Abstract:Abstract: Enhancing the quality of human resources (HR) in higher education is a crucial factor in supporting the excellence of teaching, research, and community service. This study aims to identify effective strategies…
and implementations for HR development within universities. A descriptive qualitative method was used, employing a case study approach in several higher education institutions in Indonesia. The findings reveal that HR quality improvement strategies include faculty training and competency development, academic degree advancement, implementation of a reward and punishment system, and strengthening a professional work culture. Implementation of these strategies faces several challenges, such as budget constraints, resistance to change, and the lack of integrated HR management. Nevertheless, with visionary leadership and institutional policy support, HR development can be pursued sustainably. This study recommends the importance of synergy among university leaders, faculty members, and administrative staff in fostering a conducive work environment for HR quality enhancement.
Keywords: Human Resource Quality, Higher Education, Strategy, Implementation
Abstrak: Meningkatkan kualitas sumber daya manusia (SDM) di pendidikan tinggi merupakan faktor penting dalam mendukung keunggulan pengajaran, penelitian, dan pengabdian masyarakat. Studi ini bertujuan untuk mengidentifikasi strategi dan implementasi yang efektif untuk pengembangan SDM di dalam universitas. Metode kualitatif deskriptif digunakan, dengan menggunakan pendekatan studi kasus di beberapa institusi pendidikan tinggi di Indonesia. Temuan menunjukkan bahwa strategi peningkatan kualitas SDM meliputi pelatihan dan pengembangan kompetensi dosen, peningkatan gelar akademik, implementasi sistem penghargaan dan hukuman, dan penguatan budaya kerja profesional. Implementasi strategi ini menghadapi beberapa tantangan, seperti kendala anggaran, resistensi terhadap perubahan, dan kurangnya manajemen SDM yang terintegrasi. Namun demikian, dengan kepemimpinan visioner dan dukungan kebijakan institusional, pengembangan SDM dapat dilakukan secara berkelanjutan. Studi ini merekomendasikan pentingnya sinergi antara pimpinan universitas, anggota fakultas, dan staf administrasi dalam membina lingkungan kerja yang kondusif untuk peningkatan kualitas SDM.
Kata kunci: Kualitas Sumber Daya Manusia, Pendidikan Tinggi, Strategi, Implementasi
Abstract:Abstract: The growing awareness of the importance of sustainability has prompted organizations to incorporate environmental elements into management and operational procedures. Green Human Resource Management (GHRM) is one…
ne of the most studied approaches. It is considered to be able to encourage the formation of Employee Green Behavior (EGB) and improve the company's Environmental Performance (EP). The purpose of this study is to analyze and synthesize previous research on green human resource management, green employee behavior, and environmental achievement. This study uses a qualitative literature review method. Data was obtained from 30 journal articles published from 2020–2026. This article consists of 10 articles on Green Human Resource Management, 10 articles on Green Worker Behavior, and 10 articles on Environmental Performance. The selection of articles is based on the relevance of the topic, the year of publication, and the number of citations. Content analysis and theme synthesis are used to find patterns of relationships between variables, research trends, and research gaps that need to be improved. The results of the study show that GHRM plays an important role in creating environmentally friendly worker behavior. Through various practices such as green labor acceptance, green training, and green performance assessments, GHRM plays this role. Through resource use efficiency, waste reduction, and increased environmental awareness, EGB has been shown to improve environmental performance. In addition, it was found that the research conducted was still mainly on the manufacturing and hospitality industries, while the amount of research conducted in the field of education and developing countries was very limited. According to this study, GHRM, EGB, and EP are important components in supporting the sustainable strengthening of organizational environmental performance.
Keywords: Green Human Resource Management; Employee Green Behavior; Environmental Performance; Sustainability; Literature Review.
