Endang Sugiharti
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Endang Sugiharti has a total of 44 co-authors. Here are the top co-authors by number of shared publications:
- Riza Arifudin
Universitas Negeri Semarang
4 shared publications Alamsyah Alamsyah
Department of Computer Science, Universitas Negeri Semarang
3 shared publicationsAgus Subarkah
Semarang perlu meningkatkan kompetensi literasi digitalnya
2 shared publications- Amin Suyitno
Universitas Islam Negeri Raden Fatah Palembang
2 shared publications - Emi Pujiastuti
Universitas Negeri Semarang
2 shared publications - Riza Arifudin
Universitas Negeri Semarang
2 shared publications
Latest Publications
- Open Access
- 18 March 2026
- Published by Surya Hijau Manfaat in Journal of Soft Computing Exploration
- Vol. 7 (1) , 19-30
Tuberculosis classification on chest x-ray images using DenseNet-169 and convolutional block attention module
Tuberculosis remains a major global health challenge, and the manual interpretation of chest X-rays is often limited by the subjectivity and shortage of radiology experts. While deep learning approaches like DenseNet have shown promise in medical imaging, the integration of attention mechanisms such as the Convolutional Block Attention Module (CBAM) for tuberculosis detection has been less explored. This study aimed to develop a Convolutional Neural Network (CNN) model utilizing DenseNet-169 combined with CBAM to accurately classify chest X-ray images into normal and tuberculosis classes. A dataset of 7,000 chest X-ray images was preprocessed and partitioned into training, validation, and testing sets. DenseNet-169 served as the backbone architecture, while CBAM was applied to emphasize crucial spatial and channel features. Evaluated across standard metrics, the proposed model achieved an accuracy of 99.43%, a precision of 99.72%, a recall of 99.14%, and an F1-score of 99.43%, successfully outperforming the baseline DenseNet-169 model without CBAM. Ultimately, the integration of CBAM with DenseNet-169 demonstrates remarkable potential in improving tuberculosis detection, confirming that attention mechanisms can substantially enhance deep learning performance in medical imaging.
- 18 March 2026
- Published by Surya Hijau Manfaat in Journal of Soft Computing Exploration
- Vol. 7 (1) , 19-30
Open AccessTuberculosis classification on chest x-ray images using DenseNet-169 and convolutional block attention module
Tuberculosis remains a major global health challenge, and the manual interpretation of chest X-rays is often limited by the subjectivity and shortage of radiology experts. While deep learning approaches like DenseNet have shown promise in medical imaging, the integration of attention mechanisms such as the Convolutional Block Attention Module (CBAM) for tuberculosis detection has been less explored. This study aimed to develop a Convolutional Neural Network (CNN) model utilizing DenseNet-169 combined with CBAM to accurately classify chest X-ray images into normal and tuberculosis classes. A dataset of 7,000 chest X-ray images was preprocessed and partitioned into training, validation, and testing sets. DenseNet-169 served as the backbone architecture, while CBAM was applied to emphasize crucial spatial and channel features. Evaluated across standard metrics, the proposed model achieved an accuracy of 99.43%, a precision of 99.72%, a recall of 99.14%, and an F1-score of 99.43%, successfully outperforming the baseline DenseNet-169 model without CBAM. Ultimately, the integration of CBAM with DenseNet-169 demonstrates remarkable potential in improving tuberculosis detection, confirming that attention mechanisms can substantially enhance deep learning performance in medical imaging.
