Claim Missing Document
Check
Articles

High-Accuracy Stroke Detection System Using a CBAM-ResNet18 Deep Learning Model on Brain CT Images Tahyudin, Imam; Isnanto, R Rizal; Prabuwono, Anton Satria; Hariguna, Taqwa; Winarto, Eko; Nazwan, Nazwan; Tikaningsih, Ades; Lestari, Puji; Rozak, Rofik Abdul
Journal of Applied Data Sciences Vol 6, No 1: JANUARY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i1.569

Abstract

Stroke is a brain dysfunction that occurs suddenly as a result of local or overarching damage to the brain, lasts for at least 24 hours, and causes about 15 million deaths each year globally. Immediate medical treatment is essential to reduce the potential for further brain damage in stroke patients. Medical imaging, especially computed tomography (CT scan), plays a crucial role in the diagnosis of stroke. This study aims to develop and evaluate a deep learning architecture based on Convolutional Block Attention Module (CBAM) and ResNet18 for stroke classification in CT images. This model is designed through data preprocessing, training, and evaluation stages using a cross-validation approach. The results showed that the CBAM-ResNet18 integration resulted in a high accuracy of 95% in distinguishing stroke and non-stroke cases. The accuracy rate reached 96% for nonstroke identification (class 0) and 94% for stroke (class 1), with recall rates of 96% and 93%, respectively. Outstanding classification ability is demonstrated by an Area Under the Curve (AUC) value of 0.99. In comparison, the standard ResNet18 model shows significant fluctuations in validation loss and difficulty in generalization, with training accuracy only reaching 64-68%. On the other hand, CBAM-ResNet18 showed a significant performance improvement with a validation accuracy of 95%, a validation loss of 0.0888, and good generalization on new data. However, the limitations of the dataset and the interpretation of the results indicate the need for further validation to ensure the generalization of the model. These results show the great potential of the CBAM-ResNet18 architecture as an innovative tool in stroke diagnostic technology based on CT imaging analysis. This technology can support faster and more accurate clinical decision-making, as well as open up opportunities for further research related to the development of artificial intelligence-based systems in the medical field.
Traditional-Enhance-Mobile-Ubiquitous-Smart: Model Innovation in Higher Education Learning Style Classification Using Multidimensional and Machine Learning Methods Santiko, Irfan; Soeprobowati, Tri Retnaningsih; Surarso, Bayu; Tahyudin, Imam; Hasibuan, Zainal Arifin; Che Pee, Ahmad Naim
Journal of Applied Data Sciences Vol 6, No 1: JANUARY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i1.598

Abstract

Learning achievement is undoubtedly impacted by each person's unique learning style. The assessment pattern is less focused due to the intricacy of the current components. In fact, general elements like VARK are thought to create complexity that can impair focus when combined with elements like environmental conditions, teacher effectiveness, and stakeholder policies. Although it is only ideal in specific areas, the application of supported information technology has so far yielded positive results. This essay attempts to be creative in evaluating how well students learn in higher education settings. An assessment framework that uses multidimensionality and simplifies features is the innovation that is being offered. Method, Material, and Media (3M) are the three categories into which simplification of aspects is separated. However, the Dimensions are categorized into five groups: Traditional, Enhance, Mobile, Ubiquitous, and Smart (TEMUS). Approximately 1200 respondents consisting of students and lecturers formed into a dataset in 2 types of data, namely test data and training data. The trial was conducted using 4 models, namely Random Forest, SVM, Decision Tree, and K-Nearest. The test results were interpreted in MSE, R-Square, Accuracy, Recall, Precision, and F1-Score. Based on the comparison of test results, it states that Random Forest has the most optimal results with MSE values of 0.46, R Square 0.99, Accuracy 0.86, Recall 0.86, Precision 0.87, F1 Score 0.84. Based on the results obtained, it proves that in addition to being able to carry out the classification process, the TEMUS Dimensional Framework can form a pattern of compatibility with each other, between the learning styles of Lecturers and Students. According to this TEMUS framework, teacher and student performance will be deemed suitable and effective when the 3M components are assessed from both perspectives in the same way. If not, a review will be conducted.
Performance Evaluation of CNN-LSTM and CNN-FNN Combinations for Pneumonia Classification Using Chest X-ray Images Putra, Bernardus Septian Cahya; Tahyudin, Imam
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol. 8 No. 2 (2025): Issues January 2025
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/jite.v8i2.13503

