According to the World Health Organization (WHO), falls are the second cause of death due to accidental injuries, and older adults are the ones who suffer the most from them. In Ecuador, there are about 1,300,000 olde...
详细信息
ISBN:
(纸本)9789811963469;9789811963476
According to the World Health Organization (WHO), falls are the second cause of death due to accidental injuries, and older adults are the ones who suffer the most from them. In Ecuador, there are about 1,300,000 older adults, and falls are a major problem for their quality of life. For this reason, in this article, we present a low-cost prototype system for the monitoring and detection of falls, with the aim of providing support for the care of older adults. This tool is based on a module that applies computer vision and imageprocessing techniques, convolutional neural networks (CNNs) and Web and mobile applications. They allow the monitoring and control of falls. To test the operation of the system, tests were carried out with fifteen volunteers. It was determined that the system managed to correctly detect 80% of fall-related events.
The capabilities of convolutional neural networks, and in fact all manner of artificial intelligence and machine learning capabilities, to explore data in various fields has been documented extensively throughout the ...
详细信息
ISBN:
(数字)9781510661936
ISBN:
(纸本)9781510661929;9781510661936
The capabilities of convolutional neural networks, and in fact all manner of artificial intelligence and machine learning capabilities, to explore data in various fields has been documented extensively throughout the literature. One common challenge with adopting AI/ML solutions, however, is the issue of trust. Decision makers are rightfully hesitant to take action based solely on "the computer said so" even if the computer has great confidence that it is correct. There is obvious value in a system that can answer the question of why it made a given prediction and back this up with specific evidence. Basic models like regression or nearest neighbors can support such answers but have significant limitations in real-world applications, and more capable models like neural networks are much too complex to interpret. We have developed a prototype system that combines convolutional neural networks with semantic representations of reasonableness. We use logic similar to how humans justify conclusions, breaking objects into smaller pieces that we trust a neural network to identify. Leveraging a suite of machine learning algorithms, the tool provides not merely an output "conclusion", but a supporting string of evidence that humans can use to better understand the conclusion, as well as explore potential weaknesses in the AI/ML components (whether as a result of lack of sufficient training data, adversarial attempts to corrupt the system, etc.). We have applied this system to problems of object detection and semantic segmentation of images. This paper will provide an in-depth overview of the prototype and show some exemplar results.
To detect specific objects in an image, image segmentation involves separating the image across a number of areas. One of the fundamental phases in imageprocessing is picture segmentation. When there are numerous are...
详细信息
Haze is defined as a poor condition described by an iridescent atmospheric appearance that reduces clarity and visibility. The main reason for this is lot of toxic elements like dust particles, smoke in the atmosphere...
详细信息
Artificial Neural Networks (ANN) have become one of the most powerful machine learning tools that cover a wide range of applications such as surveillance, video and image recognition, medical image analysis, control s...
详细信息
In the preparation and packing of pomegranates, sorting is an essential stage. Pomegranates are currently hand sorted into quality groups. Manual sorting, however, takes a lot of time and is not precise. Furthermore, ...
详细信息
Waste management is a pressing global issue, and the need for efficient waste separation processes is becoming increasingly important. Incorporating machine Learning techniques with waste separation has yielded promis...
详细信息
This paper introduces an innovative method that combines Computer vision and Deep Learning to extract headlines from a historical newspaper. Through the illustrations from historical newspapers, one of our goals is to...
详细信息
Grape leaf diseases like Black Rot, Eska measles, Leaf Spot and Healthy are among the most common disease types of the grape crop. Accurate detection of grape leaf diseases in the initial stages can control the diseas...
详细信息
Grape leaf diseases like Black Rot, Eska measles, Leaf Spot and Healthy are among the most common disease types of the grape crop. Accurate detection of grape leaf diseases in the initial stages can control the disease spread significantly and guarantee progressive development of the grape crop industry. The existing research provides several complex imageprocessing algorithms and cannot assure high classification accuracy. Therefore, machine learning techniques are presented in this article to enhance leaf disease classification accuracy for efficiently detecting grape leaf diseases. Moreover, two classification models are introduced in which the simple Convolutional Neural Network based Classification (CNNC) Model is detailed. Then the improvised K-Nearest Neighbour (IKNN) model for precisely detecting grape leaf diseases is detailed. Moreover, pixel encoding methods are presented to obtain a histogram representation of extracted features. Training of simple CNNC and the proposed IKNN model is conducted on Plant-village Dataset. Additionally, mathematical modeling is presented to formulate the problem in the feature extraction process. Moreover, Confined Intensity Directional Order Relation (CIDOR) operation ensures low dimensionality of histogram representation in the multiscale domain. Furthermore, Global Pixel Order Relation (GPOR) focuses on setting up a communication with long-reach pixels of an image outside of the central pixel neighborhood. Compared to the simple CNNC, the proposed IKNN model outperforms all the traditional leaf disease classification algorithms in terms of classification accuracy. However, the IKNN model provides superior results than CNNC comparatively in terms of classification accuracy.
To date, the problem of automating work with images taken using satellite systems has become relevant. This task concerns a wide range of human activities, including urban planning, transport logistics, ecology and en...
详细信息
暂无评论