- Open Access
- 28 May 2025
- Published by IntSys Research in ABDIMASKU : JURNAL PENGABDIAN MASYARAKAT
- Vol. 8 (2) , 554-563
Peran Kecerdasan Buatan Generatif Bagi Peningkatan Kompetensi Guru di SMA Muhammadiyah 2 Semarang
Tantangan yang saat ini dibutuhkan oleh guru SMA adalah menciptakan inovasi pembelajaran berbasis teknologi. Saat ini kecerdasan buatan (AI) telah muncul sebagai solusi potensial untuk meningkatkan kualitas pembelajaran di tengah pesatnya kemajuan teknologi. Namun, geografi Indonesia yang luas membuat fasilitas teknologi pendidikan belum merata. Oleh karena itu, guru di SMA Muhammadiyah 2 Semarang perlu meningkatkan kompetensi literasi digitalnya, terutama untuk teknologi terkini. Program ini telah berhasil membuka wawasan guru terhadap teknologi baru dan memberikan keterampilan praktis dalam mengintegrasikan teknologi Kecerdasan Buatan Generatif ke dalam proses pembelajaran. Para guru diberikan pembekalan penggunaan teknologi ChatGPT dan Gemini untuk mempersiapkan bahan ajar. Hasil evaluasi menunjukkan bahwa guru mampu memahami dan mulai menerapkan teknologi AI dalam pembuatan materi ajar, serta merasa termotivasi untuk terus menggunakannya secara berkelanjutan dalam pembelajaran.
- 28 May 2025
- Published by IntSys Research in ABDIMASKU : JURNAL PENGABDIAN MASYARAKAT
- Vol. 8 (2) , 554-563
Open AccessPeran Kecerdasan Buatan Generatif Bagi Peningkatan Kompetensi Guru di SMA Muhammadiyah 2 Semarang
Tantangan yang saat ini dibutuhkan oleh guru SMA adalah menciptakan inovasi pembelajaran berbasis teknologi. Saat ini kecerdasan buatan (AI) telah muncul sebagai solusi potensial untuk meningkatkan kualitas pembelajaran di tengah pesatnya kemajuan teknologi. Namun, geografi Indonesia yang luas membuat fasilitas teknologi pendidikan belum merata. Oleh karena itu, guru di SMA Muhammadiyah 2 Semarang perlu meningkatkan kompetensi literasi digitalnya, terutama untuk teknologi terkini. Program ini telah berhasil membuka wawasan guru terhadap teknologi baru dan memberikan keterampilan praktis dalam mengintegrasikan teknologi Kecerdasan Buatan Generatif ke dalam proses pembelajaran. Para guru diberikan pembekalan penggunaan teknologi ChatGPT dan Gemini untuk mempersiapkan bahan ajar. Hasil evaluasi menunjukkan bahwa guru mampu memahami dan mulai menerapkan teknologi AI dalam pembuatan materi ajar, serta merasa termotivasi untuk terus menggunakannya secara berkelanjutan dalam pembelajaran.
- Open Access
- 23 May 2025
- Published by CV Firmos in Jurnal Inovasi Pengabdian dan Pemberdayaan Masyarakat
- Vol. 5 (1) , 29-36
Pendampingan Pemanfaatan Aplikasi Berbasis Kecerdasan Buatan bagi Guru di Yayasan Waqah Al Hidayah, Hatyai, Provinsi Songkhla, Thailand
Pengabdian kepada masyarakat ini bertujuan meningkatkan literasi digital guru melalui pemanfaatan teknologi kecerdasan buatan (AI) dalam pembelajaran di Yayasan Waqaf Al-Hidayah, Hatyai, Thailand. Tantangan penggunaan teknologi di kalangan guru di Hatyai, Provinsi Songkhla menjadi perhatian utama, khususnya dalam konteks pembelajaran yang relevan bagi generasi digital. Metode kegiatan mencakup lima tahapan: identifikasi kebutuhan, pengenalan AI, praktik penggunaan agen cerdas berbasis Large Language Model (LLM), pengembangan media pembelajaran berbasis Canva AI, serta pendampingan dan monitoring melalui media sosial. Hasil kegiatan menunjukkan bahwa seluruh peserta telah menggunakan aplikasi berbasis AI sebelumnya, dan menganggap AI membantu efisiensi dan kreativitas pembelajaran. Namun, kekhawatiran terhadap ketergantungan dan dampak sosial juga muncul. Evaluasi melalui angket mengungkapkan respons positif terhadap kegiatan, meskipun partisipasi terbatas akibat kendala geografis. Simpulan dari kegiatan ini adalah bahwa pendampingan pemanfaatan AI dapat memperkuat kompetensi guru, namun tetap diperlukan penguatan etika penggunaan teknologi untuk menjaga kualitas interaksi dan keberimbangan peran guru dalam proses pembelajaran.
