Quantum technology offers a transformative approach to solving complex computational challenges in decentralized systems, particularly in blockchain transaction scheduling. Efficient transaction scheduling is critical...
详细信息
The exponential increase in video traffic on the Internet has generated a heightened demand for efficient video streaming solutions. HTTP Adaptive Streaming (HAS) has emerged as a viable strategy, facilitating dynamic...
详细信息
With the advancement of technologies, different methods are currently being used for converting spoken language into text. These systems offer a hands-free alternative to traditional input methods, especially for indi...
详细信息
This research addresses one of the major problems in agriculture that farmers are currently facing: birds causing significant crop damage in agricultural fields. To reduce this damage, a person’s presence is often re...
详细信息
This research addresses one of the major problems in agriculture that farmers are currently facing: birds causing significant crop damage in agricultural fields. To reduce this damage, a person’s presence is often required in the farm field to repel the birds. To eliminate this need and automate the repellent system, the project aims to develop a bird repellent device using computer vision techniques to detect and repel birds from fields. Existing work lags behind in using effective algorithms and developing hardware. Object detection algorithms like the Haar Cascade Classifier and YOLOv8 are used; YOLOv8 is a powerful object detection algorithm, and it is chosen as the primary algorithm for its accuracy and speed in detecting birds. A hardware device is developed using a Raspberry Pi with a Pi camera and a Bluetooth speaker. Upon detecting birds in the farm fields through the Pi camera, distress calls are produced through the Bluetooth speakers to repel the birds.
Fruit variety classification is a crucial aspect in agricultural processes and supply chain management, influencing market competitiveness, and consumer satisfaction. This paper provides a comprehensive review of vari...
详细信息
Fruit variety classification is a crucial aspect in agricultural processes and supply chain management, influencing market competitiveness, and consumer satisfaction. This paper provides a comprehensive review of various fruit variety classification techniques utilizing machine learning (ML) methodologies, highlighting the motivations driving research in this domain and the challenges that researchers and practitioner’s encounter. The capabilities of ML algorithms and deep learning (DL) models have facilitated significant advancements in fruit classification accuracy. Motivated by the growing demand globally for fruits and their varieties and the need to optimize resources utilized in agriculture, researchers have focused on developing ML-driven classification systems capable of automating fruit sorting, grading, maturity estimation, and quality control processes. DL particularly has ability to learn complex representations from images, among which the primary architecture is the convolutional neural network (CNN) for applications related to image classification. Based on the extensive literature survey conducted, its observed that utilization of CNN for fruit variety classification has immensely increased generating outstanding results using “from-scratch” or “pretrained” model for transfer learning, however it often struggles with limited datasets, leading to poor generalization, and difficulty in handling variations in fruit appearance due to lighting, orientation, or ripeness. Besides this, the paper presents frameworks, model design, and one practical application on the use of CNN for fruit variety classification.
This paper explores the application of game theoretic approaches to load balancing across edge nodes within distributed computing systems. Focusing on a non-cooperative game model, we aim to enhance system efficiency ...
详细信息
An automated damage detection method based on deep learning for wind turbine blades uses the YOLOv5 framework, which is object detection that is quite fast and relatively accurate for detecting objects and localizatio...
详细信息
ISBN:
(数字)9798331521691
ISBN:
(纸本)9798331521707
An automated damage detection method based on deep learning for wind turbine blades uses the YOLOv5 framework, which is object detection that is quite fast and relatively accurate for detecting objects and localization instances of damage in images. Source data has been a curated collection dataset of wind turbine images with annotated regions of damage; thus, a model was trained from Roboflow. This uses transfer learning in which the model is started with pre-trained YOLOv5s weights and further fine-tunes it over the specific dataset. It also fits well into the nature of the data-set including the number of classes of damage. The training process, therefore, is optimizing the model parameters to achieve the minimization of differences between predicted bounding boxes and the available ground-truth annotations. Standard metrics for object detection are used in the evaluation of the model: precision, recall, mean Average Precision (mAP), and F1-score. Qualitative assessment is also carried through as a visual check on the predictions that the model would produce on unseen images, validating its use in real conditions. It contributes to developing an automated and efficient system concerning structural health monitoring of wind turbines and enables maintenance at the appropriate time, thus decreasing down times.
Emerging AR-VR applications execute complex heterogeneous workloads, mixing Deep-Learning(DL) and Digital-Signal-Processing(DSP) tasks, on SoCs embedded in the frame of eyeglasses, with implied tight power and area co...
ISBN:
(纸本)9798350323481
Emerging AR-VR applications execute complex heterogeneous workloads, mixing Deep-Learning(DL) and Digital-Signal-Processing(DSP) tasks, on SoCs embedded in the frame of eyeglasses, with implied tight power and area constraints, especially in the case of AR. We propose ArchiMEDES, an open-source heterogeneous-SoC platform with a programmable cluster of RISC-V cores coupled with a configurable DNN engine (NEureka) targeting AR/VR workloads. ArchiMEDES features a low-overhead Heterogeneous Cluster Interconnect(HCI) to enable fast RISC-V/NEureka cooperation on a shared tightly coupled data memory (TCDM). We show post-layout results targeting 22nm technology; ArchiMEDES shows a peak combined performance of up to 1.19 TOPS and an efficiency of up to 10.6 TOPS/W. Hardware-Software cooperation in ArchiMEDES enables a 5.5× speedup in an AR-VR gaze tracking case study, compared to a non-cooperative single-RISC-V + Accelerator system.
Magnetic levitation planar motor can move at high speed and with high accuracy, and prevent vibration and noise because of no friction. This technology leads to the application of a transport system that requires high...
详细信息
This paper presents an analysis of the biquad digital oscillator, which leads to design improvements in the online oscillating frequency adjustment capabilities. The requirements for signal generation in a digital osc...
详细信息
暂无评论