Muhammad Qois Huzyan Octava

Mr. Muhammad Qois Huzyan Octava

Universitas Gadjah Mada, Yogyakarta, Indonesia
orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 October 2023 in Information
Verified
Journal Article
Open access
PDF file
Ganjar AlfianGanjar Alfian
Ganjar Alfian
Muhammad Qois Huzyan OctavaMuhammad Qois Huzyan Octava
Muhammad Qois Huzyan Octava
FHFarhan Mufti Hilmy
Farhan Mufti Hilmy
RNRachma Aurya Nurhaliza
Rachma Aurya Nurhaliza
YSYuris Mulya Saputra
Yuris Mulya Saputra
MSMuhammad Syafrudin
Muhammad Syafrudin
Analyzing customer shopping habits in physical stores is crucial for enhancing the retailer–customer relationship and increasing business revenue. However, it can be challenging to gather data on customer browsing activities in physical stores as compared to online stores. This study suggests using RFID technology on store shelves and machine learning models to analyze customer browsing activity in retail stores. The study uses RFID tags to track product movement and collects data on customer behavior using receive signal strength (RSS) of the tags. The time-domain features were then extracted from RSS data and machine learning models were utilized to classify different customer shopping activities. We proposed integration of iForest Outlier Detection, ADASYN data balancing and Multilayer Perceptron (MLP). The results indicate that the proposed model performed better than other supervised learning models, with improvements of up to 97.778% in accuracy, 98.008% in precision, 98.333% in specificity, 98.333% in recall, and 97.750% in the f1-score. Finally, we showcased the integration of this trained model into a web-based application. This result can assist managers in understanding customer preferences and aid in product placement, promotions, and customer recommendations.
1

8 March 2023 in Future Internet
Verified
Journal Article
Open access
PDF file
Ganjar AlfianGanjar Alfian
Ganjar Alfian
MSMuhammad Syafrudin
Muhammad Syafrudin
NFNorma Latif Fitriyani
Norma Latif Fitriyani
SASahirul Alam
Sahirul Alam
DPDinar Nugroho Pratomo
Dinar Nugroho Pratomo
FBFilip Beneš
Filip Beneš
In recent years, radio frequency identification (RFID) technology has been utilized to monitor product movements within a supply chain in real time. By utilizing RFID technology, the products can be tracked automatically in real-time. However, the RFID cannot detect the movement and direction of the tag. This study investigates the performance of machine learning (ML) algorithms to detect the movement and direction of passive RFID tags. The dataset utilized in this study was created by considering a variety of conceivable tag motions and directions that may occur in actual warehouse settings, such as going inside and out of the gate, moving close to the gate, turning around, and static tags. The statistical features are derived from the received signal strength (RSS) and the timestamp of tags. Our proposed model combined Isolation Forest (iForest) outlier detection, Synthetic Minority Over Sampling Technique (SMOTE) and Random Forest (RF) has shown the highest accuracy up to 94.251% as compared to other ML models in detecting the movement and direction of RFID tags. In addition, we demonstrated the proposed classification model could be applied to a web-based monitoring system, so that tagged products that move in or out through a gate can be correctly identified. This study is expected to improve the RFID gate on detecting the status of products (being received or delivered) automatically.

1 August 2024 in Bulletin of Electrical Engineering and Informatics
Verified
Journal Article
Open access
PDF file
RNRachma Aurya Nurhaliza
Rachma Aurya Nurhaliza
Muhammad Qois Huzyan OctavaMuhammad Qois Huzyan Octava
Muhammad Qois Huzyan Octava
FHFarhan Mufti Hilmy
Farhan Mufti Hilmy
UFUmar Farooq
Umar Farooq
Ganjar AlfianGanjar Alfian
Ganjar Alfian
Recent advancements in biosensors have empowered individuals with diabetes to autonomously monitor their blood glucose levels through continuous glucose monitoring (CGM) sensors. Nevertheless, the data collected from these sensors may occasionally include outliers due to the inherent imperfections of the sensor devices. Consequently, the identification of these outliers is critical to determine whether blood glucose levels deviate significantly from the norm, necessitating further action. This study employs an outlier detection approach based on the 3-sigma method and the interquartile range (IQR), along with the application of the Winsorizing technique to correct the identified outliers. Additionally, a web-based system for visualizing blood glucose levels is developed, utilizing both outlier detection methods. In order to assess the system's performance, two types of testing are conducted: black box testing and load testing. The results of black box testing indicate that all test scenarios operate as anticipated. As for the load testing response times, it is observed that the 3-sigma visualization page loads an average of 606.75 milliseconds faster compared to the IQR visualization page. This study's outcomes are expected to enhance data quality, enhance the precision of analyses, and facilitate more informed decision-making by identifying and addressing extreme data points.

