http://repository.potensi-utama.ac.id/jspui/jspui/handle/123456789/5503 2026-04-16T15:21:48Z http://repository.potensi-utama.ac.id/jspui/jspui/handle/123456789/5508 Title: Improvement of Hybrid Image Enhancement for Detection and Classification of Malaria Disease Types and Stages with Artificial Intelligence Authors: Bob Subhan, Riza Abstract: Malaria is an infectious disease throughout the world where the disease is transmitted by infected female Anopheles mosquitoes. Malaria has some symptoms that are almost like COVID-19. Malaria has several other symptoms, characterized by chills, anemia, cold sweats, nausea and vomiting, and a sudden drop in blood pressure. Identification of the type of malaria begins with preprocessing, feature extraction, and classification for identification. Image improvement is part of the preprocessing stage to improve image quality so that the malaria parasite object in the image can be seen clearly. This study tries to improve the algorithm with hybrid dark and contrast stretching. Performance evaluation of malaria parasite image improvement using Mean Square Error (MSE) and Peak Signal Noise Ratio (PSNR). The results obtained with the improvement of dark hybrids and contrast stretching can improve the image quality of malaria parasite objects with MSE value = 0.0095 and PSNR value = 22.8404, compared with dark stretching, contrast stretching, histogram equalization. Description: Malaria is an infectious disease that occurs all over the world, especially in tropical climates. The Ministry of Health said that data on malaria cases is still difficult to eliminate because several regions have not succeeded in eliminating any of these malaria cases, such as in Papua, Maluku, and West Papua. Director of Prevention and Control of Vector and Zoonotic Diseases of the Ministry of Health Didik Budijianto explained that finding malaria cases is a challenge, especially during the COVID-19 pandemic [1]. Factors causing malaria are knowledge and attitudes of the community towards malaria. Infections caused by malaria can cause death, especially in high-risk groups such as pregnant women, infants, children under five. Malaria has symptoms that are almost like COVID-19 which are characterized by clinical symptoms, namely fever, chills, anemia, cold sweat, nausea and vomiting, and a sudden drop in blood pressure [1], [2]. Malaria is caused by the Plasmodium parasite and spread by a female Anopheles mosquito bite. Human Plasmodium falciparum, vivax, malaria, and oval [3]. Some standard tests are carried out by experts to identify malaria, using microscopic tools, ant it takes long time which require a laboratory to get the type of parasite and its stage. We need a system that can make it easy to identify the type of malaria parasite and its stage. Several stages will be carried out for image identification for the type of malaria, starting with the preprocessing stage, feature extraction, and classification for identification. The image improvement stage is part of the preprocessing stage where this stage is the main priority because if the 2022-05-27T00:00:00Z http://repository.potensi-utama.ac.id/jspui/jspui/handle/123456789/5507 Title: Digitalization of Smart Student Assessment Quality in Era 4.0 Authors: Bob Subhan, Riza Abstract: Era 4.0 has had a significant impact on information technology, especially in digitalization that has entered the field of education. The purpose of this study is to explore how from lecturers to department heads to understand and proficiency in digitizing student assessment in the 4.0 era. This study uses the SDLC waterfall method in building gamificationbased smart assessment. Researchers need to explore how to understand the concept of skills towards digitizing student assessments required to produce an effective and efficient system. The findings show that lecturers are able to see digitalization with broad and complex concepts including the pedagogical, technical, administrative and academic structures of the University. The role of the lecturer seems to play an essential and complex role due to digitization so that it impacts on the level of student motivation. However, time, human resources, as well as professional development, continue to influence in supporting the learning process of lecturers and students. This paper contributes to the digitization and quality of lecturers' smart assessment of students. The contribution shown for lecturers is trying to implement and be able to digitize in 4.0 era as a form of transformation in the field of education. The application of smart assessment helps the quality of lecturers' quality of input scores in students effectively and accurately so that it impacts on students knowing the value in real-time and becomes motivated by gamification. Description: Advances in information technology in the 4.0 era are demonstrated by activities that are often carried out online so that they are readily available to meet educational needs [1]. A critical part of education is about assessment. It should be remembered that the main effect of an assessment on learning is not only from the success of educational programs but rather the quality of assessment [2]. Quality the assessment includes all elements of an evaluation practice such as the assignment, the score report, the assessment, the feedback, the programs, the criteria, and the policies [3]. At present, school leaders have the responsibility to encourage development and lead digitalization, starting from students, lecturers, to higher education organizations [4][5]. So, according to school leaders, accessibility to technology is a challenging and robust condition in development [6]. However, information about the assessment is still of minimal quality and is not digitized. 