4 research outputs found
X-ray image analysis for dental disease: A deep learning approach using EfficientNets
Get PDFDental cavities are a highly common persistent dental problem that impacts populations across different age groups on a global scale. It is crucial to get a dental issue diagnosed as early as possible and with as much accuracy as possible to treat it efficiently and prevent any related issues. If a dental infection is not treated, it will eventually grow and cause tooth loss. Dental X-ray images are crucial and beneficial in the diagnostic process of dental diseases for dentists. By applying Deep Learning (DL) techniques to dental X-ray images, dental experts can efficiently and precisely etect dental conditions, including dental cavities, fillings and implants. The objective of this research is to assess the performance of DL-based methods for dental disease detection via panoramic radiographs. In this study, we evaluated the performance of all of the EfficientNet variants (e.g., EfficientNets B0-B7) to determine which one is the most effective model for detecting dental disease. Moreover, we utilized the Borderline Synthetic Minority Oversampling Technique (SMOTE) to cope with the issue related to the minority classes contained in the dataset. To assess the efficacy of the model, various metrics are employed, including recall, accuracy, precision, loss, and F1-score. As a result, the performance of the EfficientNet-B5 model was superior to that of the other EfficientNet models. The EfficientNet-B5 model achieved the following values for its metrics: F1-score, accuracy, recall, AUC, and precision: 98.37%, 98.32%, 98.32%, 99.21%, and 98.32%, respectively. The accuracy rates for the EfficientNet-B0, EfficientNet-B1, EfficientNet-B2, EfficientNet-B3, EfficientNet-B4, EfficientNet-B6, and EfficientNet-B7, are 91.59%, 94.12%, 93.28%, 85.71%, 94.96%, 96.64% and 90.76%, respectively. The results indicated that the EfficientNet-B5 model performs better than other EfficientNet classifiers, which supports dental professionals significantly in the recognition of dental diseases
A Structural and Environmental Assessment of Pavement Solar Panels
No full textThe author has granted permission for their work to be available to the general public.The concurrent energy shortages of non-renewable energy resources have directed attention to the potential of harvesting renewable energy resources from roadway. Strong incentives to sustainable solution to this problem have led to the design of innovative pavement solar panel technology. This research is based on designing and developing a solar panel for roadway application. The designed prototype consists of a thin film solar panel, a transparent cover to protect the solar panel and a wooden frame to support the whole configuration. Since the pavement is exposed to solar radiation throughout the daytime, the pavement embedded solar panel will be utilized to harvest the solar energy and store with the integration of storage system and convert into electricity. It should also provide service during power failures in remote areas without electrical utilities. The main challenge of the project is the selection of proper transparent cover since it should bear the traffic loads and should not impair the transparency at the same time. The types of transparent covers chosen for this study are polycarbonate samples of varying thicknesses, textured glass grit sample and textured float glass with corundum skid resistant coating on the surface. Percentage transmittance of each samples was determined using transmittance spectroscopy in the visible light range. The percentage transmittance for the 10 mm, 12 mm and 16 mm polycarbonate samples were 87%, 84% and 82% and for textured glass grit sample it was 40% at each wavelength in the visible light range. The finite element analysis was carried out to replicate the in-situ installation of the solar panels with polycarbonate shield covers to determine the structural feasibility. The prototype panel was subjected to static and dynamic loading and the stress, strain and deflection analysis was performed and compared with a typical pavement model without any transparent cover. Finite element analysis demonstrated that the panel would not fail by fatigue under the loading condition considered.
