Hery Mustofa
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hery Mustofa has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Adzhal Arwani Mahfudh
UIN Walisongo Semarang
3 shared publications - Khothibul Umam
UIN Walisongo Semarang
2 shared publications Amiliya Putri
UIN Walisongo Semarang
1 shared publication- Hendra Masvika
Universitas Semarang
1 shared publication J. R. Arraafiulna
Mathematics Department, Faculty of Science and Technology, UIN Walisongo Semarang, Prof. Hamka Street, Ngaliyan, Semarang, 50185, Indonesia
1 shared publication- Juwita Ramadhani
Farmasi, Universitas Islam Kalimantan Muhammad Arsyad Al Banjari
1 shared publication
Latest Publications
- Open Access
- 9 December 2025
- Published by Politeknik Negeri Batam in JOURNAL OF APPLIED INFORMATICS AND COMPUTING
- Vol. 9 (6) , 3689-3696
Comparative Analysis of Penetration Testing Frameworks: OWASP, PTES, and NIST SP 800-115 for Detecting Web Application Vulnerabilities
Web application security faces increasingly complex challenges as digital architectures evolve, necessitating the selection of appropriate and effective penetration testing methods. This study presents a comparative analysis of the OWASP Testing Guide, PTES, and NIST SP 800-115 frameworks in detecting web application vulnerabilities. Through experiments on DVWA and OWASP Juice Shop, the frameworks were evaluated based on detection speed, vulnerability count, and severity. The results highlight a clear trade-off: OWASP proved the most efficient (85 minutes average, 59 total vulnerabilities), making it ideal for rapid assessments. PTES demonstrated the most comprehensive technical depth (63 vulnerabilities, highest severity) but required the most time, while NIST SP 800-115 (49 vulnerabilities) excelled in compliance and risk management integration. The study recommends selecting OWASP for efficiency, PTES for deep technical audits, and NIST for regulatory alignment.
- 9 December 2025
- Published by Politeknik Negeri Batam in JOURNAL OF APPLIED INFORMATICS AND COMPUTING
- Vol. 9 (6) , 3689-3696
Open AccessComparative Analysis of Penetration Testing Frameworks: OWASP, PTES, and NIST SP 800-115 for Detecting Web Application Vulnerabilities
Web application security faces increasingly complex challenges as digital architectures evolve, necessitating the selection of appropriate and effective penetration testing methods. This study presents a comparative analysis of the OWASP Testing Guide, PTES, and NIST SP 800-115 frameworks in detecting web application vulnerabilities. Through experiments on DVWA and OWASP Juice Shop, the frameworks were evaluated based on detection speed, vulnerability count, and severity. The results highlight a clear trade-off: OWASP proved the most efficient (85 minutes average, 59 total vulnerabilities), making it ideal for rapid assessments. PTES demonstrated the most comprehensive technical depth (63 vulnerabilities, highest severity) but required the most time, while NIST SP 800-115 (49 vulnerabilities) excelled in compliance and risk management integration. The study recommends selecting OWASP for efficiency, PTES for deep technical audits, and NIST for regulatory alignment.
- Open Access
- 6 December 2025
- Published by Politeknik Negeri Batam in JOURNAL OF APPLIED INFORMATICS AND COMPUTING
- Vol. 9 (6) , 3168-3176
Opinion Classification on IMDb Reviews Using Naïve Bayes Algorithm
This study aims to classify user opinions on IMDb movie reviews using the Multinomial Naïve Bayes algorithm. The dataset consists of 50,000 reviews, evenly distributed between 25,000 positive and 25,000 negative reviews. The preprocessing stage includes cleaning, case folding, stopword removal, tokenization, and lemmatization using the NLTK library. Text features are represented through the TF-IDF method to capture the significance of each word in the documents. The Multinomial Naïve Bayes model was trained using the hold-out validation technique with an 80:20 split for training and testing data. Hyperparameter tuning of α (Laplace smoothing) was conducted to enhance model stability and accuracy. The model’s performance was evaluated using accuracy, precision, recall, and F1-score metrics, supported by a confusion matrix visualization. The results show that the model achieved an accuracy of 87%, with precision of 87.9%, recall of 85.4%, and an F1-score of 86.6%. In comparison, Logistic Regression as a baseline algorithm achieved an accuracy of 91%. Nevertheless, the Naïve Bayes algorithm remains competitive and computationally efficient for large-scale text data, making it highly relevant for sentiment analysis of movie reviews.