20 November 2023
Verified
Conference Paper
Closed access
Muhammad Qois Huzyan OctavaMuhammad Qois Huzyan Octava
Muhammad Qois Huzyan Octava
DPDivi Galih Prasetyo Putri
Divi Galih Prasetyo Putri
FHFarhan Mufti Hilmy
Farhan Mufti Hilmy
UFUmar Farooq
Umar Farooq
RNRachma Aurya Nurhaliza
Rachma Aurya Nurhaliza
Ganjar AlfianGanjar Alfian
Ganjar Alfian
Social media's tendency for instant reactions can be harnessed by companies and organizations to gather feedback. Nevertheless, effectively analyzing vast amounts of social media data poses a challenge. This issue can be addressed through the use of sentiment analysis technology. In this study, a sentiment analysis model is developed, employing Support Vector Machine (SVM) and Term Frequency-Inverse Document Frequency (TF-IDF) algorithms. The study aims to investigate the impact of feature engineering on TF-IDF, by incorporating statistical features into the SVM model's sentiment analysis performance. The experimental results reveal that the prediction model utilizing the conventional TFIDF approach achieves an SVM model with an F-measure score of 84.55%. Through the implementation of feature engineering, by adding max, min, and sum features, the model's performance shows a noticeable improvement, with an increase of 0.65% in the F-measure score difference. Consequently, the proposed feature engineering method positively enhances the capability of the SVM-based sentiment analysis model. To facilitate the acquisition of sentiment analysis results through user interfaces, the trained SVM model is integrated into a web-based sentiment analysis application. By doing so, the findings of this study contribute to streamlining the process of obtaining sentiment analysis results from social media data.

20 November 2023
Verified
Conference Paper
Closed access
FHFarhan Mufti Hilmy
Farhan Mufti Hilmy
RNRachma Aurya Nurhaliza
Rachma Aurya Nurhaliza
Muhammad Qois Huzyan OctavaMuhammad Qois Huzyan Octava
Muhammad Qois Huzyan Octava
Ganjar AlfianGanjar Alfian
Ganjar Alfian
Database marketing has gained significant importance in today's business landscape due to the availability of vast customer data held by many companies. This has led to the widespread adoption of database marketing across various industries, such as retail, e-commerce, banking, and telecommunications. Continuously understanding customer behavior is crucial as their trends and preferences evolve over time. This study aims to support companies in enhancing customer loyalty, retention, and fostering long-term relationships by better understanding their customers. To achieve this, companies can monitor customer behavior and adjust their marketing strategies, one effective approach being the utilization of Recency, Frequency, and Monetary (RFM) analysis. RFM analysis, which stands for Recency, Frequency, and Monetary, is a technique used to segment customers based on their past purchasing behavior. Recency assesses how recently a customer has made a purchase, Frequency measures the frequency of a customer's purchases, and Monetary evaluates the amount a customer spends per purchase. In this study, the K-Means unsupervised learning algorithm is employed to categorize customers into three groups: Loyal, Promising, and Need Attention based on Recency, Frequency, and Monetary features. The experimental findings indicate that the K-Means algorithm outperforms K-Medoids for customer segmentation, as evidenced by higher values for the Silhouette Coefficient (0.74), Davies Bouldin Index (0.51), and Calinski Harabasz Index (8972.97). To facilitate the interpretation of these results, a web dashboard was created using the Streamlit Python library. By visualizing the analysis outcomes through this platform, companies can gain valuable insights into customer behavior and preferences.

30 May 2023 in Journal of Internet and Software Engineering
Verified
Journal Article
Open access
PDF file
YSYuris Mulya Saputra
Yuris Mulya Saputra
Ganjar AlfianGanjar Alfian
Ganjar Alfian
Muhammad Qois Huzyan OctavaMuhammad Qois Huzyan Octava
Muhammad Qois Huzyan Octava
Semakin berkembangnya pasar big data yang digunakan oleh pengguna khususnya Internet of Things (IoT) berbasis kecerdasan buatan telah menarik banyak pihak baik dari industri maupun akademisi. Melalui penggunaan data lokal dari berbagai perangkat IoT, pemberi layanan aplikasi dapat menghasilkan informasi berguna melalui pendekatan machine learning (ML) seperti centralized learning dengan menggunakan cloud server dan local learning pada perangkat IoT langsung. Namun, dengan adanya risiko bocornya privasi pengguna ketika mengirim data lokal ke cloud server dan sumber daya komputasi yang terbatas pada IoT, penggunaan federated learning (FL) dapat menjadi solusi efisien. Pendekatan FL merupakan sebuah pendekatan ML kolaboratif di mana setiap perangkat IoT dapat melakukan proses training secara independen dan kemudian hanya mengirimkan model local kepada cloud server tanpa melakukan data sharing. Secara khusus, penggunaan FL untuk layanan aplikasi pada perangkat IoT tidak hanya memperbaiki kinerja untuk proses training, namun juga dapat melindungi privasi data bagi penggunanya. Penelitian ini berfokus pada perancangan sistem FL dengan privacy-awareness yang dapat digunakan oleh para pengguna perangkat IoT. Dalam hal ini, teknik enkripsi yang berbasis homomorphic encryption untuk mengenkripsi data dari perangkat IoT ketika proses training dari FL dapat diimplementasikan sebagai bentuk perlindungan privasi pengguna IoT dari malicious attackers. Dari penelitian ini, dapat dianalisis perbandingan tingkat akurasi model dari berbagai pendekatan baik tanpa dan dengan teknik enkripsi tersebut.