Detailed experiments showed that CADBOSS outperforms state-of-the-art computer-aided diagnosis. (CAD) systems and reasonably improves physician' diagnostic success.
Vegetation is an important parameter in all bio-and ecosystems, and it should be monitored to conserve and restore the environment. This paper presents a design and implementation of a compact system for vegetation cover monitoring, which consists of a small unmanned aerial vehicle (UAV) equipped with four different cameras (RGB, NIR, NDVI, and red). These cameras simultaneously record videos and wirelessly send them to a ground station that applies on them a set of algorithms to construct a mosaic representing the covered area and segment vegetative regions. Mosaicing is performed using a fast multi-threaded approach based on binary descriptors. For segmenting vegetation, two scenarios are tested by using convolutional neural networks (CNNs). The first scenario trained a CNN using the images obtained from the four cameras, and then used it with the constructed mosaics. In the second scenario, we trained individual CNNs using images from each of the four cameras individually. The performance of the former scenario exceeded the others from the perspective of accuracy. Moreover, it proved to be highly comparable to previous approaches utilizing level sets, while the processing time is reduced. The proposed approach obtained high accuracy in terms of the Dice similarity coefficient (97 %), which demonstrates its favorable performance.
Cancer diseases are one of the worst diseases threatening the human lives for many years. There is not an effective method of preventing these cancer diseases. However, early cancer detection and diagnosis play an important role in reducing the death rates. Bone scintigraphy scan is one of the most common diagnostic procedures in nuclear medicine. In general, physician experts evaluate the images manually. In these cases, the variation of diseases, which are measured for different times, cannot be determined properly. For that reason, we proposed a method to diagnose the diseases by using Fuzzy C-Means clustering and image processing techniques. In experimental studies, we evaluated the bone scintigraphy of twelve patients who are dealing with breast and prostate cancers. We determined the locations and areas of bone involvements. Also, the deviations of diseases along the times are automatically showed in the software.
Original scientific paper Juvenile fishes which have economic value in Eğirdir Lake, the fourth largest lake in Turkey according to its size, are killed due to electric water pumps used for the purpose of irrigation and drinking water. In this study, an electric fish barrier was designed to keep fish away from withdrawal points of electric water pumps. Results were tested in laboratory conditions. Each experiment was performed in triplicate using 30 fish (that is, the total number of fish used for each experiment was 90). Analysis of variance (ANOVA) was used to evaluate the results by using SPSS program. The experimental results demonstrated that the 50 V/10 Hz value cannot be used because of the adverse effects. 20 V/10 Hz and 35 V/10 Hz values are suitable to keep fish away from the barriers. Keywords: electric field; fish barrier; fish directing; fish repellent; microcontroller Električna barijera za zaštitu malih šarana u jezeru EğirdirIzvorni znanstveni članak Sitna riba od ekonomske vrijednosti u jezeru Eğirdir, četvrtom po veličini u Turskoj, ubija se električnim vodenim pumpama koje se koriste za navodnjavanje i vodu za piće. U ovom je radu konstruirana električna barijera koja ribu drži dalje od crpilišta električnih vodenih pumpi. Rezultati su provjeravani u laboratorijskim uvjetima. Svaki je eksperiment ponovljen tri puta s 30 riba (odnosno, ukupan broj riba za svaki eksperiment bio je 90). Rezultati su se provjeravali analizom varijance (ANOVA) uz primjenu SPSS programa. Eksperimentalni rezultati su pokazali da se vrijednost 50 V/10 Hz ne može koristiti zbog negativnih učinaka. Kao barijera za ribu odgovarajuće vrijednosti su 20 V/10 Hz i 35 V/10 Hz.
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.