- 6 December 2025
- Published by Politeknik Negeri Batam in JOURNAL OF APPLIED INFORMATICS AND COMPUTING
- Vol. 9 (6) , 3168-3176
Open AccessOpinion Classification on IMDb Reviews Using Naïve Bayes Algorithm
This study aims to classify user opinions on IMDb movie reviews using the Multinomial Naïve Bayes algorithm. The dataset consists of 50,000 reviews, evenly distributed between 25,000 positive and 25,000 negative reviews. The preprocessing stage includes cleaning, case folding, stopword removal, tokenization, and lemmatization using the NLTK library. Text features are represented through the TF-IDF method to capture the significance of each word in the documents. The Multinomial Naïve Bayes model was trained using the hold-out validation technique with an 80:20 split for training and testing data. Hyperparameter tuning of α (Laplace smoothing) was conducted to enhance model stability and accuracy. The model’s performance was evaluated using accuracy, precision, recall, and F1-score metrics, supported by a confusion matrix visualization. The results show that the model achieved an accuracy of 87%, with precision of 87.9%, recall of 85.4%, and an F1-score of 86.6%. In comparison, Logistic Regression as a baseline algorithm achieved an accuracy of 91%. Nevertheless, the Naïve Bayes algorithm remains competitive and computationally efficient for large-scale text data, making it highly relevant for sentiment analysis of movie reviews.
- Open Access
- 13 June 2025
- Published by Etflin in Digital System and Computing
- Vol. 1 (1) , 13-18
Design and Evaluation of an IoT-Based Real-Time Energy Monitoring System Using NodeMCU and PZEM-004T
The increasing demand for accurate and affordable household electricity monitoring has driven the development of Internet of Things (IoT)–based systems. This study designed and evaluated a real-time energy monitoring system using a NodeMCU microcontroller integrated with a PZEM-004T sensor module. The system was tested on three household appliances, an electric iron, a fan, and a refrigerator, and its measurements were compared with a calibrated reference wattmeter and manual energy calculations. The results showed that the system’s readings closely matched those of the reference device, demonstrating reliable accuracy in capturing real-time energy consumption. Higher deviations were observed against manual calculations, mainly due to the inability of manual methods to capture dynamic load fluctuations, particularly from the refrigerator’s compressor. Overall, the system achieved an average error of 1.19% compared with the reference measurements, confirming its technical feasibility for practical household energy monitoring. Future work should improve accuracy for fluctuating loads through adaptive sampling and expand system scalability via cloud-based integration.
- 13 June 2025
- Published by Etflin in Digital System and Computing
- Vol. 1 (1) , 13-18
Open AccessDesign and Evaluation of an IoT-Based Real-Time Energy Monitoring System Using NodeMCU and PZEM-004T
The increasing demand for accurate and affordable household electricity monitoring has driven the development of Internet of Things (IoT)–based systems. This study designed and evaluated a real-time energy monitoring system using a NodeMCU microcontroller integrated with a PZEM-004T sensor module. The system was tested on three household appliances, an electric iron, a fan, and a refrigerator, and its measurements were compared with a calibrated reference wattmeter and manual energy calculations. The results showed that the system’s readings closely matched those of the reference device, demonstrating reliable accuracy in capturing real-time energy consumption. Higher deviations were observed against manual calculations, mainly due to the inability of manual methods to capture dynamic load fluctuations, particularly from the refrigerator’s compressor. Overall, the system achieved an average error of 1.19% compared with the reference measurements, confirming its technical feasibility for practical household energy monitoring. Future work should improve accuracy for fluctuating loads through adaptive sampling and expand system scalability via cloud-based integration.