- 23 May 2025
- Published by CV Firmos in Jurnal Inovasi Pengabdian dan Pemberdayaan Masyarakat
- Vol. 5 (1) , 29-36
Open AccessPendampingan Pemanfaatan Aplikasi Berbasis Kecerdasan Buatan bagi Guru di Yayasan Waqah Al Hidayah, Hatyai, Provinsi Songkhla, Thailand
Pengabdian kepada masyarakat ini bertujuan meningkatkan literasi digital guru melalui pemanfaatan teknologi kecerdasan buatan (AI) dalam pembelajaran di Yayasan Waqaf Al-Hidayah, Hatyai, Thailand. Tantangan penggunaan teknologi di kalangan guru di Hatyai, Provinsi Songkhla menjadi perhatian utama, khususnya dalam konteks pembelajaran yang relevan bagi generasi digital. Metode kegiatan mencakup lima tahapan: identifikasi kebutuhan, pengenalan AI, praktik penggunaan agen cerdas berbasis Large Language Model (LLM), pengembangan media pembelajaran berbasis Canva AI, serta pendampingan dan monitoring melalui media sosial. Hasil kegiatan menunjukkan bahwa seluruh peserta telah menggunakan aplikasi berbasis AI sebelumnya, dan menganggap AI membantu efisiensi dan kreativitas pembelajaran. Namun, kekhawatiran terhadap ketergantungan dan dampak sosial juga muncul. Evaluasi melalui angket mengungkapkan respons positif terhadap kegiatan, meskipun partisipasi terbatas akibat kendala geografis. Simpulan dari kegiatan ini adalah bahwa pendampingan pemanfaatan AI dapat memperkuat kompetensi guru, namun tetap diperlukan penguatan etika penggunaan teknologi untuk menjaga kualitas interaksi dan keberimbangan peran guru dalam proses pembelajaran.
- Open Access
- 3 February 2025
- Published by Universitas Ahmad Dahlan in International Journal of Advances in Intelligent Informatics
- Vol. 11 (1) , 120-132
Soft voting ensemble model to improve Parkinson’s disease prediction with SMOTE
Parkinson's disease is one of the major neurodegenerative diseases that affect the central nervous system, often leading to motor and cognitive impairments in affected individuals. A precise diagnosis is currently unreliable, plus there are no specific tests such as electroencephalography or blood tests to diagnose the disease. Several studies have focused on the voice-based classification of Parkinson's disease. These studies attempt to enhance the accuracy of classification models. However, a major issue in predictive analysis is the imbalance in data distribution and the low performance of classification algorithms. This research aims to improve the accuracy of speech-based Parkinson's disease prediction by addressing class imbalance in the data and building an appropriate model. The proposed new model is to perform class balancing using SMOTE and build an ensemble voting model. The research process is systematically structured into multiple phases: data preprocessing, sampling, model development utilizing a voting ensemble approach, and performance evaluation. The model was tested using voice recording data from 31 people, where the data was taken from OpenML. The evaluation results were carried out using stratified cross-validation and showed good model performance. From the measurements taken, this study obtained an accuracy of 97.44%, with a precision of 97.95%, recall of 97.44%, and F1-Score of 97.56%. This study demonstrates that implementing the soft-voting ensemble-SMOTE method can enhance the model's predictive accuracy.
