Wavelet Kernel based Convolutional Neural Network for Localization of Partial Discharge Sources within a Power Apparatus

Flocks of birds may cause major damage to fruit crops in the ripening phase. This problem is addressed by various methods for bird scaring; in many cases, however, the birds become accustomed to the distraction, and the applied scaring procedure loses its purpose. To help eliminate the difficulty, we present a system to detect flocks and to trigger an actuator that will scare the objects only when a flock passes through the monitored space. The actual detection is performed with artificial intelligence utilizing a convolutional neural network. Before teaching the network, we employed videocameras and a differential algorithm to detect all items moving in the vineyard. Such objects revealed in the images were labeled and then used in training, testing, and validating the network. The assessment of the detection algorithm required evaluating the parameters precision, recall, and F1 score. In terms of function, the algorithm is implemented in a module consisting of a microcomputer and a connected videocamera. When a flock is detected, the microcontroller will generate a signal to be wirelessly transmitted to the module, whose task is to trigger the scaring actuator.

Section: Previous Researchmentioning

confidence: 99%

A System Using Artificial Intelligence to Detect and Scare Bird Flocks in the Protection of Ripening Fruit

Marcoň

Janoušek

Pokorny

et al. 2021

“…AI applications are commonplace in digital everyday life, for example in the form of virtual assistants such as “Siri” or “Alexa” [ 1 , 4 ], and AI applications are implemented in various engineering fields [ 5 , 6 , 7 ]. In medicine, AI algorithms are ubiquitously used for image processing via feature extraction of specific images and target conducting [ 8 ].…”

Section: Introductionmentioning

confidence: 99%

The Use and Performance of Artificial Intelligence in Prosthodontics: A Systematic Review

Bernauer

Zitzmann

Joda

2021

(1) Background: The rapid pace of digital development in everyday life is also reflected in dentistry, including the emergence of the first systems based on artificial intelligence (AI). This systematic review focused on the recent scientific literature and provides an overview of the application of AI in the dental discipline of prosthodontics. (2) Method: According to a modified PICO-strategy, an electronic (MEDLINE, EMBASE, CENTRAL) and manual search up to 30 June 2021 was carried out for the literature published in the last five years reporting the use of AI in the field of prosthodontics. (3) Results: 560 titles were screened, of which 30 abstracts and 16 full texts were selected for further review. Seven studies met the inclusion criteria and were analyzed. Most of the identified studies reported the training and application of an AI system (n = 6) or explored the function of an intrinsic AI system in a CAD software (n = 1). (4) Conclusions: While the number of included studies reporting the use of AI was relatively low, the summary of the obtained findings by the included studies represents the latest AI developments in prosthodontics demonstrating its application for automated diagnostics, as a predictive measure, and as a classification or identification tool. In the future, AI technologies will likely be used for collecting, processing, and organizing patient-related datasets to provide patient-centered, individualized dental treatment.

“…Until the current time, DNNs have been developed for many applications, such as civil engineering [14], electrical engineering [15], petroleum engineering [16], industrial engineering [17], and computer vision. A DNN for object detection is mostly known as a convolutional neural network (CNN).…”

Section: Introduction 1pedestrian Safety and Challenges In Pedestriamentioning

confidence: 99%

Pedestrian Detection Using Multispectral Images and a Deep Neural Network

Nataprawira

Goncharenko

et al. 2021

Pedestrian fatalities and injuries most likely occur in vehicle-pedestrian crashes. Meanwhile, engineers have tried to reduce the problems by developing a pedestrian detection function in Advanced Driver-Assistance Systems (ADAS) and autonomous vehicles. However, the system is still not perfect. A remaining problem in pedestrian detection is the performance reduction at nighttime, although pedestrian detection should work well regardless of lighting conditions. This study presents an evaluation of pedestrian detection performance in different lighting conditions, then proposes to adopt multispectral image and deep neural network to improve the detection accuracy. In the evaluation, different image sources including RGB, thermal, and multispectral format are compared for the performance of the pedestrian detection. In addition, the optimizations of the architecture of the deep neural network are performed to achieve high accuracy and short processing time in the pedestrian detection task. The result implies that using multispectral images is the best solution for pedestrian detection at different lighting conditions. The proposed deep neural network accomplishes a 6.9% improvement in pedestrian detection accuracy compared to the baseline method. Moreover, the optimization for processing time indicates that it is possible to reduce 22.76% processing time by only sacrificing 2% detection accuracy.