Claim Missing Document
Check
Articles

Found 18 Documents
Search

Decision Support System For Manager Placement In The Plantation Industry Using Topsis Method Teguh Widodo; Nur Wening; Rianto Rianto
Journal Of Social Science (JoSS) Vol 3 No 7 (2024): JOSS : Journal of Social Science
Publisher : Al-Makki Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57185/joss.v3i7.344

Abstract

Accuracy in placing employees determines the performance of a company. Likewise done by PT XYZ in determining the placement of managers in the plantation industry by using a decision support system. This is done in order to minimize the level of subjectivity of the manager placement determination system at PT XYZ. This research aims to provide alternative preference values to prospective employees who will occupy manager positions in the plantation industry. The method used in the placement of managers with a decision support system is the technique for Order Preference by Similarity to the Ideal Solution (TOPSIS) method. The criteria used in this method are 7 criteria taken based on the criteria for BUMN talent management according to the Regulation of the Minister of BUMN Number PER-3 / MBU / 03/2023, these criteria are Professional Work Period, Variety of Work Experience, Managerial Competence, Technical Competence, Educational Strata, Performance Assessment Results, Level of Punishment that has been received. The results of this study are from the results of the calculation analysis through the TOPSIS method on 7 alternatives, then there is name number 5 managed to get the best score of 0.80 and was determined as a preference to be placed in class A garden.
Determining the Best Laboratory Head Performance: A Data-Driven Approach to Enhanced Decision Making Using the SAW Method Evada Rustina; Nur Wening; Rianto Rianto
Asian Journal of Management, Entrepreneurship and Social Science Vol. 4 No. 02 (2024): May, Asian Journal of Management Entrepreneurship and Social Science ( AJMESC
Publisher : Cita Konsultindo Research Center

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

In today's fast-paced world, vocational schools play a pivotal role in shaping the future of the workforce. These schools focus on providing practical training to students, enabling them to acquire skills that are in demand in various industries. As a result, laboratory management is very important and requires attention. This study aims to determine the laboratory head's best performance. The study employs a quantitative approach, utilizing the SAW method and the Decision Support System, in addition to a descriptive analysis that compares the results of the principal's assessment with those of peers. Assessment is done using formulas that are Likert-scaled. The research was conducted at Putra Samodera Shipping Vocational School, Yogyakarta, Indonesia, where there are four laboratories, namely: a nautical laboratory, a commercial ship engineering laboratory, a language laboratory, and a computer laboratory. According to the results, the head of the commercial ship engineering laboratory performed the best. There is no difference between the assessments of the principal and peers, but the best performance according to the criteria is not the same. Other vocational schools can incorporate the implications of this study into their decision support systems and enhance them with various techniques to advance the discussion in future studies.
Determining the Best Work Behaviour of the Laboratory Head Using The Technique For Order Of Preference By Similarity To The Ideal Solution Evada Rustina; Hening Nakuloadi; Teguh Widodo; Nur Wening; Rianto Rianto
EKOMBIS REVIEW: Jurnal Ilmiah Ekonomi dan Bisnis Vol 12 No 3 (2024): Juli
Publisher : UNIVED Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37676/ekombis.v12i3.6089

Abstract

Vocational education is in high demand because it prepares students to be job-ready. In learning, it is more about work practices, internships, and in the laboratory than theory in class. Therefore, the existence of laboratories is essential in vocational schools. The research was conducted at the maritime school of SMK Putera Samodra, Yogyakarta, Indonesia, using the quantitative approach of the TOPSIS method to determine the best work behaviour performance from the head of the laboratory. Work behaviour assessment criteria include service orientation, integrity, commitment, discipline, and cooperation. According to the assessment results by the principal and 31 colleagues, the best work behaviour is that of the head of the merchant ship engineering laboratory. Overall, the best work behaviour analysis results can have a positive impact, such as recognition, improved leadership practices, and enhanced performance in all laboratories in vocational schools. Other potential implications of work behaviour research results for schools can be developing leadership with the best strategies, identifying areas for improvement, allocating more resources to laboratories, and the positive effects of leadership qualities on vocational schools.
Pemanfaatan Teknologi Informasi untuk Inovasi Motif, Diversifikasi Produk, dan Perluasan Jaringan Pasar pada Batik Nitik Kembangsore Rianto Rianto; Enny Itje Sela; Nur Wening
I-Com: Indonesian Community Journal Vol 4 No 4 (2024): I-Com: Indonesian Community Journal (Desember 2024)
Publisher : Fakultas Sains Dan Teknologi, Universitas Raden Rahmat Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/icom.v4i4.5689