- 3 February 2025
- Published by Universitas Ahmad Dahlan in International Journal of Advances in Intelligent Informatics
- Vol. 11 (1) , 120-132
Open AccessSoft voting ensemble model to improve Parkinson’s disease prediction with SMOTE
Parkinson's disease is one of the major neurodegenerative diseases that affect the central nervous system, often leading to motor and cognitive impairments in affected individuals. A precise diagnosis is currently unreliable, plus there are no specific tests such as electroencephalography or blood tests to diagnose the disease. Several studies have focused on the voice-based classification of Parkinson's disease. These studies attempt to enhance the accuracy of classification models. However, a major issue in predictive analysis is the imbalance in data distribution and the low performance of classification algorithms. This research aims to improve the accuracy of speech-based Parkinson's disease prediction by addressing class imbalance in the data and building an appropriate model. The proposed new model is to perform class balancing using SMOTE and build an ensemble voting model. The research process is systematically structured into multiple phases: data preprocessing, sampling, model development utilizing a voting ensemble approach, and performance evaluation. The model was tested using voice recording data from 31 people, where the data was taken from OpenML. The evaluation results were carried out using stratified cross-validation and showed good model performance. From the measurements taken, this study obtained an accuracy of 97.44%, with a precision of 97.95%, recall of 97.44%, and F1-Score of 97.56%. This study demonstrates that implementing the soft-voting ensemble-SMOTE method can enhance the model's predictive accuracy.
- Open Access
- 28 November 2024
- Published by Universitas Negeri Semarang in Scientific Journal of Informatics
- Vol. 11 (4) , 1023-1034
Optimization of Mango Plant Leaf Disease Classification Using Concatenation Method of MobileNetV2 and DenseNet201 CNN Architectures
Purpose: Mango production can be severely impacted by diseases affecting mango plants. By leveraging artificial intelligence, the agricultural sector can automate the analysis of mango leaves to monitor plant health. The goal of this research is to improve the early detection of diseases in mango leaves to allow early treatment to minimize damage to the crops. Methods: This study employs an approach of combining two pre-trained CNN architectures, namely MobileNetV2 and DenseNet201 through concatenation method. To enhance the model’s generalization ability, various image augmentation techniques were applied during the training phase. Result: The model developed in this study achieved great performance in classifying mango leaf diseases with a testing accuracy of 99.25%. This result indicates the effectiveness of the concatenation method by outperforming the accuracy of either MobileNetV2 or DenseNet201 when implemented separately. Novelty: This research introduces a novel strategy by concatenating two pre-trained CNN architectures for mango leaf disease classification, a method not previously explored in this context. The model developed from this study has the potential to serve as a tool for the early detection and treatment of mango leaf diseases.
- 28 November 2024
- Published by Universitas Negeri Semarang in Scientific Journal of Informatics
- Vol. 11 (4) , 1023-1034
Open AccessOptimization of Mango Plant Leaf Disease Classification Using Concatenation Method of MobileNetV2 and DenseNet201 CNN Architectures
Purpose: Mango production can be severely impacted by diseases affecting mango plants. By leveraging artificial intelligence, the agricultural sector can automate the analysis of mango leaves to monitor plant health. The goal of this research is to improve the early detection of diseases in mango leaves to allow early treatment to minimize damage to the crops. Methods: This study employs an approach of combining two pre-trained CNN architectures, namely MobileNetV2 and DenseNet201 through concatenation method. To enhance the model’s generalization ability, various image augmentation techniques were applied during the training phase. Result: The model developed in this study achieved great performance in classifying mango leaf diseases with a testing accuracy of 99.25%. This result indicates the effectiveness of the concatenation method by outperforming the accuracy of either MobileNetV2 or DenseNet201 when implemented separately. Novelty: This research introduces a novel strategy by concatenating two pre-trained CNN architectures for mango leaf disease classification, a method not previously explored in this context. The model developed from this study has the potential to serve as a tool for the early detection and treatment of mango leaf diseases.
