Garuda - Garba Rujukan Digital

Marketing Strategy Using Frequent Pattern Growth Nazori Suhandi; Rendra Gustriansyah
Journal of Computer Networks, Architecture and High Performance Computing Vol. 3 No. 2 (2021): Journal of Computer Networks, Architecture and High Performance Computing, July
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v3i2.1039

The biggest problem faced by printing companies during the Covid-19 pandemic was that the number of orders was unstable and tends to decrease, which had the potential to harm the company. Therefore, various appropriate marketing strategies were needed so that the number of product orders was relatively stable and even increases. The impact was that the company could survive and continued to grow. This study aimed to assist company managers in developing appropriate marketing strategies based on association rules generated from one of the data mining methods, namely the Frequent Pattern Growth (FP-Growth) method. The case study of this research was a printing company where there was no similar research that used a printing company's dataset. This study produced nine association rules that meet a minimum of 25% support and a minimum of 60% confidence, but only two association rules that had a high positive correlation, namely for a custom paper bag and banner products. Therefore, several marketing strategies were suggested that could be used as guidelines for companies in managing sales packages and giving special discounts on a product. The results of this study are expected to trigger an increase in the number of product orders because this study tried to find the right product for consumers and did not try to find the right consumers for a product.

The Housing Recommendation System Uses Multi-Criteria Decision-Making Methods Nazori Suhandi; Rendra Gustriansyah
Journal of Computer Networks, Architecture and High Performance Computing Vol. 5 No. 2 (2023): Article Research Volume 5 Issue 2, July 2023
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v5i2.2497

Economic and population growth, increasing urbanization, changing habits, new welfare requirements, and lower interest rates have led to increased demand for housing in cities. However, housing conditions in many cities are slightly alarming, while housing is a primary need for the community. Selecting housing for low-income people (LIP) that meets the criteria required by LIP is not an easy task. Because most of the decisions people made did not utilize detailed information. Therefore, a recommendation system for LIP is required. This study aims to develop the housing selection recommendation system for LIP that best suits their wishes. This study integrated two multi-criteria decision-making (MCDM) methods: the Best Worst (BW) method, which has fewer pairwise comparisons compared to other MCDM methods for selecting criteria and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method for determining housing recommendations for LIP according to their wishes. Based on the analysis results, ten criteria dominate the housing selection for LIP sequentially: Location, Land Size, Down Payment, Public Facilities, Price, Booking Fee, Home Design, House Specifications, House Quality, and Home Ownership Credit. Furthermore, the sensitivity analysis results showed that the robustness score of this approach was high. The model could recommend housing for LIP that best suits their wishes.

Improving Information Security with Machine Learning Ahmad Sanmorino; Rendra Gustriansyah; Shinta Puspasari; Juhaini Alie
Journal of Computer Networks, Architecture and High Performance Computing Vol. 6 No. 1 (2024): Article Research Volume 6 Issue 1, January 2024
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v6i1.3317

The study Improving Information Security with Machine Learning explores the fusion of machine learning methodologies within information security, aiming to fortify conventional protocols against evolving cyber threats. By conducting a comprehensive literature review and empirical analysis, this scholarly endeavor highlights the efficacy of machine learning in anomaly detection, threat identification, and predictive analytics within security frameworks. Through practical demonstrations, such as z-score-based anomaly detection in network traffic data and NLP-based email security systems, the study illustrates the practical applications of machine learning techniques. Additionally, it delves into the mathematical underpinnings of predictive analytics and the architecture of neural networks for malware detection. However, while showcasing the transformative potential of machine learning, the study also confronts significant challenges. Ethical, legal, and privacy considerations emerge prominently, emphasizing the need for regulations addressing algorithmic biases, ethical dilemmas, and data protection. Moreover, the study emphasizes the practical challenges of scalability, interpretability, continual adaptation to evolving threats, and the harmonious interaction between human expertise and machine intelligence. By offering practical recommendations and future research directions, this scholarly exploration aims to empower researchers, practitioners, and policymakers in navigating the complex intersection of machine learning and information security, thereby fostering innovation and comprehension in this evolving domain.

Toddlers’ Nutritional Status Prediction Using the Multinomial Logistics Regression Method Rendra Gustriansyah; Nazori Suhandi; Shinta Puspasari; Ahmad Sanmorino; Dewi Sartika
Journal of Computer Networks, Architecture and High Performance Computing Vol. 6 No. 1 (2024): Article Research Volume 6 Issue 1, January 2024
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v6i1.3372

Malnutrition is one of the foremost health problems experienced by children under five in many countries, especially in low and middle-income countries. Meanwhile, the target of Sustainable Development Goals (SDGs) 2.2 is that all forms of malnutrition must end by 2025. Therefore, this study aims to predict the toddlers’ nutritional status (malnutrition, undernutrition, overnutrition, and normal nutrition) based on age, body mass index (BMI), weight, and length using the Multinomial Logistic Regression (MLR) classification method. The dataset consists of two hundred toddlers obtained from the Kaggle site. Following pre-processing, the dataset is divided, with 80 percent of the data for training and the remaining 20 percent for testing. The model was trained using 10-fold cross-validation (CV). In Addition, the MLR model performance was evaluated using the confusion matrix (CM), the area under the curve (AUC), and the Kappa coefficient (KC). The evaluation results using CM show that the accuracy, sensitivity, and specificity values are 0.9412, 0.9375, and 0.9790, respectively. AUC and KC also show excellent results. It indicates that the MLR method is an esteemed and recommended method for predicting the nutritional status of toddlers. Therefore, this research can contribute to providing early information so that the Government can immediately determine the necessary treatment.

