Rural Remote Sensing Layout Planning Model Based on Cascaded Deep Residual Network

AN ASSESSMENT OF SPATIAL VARIATION OF LAND SURFACE CHARACTERISTICS OF MINNA, NIGER STATE NIGERIA FOR SUSTAINABLE URBANIZATION USING GEOSPATIAL TECHNIQUES

Aiming at the problem that the difference in fault data distribution caused by the variation of gear and bearing conditions during the operation of rotating machinery affects the accuracy of fault diagnosis, a multi-condition fault diagnosis approach based on whale optimization algorithm (WOA), variational mode decomposition (VMD), and deep residual shrinkage network (DRSN) is proposed. Firstly, WOA is employed to optimize the parameters of the decomposition level and the penalty factor value in VMD, enhancing its noise resistance. Subsequently, VMD processing yields several modal components, each characterized by a permutation entropy feature vector, ensuring optimal feature extraction. DRSN is then utilized, employing an attention mechanism to adaptively set soft threshold functions, thereby improving gear fault diagnosis accuracy under multiple operating conditions. Finally, the proposed method’s performance was validated through the collection of gear running signals under various conditions, and the fault diagnosis accuracy was used as the model evaluation index to conduct comparative experiments and ablation experiments. The experimental results indicate that the WOA-VMD feature extraction and DRSN fault diagnosis techniques outperform traditional methods in multi-condition gear fault diagnosis. This study provides a new effective approach for multi-condition diagnosis of rotating machinery.

Data-driven rolling-bearing fault diagnosis methods are mostly based on deep-learning models, and their multilayer nonlinear mapping capability can improve the accuracy of intelligent fault diagnosis. However, problems such as gradient disappearance occur as the number of network layers increases. Moreover, directly taking the raw vibration signals of rolling bearings as the network input results in incomplete feature extraction. In order to efficiently represent the state characteristics of vibration signals in image form and improve the feature learning capability of the network, this paper proposes fault diagnosis model MTF-ResNet based on a Markov transition field and deep residual network. First, the data of raw vibration signals are augmented by using a sliding window. Then, vibration signal samples are converted into two-dimensional images by MTF, which retains the time dependence and frequency structure of time-series signals, and a deep residual neural network is established to perform feature extraction, and identify the severity and location of the bearing faults through image classification. Lastly, experiments were conducted on a bearing dataset to verify the effectiveness and superiority of the MTF-ResNet model. Features learned by the model are visualized by t-SNE, and experimental results indicate that MTF-ResNet showed better average accuracy compared with several widely used diagnostic methods.

Remote Sensing (RS) images capture spatial-temporal data on the Earth's surface that is valuable for understanding geographical changes over time. Change detection (CD) is applied in monitoring land use patterns, urban development, evaluating disaster impacts among other applications. Traditional CD methods often face challenges in distinguishing between changes and irrelevant variations in data, arising from comparison of pixel values, without considering their context. Deep feature based methods have shown promise due to their content extraction capabilities. However, feature extraction alone might not be enough for accurate CD. This study proposes incorporating spatial-temporal dependencies to create contextual understanding by modelling relationships between images in space and time dimensions. The proposed model processes dual time points using parallel encoders, extracting highly representative deep features independently. The encodings from the dual time points are then concatenated and passed through Long Short Term Memory (LTSM) layers and a decoder. The output from the LSTM is then concatenated with that from the decoder in a space-time feature fusion. This optimizes information representation of spectral, spatial and temporal details, in RS images before further analysis of change. This approach aims to maximize authentic information while reducing noise interference by introducing the context of change. Compared to conventional CD methods, the proposed technique achieves higher overall accuracy of 97.4%, an F1 Score of 89% and an intersection over union (IoU) of 86.7 when evaluated on the EGY-BCD dataset. The results demonstrate the potential of incorporating spatial-temporal dependencies in CD tasks for RS images.