Abstract

Pneumonia is one of the deadliest infectious diseases worldwide, particularly affecting children under five years old and the elderly, with a significant mortality rate annually. This disease is caused by bacterial, viral, or fungal infections, leading to inflammation in the air sacs (alveoli) of the lungs, which disrupts respiratory function. A major challenge in diagnosing pneumonia lies in the reliance on radiological expertise to interpret chest X-ray images, a process that is time-consuming and prone to errors in interpretation. This study aims to compare the performance of deep learning models, specifically the combination of Convolutional Neural Networks (CNN) with Long Short-Term Memory (LSTM) and CNN with Feedforward Neural Networks (FNN), in classifying pneumonia based on chest X-ray images. The results indicate that the CNN & LSTM model achieved an accuracy of 96.59%, a loss of 9.95%, precision of 96%, recall of 95%, and F1-score of 96%, slightly outperforming the CNN & FNN model, which achieved an accuracy of 96.13%, a loss of 12.16%, precision of 96%, recall of 94%, and F1-score of 95%. The advantage of CNN & LSTM lies in its ability to capture sequential patterns through LSTM, making it more effective in detecting positive pneumonia cases. In conclusion, the CNN & LSTM model outperforms the CNN & FNN model in accuracy, recall, and F1-score, making it a more reliable choice for automatic pneumonia classification. The findings suggest the potential use of deep learning models, particularly CNN & LSTM, to support medical professionals and the public in quickly and accurately detecting pneumonia through chest X-ray images analysis
Optimasi Prediksi Prediabetes dengan Metode Fitur Selection dan Imbalance Learning Arifin, Samsul; Tahyudin, Imam
Techno.Com Vol. 24 No. 1 (2025): Februari 2025
Publisher : LPPM Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62411/tc.v24i1.11730

Abstract

Diabetes adalah salah satu tantangan kesehatan global yang terus meningkat, dengan deteksi dini pradiabetes menjadi kunci untuk pencegahan. Data yang digunakan diambil dari Diabetes Health Indicators Dataset dan dipersiapkan melalui tahap feature engineering, analisis korelasi, dan penanganan missing value. Selanjutnya, model dibangun menggunakan tiga algoritma utama, yaitu Random Forest, XGBoost, dan Logistic Regression. Penelitian ini menggabungkan analisis korelasi variabel dan metode imbalance learning untuk mengoptimalkan prediksi pradiabetes menggunakan algoritma machine learning. Untuk menangani ketidakseimbangan data, teknik SMOTE diterapkan guna menghasilkan data sintetik pada kelas minoritas. Hasil penelitian menunjukkan model Random Forest memberikan kinerja terbaik dengan akurasi 97,57%, mengungguli XGBoost dan Logistic Regression. Penerapan analisis korelasi variabel dan imbalance learning terbukti efektif dalam meningkatkan kinerja prediksi dengan identifikasi fitur penting. Penelitian ini menunjukkan bahwa pendekatan yang diterapkan dapat membantu deteksi dini pradiabetes secara lebih akurat dan tepat.   Kata kunci: Diabetes, Deteksi Prediabetes, Machine Learning, Random Forest
Integrasi Virtual Reality dan Sistem Treadmill untuk Meningkatkan Pengalaman Wisatawan: Studi Kasus Destinasi Wisata Balekemambang Rozak, Rofiq 'Abdul; Tahyudin, Imam; Tikaningsih, Ades; Saefullah, Ufu; Prasetya, Subani Charis; Alam, Yusuf Nur
Techno.Com Vol. 24 No. 1 (2025): Februari 2025
Publisher : LPPM Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62411/tc.v24i1.11886

Abstract

Sektor pariwisata memegang peranan penting dalam pertumbuhan ekonomi negara-negara berkembang seperti Indonesia. Namun, metode promosi tradisional mungkin tidak lagi memadai untuk menarik pengunjung di era digital. Penelitian ini menyelidiki penerapan teknologi Virtual Reality (VR) yang terintegrasi dengan sistem treadmill untuk mempromosikan Balekemambang, destinasi wisata di Purwokerto, Jawa Tengah. Dengan menggabungkan sistem berbasis Raspberry Pi dan video 360 derajat Balekemambang, pengalaman VR memungkinkan pengguna menjelajahi situs secara virtual sambil berjalan di atas treadmill, mensimulasikan kunjungan di dunia nyata. Penelitian ini mengevaluasi efektivitas sistem ini dalam meningkatkan pengalaman imersif dan pengaruhnya terhadap minat wisatawan. Peserta diminta untuk mencoba sistem VR dan kemudian mengisi kuesioner untuk mengukur berbagai faktor, termasuk keterlibatan emosional, minat terhadap destinasi, dan kemungkinan berkunjung. Model regresi logistik mengungkapkan hasil yang signifikan, dengan tingkat akurasi 100%, seperti yang ditunjukkan oleh matriks kebingungan. Temuan ini menunjukkan bahwa pengalaman VR yang imersif dapat memengaruhi minat wisatawan secara signifikan, menjadikan VR sebagai alat yang ampuh untuk mempromosikan pariwisata.   Kata kunci: Realitas Virtual, Integrasi Treadmill, Regresi Logistik, Balekemambang
Perbandingan Algoritma CNN, LSTM, FNN untuk Diagnosa Fibrosis Hati dengan Citra Medis Febryanto, Bagas Aji; Tahyudin, Imam
Techno.Com Vol. 24 No. 1 (2025): Februari 2025
Publisher : LPPM Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62411/tc.v24i1.12020