- Open Access
- 30 September 2023
- Published by IntSys Research in ABDIMASKU : JURNAL PENGABDIAN MASYARAKAT
- Vol. 6 (3) , 719-728
Pelatihan New Media pada Perangkat Desa Wadaslintang Wonosobo dalam Digitalisasi Promosi Wisata
Pelatihan New Media pada Perangkat Desa Wadaslintang Wonosobo dalam Digitalisasi Promosi Wisata
- 30 September 2023
- Published by IntSys Research in ABDIMASKU : JURNAL PENGABDIAN MASYARAKAT
- Vol. 6 (3) , 719-728
Open AccessPelatihan New Media pada Perangkat Desa Wadaslintang Wonosobo dalam Digitalisasi Promosi Wisata
Pelatihan New Media pada Perangkat Desa Wadaslintang Wonosobo dalam Digitalisasi Promosi Wisata
- Open Access
- 3 June 2023
- Published by Universitas Negeri Semarang in Scientific Journal of Informatics
- Vol. 10 (3) , 239-250
Alphabet Classification of Sign System Using Convolutional Neural Network with Contrast Limited Adaptive Histogram Equalization and Canny Edge Detection
Purpose: There are deaf people who have problems in communicating orally because they do not have the ability to speak and hear. The sign system is used as a solution to this problem, but not everyone understands the use and meaning of the sign system, even in terms of the alphabet. Therefore, it is necessary to classify a sign system in the form of American Sign Language (ASL) using Artificial Intelligence technology to get good results.Methods: This research focuses on improving the accuracy of ASL alphabet classification using the VGG-19 and ResNet50 architecture of the Convolutional Neural Network (CNN) method combined with Contrast Limited Adaptive Histogram Equalization (CLAHE) to improve the detail quality of images and Canny Edge Detection to produce images that focus on the objects in it. The focused result is the accuracy value. This study uses the ASL alphabet dataset from Kaggle.Result: Based on the test results, there are three best accuracy results. The first is using the ResNet50 architecture, CLAHE, and an image size of 128 x 128 pixels with an accuracy of 99.9%, followed by the ResNet50 architecture, CLAHE + Canny Edge Detection, and an image size of 128 x 128 pixels with an accuracy of 99.82 %, and in third place are the VGG-19 architecture, CLAHE, and an image size of 128 x 128 pixels with an accuracy of 98.93%.Novelty: The novelty of this study is the increase in the accuracy value of ASL image classification from previous studies.
- 3 June 2023
- Published by Universitas Negeri Semarang in Scientific Journal of Informatics
- Vol. 10 (3) , 239-250
Open AccessAlphabet Classification of Sign System Using Convolutional Neural Network with Contrast Limited Adaptive Histogram Equalization and Canny Edge Detection
Purpose: There are deaf people who have problems in communicating orally because they do not have the ability to speak and hear. The sign system is used as a solution to this problem, but not everyone understands the use and meaning of the sign system, even in terms of the alphabet. Therefore, it is necessary to classify a sign system in the form of American Sign Language (ASL) using Artificial Intelligence technology to get good results.Methods: This research focuses on improving the accuracy of ASL alphabet classification using the VGG-19 and ResNet50 architecture of the Convolutional Neural Network (CNN) method combined with Contrast Limited Adaptive Histogram Equalization (CLAHE) to improve the detail quality of images and Canny Edge Detection to produce images that focus on the objects in it. The focused result is the accuracy value. This study uses the ASL alphabet dataset from Kaggle.Result: Based on the test results, there are three best accuracy results. The first is using the ResNet50 architecture, CLAHE, and an image size of 128 x 128 pixels with an accuracy of 99.9%, followed by the ResNet50 architecture, CLAHE + Canny Edge Detection, and an image size of 128 x 128 pixels with an accuracy of 99.82 %, and in third place are the VGG-19 architecture, CLAHE, and an image size of 128 x 128 pixels with an accuracy of 98.93%.Novelty: The novelty of this study is the increase in the accuracy value of ASL image classification from previous studies.