Abstrak: Bertambahnya kesadaran akan pentingnya keberlanjutan telah mendorong organisasi untuk memasukkan elemen lingkungan ke dalam prosedur manajemen dan operasional. Green Human Resource Management (GHRM) adalah salah satu pendekatan yang banyak dipelajari. Dianggap dapat mendorong pembentukan Employee Green Behavior (EGB) dan peningkatan Environmental Performance (EP) perusahaan. Tujuan dari penelitian ini adalah untuk menganalisis dan mensintesis penelitian sebelumnya tentang manajemen sumber daya manusia hijau, perilaku karyawan hijau, dan prestasi lingkungan. Penelitian ini menggunakan metode review literatur kualitatif. Data diperoleh dari 30 artikel jurnal yang dipublikasikan dari tahun 2020–2026. Artikel ini terdiri dari 10 artikel Manajemen Sumber Daya Manusia Hijau, 10 artikel Perilaku Pekerja Hijau, dan 10 artikel Kinerja Lingkungan. Pemilihan artikel didasarkan pada relevansi topik, tahun publikasi, dan jumlah sitasi. Analisis isi dan sintesis tema digunakan untuk menemukan pola hubungan antarvariabel, tren penelitian, dan kesenjangan penelitian yang perlu diperbaiki. Hasil penelitian menunjukkan bahwa GHRM memainkan peran penting dalam menciptakan perilaku pekerja yang ramah lingkungan. Melalui berbagai praktik seperti penerimaan tenaga kerja hijau, pelatihan hijau, dan penilaian kinerja hijau, GHRM memainkan peran ini. Melalui efisiensi penggunaan sumber daya, pengurangan limbah, dan peningkatan kesadaran lingkungan, EGB telah terbukti meningkatkan kinerja lingkungan. Selain itu, ditemukan bahwa penelitian yang dilakukan masih terutama pada industri manufaktur dan perhotelan, sementara jumlah penelitian yang dilakukan pada bidang pendidikan dan negara berkembang sangat terbatas. Menurut penelitian ini, GHRM, EGB, dan EP merupakan komponen penting dalam mendukung penguatan kinerja lingkungan organisasi secara berkelanjutan..
Kata Kunci: Green Human Resource Management; Employee Green Behavior; Environmental Performance; Sustainability; Literature Review.
Abstract:Abstract: Unemployment Rate is one of the important indicators used to assess the employment and economic conditions of a region. A high unemployment rate can hinder economic growth and reduce public welfare. This study…
aims to analyze the factors influencing the Unemployment Rate and to develop a prediction model for the Unemployment Rate in regencies/cities of North Sumatra Province using a Data Mining approach with the Multiple Linear Regression algorithm. The data used in this study are secondary data obtained from the Central Statistics Agency (BPS) of North Sumatra Province for the 2019–2023 period, including population, Gross Regional Domestic Product (GRDP), and education level variables with a total of 165 observations. The research stages include data collection, data cleaning, data exploration, splitting the dataset into training and testing data with an 80:20 ratio, model development, and evaluation using MAE, RMSE, and coefficient of determination (R²) metrics. The results show that the education level is a significant variable affecting the Unemployment Rate, indicating the phenomenon of educated unemployment, while population and GRDP do not have a partially significant effect. The resulting model obtained an R² value of 30.88%, an MAE of 1.76, and an RMSE of 2.15, indicating that the model has fairly good and stable predictive performance. The findings of this study are expected to support employment policy-making and data-driven regional economic development planning in North Sumatra Province.
Keywords: Unemployment Rate, Data Mining, Multiple Linear Regression, GRDP, Education Level.