2020-01-01T00:00:00Z http://repository.potensi-utama.ac.id/jspui/jspui/handle/123456789/5506 Title: Development of video-based emotion recognition using deep learning with Google Colab Authors: Bob Subhan, Riza Abstract: Emotion recognition using images, videos, or speech as input is considered as a hot topic in the field of research over some years. With the introduction of deep learning techniques, e.g., convolutional neural networks (CNN), applied in emotion recognition, has produced promising results. Human facial expressions are considered as critical components in understanding one's emotions. This paper sheds light on recognizing the emotions using deep learning techniques from the videos. The methodology of the recognition process, along with its description, is provided in this paper. Some of the video-based datasets used in many scholarly works are also examined. Results obtained from different emotion recognition models are presented along with their performance parameters. An experiment was carried out on the fer2013 dataset in Google Colab for depression detection, which came out to be 97% accurate on the training set and 57.4% accurate on the testing set. Description: In the past few years, emotion recognition has become one of the leading topics in the field of machine learning and artificial intelligence. The tremendous increase in the development of sophisticated human-computer interaction technologies has further boosted the pace of progress in this field. Facial actions convey the emotions, which, in turn, convey a person’s personality, mood, and intentions. Emotions usually depend upon the facial features of an individual along with the voice. Nevertheless, there are some other features as well, namely physiological features, social features, physical features of the body, and many more. More and more work has been done to recognize emotions with more accuracy and precision. The target of emotion recognition can be achieved broadly using visual-based techniques or sound-based techniques. Artificial intelligence has revolutionized the field of human-computer interaction and provides many machine learning techniques to reach our aim. There are many machine learning techniques to recognize the emotion, but this paper will mostly focus on video-based emotion recognition using deep learning. Video-based emotion recognition is multidisciplinary and includes fields like psychology, affective computing, and human-computer 2020-05-11T00:00:00Z http://repository.potensi-utama.ac.id/jspui/jspui/handle/123456789/5505 Title: Convolutional Neural Network as an Image Processing Technique for Classification of Bacilli Tuberculosis Extra Pulmonary (TBEP) Disease Authors: Bob Subhan, Riza Abstract: Tuberculosis Extra Pulmonary (TBEP) is an infectious disease caused by the bacterium Mycobacterium tuberculosis and can cause death. Patients suffering from this disease must be treated quickly without waiting for a long time. Biopsy is one of the techniques used to take the patient's lung fluid and given Ziehl Neelsen chemical dye and then observed using a microscope to determine this TBEP disease. In this research, the TBEP detection process was developed using a classification method, namely CNN with feature extraction and feature selection. The feature uses 5 features where these features are a combination of shape features and texture features with the highest information gain value. From the results of research conducted through the training and testing stages of the classification method using feature selection, the accuracy rate is higher than not using feature selection with a comparison of the feature selection stage increasing 0.6536% for the training process, and 0.8942% for the testing process. Description: Tuberculosis is a life-threatening infectious disease worldwide caused by the bacterium Mycobacterium tuberculosis. These bacteria are in the form of AcidFast Bacilli (AFB). These bacilli are 1-4 m long and 0.3-0.56 m wide as shown in Figure 1., are nonspore-forming, non-motile, and facultative. Bacterial cell walls contain long chain glycolipids that are mycolic, rich in acids and phosphopoglycans [1], [2]. Tuberculosis (TB) is a chronic and infectious disease that affects the world's human population and requires complex treatment. It is a public health problem with more than 9 million estimated new cases and 1.5 million deaths annually worldwide [3]. Of the estimated 9 million people who contracted TB in 2013, more than 80% were in Southeast Asia, the Western Pacific and Africa. Most of the infected population comes from poor and marginalized communities with weak health services infrastructure 2022-08-29T00:00:00Z