Abstract

Fibrosis hati merupakan kondisi yang berpotensi berkembang menjadi sirosis atau kanker hati jika tidak terdiagnosis dengan tepat. Prosedur biopsi hati yang invasif sering digunakan dalam diagnosis, namun memiliki risiko dan keterbatasan biaya. Penelitian ini bertujuan untuk membandingkan kinerja model deep learning, yaitu Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), dan Feedforward Neural Network (FNN) dalam klasifikasi fibrosis hati menggunakan citra medis. Metode yang digunakan adalah evaluasi kinerja model berdasarkan metrik akurasi, presisi, recall, F1-score, dan loss pada dataset citra medis fibrosis hati. Hasil penelitian menunjukkan bahwa CNN memberikan kinerja terbaik dengan akurasi 98%, diikuti oleh LSTM dengan akurasi 97%, dan FNN dengan akurasi 80%. CNN unggul karena kemampuannya dalam mengekstraksi fitur spasial secara otomatis dari citra medis, sementara LSTM lebih cocok untuk data sekuensial dan FNN terbatas dalam menangani data citra kompleks. Penelitian ini menyimpulkan bahwa CNN lebih efektif dalam klasifikasi fibrosis hati dan dapat menjadi alternatif non-invasif yang lebih efisien dibandingkan metode konvensional seperti biopsi. Teknologi ini berpotensi mempercepat diagnosis fibrosis hati dengan akurasi tinggi dan tanpa risiko komplikasi invasif.   Kata kunci: Fibrosis hati, CNN, LSTM, FNN, klasifikasi citra medis.
Teknologi Text To Speech Menggunakan Amazon Polly Untuk Meningkatkan Kemampuan Membaca Pada Anak Dengan Gejala Disleksia Fatmawati, Karlina Diah; Tahyudin, Imam
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 11 No 6: Desember 2024
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik2024117426

Abstract

Disleksia adalah gangguan dalam proses belajar yang ditandai dengan kesulitan membaca, menulis dan mengeja. Perkembangan teknologi saat ini dapat dimanfaatkan dalam semua bidang, termasuk pada pembelajaran anak berkebutuhan khusus seperti disleksia. Penelitian ini bertujuan untuk meningkatkan kemampuan membaca menggunakan teknologi Text-To-Speech (TTS) dengan Machine Learning Amazon Polly yang ada pada AWS cloud. Penelitian menggunakan dua metode: review literatur dan eksperimen dengan pre-test dan post-test untuk menilai pengaruh teknologi terhadap kemampuan membaca. Review literatur dengan mengkaji kumpulan literatur dari penelitian terdahulu sebagai sumber data dan data yang diperoleh akan dianalisis secara deskriptif kualitatif untuk mengetahui pengaruh teknologi terhadap  kemampuan membaca. Metode kedua adalah pengujian dengan alat ukur berupa pre-test & post-test yang terdiri dari 10 kata. Pengujian dilakukan sebanyak empat pertemuan dengan subjek penelitian 30 responden. Kemudian data dianalisis menggunakan analisis statistik deskriptif, yaitu merupakan analisis statistik yang memberikan gambaran secara umum mengenai karakteristik dari masing – masing variable penelitian yang dilihat dari nilai rata – rata (mean), maximum, minimum. Hasil pre-test menunjukkan nilai rata-rata 2,91, kelompok TTS menunjukkan peningkatan signifikan dengan nilai rata-rata post-test 4,30 dibandingkan dengan kelompok visual 3,72. Data kuesioner menunjukkan aplikasi TTS mudah dimengerti dan diterima baik, dengan 90,9% responden melaporkan peningkatan kemampuan membaca. Analisis statistik deskriptif membuktikan teknologi TTS secara signifikan meningkatkan kemampuan membaca pada anak disleksia.   Abstract Dyslexia is a learning disorder characterized by difficulties in reading, writing and spelling. Current technological developments can be utilized in all fields, including in the learning of children with special needs such as dyslexia. This research aims to improve reading skills using Text-To-Speech (TTS) technology with Amazon Polly Machine Learning on the AWS cloud. The research used two methods: literature review, and experiments with pre-test and post-test to assess the effect of technology on reading ability. The literature review involves examining a collection of literature from previous research as a data source. The data obtained will be analyzed descriptively and qualitatively to determine the effect of technology on reading ability. The second method involves testing with measuring instruments in the form of a pre-test and post-test consisting of 10 words. Testing was carried out over four meetings with a research sample of 30 respondents. Then, the data are analyzed using descriptive statistical analysis, which provides a general description of the characteristics of each research variable as seen from the average (mean), maximum, and minimum values. The pre-test results showed an average score of 2.91. The TTS group showed significant improvement with a post-test average score of 4.30 compared to the visual group’s score of 3.72. Questionnaire data show that the TTS application is easy to understand and well received, with 90.9% of respondents reporting improved reading ability. Descriptive statistical analysis proves that TTS technology significantly improves reading abilities in dyslexic children.    
User Satisfaction Analysis Of Tourist Ticket Applications Using The Heuristic Evaluation Evaluation Method (Case Study: Pagubugan Melung Tour Manager) Evania Adna; Tahyudin, Imam
Computer Science Research and Its Development Journal Vol. 16 No. 3 (2024): October 2024
Publisher : LPPM Universitas Potensi Utama