- Open Access
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2614 (1)
Mask region-based convolutional neural network for detection of skin cancer
As the amount of data and information about cancer features has grown dramatically, a growing number of researchers have turned to Machine Learning technology and Deep Learning strategies. The growing interest in deep learning has made Convolutional Neural Network (CNN) the most used method for image analysis and classification. Mask Region-based Convolutional Neural Network (Mask R-CNN) is a new CNN method for object detection and segmentation. The objectives of this study are: (1) To reveal the stages of implementing of Mask R-CNN for the detection of skin cancer. (2) To obtain the level of accuracy of Mask R-CNN for detection of skin cancer. Methods include: (1) Data collection. (2) separating the dataset into training and validation. (3) Stages of Mask R-CNN. The results, (1) Obtained the implementation stage of Mask R-CNN for detection of skin cancer. (2) Accuracy results obtained by Mask R-CNN in detecting Skin Cancer.
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2614 (1)
Open AccessMask region-based convolutional neural network for detection of skin cancer
As the amount of data and information about cancer features has grown dramatically, a growing number of researchers have turned to Machine Learning technology and Deep Learning strategies. The growing interest in deep learning has made Convolutional Neural Network (CNN) the most used method for image analysis and classification. Mask Region-based Convolutional Neural Network (Mask R-CNN) is a new CNN method for object detection and segmentation. The objectives of this study are: (1) To reveal the stages of implementing of Mask R-CNN for the detection of skin cancer. (2) To obtain the level of accuracy of Mask R-CNN for detection of skin cancer. Methods include: (1) Data collection. (2) separating the dataset into training and validation. (3) Stages of Mask R-CNN. The results, (1) Obtained the implementation stage of Mask R-CNN for detection of skin cancer. (2) Accuracy results obtained by Mask R-CNN in detecting Skin Cancer.
- Open Access
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2705 (1) , 040089
The giving of mathematical connection problems for revealing the growth of junior high school students in problem solving process
The aim is to obtain qualitative results of the growth of the Problem Solving Process for JHS/SMP students throughthe online Mathematical Connection problems. T
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2705 (1) , 040089
Open AccessThe giving of mathematical connection problems for revealing the growth of junior high school students in problem solving process
The aim is to obtain qualitative results of the growth of the Problem Solving Process for JHS/SMP students throughthe online Mathematical Connection problems. T
- Open Access
- 1 June 2022
- Published by Universitas Negeri Semarang in Kreano, Jurnal Matematika Kreatif-Inovatif
- Vol. 13 (1) , 163-173
Sign Language Mathematics Lecture Video as Assistive Technology for Inclusive Class in Higher Education
This research was motivated by the acceptance of one deaf student in the Department of Computer Science UNNES in the 2020/2021 academic year. Therefore, this research aims to provide the study with efforts to increase the absorption of deaf students in the inclusive class through the discovery of Assistive Technology. The method used in this research is Mixed Method with a qualitative and Research Development (RD) approach. Data collection includes class observations, interviews, triangulation of results, and stages of RD. Research activities include: (1) lecturer of mathematical courses made PPt files, filled in Lecturer's Voice, and filled in Sign Language. (2) Video tested in inclusive class. (3) Finalization of Assistive Technology Videos and the results were noted. Research Results: (1) multi-function video prototypes were obtained for deaf students in inclusive classes in mathematical