Abstrak: Tingkat Pengangguran merupakan salah satu indikator penting dalam menilai kondisi ketenagakerjaan dan perekonomian suatu daerah. Tingginya tingkat pengangguran dapat menghambat pertumbuhan ekonomi dan menurunkan kesejahteraan masyarakat. Penelitian ini bertujuan untuk menganalisis faktor-faktor yang memengaruhi Tingkat Pengangguran serta membangun model prediksi Tingkat Pengangguran pada kabupaten/kota di Provinsi Sumatera Utara menggunakan pendekatan Data Mining dengan algoritma Multiple Linear Regression. Data yang digunakan merupakan data sekunder yang diperoleh dari Badan Pusat Statistik (BPS) Provinsi Sumatera Utara periode 2019–2023, meliputi variabel jumlah penduduk, Produk Domestik Regional Bruto (PDRB), dan tingkat pendidikan dengan total 165 observasi. Tahapan penelitian meliputi pengumpulan data, pembersihan data, eksplorasi data, pembagian data training dan testing dengan rasio 80:20, pembangunan model, serta evaluasi menggunakan metrik MAE, RMSE, dan koefisien determinasi (R²). Hasil penelitian menunjukkan bahwa tingkat pendidikan merupakan variabel yang berpengaruh signifikan terhadap Tingkat Pengangguran dengan indikasi terjadinya fenomena educated unemployment, sedangkan jumlah penduduk dan PDRB tidak berpengaruh signifikan secara parsial. Model yang dihasilkan memperoleh nilai R² sebesar 30,88%, MAE sebesar 1,76, dan RMSE sebesar 2,15, yang menunjukkan kemampuan prediksi yang cukup baik dan stabil. Hasil penelitian ini diharapkan dapat menjadi pendukung dalam pengambilan kebijakan ketenagakerjaan dan perencanaan pembangunan ekonomi daerah berbasis data di Provinsi Sumatera Utara.
Kata kunci: Tingkat Pengangguran, Data Mining, Multiple Linear Regression, PDRB, Pendidikan.
Abstract:Abstract: Lung disease classification based on Chest X-Ray (CXR) images has become an important focus in the development of deep learning for medical imaging. However, most modern classification models still rely heavily…
on large amounts of labeled data, while medical image annotation requires radiology experts, high costs, and considerable time. This study aims to implement a self-supervised learning approach based on contrastive learning for lung disease classification on CXR images using the CheXpert dataset under limited labeled data conditions. The research stages include data preprocessing, image augmentation, self-supervised pretraining, fine-tuning, and model evaluation using accuracy, precision, recall, and F1-score metrics. The dataset was divided into 70% training data and 30% testing data. The experimental results showed that the model achieved an accuracy of 0.87, precision of 0.87, recall of 0.84, and F1-score of 0.85. These results indicate that the self-supervised learning approach is capable of utilizing unlabeled data to generate robust visual representations and improve lung disease classification performance under limited labeled data conditions. This study is expected to contribute to the development of more efficient deep learning-based medical image analysis systems with reduced dependency on medical annotations.
Keywords: Chest X-Ray, Self-Supervised Learning, Contrastive Learning, Deep Learning, Lung Disease Classification.
Abstrak: Klasifikasi penyakit paru berbasis citra CXR menjadi salah satu fokus penting dalam pengembangan deep learning pada bidang pencitraan medis. Namun, sebagian besar model klasifikasi modern masih bergantung pada data berlabel dalam jumlah besar, sedangkan proses anotasi citra medis membutuhkan tenaga ahli radiologi, biaya tinggi, dan waktu yang panjang. Penelitian ini bertujuan menerapkan pendekatan self-supervised learning berbasis contrastive learning untuk klasifikasi penyakit paru pada citra CXR menggunakan dataset CheXpert dengan kondisi data berlabel terbatas. Tahapan penelitian meliputi pra-pemrosesan data, augmentasi citra, self-supervised pretraining, fine-tuning, dan evaluasi model menggunakan metrik accuracy, precision, recall, dan F1-score. Dataset dibagi menggunakan rasio 70% data pelatihan dan 30% data pengujian. Hasil penelitian menunjukkan bahwa model mampu menghasilkan nilai accuracy sebesar 0.87, precision 0.87, recall 0.84, dan F1-score 0.85. Hasil tersebut menunjukkan bahwa pendekatan self-supervised learning mampu memanfaatkan data tidak berlabel untuk menghasilkan representasi visual yang robust dan meningkatkan performa klasifikasi penyakit paru pada kondisi data berlabel terbatas. Penelitian ini diharapkan dapat mendukung pengembangan sistem analisis citra medis berbasis deep learning yang lebih efisien terhadap kebutuhan anotasi medis.
Kata Kunci: Chest X-Ray, Self-Supervised Learning, Contrastive Learning, Deep Learning, Klasifikasi Penyakit Paru.