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

Abstract

The development of digital technology has changed the way information is interacted with and managed, including in the tourism sector. Nature tourism, as an important part of Indonesia's tourism industry, has also undergone a significant transformation in terms of technology use. This research investigates the application of information technology through websites in improving the accessibility, efficiency, management, and promotion of Pagubugan Melung Tourism in Banyumas. By adopting a website-based ticketing application, Wisata Pagubugan Melung is able to provide more complete and interactive information for visitors and simplify the process of ticket sales and visitor management. Evaluation of user acceptance of the ticketing application was conducted using the Heuristic Evaluation method and Partial Least Square Equation Model (PLS-SEM) statistical analysis. The variables that become indicators in evaluating user acceptance of ticketing applications using PLS-SEM statistical analysis are Visibility of System Status, Match Between System and the Real World, User Control and Freedom, Consistency and Standards, Error Prevention, Recognition Rather Than Recall, Flexibility and Efficient of Use, Aesthetic and Minimalist Design, Help Users Recognize, Diagnose, and Recover from Errors, Help and Documentation and Usability. The results showed that most features were well received by users. Overall, the Wisata Pagubugan Melung ticketing app is popular, showcasing the blend of technology and tourism. This research provides a better understanding of user acceptance of technological innovations in the context of tourism and provides guidance for further development in improving technology-based tourism services.
Sentiment Analysis on Slang Enriched Texts Using Machine Learning Approaches Prastyo, Priyo Agung; Berlilana, Berlilana; Tahyudin, Imam
Journal of Applied Data Sciences Vol 6, No 2: MAY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i2.626

Abstract

This study explores sentiment analysis of slang-enriched user reviews using machine learning techniques, specifically Naive Bayes, Support Vector Machine (SVM), and Random Forest, to classify user sentiment into Positive, Negative, and Neutral categories while addressing challenges posed by informal and conversational language through slang normalization. A lexicon-based scoring method was employed to standardize slang terms such as “gak,” “aja,” and “banget,” ensuring consistency in sentiment analysis. The results indicate that Neutral sentiment dominates the dataset (51%), followed by Negative (28%) and Positive (21%), with lexicon-based scores confirming this distribution. Negative sentiment exhibits a broader intensity range, reflecting user dissatisfaction primarily related to network quality, service reliability, and pricing, as evident from recurring terms like “sinyal” (signal), “jaringan” (network), and “mahal” (expensive). Word cloud visualizations reinforce these findings, highlighting the prevalence of these concerns in user feedback. Performance evaluation of the machine learning models reveals that SVM and Random Forest achieved the highest accuracy (96%), significantly outperforming Naive Bayes (73%), demonstrating their effectiveness in handling high-dimensional text data and accurately classifying slang-rich content. These findings underscore the importance of slang normalization in preprocessing, as it significantly enhances sentiment classification accuracy. This study provides actionable insights for service providers, helping them identify and address key sources of user dissatisfaction. Future research can explore deep learning models such as BERT and LSTM to further enhance sentiment analysis by capturing contextual relationships within text data, while topic modeling techniques could uncover deeper thematic patterns in user feedback, enabling data-driven strategies to improve customer satisfaction.
Measuring interest and talent in determining learning using the quadrant model in the learning process in a smart classroom Santiko, Irfan; Soeprobowati, Tri Retnaningsih; Surarso, Bayu; Tahyudin, Imam
Jurnal Inovasi Teknologi Pendidikan Vol. 12 No. 1 (2025): March
Publisher : Universitas Negeri Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21831/jitp.v12i1.73585