courses. (2) There was an increase in the activity and absorption of students in the inclusive class. In conclusion, it is necessary to make assistive technology in the form of learning videos that contain sign language to increase the absorption of deaf students in the inclusive class in mathematical courses.Penelitian ini dilatarbelakangi telah diterimanya satu mahasiswa Tunarungu pada Jurusan Ilmu Komputer UNNES pada tahun ajaran 2020/2021. Oleh karena itu tujuan penelitian ini adalah memberikan kajian upaya meningkatkan daya serap mahasiswa Tunarungu di kelas Insklusif melalui penemuan Teknologi Asistif. Metode dalam penelitian ini menggunakan metode mixed method dengan pendekatan kualitatif dan Research Development (RD). Pengumpulan data meliputi; observasi kelas, wawancara, triangulasi hasil, dan tahapan RD. Kegiatan penelitian meliputi: (1) dosen pengampu mata kuliah matematis membuat file PPt, diisi suara dosen, dan diisi Bahasa Isyaratnya. (2) Video diujicobakan di kelas Inklusif. (3) Finalisasi video Teknologi Asistif dan dicatat hasilnya. Hasil penelitian: (1) Diperoleh Prototip video Multi-Fungsi untuk mahasiswa Tunarungu di kelas Inklusif pada mata kuliah matematis. (2) Ada peningkatan aktivitas dan Daya Serap mahasiswa di kelas Inklusif. Kesimpulannya: Untuk meningkatkan daya serap mahasiswa Tunarungu di kelas Insklusif pada mata kuliah matematis, perlu dibuat Teknologi Asistif berupa video pembelajaran yang berisi Bahasa Isyarat.
- 1 June 2022
- Published by Universitas Negeri Semarang in Kreano, Jurnal Matematika Kreatif-Inovatif
- Vol. 13 (1) , 163-173
Open AccessSign Language Mathematics Lecture Video as Assistive Technology for Inclusive Class in Higher Education
This research was motivated by the acceptance of one deaf student in the Department of Computer Science UNNES in the 2020/2021 academic year. Therefore, this research aims to provide the study with efforts to increase the absorption of deaf students in the inclusive class through the discovery of Assistive Technology. The method used in this research is Mixed Method with a qualitative and Research Development (RD) approach. Data collection includes class observations, interviews, triangulation of results, and stages of RD. Research activities include: (1) lecturer of mathematical courses made PPt files, filled in Lecturer's Voice, and filled in Sign Language. (2) Video tested in inclusive class. (3) Finalization of Assistive Technology Videos and the results were noted. Research Results: (1) multi-function video prototypes were obtained for deaf students in inclusive classes in mathematical courses. (2) There was an increase in the activity and absorption of students in the inclusive class. In conclusion, it is necessary to make assistive technology in the form of learning videos that contain sign language to increase the absorption of deaf students in the inclusive class in mathematical courses.Penelitian ini dilatarbelakangi telah diterimanya satu mahasiswa Tunarungu pada Jurusan Ilmu Komputer UNNES pada tahun ajaran 2020/2021. Oleh karena itu tujuan penelitian ini adalah memberikan kajian upaya meningkatkan daya serap mahasiswa Tunarungu di kelas Insklusif melalui penemuan Teknologi Asistif. Metode dalam penelitian ini menggunakan metode mixed method dengan pendekatan kualitatif dan Research Development (RD). Pengumpulan data meliputi; observasi kelas, wawancara, triangulasi hasil, dan tahapan RD. Kegiatan penelitian meliputi: (1) dosen pengampu mata kuliah matematis membuat file PPt, diisi suara dosen, dan diisi Bahasa Isyaratnya. (2) Video diujicobakan di kelas Inklusif. (3) Finalisasi video Teknologi Asistif dan dicatat hasilnya. Hasil penelitian: (1) Diperoleh Prototip video Multi-Fungsi untuk mahasiswa Tunarungu di kelas Inklusif pada mata kuliah matematis. (2) Ada peningkatan aktivitas dan Daya Serap mahasiswa di kelas Inklusif. Kesimpulannya: Untuk meningkatkan daya serap mahasiswa Tunarungu di kelas Insklusif pada mata kuliah matematis, perlu dibuat Teknologi Asistif berupa video pembelajaran yang berisi Bahasa Isyarat.