Abstract:Lung diseases are a serious health issue that requires prompt and accurate treatment. However, in practice, medical professionals often face challenges such as high patient volumes, limited examination time, and the similarity…
larity of symptoms across different types of lung diseases, which make it difficult to consistently establish an initial diagnosis. This study aims to design and develop a medical decision support system to diagnose lung diseases using an Artificial Neural Network (ANN) with the Hebb Rule algorithm. The types of diseases focused on in this study include Asthma, Bronchitis, COPD, and Pulmonary TB. The research methodology utilized 100 patient medical records from H. OK Arya Zulkarnain General Hospital as training data, consisting of 39 clinical symptom variables. The system was developed using the PHP programming language and a MySQL database. The Hebb Rule algorithm was applied to perform network weight learning so that the system could recognize patterns of relationships between symptoms and disease types based on historical data. The results of the study show that the Hebb Rule algorithm was successfully implemented into a web-based system capable of generating diagnostic decisions based on the highest activation values in the output neurons. This system can process patient symptom data quickly and provide prediction results consistent with the training data patterns. This study concludes that the use of ANNs with the Hebb Rule method is effective as a tool for early detection and decision support for medical personnel to improve the efficiency of healthcare services in hospitals.
Abstract:Abstract: Oil palm leaf diseases can significantly reduce harvest productivity. Manual identification is considered less effective because it requires a long time and carries the risk of misidentification. This study develops…
elops a leaf image detection system using a CNN with the MobileNetV2 architecture, implemented on both web and mobile platforms. A dataset of 1,200 images from Kaggle and field observations covers four classes: leaf spot, anthracnose, yellow stripe, and Other. The research stages include data collection, image preprocessing, dataset splitting, CNN model training using the MobileNetV2 architecture, model testing, performance evaluation, and system implementation on web and mobile platforms. Evaluation was conducted using confusion matrix, accuracy, precision, recall, and F1-score parameters. Based on testing results, the model achieved 93.33% accuracy, 93.71% precision, 92.92% recall, and 93.31% F1-score. The developed system was successfully implemented on web and mobile platforms with features such as image upload, automatic classification, detection history, and disease management recommendations. With this system, users are expected to perform early detection of oil palm leaf diseases more quickly, practically, and accurately.
Keywords: CNN, Deep Learning, Image Classification, MobileNetV2, Oil Palm Leaf Disease.
Abstrak: Penyakit daun kelapa sawit dapat menurunkan produktivitas panen secara signifikan. Identifikasi manual dinilai kurang efektif karena membutuhkan waktu lama dan berpotensi salah identifikasi. Penelitian ini membangun sistem deteksi citra daun menggunakan CNN arsitektur MobileNetV2 berbasis web dan mobile. Dataset 1.200 citra dari Kaggle dan observasi lapangan mencakup empat kelas: bercak daun, antraknosa, garis kuning, dan Other. Tahapan penelitian meliputi pengumpulan data, preprocessing citra, pembagian dataset, pelatihan model CNN menggunakan arsitektur MobileNetV2, pengujian model, evaluasi performa, serta implementasi sistem berbasis web dan mobile. Proses evaluasi dilakukan menggunakan parameter confusion matrix, accuracy, precision, recall, dan F1-score. Berdasarkan hasil pengujian, model memperoleh akurasi 93,33%, precision 93,71%, recall 92,92%, dan F1-score 93,31%. Sistem yang dibangun berhasil diimplementasikan pada platform web dan mobile dengan fitur unggah citra, proses klasifikasi otomatis, riwayat deteksi, serta rekomendasi penanganan penyakit. Dengan adanya sistem ini, pengguna diharapkan dapat melakukan deteksi dini penyakit daun kelapa sawit secara lebih cepat, praktis, dan akurat.
Kata Kunci: CNN, Deep Learning, Klasifikasi Citra, MobileNetV2, Penyakit Daun Sawit.