- Open Access
- 10 June 2025
- Published by Politeknik Negeri Batam in JOURNAL OF APPLIED INFORMATICS AND COMPUTING
- Vol. 9 (3) , 1013-1024
HANA: An AI Chatbot for Islamic Jurisprudence on Menstruation using SBERT and TF-IDF
The advancement of Artificial Intelligence (AI), particularly in Natural Language Processing (NLP), has opened new opportunities for religious technological innovation, especially in addressing practical Islamic jurisprudence issues such as menstruation (fiqh haid). This research proposes and implements HANA, an AI chatbot developed for Telegram, utilizing a hybrid approach combining Term Frequency-Inverse Document Frequency (TF-IDF) and Sentence-BERT (SBERT) models. A curated dataset of over 1000 question-answer pairs from classical and contemporary Islamic literature was used, primarily based on the Shafi'i school of thought. The chatbot matches user queries through a two-stage retrieval: initial keyword matching via TF-IDF and deeper semantic matching via SBERT embeddings. Evaluations were conducted by comparing TF-IDF, SBERT, and hybrid approaches using cosine similarity, precision, recall, and F1-score metrics, focused on top-1 retrieval accuracy. HANA achieved an average cosine similarity score of 0.6581 and a semantic relevance rating of 87% based on expert validation, while User Acceptance Testing (UAT) involving 15 respondents indicated 86.7% satisfaction. Although the system is deployed as a proof-of-concept on Google Colab without persistent hosting, it demonstrates the viability of lightweight AI chatbots for Shariah consultation services. Future improvements include multi-turn conversation handling and integration with large language models for better context understanding. This research contributes to expanding NLP applications within techno-dakwah initiatives, providing a scalable approach to enhance women's access to Islamic jurisprudence knowledge.
- 10 June 2025
- Published by Politeknik Negeri Batam in JOURNAL OF APPLIED INFORMATICS AND COMPUTING
- Vol. 9 (3) , 1013-1024
Open AccessHANA: An AI Chatbot for Islamic Jurisprudence on Menstruation using SBERT and TF-IDF
The advancement of Artificial Intelligence (AI), particularly in Natural Language Processing (NLP), has opened new opportunities for religious technological innovation, especially in addressing practical Islamic jurisprudence issues such as menstruation (fiqh haid). This research proposes and implements HANA, an AI chatbot developed for Telegram, utilizing a hybrid approach combining Term Frequency-Inverse Document Frequency (TF-IDF) and Sentence-BERT (SBERT) models. A curated dataset of over 1000 question-answer pairs from classical and contemporary Islamic literature was used, primarily based on the Shafi'i school of thought. The chatbot matches user queries through a two-stage retrieval: initial keyword matching via TF-IDF and deeper semantic matching via SBERT embeddings. Evaluations were conducted by comparing TF-IDF, SBERT, and hybrid approaches using cosine similarity, precision, recall, and F1-score metrics, focused on top-1 retrieval accuracy. HANA achieved an average cosine similarity score of 0.6581 and a semantic relevance rating of 87% based on expert validation, while User Acceptance Testing (UAT) involving 15 respondents indicated 86.7% satisfaction. Although the system is deployed as a proof-of-concept on Google Colab without persistent hosting, it demonstrates the viability of lightweight AI chatbots for Shariah consultation services. Future improvements include multi-turn conversation handling and integration with large language models for better context understanding. This research contributes to expanding NLP applications within techno-dakwah initiatives, providing a scalable approach to enhance women's access to Islamic jurisprudence knowledge.
