With the development of the Internet, information carriers and communication methods have become diversified. As an important carrier for obtaining information, images are easily copied and tampered with during the co...
详细信息
People from all around the world are afflicted by the fatal condition known as diabetes mellitus (DM). A timely diagnosis of DM is particularly advantageous because it may be managed before the beginning of the condit...
详细信息
People from all around the world are afflicted by the fatal condition known as diabetes mellitus (DM). A timely diagnosis of DM is particularly advantageous because it may be managed before the beginning of the condition. In this work, different pre-processing methods for the diagnosis of DM are discussed and contrasted. Additionally, the accuracy of several methods for data mining has been evaluated depending on missing scores, with a particular emphasis on artificialneuralnetworks (ANN) to handle missing data utilizing z-value and MinMax procedures. IoT (Internet of Things) devices are used in this research to track the patients' situations. Statistics are sent from IoT gadgets to smartphones for surveillance, and subsequently from smartphones to the web, where categorization is done. Employing a Python instrument, the simulation is carried out on the data sets that were obtained. The simulation findings demonstrate that the suggested strategy outperforms current state-of-the-art ensemble approaches in terms of accuracy pace, recall, precision, and f-value.
Integration of artificial intelligence in industrial automation has led to significant advancements in new techniques for automation. Such an aspect of industrial automation includes sorting consumables on conveyor be...
详细信息
ISBN:
(纸本)9798350362923;9798350362916
Integration of artificial intelligence in industrial automation has led to significant advancements in new techniques for automation. Such an aspect of industrial automation includes sorting consumables on conveyor belt systems via imageprocessing. Typically, these applications use expensive dedicated, and focus-driven hardware and individual image-processing coding. This paper discusses the development of such an image-processing sorting conveyor belt but utilizing low-cost processors compared to dedicated and focus-driven hardware. This is achieved by using at the core of this system a Convolutional neural Network (CNN), specifically tailored for hue-based imageprocessing, and implemented on a Raspberry Pi 4B. A standard Pi camera, attached to the Raspberry Pi, captures images for real-time object classification. A key innovation of the system is the utilization of a pixel-based trigger mechanism for image capture, which significantly improves the accuracy and efficiency of the sorting process. The system achieves an accuracy rate of 92.74% in classifying objects as trained, underscoring the efficacy of the approach. Additionally, the system operates in a dual-mode capacity, enabling not only the sorting of existing object types but also the learning and adaptation to new objects through user input. This feature enhances the system's versatility and applicability in various industrial contexts. The paper details the design, implementation, and testing of this AI-driven sorting mechanism, highlighting its potential as a scalable and low-cost solution for modern industrial sorting needs.
neuralnetworks have achieved remarkable success in various applications such as image classification, speech recognition, and natural language processing. However, the growing size of neuralnetworks poses significan...
详细信息
ISBN:
(纸本)9783031490071;9783031490088
neuralnetworks have achieved remarkable success in various applications such as image classification, speech recognition, and natural language processing. However, the growing size of neuralnetworks poses significant challenges in terms of memory usage, computational cost, and deployment on resource-constrained devices. Pruning is a popular technique to reduce the complexity of neuralnetworks by removing unnecessary connections, neurons, or filters. In this paper, we present novel pruning algorithms that can reduce the number of parameters in neuralnetworks by up to 98% without sacrificing accuracy. This is done by scaling the pruning rate of the models to the size of the model and scheduling the pruning to execute throughout the training of the model. Code related to this work is openly available.
This study investigates the performance of different methods for image classification tasks using the CIFAR-10 dataset. Four neuralnetworks, namely Convolutional neuralnetworks (CNNs), artificialneuralnetworks (AN...
详细信息
We are training neuralnetworks to predict house rents using artificial intelligence and deep learning, which is being used in the real estate and financial industries. Real estate agents, financial institutions, and ...
详细信息
Crowd counting is an approach for the process of counting the people in an image. Extensive studies on crowd detection and density estimation are being carried out for crime prevention, crowd irregularities, public sa...