Improving Information Security with Machine Learning Sanmorino, Ahmad; Gustriansyah, Rendra; Puspasari, Shinta; Alie, Juhaini
Journal of Computer Networks, Architecture and High Performance Computing Vol. 6 No. 1 (2024): Article Research Volume 6 Issue 1, January 2024
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v6i1.3317

The study Improving Information Security with Machine Learning explores the fusion of machine learning methodologies within information security, aiming to fortify conventional protocols against evolving cyber threats. By conducting a comprehensive literature review and empirical analysis, this scholarly endeavor highlights the efficacy of machine learning in anomaly detection, threat identification, and predictive analytics within security frameworks. Through practical demonstrations, such as z-score-based anomaly detection in network traffic data and NLP-based email security systems, the study illustrates the practical applications of machine learning techniques. Additionally, it delves into the mathematical underpinnings of predictive analytics and the architecture of neural networks for malware detection. However, while showcasing the transformative potential of machine learning, the study also confronts significant challenges. Ethical, legal, and privacy considerations emerge prominently, emphasizing the need for regulations addressing algorithmic biases, ethical dilemmas, and data protection. Moreover, the study emphasizes the practical challenges of scalability, interpretability, continual adaptation to evolving threats, and the harmonious interaction between human expertise and machine intelligence. By offering practical recommendations and future research directions, this scholarly exploration aims to empower researchers, practitioners, and policymakers in navigating the complex intersection of machine learning and information security, thereby fostering innovation and comprehension in this evolving domain.

Toddlers’ Nutritional Status Prediction Using the Multinomial Logistics Regression Method Gustriansyah, Rendra; Suhandi, Nazori; Puspasari, Shinta; Sanmorino, Ahmad; Sartika, Dewi
Journal of Computer Networks, Architecture and High Performance Computing Vol. 6 No. 1 (2024): Article Research Volume 6 Issue 1, January 2024
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v6i1.3372

Malnutrition is one of the foremost health problems experienced by children under five in many countries, especially in low and middle-income countries. Meanwhile, the target of Sustainable Development Goals (SDGs) 2.2 is that all forms of malnutrition must end by 2025. Therefore, this study aims to predict the toddlers’ nutritional status (malnutrition, undernutrition, overnutrition, and normal nutrition) based on age, body mass index (BMI), weight, and length using the Multinomial Logistic Regression (MLR) classification method. The dataset consists of two hundred toddlers obtained from the Kaggle site. Following pre-processing, the dataset is divided, with 80 percent of the data for training and the remaining 20 percent for testing. The model was trained using 10-fold cross-validation (CV). In Addition, the MLR model performance was evaluated using the confusion matrix (CM), the area under the curve (AUC), and the Kappa coefficient (KC). The evaluation results using CM show that the accuracy, sensitivity, and specificity values are 0.9412, 0.9375, and 0.9790, respectively. AUC and KC also show excellent results. It indicates that the MLR method is an esteemed and recommended method for predicting the nutritional status of toddlers. Therefore, this research can contribute to providing early information so that the Government can immediately determine the necessary treatment.

Marketing Strategy Using Frequent Pattern Growth Suhandi, Nazori; Gustriansyah, Rendra
Journal of Computer Networks, Architecture and High Performance Computing Vol. 3 No. 2 (2021): Journal of Computer Networks, Architecture and High Performance Computing, July
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v3i2.1039

The biggest problem faced by printing companies during the Covid-19 pandemic was that the number of orders was unstable and tends to decrease, which had the potential to harm the company. Therefore, various appropriate marketing strategies were needed so that the number of product orders was relatively stable and even increases. The impact was that the company could survive and continued to grow. This study aimed to assist company managers in developing appropriate marketing strategies based on association rules generated from one of the data mining methods, namely the Frequent Pattern Growth (FP-Growth) method. The case study of this research was a printing company where there was no similar research that used a printing company's dataset. This study produced nine association rules that meet a minimum of 25% support and a minimum of 60% confidence, but only two association rules that had a high positive correlation, namely for a custom paper bag and banner products. Therefore, several marketing strategies were suggested that could be used as guidelines for companies in managing sales packages and giving special discounts on a product. The results of this study are expected to trigger an increase in the number of product orders because this study tried to find the right product for consumers and did not try to find the right consumers for a product.

The Housing Recommendation System Uses Multi-Criteria Decision-Making Methods Suhandi, Nazori; Gustriansyah, Rendra
Journal of Computer Networks, Architecture and High Performance Computing Vol. 5 No. 2 (2023): Article Research Volume 5 Issue 2, July 2023
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v5i2.2497

Economic and population growth, increasing urbanization, changing habits, new welfare requirements, and lower interest rates have led to increased demand for housing in cities. However, housing conditions in many cities are slightly alarming, while housing is a primary need for the community. Selecting housing for low-income people (LIP) that meets the criteria required by LIP is not an easy task. Because most of the decisions people made did not utilize detailed information. Therefore, a recommendation system for LIP is required. This study aims to develop the housing selection recommendation system for LIP that best suits their wishes. This study integrated two multi-criteria decision-making (MCDM) methods: the Best Worst (BW) method, which has fewer pairwise comparisons compared to other MCDM methods for selecting criteria and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method for determining housing recommendations for LIP according to their wishes. Based on the analysis results, ten criteria dominate the housing selection for LIP sequentially: Location, Land Size, Down Payment, Public Facilities, Price, Booking Fee, Home Design, House Specifications, House Quality, and Home Ownership Credit. Furthermore, the sensitivity analysis results showed that the robustness score of this approach was high. The model could recommend housing for LIP that best suits their wishes.

Title

Found 8 Documents
Search
Journal : journal of computer networks architecture and high performance computing

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 8 Documents Search Journal : journal of computer networks architecture and high performance computing

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 8 Documents
Search
Journal : journal of computer networks architecture and high performance computing