- Open Access
- 6 April 2025
- Published by Universitas Teknokrat Indonesia in Jurnal Tekno Kompak
- Vol. 19 (2) , 319-330
Klasifikasi Konten Moderasi Beragama pada Media Sosial dengan Menggunakan Algoritma Naïve Bayes Multinominal Teks
Fenomena peningkatan penggunaan media sosial telah menjadikan platform ini sebagai media utama penyebaran narasi moderasi beragama. Namun, eskalasi konten tersebut tidak selalu diiringi dengan akurasi, sering kali memuat narasi yang berpotensi menyesatkan. Untuk mengatasi tantangan ini, diperlukan pendekatan text mining guna mengklasifikasikan konten narasi moderasi beragama secara otomatis dan akurat. Penelitian ini berhasil melakukan klasifikasi teks moderasi beragama di media sosial menggunakan algoritma Multinomial Naive Bayes. Dengan memanfaatkan dataset berjumlah 1996 tweet yang telah dilabeli oleh ahli, dari hasil evaluasi diketahui model ini menunjukkan kinerja yang baik, ditandai dengan accuracy 0.91, precision 0.93, recall 0.89, dan F1-Score 0.90. Temuan ini mengindikasikan bahwa Multinomial Naive Bayes merupakan metode yang efektif untuk identifikasi dan klasifikasi konten moderasi beragama di media sosial.
- 6 April 2025
- Published by Universitas Teknokrat Indonesia in Jurnal Tekno Kompak
- Vol. 19 (2) , 319-330
Open AccessKlasifikasi Konten Moderasi Beragama pada Media Sosial dengan Menggunakan Algoritma Naïve Bayes Multinominal Teks
Fenomena peningkatan penggunaan media sosial telah menjadikan platform ini sebagai media utama penyebaran narasi moderasi beragama. Namun, eskalasi konten tersebut tidak selalu diiringi dengan akurasi, sering kali memuat narasi yang berpotensi menyesatkan. Untuk mengatasi tantangan ini, diperlukan pendekatan text mining guna mengklasifikasikan konten narasi moderasi beragama secara otomatis dan akurat. Penelitian ini berhasil melakukan klasifikasi teks moderasi beragama di media sosial menggunakan algoritma Multinomial Naive Bayes. Dengan memanfaatkan dataset berjumlah 1996 tweet yang telah dilabeli oleh ahli, dari hasil evaluasi diketahui model ini menunjukkan kinerja yang baik, ditandai dengan accuracy 0.91, precision 0.93, recall 0.89, dan F1-Score 0.90. Temuan ini mengindikasikan bahwa Multinomial Naive Bayes merupakan metode yang efektif untuk identifikasi dan klasifikasi konten moderasi beragama di media sosial.
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2958 (1) , 020009
Forecasting of JP-ASPRI personal accident insurance customers using the ARIMA model
This study aims to determine the number of JP-ASPRI Personal Accident Insurance customers in the next year. The data used is monthly time series data from Janua
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2958 (1) , 020009
Forecasting of JP-ASPRI personal accident insurance customers using the ARIMA model
This study aims to determine the number of JP-ASPRI Personal Accident Insurance customers in the next year. The data used is monthly time series data from Janua
- Open Access
- 26 November 2022
- Published by STMIK Lombok in Jurnal Informatika dan Rekayasa Elektronik
- Vol. 5 (2) , 283-290
IMPLEMENTASI METODE SIMPLE ADDITIVE WEIGHTING UNTUK PENGUKURAN KINERJA KARYAWAN
Employee performance appraisal system is used to assess employees who have good performance. The agency or company conducts performance appraisals on employees to evaluate, motivate, verify and improve employee performance. The decision support system will assist the company in the process of evaluating employees quickly and objectively. The simple additive weighting (SAW) method is one of the good methods and can be applied in the decision-making system. From the research results, it is known that the simple additive wighting (SAW) method can determine employee performance appraisals using four criteria, namely attendance, behavior, workload, and work realization. The highest ranking value is obtained with a value of 86.25, while the lowest value is obtained with a value of 66.6.
- 26 November 2022
- Published by STMIK Lombok in Jurnal Informatika dan Rekayasa Elektronik
- Vol. 5 (2) , 283-290
Open AccessIMPLEMENTASI METODE SIMPLE ADDITIVE WEIGHTING UNTUK PENGUKURAN KINERJA KARYAWAN
Employee performance appraisal system is used to assess employees who have good performance. The agency or company conducts performance appraisals on employees to evaluate, motivate, verify and improve employee performance. The decision support system will assist the company in the process of evaluating employees quickly and objectively. The simple additive weighting (SAW) method is one of the good methods and can be applied in the decision-making system. From the research results, it is known that the simple additive wighting (SAW) method can determine employee performance appraisals using four criteria, namely attendance, behavior, workload, and work realization. The highest ranking value is obtained with a value of 86.25, while the lowest value is obtained with a value of 66.6.
