Current Issue : July-September Volume : 2022 Issue Number : 3 Articles : 5 Articles
Changes in clouds can affect the outpower of photovoltaics (PVs). Ground-based cloud images classification is an important prerequisite for PV power prediction. Due to the intra-class difference and inter-class similarity of cloud images, the classical convolutional network is obviously insufficient in distinguishing ability. In this paper, a classification method of ground-based cloud images by improved combined convolutional network is proposed. To solve the problem of subnetwork overfitting caused by redundancy of pixel information, overlap pooling kernel is used to enhance the elimination effect of information redundancy in the pooling layer. A new channel attention module, ECA-WS (Efficient Channel Attention–Weight Sharing), is introduced to improve the network’s ability to express channel information. The decision fusion algorithm is employed to fuse the outputs of sub-networks with multi-scales. According to the number of cloud images in each category, different weights are applied to the fusion results, which solves the problem of network scale limitation and dataset imbalance. Experiments are carried out on the open MGCD dataset and the self-built NRELCD dataset. The results show that the proposed model has significantly improved the classification accuracy compared with the classical network and the latest algorithms....
Our aim is to promote the widespread use of electronic insect traps that report captured pests to a human-controlled agency. This work reports on edge-computing as applied to camerabased insect traps. We present a low-cost device with high power autonomy and an adequate picture quality that reports an internal image of the trap to a server and counts the insects it contains based on quantized and embedded deep-learning models. The paper compares different aspects of performance of three different edge devices, namely ESP32, Raspberry Pi Model 4 (RPi), and Google Coral, running a deep learning framework (TensorFlow Lite). All edge devices were able to process images and report accuracy in counting exceeding 95%, but at different rates and power consumption. Our findings suggest that ESP32 appears to be the best choice in the context of this application according to our policy for low-cost devices....
Human–computer interactions (HCIs) use computer technology to manage the interfaces between users and computers. Object detection systems that use convolutional neural networks (CNNs) have been repeatedly improved. Computer vision is also widely applied to multiple specialties. However, self-checkouts operating with a faster region-based convolutional neural network (faster R-CNN) image detection system still feature overlapping and cannot distinguish between the color of objects, so detection is inhibited. This study uses a mask R-CNN with data augmentation (DA) and a discrete wavelet transform (DWT) in lieu of a faster R-CNN to prevent trivial details in images from hindering feature extraction and detection for deep learning (DL). The experiment results show that the proposed algorithm allows more accurate and efficient detection of overlapping and similarly colored objects than a faster R-CNN with ResNet 101, but allows excellent resolution and real-time processing for smart retail stores....
As traditional cloud computing is not efficient enough to support large-scale computational task execution in IoT environments, a task offloading and resource allocation algorithm for mobile edge computing (MEC) is proposed in this paper. First, a multiuser computation offloading model is constructed, including a communication model and computation offloading model, which is transformed into the minimization of users’ time delay and energy consumption (i.e., total system overhead) in the MEC system. Then, the task offloading model is formulated into a Markov decision process, and an offloading strategy based on a deep Q network (DQN) is designed to dynamically make fine tunings on the offloading proportion of each user so as to realize a low-cost MEC system. The proposed algorithm is analyzed based on the constructed simulation platform. The simulation results show that when the number of user terminals is 40, the average delay of the proposed algorithm does not exceed 0.9 s, and the average energy consumption tends to 65 J, which is better than the comparison method. Therefore, the proposed algorithm has certain application prospects....
The problem surrounding convolutional neural network robustness and noise immunity is currently of great interest. In this paper, we propose a technique that involves robustness estimation and stability improvement. We also examined the noise immunity of convolutional neural networks and estimated the influence of uncertainty in the training and testing datasets on recognition probability. For this purpose, we estimated the recognition accuracies of multiple datasets with different uncertainties; we analyzed these data and provided the dependence of recognition accuracy on the training dataset uncertainty. We hypothesized and proved the existence of an optimal (in terms of recognition accuracy) amount of uncertainty in the training data for neural networks working with undefined uncertainty data. We have shown that the determination of this optimum can be performed using statistical modeling. Adding an optimal amount of uncertainty (noise of some kind) to the training dataset can be used to improve the overall recognition quality and noise immunity of convolutional neural networks....
Loading....