Abstract:Abstract: In managing its business strategy, PT. Halindo Berjaya Mandiri requires an intelligent computational approach to evaluate and predict the achievement level of sales targets based on historical data. This study…
aims to implement an Artificial Neural Network (ANN) using the Perceptron algorithm to classify overall fish sales data into two binary categories: 'Target Achieved' and 'Target Not Achieved'. The data used in this study relies on three independent input variables, namely the sales history in 2023, 2024, and 2025. The computational stages applied include data matrix preprocessing through the Min-Max Scaling normalization technique, linear combination calculation (Weighted Sum) mapped through the Sigmoid activation function, and an iterative optimization stage using the Delta Rule to update the weight and bias values. Based on the simulation and training conducted, the model was quantitatively evaluated using the Confusion Matrix method. The system testing results show that the Perceptron algorithm is capable of performing classification with a highly optimal accuracy rate of 94.81% and producing a very low error rate (Mean Squared Error) of 0.030291. This study proves that the ANN method with the Perceptron algorithm has high reliability and is highly feasible to be implemented as the foundation for a predictive decision support system at PT. Halindo Berjaya Mandiri.
Keywords: Artificial Neural Network, Perceptron Algorithm, Classification, Delta Rule, Sigmoid Function, Fish Sales.
Abstrak: PT. Halindo Berjaya Mandiri dalam mengelola strategi bisnisnya memerlukan pendekatan komputasi cerdas untuk mengevaluasi dan memprediksi tingkat pencapaian target penjualan berdasarkan data historis. Penelitian ini bertujuan untuk mengimplementasikan Jaringan Saraf Tiruan (JST) menggunakan algoritma Perceptron guna mengklasifikasikan data keseluruhan penjualan ikan ke dalam dua kategori biner, yaitu 'Mencapai Target' dan 'Tidak Mencapai Target'. Data yang digunakan dalam penelitian ini bertumpu pada tiga variabel masukan independen, yakni riwayat penjualan pada Tahun 2023, 2024, dan 2025. Tahapan komputasi yang diterapkan meliputi prapemrosesan matriks data melalui teknik normalisasi Min-Max Scaling, perhitungan kombinasi linear (Weighted Sum) yang dipetakan melalui fungsi aktivasi Sigmoid, serta tahapan optimasi iteratif menggunakan aturan Delta Rule untuk memperbarui nilai bobot dan bias. Berdasarkan simulasi dan pelatihan yang dilakukan, model dievaluasi secara kuantitatif menggunakan metode Confusion Matrix. Hasil pengujian sistem menunjukkan bahwa algoritma Perceptron mampu melakukan klasifikasi dengan tingkat akurasi yang sangat optimal sebesar 94,81% serta menghasilkan rasio tingkat kesalahan (Mean Squared Error) yang sangat rendah, yaitu 0,030291. Penelitian ini membuktikan bahwa metode JST algoritma Perceptron memiliki keandalan yang tinggi dan sangat layak untuk diimplementasikan sebagai landasan sistem pendukung keputusan prediktif pada PT. Halindo Berjaya Mandiri.
Kata Kunci: Jaringan Saraf Tiruan, Algoritma Perceptron, Klasifikasi, Delta Rule, Fungsi Sigmoid, Penjualan Ikan.
Abstract:Abstract: This study aims to classify provinces in Indonesia based on tourist stay patterns in star-rated hotels using the Hebb Network method. Computational data is sourced from official publications of the Central Statistics…
istics Agency (BPS) covering 38 provinces in Indonesia. The Hebb Network method was chosen because of its effectiveness in linearly adjusting the strength of weights between neurons based on the bipolar correlation of input and output values, thus mapping provinces into three target classes: Low, Medium, and High. The system is implemented using the PHP programming language to facilitate the training and computational testing process. Based on the results of testing 38 test data using the final network weight parameters, the model successfully classified 29 data sets correctly according to their actual target classes. The evaluation results showed that the system achieved an accuracy level of 76.32%. Misclassification of 23.68% generally occurred in data with values in the threshold area due to the dominance of the final network bias parameters. Overall, this model classification is valid in identifying stay patterns, thus providing strategic insights for local governments and tourism industry players in formulating more targeted and data-driven development policies.