- Open Access
- 1 December 2020
- Published by Universitas Muhammadiyah Bengkulu in JSAI (Journal Scientific and Applied Informatics)
- Vol. 3 (3) , 122-128
TINGKAT KEMATANGAN TATA KELOLA TEKNOLOGI INFORMASI MENGGUNAKAN METODE TESCA
Evaluasi tata kelola TIK menjadi bagian penting dalam penerapan TIK dalam sebuah perguruan tinggi. Tata kelola teknologi informasi yang baik akan membantu mempercepat terwujudnya visi dan misi sebuah perguruan tinggi. Pusat Teknologi Informasi dan Pangkalan Data (PTIPD) UIN Walisongo merupakan unit teknis yang mempunyai tugas mengelola dan mengembangkan sistem informasi di lingkungan Institusi. Mengingat pentingnya PTIPD maka perlu dilakukan evaluasi tingkat kematangan teknologi informasi dengan menggunakan metode TeSCA. Analisis dilakukan dengan teknik observasi, wawancara, penelaah dokumen dan konfirmasi untuk mendukung analisis terhadap PTIPD. Hasil analisis menunjukkan bahwa tingkat kematangan TIK UIN Walisongo pada tingkat Level Madya dengan scores total 55.43.
- 1 December 2020
- Published by Universitas Muhammadiyah Bengkulu in JSAI (Journal Scientific and Applied Informatics)
- Vol. 3 (3) , 122-128
Open AccessTINGKAT KEMATANGAN TATA KELOLA TEKNOLOGI INFORMASI MENGGUNAKAN METODE TESCA
Evaluasi tata kelola TIK menjadi bagian penting dalam penerapan TIK dalam sebuah perguruan tinggi. Tata kelola teknologi informasi yang baik akan membantu mempercepat terwujudnya visi dan misi sebuah perguruan tinggi. Pusat Teknologi Informasi dan Pangkalan Data (PTIPD) UIN Walisongo merupakan unit teknis yang mempunyai tugas mengelola dan mengembangkan sistem informasi di lingkungan Institusi. Mengingat pentingnya PTIPD maka perlu dilakukan evaluasi tingkat kematangan teknologi informasi dengan menggunakan metode TeSCA. Analisis dilakukan dengan teknik observasi, wawancara, penelaah dokumen dan konfirmasi untuk mendukung analisis terhadap PTIPD. Hasil analisis menunjukkan bahwa tingkat kematangan TIK UIN Walisongo pada tingkat Level Madya dengan scores total 55.43.
- Open Access
- 20 December 2019
- Published by UIN Walisongo Semarang in Walisongo Journal of Information Technology
- Vol. 1 (2) , 101-110
Klasifikasi Pemahaman Santri Dalam Pembelajaran Kitab Kuning Menggunakan Algoritma Naive Bayes Berbasis Forward Selection
Kitab kuning merupakan kitab tradisional yang mengandung diraasah islamiyah yang diajarakan pada pondok pesantren, mulai dari struktur bahasa arab (ilmu nahwu dan shorof), ‘ulumul qur’an, hadits, aqidah, tasawuf/akhlaq, tafsir, fiqh sampai ilmu sosial dan kemasyarakatan (mu’amalah). Disebut juga dengan kitab gundul karena tidak memiliki harakat (fathah, kasroh, dhammah, sukun) untuk bisa membaca dan memahami secara menyeluruh dibutuhkan waktu yang relatif lama. Penelitian ini bertujuan untuk mendapatkan model klasifikasi dari data pembelajaran kitab kuning di pondok pesantren. Metode yang digunakan dalam penelitian ini adalah forward selection sebagai praproses dalam mengurangi dimensi data, menghilangkan data yang tidak relevan dan naive bayes yang berguna untuk mengklasifikasi data. Hasil dari klasifikasi data pembelajaran kitab kuning menggunakan atribut yang telah diklasifikasi berdasarkan fitur-fiturnya dan dilakukan iterasi pada cross validation sehingga menghasilkan akurasi yang tepat. Berdasarkan hasil pengujian dengan dua metode, pengujian dengan algoritma Naive bayes saja menghasilkan akurasi 96,02%, untuk algoritma Naive bayes berbasis forward selection menghasilkan akurasi 97,38% . Terdapat peningkatan akurasi dengan penambahan fitur seleksi.
