the top performer, outclassing ten other pretrained models, with a training time of 13.35s per epoch. Results exhibit that finetuned ConvNext outperforms in terms of accuracy, recall, precision, and F1-score. In conclusion, Integrating ConvNeXt and MLP for multi-object waste classification effectively supports intelligent waste management, enabling practical real-world deployment in smart bins, Material Recovery Facilities, and IoT-integrated urban waste systems.
Educational Strategies for Addressing Student Anxiety and Depression through Artificial Intelligence: A Bibliometric and Conceptual Analysis Muhammad Nurtanto, Asta Adyani, Mohd Kasturi Nor Abd Aziz, Najirah Umar, Valiant Lukad Perdana Sutrisno, Septiari Nawanksari, Munawar Thoharudin, Arina Zaida Ilma, Nur Kholifah Salud Ciencia Y Tecnologia, 2025 Introduction: La tecnología de inteligencia artificial (IA) ha transformado la educación, impactando positivamente diversas tareas académicas, incluidas las experiencias de aprendizaje y el apoyo a la salud mental del estudiantado. Sin embargo, factores relacionados con los usuarios, en particular los estudiantes y educadores, han influido en la implementación exitosa de la tecnología de IA. Diversos estudios han reportado impactos negativos, tales como ansiedad y depresión, durante el aprendizaje en línea, los cuales requieren una mayor investigación.Method: Este estudio tuvo como objetivo identificar tendencias, patrones de agrupación y análisis temáticos con respecto al impacto de la tecnología de IA y el papel del profesorado en la mitigación de los riesgos de ansiedad y depresión. Se empleó un enfoque de revisión sistemática de la literatura (RSL) utilizando el protocolo PRISMA para realizar una exploración en profundidad. Se recuperaron un total de 33 artículos de la base de datos Scopus entre 2017 y 2024 utilizando las palabras clave "inteligencia artificial", "IA", "ansiedad" y "depresión". Los datos fueron analizados mediante VosViewer, Biblioshiny y análisis temático.Results: The main findings indicated that AI technology posed several disadvantages when implemented without proper preparedness and control. These included reduced social interaction, technological complexity, dependency, and loss of autonomy, biased feedback, and the misuse of information—all of which reinforced students' anxiety and depression. Proposed strategies involved early detection of stress indicators, the creation of inclusive and pressure-free learning environments, the integration of mental health awareness into curricula, access to information and counseling services, fostering positive and open relationships, balanced use of AI technologies, fair empathy and concern, and professional development for educators.Conclusions: This study provides a theoretical framework and practical strategies for educators and policymakers to promote balanced or hybrid uses of AI technology. Future research should ensure that AI is utilized appropriately, particularly in reducing the risks of emotional disturbances and mental health issues.
Developing a Smart Belt for Monitoring Elderly Activities Based on Multi-Modal Sensors Integration and Internet of Things Proceedings of International Conference on Artificial Life and Robotics, 2024
Comparative Study of Word2Vec, FastText, and Glove Embeddings for Synonym Identification in Bugis Language Wahyu Ramadhan Arianto, Yuyun, Ahmad Abrar, Najirah Umar, Nasrullah, Nurfaedah, Gusnawaty, Asril Jarin 2024 Beyond Technology Summit on Informatics International Conference Bts I2c 2024, 2024 This research aims to analyze the performance of word vectors generated by three pre-trained word embedding models, namely Word2Vec, Fast'Text, and Glove, to detect synonyms at the word level in the Bugis language. The word vectors from each model were integrated with a Bugis language dataset containing 12,060 monolingual texts, and then trained using the Long Short-Term Memory (LSTM) model. The results show that Word2Vec has the highest accuracy of 0.9412, followed by Glove with 0.9353 and FastText with 0.9262. Additional experiments with cosine similarity revealed that Glove performed best for predicting synonyms across all word occurrence frequency categories, while FastText and Word2Vec had inferior results. These findings indicate that although high training accuracy is achieved, it does not always imply that the model will excel in predicting synonyms.