Keywords: Hebb Network, Classification, Length of Stay, Starred Hotels, Machine Learning, Indonesian Tourism.
Abstrak: Penelitian ini bertujuan untuk mengklasifikasikan provinsi di Indonesia berdasarkan pola durasi menginap wisatawan pada hotel berbintang menggunakan metode Jaringan Hebb. Data komputasi bersumber dari publikasi resmi Badan Pusat Statistik (BPS) yang mencakup 38 provinsi di Indonesia. Metode Jaringan Hebb dipilih karena efektivitasnya dalam menyesuaikan kekuatan bobot antar neuron secara linier berdasarkan korelasi nilai masukan dan keluaran bipolar, sehingga mampu memetakan provinsi ke dalam tiga kelas target: Rendah, Sedang, dan Tinggi. Sistem diimplementasikan menggunakan bahasa pemrograman PHP untuk memfasilitasi proses pelatihan dan pengujian komputasi. Berdasarkan hasil pengujian terhadap 38 data uji menggunakan parameter bobot akhir jaringan, model berhasil mengklasifikasikan 29 data dengan tepat sesuai kelas target aktualnya. Hasil evaluasi menunjukkan bahwa sistem mampu mencapai tingkat akurasi sebesar 76,32%. Misklasifikasi sebesar 23,68% umumnya terjadi pada data dengan nilai di area batas ambang (threshold) akibat dominasi parameter bias akhir jaringan. Secara keseluruhan, model klasifikasi ini valid dalam mengidentifikasi pola durasi menginap, sehingga dapat memberikan wawasan strategis bagi pemerintah daerah dan pelaku industri pariwisata dalam merumuskan kebijakan pengembangan yang lebih terarah dan berbasis data.
Kata Kunci: Jaringan Hebb, Klasifikasi, Durasi Menginap, Hotel Berbintang, Machine Learning, Pariwisata Indonesia.
Abstract:The aims of this study is to determine the effect of the Treffinger Learning model assisted by the Wordwall application on the mathematical problem-solving abilities of students at SMA N 1 Air Batu. This study is a quasi-experimental…
-experimental study with a Two Group Pretest-Posttest Design. The population in this study was the entire tenth grade, consisting of five classes. The sample consisted of two classes (Xth-1 and Xth-2) selected using cluster random sampling. Xth-1 class served as the control class using the conventional learning model, while Xth-2 class served as the control class using the Treffinger Learning model. After the instruction is completed, a posttest is conducted, showing the average results for the experimental 53,793 and control classes 40,459. The t-test results tcount = 8,057>ttable=2,003 so Ho is rejected and H1 accepted, indicating the influence of the Treffinger Learning model assisted by the Wordwall application on the mathematical problem-solving abilities of students at SMA N 1 Air Batu.
Abstract: Higher education institutions are required to produce graduates who are competitive in the job market, yet tracer study data is often analyzed only descriptively, leaving deeper patterns unexplored. This study proposes…
ses an integrated approach combining Random Forest, SHAP (SHapley Additive exPlanations), and fairness evaluation to analyze alumni career outcomes. Data were sourced from the 2024 tracer study of Universitas Royal, comprising 466 alumni records with a binary target variable indicating employment status. Preprocessing included missing value handling, one-hot encoding, and stratified train-test splitting with an 80:20 ratio. Class imbalance was addressed using the class_weight='balanced' parameter. The Random Forest model achieved an accuracy of 95.7%, F1-score of 0.946, and AUC-ROC of 0.938, significantly outperforming the dummy baseline of 58.5%. Cross-validation across five folds yielded a mean accuracy of 96.4%, confirming model stability. SHAP analysis revealed that features related to educational level appropriateness and relevance of study field to current occupation were the most dominant predictors. Fairness evaluation per study program showed minimal performance disparity between Sistem Informasi (94.7%) and Sistem Komputer (100%), indicating no significant predictive bias. This framework demonstrates that explainable and fair machine learning can serve as a reliable foundation for evidence-based academic policy making