Automatic semantic segmentation has expected increasing interest for researchers in recent years on multispectral remote sensing (RS) system. The agriculture supports 58 % of the population, in which 51 % of geographical area is under cultivation. Furthermore, the RS in agriculture can be used for identification, area estimation and monitoring, crop detection, soil mapping, crop yield modelling and production modelling etc. The RS images are high resolution images which can be used for agricultural and land cover classifications. Due to its high dimensional feature space, the conventional feature extraction techniques represent a progress of issues when handling huge size information e.g., computational cost, processing capacity and storage load. In order to overcome the existing drawback, we propose an automatic semantic segmentation without losing the significant data. In this paper, we use SOMs for segmentation purpose. Moreover, we proposed the particle swarm optimization technique (PSO) algorithm for finding cluster boundaries directly from the SOMs. On the other hand, we propose the deep residual network to achieve faster training process. Deep Residual Networks have been proved to be a very successful model on RS image classification. The main aim of this work is to achieve the overall accuracy greater than 85 % (OA > 85 %). So, we use a convolutional neural network (CNN), which outperforms better classification of certain crop types and yielding the target accuracies more than 85 % for all major crops. Furthermore, the proposed methods achieve good segmentation and classification accuracy than existing methods. The simulation results are further presented to show the performance of the proposed method applied to synthetic and real-world datasets.

Due to the favorable denoising performance of the discriminative learning model, a large number of discriminative learning models have been designed to remove noise. However, most discriminative learning models can only deal with the noise that already exists in the training data. In this paper, a multi-scale trainable deep residual convolutional neural network (DCMSNet) based on dilated convolution is proposed. DCMSNet consists of a chain of dilated convolution layers, convolution layers, normalized multi-scale convolution blocks (BNMCBlock), multi-scale convolution blocks (MCBlock) and multi-scale dropout convolution blocks (MCDBlock). The use of dilated convolution can avoid over-parameterization problems caused by too deep networks. In order to capture more feature information during feature extraction and image reconstruction, we designed novel BNMCBlock and MCBlock. In order to reduce the degree of coupling between image features and improve the generalization ability of the network, we also designed a MCDBlock. Meanwhile, residual learning, batch normalization and dropout are utilized to speed up the training process and boost the denoising performance. Unlike existing denoising models, DCMSNet is able to remove different degrees of noise. Compared with state-of-the-art image denoising methods, DCMSNet has achieved relatively competitive results.

Uyo is one of the fastest-growing cities in Nigeria. In recent years, there has been a widespread change in land use, yet to date, there is no thorough mapping of vegetation change across the area. This study focuses on land use change, urban development, and the driving forces behind natural vegetation loss in Uyo. Based on time series Landsat Thematic Mapper (TM)/Enhanced Thematic Mapper Plus (ETM+)/Operational Land Imager (OLI) image data, the relationships between urban land development and its influencing factors from 1985 to 2018 were analyzed using remote sensing (RS) and time series data. The results show eight land use cover classes. Three of these (forest, swamp vegetation, and mixed vegetation) are related to natural vegetation, and three (sparse built-up, dense built-up, and borrow pit) are direct consequences of urban infrastructure development changes to the landscape. Swamp vegetation, mixed vegetation, and forest are the most affected land use classes. Thus, the rapid growth of infrastructure and industrial centers and the rural and urban mobility of labor have resulted in an increased growth of built-up land. Additionally, the growth pattern of built-up land in Uyo corresponds with socioeconomic interviews conducted in the area. Land use changes in Uyo could be attributed to changes in economic structure, urbanization through infrastructure development, and population growth. Normalized difference vegetation index (NDVI) analysis shows a trend of decreasing vegetation in Uyo, which suggests that changes in economic structure represent a key driver of vegetation loss. Furthermore, the implementation of scientific and national policies by government agencies directed at reducing the effects of urbanization growth should be strengthened, in order to calm the disagreement between urban developers and environmental managers and promote sustainable land use.

