Developing a breast cancer screening method is very important to facilitate early breast cancer detection and treatment. Building a screening method using medical imaging modality that does not cause body tissue damage (non-invasive) and does not involve physical touch is challenging. Thermography, a non-invasive and non-contact cancer screening method, can detect tumors at an early stage even under precancerous conditions by observing temperature distribution in both breasts. The thermograms obtained on thermography can be interpreted using deep learning models such as convolutional neural networks (CNNs). CNNs can automatically classify breast thermograms into categories such as normal and abnormal. Despite their demostrated utility, CNNs have not been widely used in breast thermogram classification. In this study, we aimed to summarize the current work and progress in breast cancer detection based on thermography and CNNs. We first discuss of breast thermography potential in early breast cancer detection, providing an overview of the availability of breast thermal datasets together with publicly accessible. We also discuss characteristics of breast thermograms and the differences between healthy and cancerous thermographic patterns. Breast thermogram classification using a CNN model is described step by step including a simulation example illustrating feature learning. We cover most research related to the implementation of deep neural networks for breast thermogram classification and propose future research directions for developing representative datasets, feeding the segmented image, assigning a good kernel, and building a lightweight CNN model to improve CNN performance. INDEX TERMS breast cancer; convolutional neural network; deep learning; early detection; thermogram
<abstract><p>The presence of a well-trained, mobile CNN model with a high accuracy rate is imperative to build a mobile-based early breast cancer detector. In this study, we propose a mobile neural network model breast cancer mobile network (BreaCNet) and its implementation framework. BreaCNet consists of an effective segmentation algorithm for breast thermograms and a classifier based on the mobile CNN model. The segmentation algorithm employing edge detection and second-order polynomial curve fitting techniques can effectively capture the thermograms' region of interest (ROI), thereby facilitating efficient feature extraction. The classifier was developed based on ShuffleNet by adding one block consisting of a convolutional layer with 1028 filters. The modified Shufflenet demonstrated a good fit learning with 6.1 million parameters and 22 MB size. Simulation results showed that modified ShuffleNet alone resulted in a 72% accuracy rate, but the performance excelled to a 100% accuracy rate when integrated with the proposed segmentation algorithm. In terms of diagnostic accuracy of the normal and abnormal test, BreaCNet significantly improves the sensitivity rate from 43% to 100% and specificity of 100%. We confirmed that feeding only the ROI of the input dataset to the network can improve the classifier's performance. On the implementation aspect of BreaCNet, the on-device inference is recommended to ensure users' data privacy and handle an unreliable network connection.</p></abstract>
Artikel ini membahas tentang desain prototipe kursi light follower dengan pengaturan kecepatan putar motor DC berdasarkan tingkat intensitas cahaya berbasis mikrokontroler ATmega328p. Prototipe ini memberikan solusi agar kursi dapat kembali ke bawah meja secara otomatis dengan memanfaatkan prinsip kerja robot light follower. Posisi kursi setelah digunakan dapat saja menghadap tegak lurus terhadap meja, serong terhadap meja, atau membelakangi meja. Karena arah kursi terhadap meja bervariasi maka digunakan cahaya sebagai penentu arah pergerakan kursi karena pancaran cahaya mampu menjangkau berbagai area kursi kecuali bagian belakang kursi. Prototipe ini berfungsi jika kursi berada di hadapan meja, prototipe ini tidak dirancang untuk berfungsi bila posisi kursi tepat membelakangi meja. Untuk mendeteksi cahaya digunakan sensor LDR (Light Dependent Resistor). Sumber cahaya yang digunakan adalah sebuah LED (Light Emitting Diode) high power 1 W yang diletakkan di bawah meja. Mikrokontroler ATmega328p digunakan untuk memproses data masukan dan keluaran. Kursi digerakkan dengan menggunakan dua unit motor DC yang berfungsi menggerakkan roda dengan arah pergerakan menuju cahaya di bawah meja. Sensor ultrasonik HC-SR04 digunakan untuk mendeteksi jarak terhadap meja di hadapannya sehingga kursi dapat berhenti pada posisi yang diinginkan.