Abstract

Batik Nitik Kembangsore operates in the traditional batik industry, with unique and exclusive motifs. However, the current production is limited to jarit cloth with a relatively high price, resulting in low sales turnover due to the high selling price. This Community Partnership Program proposes a solution to overcome these challenges by diversifying products and creating contemporary batik motifs using artificial intelligence. Leonardo.ai's online tools will be used to design new motifs while maintaining the aesthetic value and philosophy of Batik Nitik Kembangsore. In addition, to strengthen the marketing and sales system, the website www.kembangsore.com will be developed as an integrated digital platform. With this strategy, it is hoped that Batik Nitik Kembangsore can expand its market reach, increase competitiveness, and reach broader consumers. This innovation supports the sustainability of the traditional batik industry and strengthens Batik Nitik Kembangsore's position in the modern market.
Optimizing The User Interface of Waste Bank Application Using UCD and UEQ Prihatini, Retno; Rianto
Jurnal Nasional Pendidikan Teknik Informatika : JANAPATI Vol. 13 No. 3 (2024)
Publisher : Prodi Pendidikan Teknik Informatika Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/janapati.v13i3.83998

Abstract

Environmental cleanliness is an essential aspect of life to make a healthy and comfortable environment. In Indonesia, the volume of waste will reach 70 million tons by 2022, with around 24% or 16 million tons needing to be appropriately managed. Related to the significant waste growth, the Ministry of Environment has developed the Waste Bank initiative, a collaborative effort that aims to educate the public in sorting waste and raising awareness of the importance of wise waste management. The desire of the local environmental agency to connect with the community supports the researcher in developing the Waste Bank application. The application will implement an optimal User Interface (UI) and User Experience (UX) design. The User-Centered Design (UCD) method will be employed, supported by the User Experience Questionnaire (UEQ), and is used to design UI and UX for the Waste Bank mobile application. The application prototypes were tested and evaluated using UEQ. The first design achieved an average score but still required improvement. In contrast, the second design scored excellently in six aspects measured: attractiveness, perspicuity, efficiency, dependability, stimulation, and novelty, with significant improvement. These results show that the UCD and UEQ methods are effective for developing UI/UX designs to meet user needs and can be applied in mobile application developments.
Analisis Perbandingan Algoritma Decision Tree dengan Random Forest dalam Deteksi Bot DDOS Kristianto Pratama Dessan Putra; Rianto Rianto; EIH Ujianto
IJAI (Indonesian Journal of Applied Informatics) Vol 10, No 1 (2025)
Publisher : Universitas Sebelas Maret