Scene recognition is quite important in the field of robotics and computer vision. Aiming at providing high performance and universality of feature extraction, a convolutional neural network-based scene recognition model entitled Scene-RecNet is proposed. To reduce parameter space and improve the feature quality, deep residual network is introduced as the feature extractor. A feature adjustment layer composed of a convolutional layer and a fully connected layer is added after the feature extractor to further synthesize and compress the extracted features. Migration learning-based ‘pre-training and fine-tuning’ mode is used to train Scene-RecNet. The feature extractor is pre-trained by ImageNet, and the overall network performance is fine-tuned on specific data sets. Experiments show that comparing with other algorithms, the features obtained by Scene-RecNet have high generality and robustness, and Scene-RecNet can provide better scene classification accuracy rate.

In recent decades, it is easy to obtain remote sensing images which have been successfully applied to various applications, such as urban planning, hazard monitoring, etc. In particular, high resolution (HR) remote sensing (RS) images can better monitor our living environment from a broader spatial perspective. However, raw remote sensing images provide no labeling information to train a classifier, which usually is exploited to generate remote sensing maps. Based on our previous work, in the paper, an automatic classification system is proposed to classify high resolution urban RS images using deep neural networks, in particular, convolutional neural networks and fully convolutional networks. The labeling information is assigned on the context of both social media photos and HR remote sensing images by significantly reducing the cost of manual labeling without the necessity of remote sensing experts. The experiments carried out on high resolution remote sensing images acquired in the city Frankfurt taken by the Jilin-1 satellites confirm the effectiveness of the proposed strategy compared to the state of the art.

As one of the representative algorithms of convolutional neural networks, deep residual network has achieved very good results in computer vision, classification and other fields. Deep residual networks redefine the way networks learn, allowing networks to directly learn the difference between input and output information. This paper takes the deep residual network as the main research object, introduces the innovation of the deep residual network, and uses the deep residual network and other neural network models to train on different datasets. It is found that the highest accuracy of the test set of the deep residual network on the MNIST dataset is 0.555% higher than that of LeNet. 0.225% higher than AlexNet; The maximum accuracy of the test set on the CIFAR-10 dataset is 23.13% higher than LeNet and 2.46% higher than AlexNet.

As an important part of the power system, gas insulated switchgear (GIS) will cause serious failures once they break down, threatening the safety of the entire power grid. In the construction of the Ubiquitous Power Internet of Things (UPIoT), the intelligent terminal taking online monitoring as the means keeps the equipment fault samples and forms the sample database, which is of great significance to discover the latent insulation defects of GIS and take necessary measures in advance to ensure the safe and reliable operation of power grid. Aiming at the sample database provided by the intelligent terminal of the Internet of things, this paper proposes a method of GIS partial discharge (PD) using the depth residual network, which effectively improves the accuracy of model recognition. Although the comprehensiveness of the sample has been solved, as a transitional stage, the sample size is relatively small. Therefore, this paper uses transfer learning to solve the problem of high accuracy under the sample. In order to compare the state of art performance of the proposed method, some traditional convolutional networks such as LeNet, AlexNet, and VGG16 are used for comparison. After verification, the recognition accuracy of the deep residual network proposed in this paper is 94.6%, which is significantly higher than other models. At the same time, the parameter amount and storage space of the deep residual network are also significantly lower than those of other networks, further verifying that the model has a broad application space in the UPIoT context.

The image captured by the camera in the rainy day contains a large amount of rain mark information. The existence of such a large amount of rain mark information will cause the background information of the image to be highly blurred, which will affect the visual effect of people's observation or the processing effect of subsequent algorithms. The deep residual network (ResNet) solves the problem that the accuracy of the network reaches saturation and then degenerates sharply when the number of network layers increases. This method is now widely used in various fields of computer vision. The use of deep residual networks to remove rain marks in images is a hot topic of research. Existing deep learning methods usually require a large number of positive and negative samples to train the network.How to train the rain well with fewer samples is a problem that needs to be solved in the field.By improving the rensnet network and densenet network, we propose a rain removal method based on densely connected deep residual network images. First, use a guided filter to extract the detailed information of the image to generate a detailed image, and then train the detailed image through the constructed multi-scale deep residual network to extract Raindrop information.The extracted rainfall marker information is formed into a negative residual map. We can add the synthesized image with rain to the negative residual map to achieve the effect of rain removal.