Power generation data from these solar panels were collected and compared in a wide range of weather conditions and different seasons to assess the relationship of power and other environmental factors such as irradiance, illuminance, temperature, and cloud cover Since the panels were designed for pavement application, the panels were subjected to vehicular loading during the field tests to determine the decline in the power output due to shading of vehicles. Another purpose of the field test is to analyze whether the transparent covers face any disruption, damage, or failure under the wheel loading. Although polycarbonate samples and textured float glass sample can withstand traffic loads, the textured glass grit sample failed in fracture without any warning of failure under wheel loading. Experimental results also showed that 12 inch × 12 inch pavement solar panels generate an average of 2.2 W in sunny condition but produce less power in cloudy condition. Based on the power production data of SP10 from 12 PM to 6 PM, its feasibility was assessed for utilizing in the smart pedestrian system to lighten the crosswalk and alert the drivers of approaching vehicles.Civil and Environmental Engineerin
X-ray Image Analysis for Dental Disease: A Deep Learning Approach Using EfficientNets
Get PDFDental cavities are a highly common persistent dental problem that impacts populations across different age groups on a global scale. It is crucial to get a dental issue diagnosed as early as possible and with as much accuracy as possible to treat it efficiently and prevent any related issues. If a dental infection is not treated, it will eventually grow and cause tooth loss. Dental X-ray images are crucial and beneficial in the diagnostic process of dental diseases for dentists. By applying Deep Learning (DL) techniques to dental X-ray images, dental experts can efficiently and precisely detect dental conditions, including dental cavities, fillings and implants. The objective of this research is to assess the performance of DL-based methods for dental disease detection via panoramic radiographs. In this study, we evaluated the performance of all of the EfficientNet variants (e.g., EfficientNets B0-B7) to determine which one is the most effective model for detecting dental disease. Moreover, we utilized the Borderline Synthetic Minority Oversampling Technique (SMOTE) to cope with the issue related to the minority classes contained in the dataset. To assess the efficacy of the model, various metrics are employed, including recall, accuracy, precision, loss, and F1-score. As a result, the performance of the EfficientNet-B5 model was superior to that of the other EfficientNet models. The EfficientNet-B5 model achieved the following values for its metrics: F1-score, accuracy, recall, AUC, and precision: 98.37%, 98.32%, 98.32%, 99.21%, and 98.32%, respectively. The accuracy rates for the EfficientNet-B0, EfficientNet-B1, EfficientNet-B2, EfficientNet-B3, EfficientNet-B4, EfficientNet-B6, and EfficientNet-B7, are 91.59%, 94.12%, 93.28%, 85.71%, 94.96%, 96.64% and 90.76%, respectively. The results indicated that the EfficientNet-B5 model performs better than other EfficientNet classifiers, which supports dental professionals significantly in the recognition of dental diseases
LAPORAN INDIVIDU PRAKTIK LAPANGAN TERBIMBING (PLT)
Get PDFMagang III terintegrasi dengan mata kuliah Praktik Lapangan Terbimbing
(PLT) mempunyai kegiatan yang terkait dengan pembelajaran maupun kegiatan yang
mendukung berlangsungnya pembelajaran. Mata kuliah PLT diharapkan dapat
memberikan pengalaman belajar bagi mahasiswa, terutama dalam hal pengalaman
mengajar, memperluas wawasan, pelatihan dan pengembangan kompetensi yang
diperlukan dalam bidangnya, peningkatan keterampilan, kemandirian, tanggung
jawab, dan kemampuan dalam memecahkan masalah.
Secara umum, pelaksanaan PLT meliputi empat tahapan yaitu tahap
persiapan, pelaksanaan, evaluasi dan penyusunan laporan. Tahapan pelaksanaan PLT
meliputi tahap pembekalan, penerjunan, dan praktik mengajar. Pelaksanaan program
PLT dimulai dari tanggal 15 September 2017 sampai dengan 15 November 2017
yang diisi dengan observasi kelas dan lembaga, konsultasi, pembuatan Rencana
Pelaksanaan Pembelajaran, pembuatan materi ajar dan media pembelajaran, praktik
mengajar, dan evaluasi. Dalam praktik mengajar, kelas yang diampu adalah kelas X
Teknik Pemesinan 1 dan X Teknik Pemesinan 2. Mata pelajaran yang diampu adalah
teknologi mekanik dan praktik kerja bangku.
Penyelenggaraan PLT untuk mendukung pengembangan kompetensi
mahasiswa sebagai calon guru atau tenaga pendidik. Melalui program ini, praktikan
diharapkan memiliki keterampilan dalam mengelola kelas sehingga kegiatan
pembelajaran dapat berjalan dengan baik dan menghasilkan lulusan yang
berkompeten. Pelaksanaan PLT di SMK Muhammadiyah 1 Bantul ini juga
diharapkan dapat menjadi salah satu fungsi kehumasan mahasiswa sehingga sekolah
dapat menjadi mitra Universitas Negeri Yogyakarta untuk melaksanakan PLT tahun berikutnya