<p>Indonesia is geographically located in the disaster vulnerable area and frequently hit by various disasters such as earthquake, flood, etc. So that Indonesian people aware that the disaster information system is very important. Thus, the development of information and communication technology application is needed for disaster management. For this purpose, this paper proposes on the development of online disaster information system based on location based service (LBS) technology by using short message service (SMS) gateway and global positioning system (GPS). Then,the web-based prototype of online disaster information system is designed and developed as the media to provide information of location and situation of the disaster area. Furthermore, a user interface is also designed and developed to transmit input data as the location information using manual SMS and automatically using smartphone based on SMS/GPS. The research method used in this research is a spiral method that begins with conceptual design, prototype development, application test, and evaluation. The results of this research are the web-based information system and the implemented user interface application (we called ASIKonLBS) for Android based smartphone. The online mapping of input data from smartphone to the web-based system has been tested. It shows that the disaster location information can be mapped to Google Maps timely and accurately that can be accessed using the Internet connection. The evaluation to mapping delay time shows that it is lower than the refresh time of the web-based system. Therefore, the proposed online system can be categorized as a real-time system.</p>
The model development for breast thermal image classification can be done using deep learning methods, especially the convolutional neural network (CNN) architecture. This article focuses on adapting a trained CNN (trained model) on a mobile application for binary classification of breast thermal images into normal and abnormal classes. The CNN model applied in this study was based on ShuffleNet, called BreaCNet, with a learning weight of 1028 filters generated from training on images downloaded from the Database for Mastology Research (DMR) and a model size of 22 MB. The model must be converted into a mobile application to enable a trained model to be adapted into a mobile platform. The BreaCNet model was built using MatLab; thus, the stages in the adaptation process consisted of converting the model into ONNX file format, converting ONNX files into Tensorflow files, and Tensorflow files into Tensorflow Lite format. However, not all nodes are fully supported by MATLAB. The shuffle node on ShuffleNet cannot be fully exported using ExportToOnnx, so it needs to be re-defined with a placeholder named “MATLAB PLACEHOLDER”. In addition to the model conversion process, this article describes the user interaction process with the application using UML diagrams and application feature menu designs. The application was also tested on 20 thermal images of the breast. The testing results show that the application can perform the image classification process on mobile devices in less than 1 second with an accuracy rate of 85%. Finally, the breast thermal image screening application has been successfully built by directly interpreting the thermal image of the breast on a mobile device to keep the user data private.
Recently, the identification system is not limited in using an ID and personal identification number (PIN) but also in using biometriccharacteristics.One of biometric characteristics that has been widely used is fingerprint.This paper proposes a fingerprint matching algorithms using ordinal measure of DCT coefficient. The ordinal measure of DCT coefficient is generated from DCT blocks with size 8x8 pixels. Matching level was determined by computing the Minkowski distance between features of input fingerprint image and fingerprint images in the database. The simulations were accomplished using 128 fingerprints that have been normalized, from which as many as 1024 genuine attempts and 15360 impostor attempts were generated. The proposed algorithms achievedan Equal Error Rate (EER) at threshold 0.3. At the EER, it resulted in FAR value of 0.82%, and FRR value of 78.41% respectively. The low value of FAR showed that the system wasconsiderably secure.
Pada masa pandemi COVID-19 saat ini, pemerintah memberlakukan peraturan yaitu ketika akan masuk ke dalam ruangan (khususnya gedung publik) diharuskan mematuhi protokol kesehatan berupa menggunakan masker dan dilakukan pengukuran suhu tubuh. Namun banyak dari masyarakat yang tidak mematuhi peraturan tersebut sehingga apabila memasuki suatu ruangan yang berisi banyak orang dan tanpa protokol kesehatan akan berpotensi terpapar virus COVID-19. Salah satu solusi untuk mengimplementasikan protokol kesehatan tersebut adalah dengan menggunakan pintu otomatis yang dapat terbuka dengan sendirinya apabila seseorang memakai masker dan suhu tubuhnya kurang dari 38 ̊ C. Pada penelitian ini akan dibuat sebuah prototipe pintu yang mendeteksi penggunaan masker dan suhu tubuh dengan kamera dan sensor suhu tubuh. Penelitian ini menggunakan metode deep learning untuk mendeteksi masker dan pengukuran sensor suhu tubuh untuk mendeteksi suhu tubuh serta sebagai pemrosesan sensor, aktuator dan komponen lainnya digunakan raspberry pi 4. Hasil dari penelitian ini berupa prototipe pintu otomatis yang akan bekerja saat user berada pada posisi ≤ 6 cm, Adapun kondisi yang harus terpenuhi agar pintu terbuka adalah user memakai masker dan suhu tubuh 38 ̊ C maka pintu terbuka, user memakai masker dan suhu tubuh ≥ 38 ̊ C maka buzzer berbunyi dan pintu tidak terbuka, user tidak memakai masker dan suhu tubuh 38 ̊ C maka buzzer berbunyi dan pintu tidak terbuka, user tidak memakai masker dan suhu tubuh ≥ 38 ̊ C maka buzzer berbunyi dan pintu tidak akan terbuka. Adapun hasil akurasi deteksi masker tertinggi yaitu pada masker kn95 dengan akurasi 99.95 % dan pendeteksian suhu akurat pada jarak 2 cm yang menghasilkan galat 0.05%. Dengan demikian prototipe pintu otomatis telah diuji dan berjalan dengan baik mengikuti kondisi yang ditentukan.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.