Grammar Error Correction in Indonesian Sports News: Comparing the Performance of Pre-Trained T5 and BART Models Muh Adnan, Esa Prakasa, Yuyun, Najirah Umar, Nasrullah, Adi Sadli, A. Edeth Fuari Anatasya, Hazriani, Mashur Razak 2024 Beyond Technology Summit on Informatics International Conference Bts I2c 2024, 2024 This research compares the performance of two pre-trained models based on the transformer, namely text-to-text transfer transformer (T5) and bidirectional and auto-regressive transformer (BART), through a fine-tuned for correcting grammar in Indonesian sports news texts. We used vennify/t5-base-grammar-correction and onionLad/grammar-correction-bart-base, was trained using a dataset of 10,075 sentences from Indonesian language sports news sites. We tested the model performance using bilingual evaluation understudy (BLEU), google's language evaluation understanding (GLEU), training loss, and validation loss. The results show that BART was more efficient in learning data patterns and has better generalization ability, supported by BLEU and GLEU scores of 0.8560 and 0.9655. Meanwhile, T5 maintains simpler sentence structures, supported by BLEU and GLEU scores of 0.8120 and 0.9564. BART excels at handling more complex contexts, making it more effective at accurately correcting errors in dynamic sports news. Both models have their respective advantages, with BART being better at correcting detailed grammatical errors, while T5 offers consistent correction of more simple sentence structures.
Application of Naïve Bayes Algorithm Variations On Indonesian General Analysis Dataset for Sentiment Analysis Najirah Umar, M. Adnan Nur Jurnal Resti, 2022 Indonesian General Analysis Dataset is a dataset sourced from social media twitter by using keywords in the form of conjunctions to get a dataset that does not only focus on a particular topic. The use of Indonesian language datasets with general topics can be used to test the accuracy of the classification model so as to provide additional reference in choosing the right methods and parameters for sentiment analysis. One of the algorithms which in several studies produces the highest level of accuracy is naive Bayes which has several variations. This study aims to obtain the method with the best accuracy from the naive Bayes variation by setting the minimum and maximum document frequency parameters on the Indonesian General Analysis Dataset for sentiment analysis. The naive Bayes classifier variations used include Bernoulli naive Bayes, gaussian naive Bayes, complement naive Bayes and multinomial naive Bayes. The research stage begins with downloading the dataset. Preprocessing becomes the next stage which consists of tokenizing, stemming, converting abbreviations and eliminating conjunctions. In the preprocessed data, feature extraction is carried out by converting the dataset into vectors and applying the TF-IDF method before entering the sentiment analysis classification stage. Tests in this study were carried out by applying the minimum document frequency (min-df) and maximum document frequency (max-df) for each variation of naive Bayes to obtain the appropriate parameters. The test uses k-fold cross validation of the dataset to divide the training data and sentiment analysis test data. The next confusion matrix is made to evaluate the level of accuracy.
Implementation of TOPSIS Methods in Determining Makassar Special Culinary Business Location Najirah Umar, Billy Eden William Asrul Proceedings 2nd East Indonesia Conference on Computer and Information Technology Internet of Things for Industry Eiconcit 2018, 2018 A typical Makassar culinary business that offers a variety of benefits such as typical food is sought after by tourists visiting the city of Makassar, and typical Makassar food has been widely known by the public. Nevertheless, culinary business is not infrequently failing, one of the causes is location. The selection of locations that do not meet certain criteria directly impacts the failure of the culinary business. During this time, the determination of the feasibility of the business location for the object under study still uses conventional methods that require time and cost to conduct a location determination survey, therefore, it is important to choose a method to determine the proper location of the business and supported by the appropriate calculation pattern. In this study, the TOPSIS method was used to build a system that can solve the Multi Criteria Decision Making (MCDM) problem for the feasibility of the best culinary business location, by calculating 5 criteria and 10 alternatives, the positive ideal solution value is 11.66, the negative solution value the ideal is 13.41, and the Closeness Relative value is 0.535.