详细信息
ISBN:
(纸本)9789819984787;9789819984794
Crowd counting is an approach for the process of counting the people in an image. Extensive studies on crowd detection and density estimation are being carried out for crime prevention, crowd irregularities, public safety, visual monitoring, and urban planning. Approaches to detect crowd count are available in the literature;however, available algorithms could not detect the accurate number of people. Therefore, in the current work, computer vision techniques in fusion with convolutional neuralnetworks (CNNs) are employed to produce impressively precise estimates. The proposed work will precisely detect count of the persons in an image using computer vision and CNN. Pattern recognition techniques are employed for crowd count detection by using face detection. However, detecting a face in the crowd is complex as inconsistency prevails in human faces comprising of color, pose, expression, position, orientation, and illumination. Congested Scene Recognition Network (CSRNet) attains 47.3% lower mean absolute error compared with existing techniques. The current work is also extended to various intended applications such as vehicles. The experimental results reveal that CSRNet has shown significant improvement in the output by 15.4% better MAE than existing contemporary approaches.
Noisy images are a challenge to image compression algorithms due to the inherent difficulty of compressing noise. As noise cannot easily be discerned from image details, such as high-frequency signals, its presence le...
详细信息
ISBN:
(纸本)9798350349405;9798350349399
Noisy images are a challenge to image compression algorithms due to the inherent difficulty of compressing noise. As noise cannot easily be discerned from image details, such as high-frequency signals, its presence leads to extra bits needed for compression. Since the emerging learned image compression paradigm enables end-to- end optimization of codecs, recent efforts were made to integrate denoising into the compression model, relying on clean image features to guide denoising. However, these methods exhibit suboptimal performance under high noise levels, lacking the capability to generalize across diverse noise types. In this paper, we propose a novel method integrating a multi-scale denoiser comprising of Self Organizing Operational neuralnetworks, for joint image compression and denoising. We employ contrastive learning to boost the network ability to differentiate noise from high frequency signal components, by emphasizing the correlation between noisy and clean counterparts. Experimental results demonstrate the effectiveness of the proposed method both in rate-distortion performance, and codec speed, outperforming the current state-of-the-art.
In this study, we present an optimized convolutional neural network model for classification of cyber-attacks from network traffic data, using the N-BaIoT dataset. The proposed model consists of convolutional, max poo...
详细信息
ISBN:
(纸本)9798350352368
In this study, we present an optimized convolutional neural network model for classification of cyber-attacks from network traffic data, using the N-BaIoT dataset. The proposed model consists of convolutional, max pooling and dense layers. Different architectural models have been experimented with different settings such as utilizing 3,5,7,9 and 11 convolutional layers. Among these settings, the model with 5 convolutional layers outperformed the others with test accuracy of 99.91% and an average recall, precision and F1 score of 0.99. Along with this, the proposed model has been evaluated by class wise classification report and confusion matrices. Furthermore, the model performance complexity has also been discussed and measured in GFLOPS (Giga Floating Point Operations Per Second), it shows that the proposed model with best and optimized settings achieved a value of 3.158.
Taking photos against the light generates a certain visual effect. Taking a photo in the direction where the sun is located also results in a change in the temperature of the photo as well as the appearance of a visua...
详细信息
ISBN:
(纸本)9798350359329;9798350359312
Taking photos against the light generates a certain visual effect. Taking a photo in the direction where the sun is located also results in a change in the temperature of the photo as well as the appearance of a visual effect in the form of the flare of light. In this article, we present an innovative neural network model called Y-ResNet, whose input consists of two samples and the output consists of one. This solution makes it possible to train the network by providing the original image and the flare effect, which will result in a modified sample. The training was conducted on a commonly known CityScapes dataset, where, by using classic data processing methods and the k-means algorithm, it was possible to add a flare if there was a visible portion of the sky in the input image. The proposed solution was described and tested to demonstrate the capabilities of the proposed method. The results show the superiority of the approach against the traditional ResNet without a second encoding path, generating better results, and creating a better impression of the lens-flare effect.
暂无评论