Salient object detection is a fundamental problem in both pattern recognition and image processing tasks. Previous salient object detection algorithms usually involve various features based on priors/assumptions about the properties of the objects. Inspired by the effectiveness of recently developed feature learning, we propose a novel deep salient object detection (DSOD) model using the deep residual network (ResNet 152-layers) for saliency computation. In particular, we model the image saliency from both local and global perspectives. In the local feature estimation stage, we detect local saliency by using a deep residual network (ResNet-L) which learns local region features to determine the saliency value of each pixel. In the global feature extraction stage, another deep residual network (ResNet-G) is trained to predict the saliency score of each image based on the global features. The final saliency map is generated by a conditional random field (CRF) to combining the local and global-level saliency map. Our DSOD model is capable of uniformly highlighting the objects-of-interest from complex background while well preserving object details. Quantitative and qualitative experiments on three benchmark datasets demonstrate that our DSOD method outperforms state-of-the-art methods in the salient object detection.

To overcome the difficulty of automating and intelligently classifying the ground features in remote-sensing hyperspectral images, machine learning methods are gradually introduced into the process of remote-sensing imaging. First, the PaviaU, Botswana, and Cuprite hyperspectral datasets are selected as research subjects in this study, and the objective is to process remote-sensing hyperspectral images via machine learning to realize the automatic and intelligent classification of features. Then, the basic principles of the support vector machine (SVM) and extreme learning machine (ELM) classification algorithms are introduced, and they are applied to the datasets. Next, by adjusting the parameter estimates using a restricted Boltzmann machine (RBM), a new terrain classification model of hyperspectral images that is based on a deep belief network (DBN) is constructed. Next, the SVM, ELM, and DBN classification algorithms for hyperspectral image terrain classification are analysed and compared in terms of accuracy and consistency. The results demonstrate that the average detection accuracies of ELM on the three datasets are 89.54%, 96.14%, and 96.28%, and the Kappa coefficient values are 0.832, 0.963, and 0.924; the average detection accuracies of SVM are 88.90%, 92.11%, and 91.68%, and the Kappa coefficient values are 0.768, 0.913, and 0.944; the average detection accuracies of the DBN classification model are 92.36%, 97.31%, and 98.84%, and the Kappa coefficient values are 0.883, 0.944, and 0.972. The results also demonstrate that the classification accuracy of the DBN algorithm exceeds those of the previous two methods because it fully utilizes the spatial and spectral information of hyperspectral remote-sensing images. In summary, the DBN algorithm that is proposed in this study has high application value in object classification for remote-sensing hyperspectral images.

While the Internet of Things (IoT), coupled with integrated terrestrial-aerial-space networks, has revolutionized the domain of ubiquitous remote sensing for natural resource management, several research challenges emerge due to the explosion of the collected IoT data. For instance, the edge nodes in these hybrid, next-generation networks are anticipated to carry out edge computing on the collected data to provide localized computing to enable early warning systems, including forest fire occurrence and spread, earth- quake wave detection, tsunami forecasting, and so forth. While edge computing can significantly reduce the high communication time required in the traditional cloud-based remote sensing analytics, it is important to develop a lightweight training framework to obtain smart remote sensing analytics at the edge devices in the integrated network while preserving the privacy of the collected data. In this article, we propose an asynchronously updating federated learning model for the edge nodes to build local artificial intelligence models for smart remote sensing with a forest fire detection use case without the need for explicit data exchange with the cloud. This jointly preserves data privacy and also alleviates the network overhead. Extensive experimental results demonstrate the viability of our proposal in terms of significantly high remote sensing accuracy, low convergence time, and low bandwidth overhead compared to existing methods.