Abstract

Naturally, the learning process in smart classrooms is greatly impacted by the trend of individual learning, now known as personalized learning. Several studies have demonstrated that, because of the problem of technological advances, the effectiveness of the anticipated results has not been fully achieved. While there are technology benefits, some scholars link them to issues. This study aims to demonstrate it by evaluating learning interests and talents. A sample of at least 1000 students from 419 universities participated in the questionnaire experiment. Each of the three questionnaire domains, affective, cognitive, and psychomotor, was examined using ANOVA. The coefficient test uses two variables: interest and talent. With an ANOVA P-value of 0.021 for psychomotor and 0.031 for affective and cognitive, the three domains demonstrated a statistically significant connection. The coefficients of interest and talent, which average between 1 and 0.05 for P emotional and cognitive interest (0.054) and P talent (0.023) and between 0.027 and 0.055 for P psychomotor interest and P talent, demonstrate the significant values of both factors. The developed interest and talent measuring model can be used to forecast learning outcomes based on these findings. In addition to information technology, the results of this interest and talent-measuring design can be utilized to define and evaluate the learning process, including its appropriateness. Further research recommendations include a framework to measure interests and talents early, aiding admissions, curriculum, resources, methods, and learning media development.
Co-Authors Agustina, Nur Ngaenun Al-Haq, Ahnaf Vanning Al-Haq Alam, Yusuf Nur Alfirnanda, Weersa Talta Ammar Fauzan, Ammar Ananda, Fahesta Ananda, Rona Sepri Andrianto Andrianto Anggraini, Lintang Wahyu ANNISA HANDAYANI Anton Satria Prabuwono Arifa, Pujana Nisya Aris Munandar Azhari Shouni Barkah Bayu Surarso Berlilana Berlilana Che Pee, Ahmad Naim Daffa, Nauffal Ammar Dani Arifudin Dhanar Intan Surya Saputra Diniyati, Faoziyah Fahiya Eko Priyanto Eko Winarto Evania Adna Faiz Ichsan Jaya Fajariyanti, Alya Nur Fandy Setyo Utomo Fatmawati, Karlina Diah Febryanto, Bagas Aji Fitriani, Intan Indri Giat Karyono Hadie, Agus Nur Hellik Hermawan Hermanto, Aldy Agil Hidayah, Septi Oktaviani Nur Ilham, Rifqi Arifin Irfan Santiko Iskoko, Angga Isnaini, Khairunnisak Nur Khoerida, Nur Isnaeni khusnul khotimah Kuat Indartono Kusuma, Bagus Adhi Lestari, Silvia Windri Ma'arifah, Windiya Maulida, Trisna Melia Dianingrum Miftahus Surur, Miftahus Muhammad Reza Pahlevi Murtiyoso Murtiyoso Musyafa, Muhamad Fahmi Nabila, Putri Isma Najibulloh, Imam Kharits Nanjar, Agi Nazwan, Nazwan Nur Adiya, Az Zahra Dwi Nur Faizah Nur holifah, Anggita Oyabu, Takashi Prasetya, Subani Charis Prastyo, Priyo Agung PUJI LESTARI Purwadi Purwadi Purwadi Purwadi Putra, Bernardus Septian Cahya Putra, Feishal Azriel Arya R Rizal Isnanto Rahayu, Dania Gusmi Rahma, Felinda Aprilia Ramadani, Nevita Cahaya Rizaqi, Hanif Rozak, Rofik Abdul Rozak, Rofiq 'Abdul Rozak, Rofiq Abdul Rozak, Rofiq ‘Abdul Rozaq, Hasri Akbar Awal Saefullah, Ufu Samsul Arifin Santoso, Bagus Budi Sarmini Sarmini Satriani, Laela Jati Setiabudi, Rizki Sholikhatin, Siti Alvi Syafaat, Alif Yahya Syafiq, Bayu Ibnu Taqwa Hariguna Tikaningsih, Ades Tri Retnaningsih Soeprobowati Triana, Latifah Adi Triawan, Puas Wardani, Syafa Wajahtu Widiawati, Neta Tri Widya Cholid Wahyudin Wini Audiana Wulandari, Hendita Ayu Yarsasi, Sri Zainal Arifin Hasibuan Zulfa Ummu Hani Zumaroh, Agnis Nur Afa