RECENT SCHOLAR PUBLICATIONS
A Web-Based Descision Support System for Toddler Nutritional Status Using the Certainty Factor Methode N Umar International Conference of Multidisciplinary Cel: Proceeding 3 (1), 47-56 , 2026 2026
Sistem Cerdas: Teori, Metode, dan Implementasi Modern R Rustiyana, N Umar, L Judijanto, IGTS Dharma, E Padang PT. Sonpedia Publishing Indonesia , 2026 2026
Type Deep Learning Model for Multi-Label Waste Classification in Canal Environments: A Comparative Study with CNN Architectures N Umar, BEW Asrul, Y Yuyun Journal of Applied Data Sciences 7 (1), 261-276 , 2026 2026 Citations: 1
Sistem Pendukung Keputusan Penentuan Dosen Pengampu Menggunakan Algoritma Cosine Similarity N Umar, H Hazriani JURNAL IT 16 (3), 167-174 , 2025 2025
Data Mining: Konsep dan Penerapannya N Umar, L Judijanto, RJ Situmeang, F Syafa'at, E Widarti, R Azhar, ... PT. Sonpedia Publishing Indonesia , 2025 2025
Decision Support System for Porang Land Selection based on Multi Attribute Utility Theory (MAUT) N Umar, M Idris, A Rahmat Sistemasi: Jurnal Sistem Informasi 14 (6), 2552-2564 , 2025 2025
EDUKASI LITERASI DIGITAL UNTUK MENINGKATKAN KESADARAN SISWA TERHADAP BERITA HOAKS DI SMAN 13 BULUKUMBA N Umar, H Herman, AEF Anatasya, N Mustika, AAM Afdal, J Jusman GERVASI: Jurnal Pengabdian kepada Masyarakat 9 (2), 1098-1110 , 2025 2025
Evaluating the Performance of an LBS-Based Waste Reporting Application for Digital Waste Management N Umar, BEW Asrul, Y Wabula Journal of Applied Informatics and Computing 9 (4), 1730-1739 , 2025 2025 Citations: 2
Tahapan dan Tantangan Pembangunan Literasi Digital di Era Transformasi Digital N Umar, AAJ Arsyad Journal of Digital Literacy and Volunteering 3 (2), 48-53 , 2025 2025 Citations: 1
Training on the Utilization of Green Grass Jelly for Food and Beverage Ingredients: Participatory Training-Based Intervention S Sutiharni, D Handayani, I Indriyani, N Umar, M Apriyanto, C Indriyati, ... Jurnal Medika: Medika 4 (3), 331-335 , 2025 2025
Implementation of Least Square and Simple Moving Average to Predict Web-Based Sales N Umar International Conference of Multidisciplinary Cel: Proceeding 2 (1) , 2025 2025
Educational Strategies for Addressing Student Anxiety and Depression through Artificial Intelligence: A Bibliometric and Conceptual Analysis NK Muhammad Nurtanto, Asta Adyani, Mohd Kasturi Nor Abd Aziz, Najirah Umar ... Salud, Ciencia y Tecnología. 2025; 5:1669, 1669-1700 , 2025 2025
Implementasi Algoritma Learning Vector Quantization untuk Deteksi Dini Penyakit Mata M Mansur, N Umar, S Zuhriyah Jurnal Sains dan Informatika 11 (1), 1-10 , 2025 2025
Aplikasi 3D Menggunakan Virtual Reality sebagai Media Pengenalan Museum Kota Makassar N Umar, Z Tahir, S Syam Jurnal Riset dan Aplikasi Mahasiswa Informatika (JRAMI) 6 (02), 297-306 , 2025 2025
A Hybrid MOO-MCDM-PSOM Approach for Mapping Urban Carbon Trade Policies M Faisal, EM Hasiri, D Darniati, TK Abd Rahman, BEW Asrul, H Gani, ... Preprints , 2025 2025 Citations: 1
Educational Strategies for Addressing Student Anxiety and Depression through Artificial Intelligence: A Bibliometric and Conceptual Analysis M Nurtanto, A Adyani, MKNA Aziz, N Umar, VLP Sutrisno, S Nawanksari, ... Salud, Ciencia y TecnologÃa 5 , 2025 2025 Citations: 3
Najirah; KH, Musliadi; Humaera B, Panduan Praktis Menguasai Basis Data Untuk Pemula Hingga Mahir NH Umar PT Mafy Media Literasi Indonesia , 2025 2025 Citations: 5
Comparative Study of Word2Vec, FastText, and Glove Embeddings for Synonym Identification in Bugis Language WR Arianto, A Abrar, N Umar, A Jarin 2024 Beyond Technology Summit on Informatics International Conference (BTS … , 2024 2024 Citations: 2
Grammar Error Correction in Indonesian Sports News: Comparing the Performance of Pre-Trained T5 and BART Models M Adnan, E Prakasa, N Umar, A Sadli, AEF Anatasya, M Razak 2024 Beyond Technology Summit on Informatics International Conference (BTS … , 2024 2024 Citations: 2