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20961/ijai.v10i1.103161

Abstract

Abstrak : Tingkat penetrasi internet yang semakin meningkat setiap tahunnya juga berpengaruh pada banyaknya peralihan layanan dari konvensional ke platform internet. Peralihan layanan tersebut terbukti membawa dampak baik, seperti meningkatnya volume penjualan produk. Namun, di sisi lain dengan semakin banyaknya peralihan layanan ke platform internet maka semakin banyak pula celah-celah keamanan yang dapat dieksploitasi, salah satunya serangan bot DDos. Oleh karena itu, diperlukan adanya sistem yang mampu mendeteksi serangan bot DDos dan algoritma yang akan dianalisis dalam penelitian ini adalah Decision Tree dan Random Forest. Penelitian ini akan membandingkan kedua algoritma tersebut untuk menentukan algoritma yang paling optimal dalam mendeteksi serangan bot DDos. Penelitian ini menggunakan dua dataset dalam proses implementasi algoritma, yaitu KDD CUP 1999 dan CICIDS 2017. Ruang lingkup dari perbandingan kedua algoritma meliputi tingkat akurasi dan durasi waktu pemrosesan data. Hasil dari penelitian menunjukkan bahwa algoritma Random Forest unggul tipis dalam hal tingkat akurasi dibandingkan dengan Decision Tree, yaitu 0.9998 untuk Random Forest berbanding 0.9997 untuk Decision Tree. Namun, algoritma Decision Tree unggul jauh dalam hal durasi waktu dibandingkan dengan Random Forest, yaitu 20-30 detik untuk Decision Tree berbanding 210-300 detik untuk Random Forest. Hal tersebut dapat terjadi dikarenakan Random Forest memproses lebih banyak pohon kemungkinan dibandingkan Decision Tree.=============================================Abstract : The increasing internet penetration each year also affects the shift of services from conventional methods to internet platforms. This shift has proven to bring positive impacts, such as an increase in product sales volume. However, there are increasingly more security vulnerabilities that can be exploited, such as DDoS bot attacks. Therefore, a system that capable to detect bot DDoS attacks is needed. This study compares these two algorithms (Decision Tree and Random Forest) to determine which is the most optimal for detecting bot DDoS attacks. The scope of the comparison includes accuracy levels and data processing time. The results show that Random Forest slightly outperforms Decision Tree in terms of accuracy, with a score of 0.9998 for Random Forest compared to 0.9997 for Decision Tree. However, Decision Tree is significantly superior in processing time compared to Random Forest (20–30 seconds for Decision Tree versus 210–300 seconds for Random Forest). This occurs because Random Forest processes more trees than Decision Tree. 
Improving Online Exam Verification with Class-Weighted and Augmented CNN Models Ilham Fanani; Rianto Rianto
Jurnal Teknologi Informasi dan Terapan Vol 11 No 2 (2024): December
Publisher : Jurusan Teknologi Informasi Politeknik Negeri Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25047/jtit.v11i2.435

Abstract

The COVID-19 pandemic has shifted interactions to virtual platforms, significantly impacting education, particularly online exams. However, these online exams have vulnerabilities, including exam jockeys. This study proposes a face classification model using a Convolutional Neural Network (CNN) to verify online exam takers. The model uses preprocessing techniques, i.e. normalization, data augmentation, and class weighting, to balance data and enhance generalization utilizing TensorFlow. The results show an overall accuracy of 85%, with a precision of 86.34%, a recall of 84.24%, an F1-score of 85.28% for legal takers, and a precision of 83.65%, recall of 85.81%, and an F1-score of 84.71% for illegal takers. These results indicate the model's balanced performance between legal and illegal classes. By integrating CNN with tailored preprocessing and training strategies, this study addresses gaps in existing authentication methods, offering a robust approach to online exam verification. The proposed model shows a chance for practical applications. However, further optimization through larger datasets and advanced augmentation techniques is recommended to improve its accuracy and adaptability to diverse real-world contexts
Enhancing SVM-Based Classification Performance on Indonesian Sentences through TF-IDF and Directional Augmentation Rianto, Rianto; Humanika, Eko Setyo; Untoro, Iwan Hartadi Tri
INTENSIF: Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem Informasi Vol 10 No 1 (2026)
Publisher : Universitas Nusantara PGRI Kediri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29407/intensif.v10i1.25179

Abstract

Background: The distinction between standard and non-standard Indonesian sentences is traditionally well-defined, yet the ubiquity of digital communication has increasingly blurred these boundaries. This convergence introduces significant lexical ambiguity in formal contexts, complicating the performance of automated text classification systems. Objective: This study aims to enhance the robustness of Support Vector Machine (SVM) classification by addressing these linguistic irregularities through TF-IDF vectorization and a targeted directional augmentation strategy. Methods: A corpus comprising 5,394 labeled sentences was processed under a strict anti-leak grouping strategy to rigorously prevent semantic leakage between training, validation, and testing sets. To resolve decision boundary overlaps often missed by the baseline model, manual directional augmentation was applied, specifically targeting ambiguous sentence structures to enrich the training distribution and linguistic diversity. Results: The experiments demonstrated that directional augmentation significantly refined the model's decision margins. While the baseline model achieved a test accuracy of 94.39%, the augmented approach substantially improved generalization capabilities across unseen groups, elevating validation accuracy from 96.11% to 97.39% and test accuracy to 96.16%. Conclusion: These findings substantiate that structurally enriching the dataset effectively mitigates overfitting and improves sensitivity. However, given the scalability constraints of manual intervention, future research should prioritize automated augmentation techniques and contextual embeddings to handle deep linguistic nuances further.