- 20 December 2019
- Published by UIN Walisongo Semarang in Walisongo Journal of Information Technology
- Vol. 1 (2) , 101-110
Open AccessKlasifikasi Pemahaman Santri Dalam Pembelajaran Kitab Kuning Menggunakan Algoritma Naive Bayes Berbasis Forward Selection
Kitab kuning merupakan kitab tradisional yang mengandung diraasah islamiyah yang diajarakan pada pondok pesantren, mulai dari struktur bahasa arab (ilmu nahwu dan shorof), ‘ulumul qur’an, hadits, aqidah, tasawuf/akhlaq, tafsir, fiqh sampai ilmu sosial dan kemasyarakatan (mu’amalah). Disebut juga dengan kitab gundul karena tidak memiliki harakat (fathah, kasroh, dhammah, sukun) untuk bisa membaca dan memahami secara menyeluruh dibutuhkan waktu yang relatif lama. Penelitian ini bertujuan untuk mendapatkan model klasifikasi dari data pembelajaran kitab kuning di pondok pesantren. Metode yang digunakan dalam penelitian ini adalah forward selection sebagai praproses dalam mengurangi dimensi data, menghilangkan data yang tidak relevan dan naive bayes yang berguna untuk mengklasifikasi data. Hasil dari klasifikasi data pembelajaran kitab kuning menggunakan atribut yang telah diklasifikasi berdasarkan fitur-fiturnya dan dilakukan iterasi pada cross validation sehingga menghasilkan akurasi yang tepat. Berdasarkan hasil pengujian dengan dua metode, pengujian dengan algoritma Naive bayes saja menghasilkan akurasi 96,02%, untuk algoritma Naive bayes berbasis forward selection menghasilkan akurasi 97,38% . Terdapat peningkatan akurasi dengan penambahan fitur seleksi.
- Open Access
- 1 June 2019
- Published by UIN Walisongo Semarang in Walisongo Journal of Information Technology
- Vol. 1 (1) , 1-13
Klasifikasi Berita Hoax Dengan Menggunakan Metode Naive Bayes
Hoaxes contain false news or non-sourced news. Today, hoaxes are very widely spread through internet media. The development of information technology that has so quickly triggered the spread of hoax information through the internet has become uncontrolled. So we need an intelligent system that can classify hoax news content that is spread through internet media. The hoax classification process can be done through the preprocessing stage then weighting the word and classification using naive bayes. Measurements were made using the 10-ford cross validation method. The results obtained from these measurements, it is known that the value of fold 6 has the highest accuracy, which is equal to 85.28% which is classified as relevant documents as much as 307 and irrelevant as much as 53 or an error rate of 14.72%. While the average value based on hoax news and true news value precision 0.896 and recall 0.853
- 1 June 2019
- Published by UIN Walisongo Semarang in Walisongo Journal of Information Technology
- Vol. 1 (1) , 1-13
Open AccessKlasifikasi Berita Hoax Dengan Menggunakan Metode Naive Bayes
Hoaxes contain false news or non-sourced news. Today, hoaxes are very widely spread through internet media. The development of information technology that has so quickly triggered the spread of hoax information through the internet has become uncontrolled. So we need an intelligent system that can classify hoax news content that is spread through internet media. The hoax classification process can be done through the preprocessing stage then weighting the word and classification using naive bayes. Measurements were made using the 10-ford cross validation method. The results obtained from these measurements, it is known that the value of fold 6 has the highest accuracy, which is equal to 85.28% which is classified as relevant documents as much as 307 and irrelevant as much as 53 or an error rate of 14.72%. While the average value based on hoax news and true news value precision 0.896 and recall 0.853