Big Data: Panduan dan Peluang di Era Digital N Nirsal, A Apriyanto, FM Sinaga, YM Saragih, SY Kusumastuti, ... PT. Sonpedia Publishing Indonesia , 2024 2024 Citations: 2
MOST CITED SCHOLAR PUBLICATIONS
Sistem Pendukung Keputusan DU Daihani Penerbit Elex Media Komputindo, Jakarta , 2001 2001.0 Citations: 90
Tren teknologi AI: Pengantar, teori, dan contoh penerapan Artificial Intelligence di berbagai bidang GS Mahendra, DA Ohyver, N Umar, L Judijanto, A Abadi, B Harto, ... PT. Sonpedia Publishing Indonesia , 2024 2024.0 Citations: 74
& Judijanto, L.(2024) H Hildawati, H Haryani, N Umar, D Suprayitno, IR Mukhlis, ... Literasi Digital: Membangun Wawasan Cerdas dalam Era Digital terkini , 2024 2024.0 Citations: 50
Literasi Digital: Membangun Wawasan Cerdas dalam Era Digital terkini H Hildawati, H Haryani, N Umar, D Suprayitno, IR Mukhlis, ... PT. Green Pustaka Indonesia , 2024 2024.0 Citations: 37
TRANSFORMASI DIGITAL R Subekti, S Kom, M Kom, DA Ohyver, MP SE, L Judijanto, M MM, ... 2023.0 Citations: 37
& Sutarwiyasa, IK (2024) GS Mahendra, DA Ohyver, N Umar, L Judijanto, A Abadi, B Harto Tren Teknologi AI: Pengantar, Teori, dan Contoh Penerapan Artificial … , 2024 2024.0 Citations: 35
Application of naive bayes algorithm variations on indonesian general analysis dataset for sentiment analysis N Umar, MA Nur Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) 6 (4), 585-590 , 2022 2022.0 Citations: 32
Sistem Pendukung Keputusan IG Sudipa, JP Suyono, AE Trihandoyo Pt. Mifandi Mandiri Digital , 2023 2023.0 Citations: 26
Konsep dasar e-business B Irawan, I Sani, WD Febrian, Z Setiawan, A Abdullah, M Wasil, A Dewi, ... Padang: Global Eksekutif Teknologi 18 , 2023 2023.0 Citations: 23
Data Mining: Teori dan Penerapannya dalam Berbagai Bidang S Syam, Y Tokoro, L Judijanto, M Garonga, FM Sinaga, N Umar, ... PT. Sonpedia Publishing Indonesia , 2024 2024.0 Citations: 18
Analisis Peranan Pemilih Pemula dan Pentingnya Teknologi Digital Untuk Pemilihan Umum 2024 di Indonesia (Studi Kasus: Pemilih Pemula SMA Negeri 20 Makassar) U Tamrin, AH RS, AAJ Arsyad, N Umar, D Kurniawan Journal of Digital Literacy and Volunteering 2 (2), 52-60 , 2024 2024.0 Citations: 11
& Saktisyahputra, S.(2024). Transformasi Digital: Teori & implementasi Menuju Era Society 5.0. PT R Subekti, DA Ohyver, L Judijanto, IKS Satwika, N Umar, N Hayati Sonpedia Publishing Indonesia , 2024 2024.0 Citations: 11
Generative Artificial Intelligence (GenAI): Pengetahuan Dasar GenAI Beserta Penerapannya B Sisephaputra, L Judijanto, A Apriyanto, L Lukman, M Migunani, N Umar, ... PT. Green Pustaka Indonesia , 2024 2024.0 Citations: 10
Literasi Digital: Wawasan Cerdas Dalam Perkembangan Dunia Digital Terkini H Hildawati, N Umar, D Suprayitno, IR Mukhlis, DID Sulistyowati, ... Green Pustaka , 2024 2024.0 Citations: 10
Strategi Hukum Preventif dalam Meningkatkan Perlindungan Anak di Era Digital MFR Mahka, N Umar, S Zuhriyah, NL Sukanda Prosiding Sisfotek 7 (1), 371-379 , 2023 2023.0 Citations: 10
Buku Ajar Analisis Perancangan Sistem R Utami, PP Santika, MF Ahnaf, N Umar, GF Adnyana, IMA Pradnyana, ... PT. Sonpedia Publishing Indonesia , 2024 2024.0 Citations: 9
Implementation of TOPSIS methods in determining Makassar special culinary business location N Umar, BEW Asrul 2018 2nd East Indonesia Conference on Computer and Information Technology … , 2018 2018.0 Citations: 9
Sistem Pendukung Keputusan I As' ad, SR Yahya, Y Efendi, L Efriyanti, R Oktavera, B Sena, A Rakhman, ... Nuta Media , 0 Citations: 8
Buku Ajar Rekayasa Perangkat Lunak N Umar, H Setiawan, H Yutanto, S Sujarwo, KO Sanjaya, PA Minarni, ... PT. Sonpedia Publishing Indonesia , 2024 2024.0 Citations: 7
(2024) H Hildawati, H Haryani, N Umar, D Suprayitno Literasi Digital: Membangun Wawasan Cerdas dalam Era Digital terkini … , 0 Citations: 7
