Redundant Noise Research Articles

Attribute expansion relation extraction approach for smart engineering decision‐making in edge environments

SummaryIn sedimentology, the integration of intelligent engineering decision‐making with edge computing environments aims to furnish engineers and decision‐makers with precise, real‐time insights into sediment‐related issues. This approach markedly reduces data transfer time and response latency by harnessing the computational power of edge computing, thereby bolstering the decision‐making process. Concurrently, the establishment of a sediment knowledge graph serves as a pivotal conduit for disseminating sediment‐related knowledge in the realm of intelligent engineering decision‐making. Moreover, it facilitates a comprehensive exploration of the intricate evolutionary and transformative processes inherent in sediment materials. By unveiling the evolutionary trajectory of life on Earth, the sediment knowledge graph catalyzes a deeper understanding of our planet's history and dynamics. Relationship extraction, as a key step in knowledge graph construction, implements automatic extraction and establishment of associations between entities from a large amount of sedimentary literature data. However, sedimentological literature presents multi‐source heterogeneous features, which leads to a weak representation of hidden relationships, thus decreasing the accuracy of relationship extraction. In this article, we propose an attribute‐extended relation extraction approach (AERE), which is specifically designed for sedimentary relation extraction scenarios. First, context statements containing sediment entities are obtained from the literature. Then, a cohesive hierarchical clustering algorithm is used to extend the relationship attributes between sediments. Finally, mine the relationships between entities based on AERE. The experimental results show that the proposed model can effectively extract the hidden relations and exhibits strong robustness in dealing with redundant noise before and after sentences, which in turn improves the completeness of the relations between deposits. After the relationship extraction, a proprietary sediment knowledge graph is constructed with the extracted triads.

Learning with privileged knowledge of multiple kernels via joint prediction for CT Kernel conversion.

Most existing models for CT kernel conversion take images reconstructed with a single predetermined source kernel as input and convert them to images that are reconstructed with a target kernel. However, these models can achieve even better performance if they leverage complementary information obtained from images reconstructed with multiple different kernels. In many clinical practice scenarios, only images with one kernel can beacquired. We propose a privileged knowledge learning framework that learns privileged knowledge of other source kernels available only in the training data (called privileged information) to guide the conversion from a specific single source kernel to the target kernel, via a joint prediction (JP)task. We construct an ensemble of kernel-specific (KS) tasks where a KS network (KSNet) takes images reconstructed with a specific source kernel as input and converts them to images reconstructed with the target kernel. Then, a JP task is designed to provide extra regularization, which helps each KSNet learn more informative feature representations for kernel conversion, such as detail and structure representations. Meanwhile, we use a cross-shaped window-based attention mechanism in the JP task to highlight the most relevant features to strengthen privileged knowledge learning, thereby alleviating the problems of redundant noise unrelated to images reconstructed with target kernel and inconsistent features that arise from images reconstructed with different kernels. All KSNets can be trained collaboratively by using a JP task to improve the performance of each individual KSNet. We extensively evaluate our method on a clinical dataset with scanners from three manufacturers, that is, Siemens, GE and Philips. The experimental results demonstrate that our privileged knowledge learning framework is effective in improving CT kernel conversion. Through both quantitative and qualitative research, our privileged knowledge learning framework improves the kernel conversion results, thereby contributing to the improvement of diagnostic accuracy and the advancement of comparative research in quantitativemeasurements.

Review-Enhanced Hierarchical Contrastive Learning for Recommendation

Designed to establish potential relations and distill high-order representations, graph-based recommendation systems continue to reveal promising results by jointly modeling ratings and reviews. However, existing studies capture simple review relations, failing to (1) completely explore hidden connections between users (or items), (2) filter out redundant information derived from reviews, and (3) model the behavioral association between rating and review interactions. To address these challenges, we propose a review-enhanced hierarchical contrastive learning, namely ReHCL. First, ReHCL constructs topic and semantic graphs to fully mine review relations from different views. Moreover, a cross-view graph contrastive learning is used to achieve enhancement of node representations and extract useful review knowledge. Meanwhile, we design a neighbor-based positive sampling to capture the graph-structured similarity between topic and semantic views, further performing efficient contrast and reducing redundant noise. Next, we propose a cross-modal contrastive learning to match the rating and review representations, by exploring the association between ratings and reviews. Lastly, these two contrastive learning modes form a hierarchical contrastive learning task, which is applied to enhance the final recommendation task. Extensive experiments verify the superiority of ReHCL compared with state-of-the-arts.

Structural Entropy Based Graph Structure Learning for Node Classification

As one of the most common tasks in graph data analysis, node classification is frequently solved by using graph structure learning (GSL) techniques to optimize graph structures and learn suitable graph neural networks. Most of the existing GSL methods focus on fusing different structural features (basic views) extracted from the graph, but very little graph semantics, like hierarchical communities, has been incorporated. Thus, they might be insufficient when dealing with the graphs containing noises from real-world complex systems. To address this issue, we propose a novel and effective GSL framework for node classification based on the structural information theory. Specifically, we first prove that an encoding tree with the minimal structural entropy could contain sufficient information for node classification and eliminate redundant noise via the graph's hierarchical abstraction. Then, we provide an efficient algorithm for constructing the encoding tree to enhance the basic views. Combining the community influence deduced from the encoding tree and the prediction confidence of each view, we further fuse the enhanced views to generate the optimal structure. Finally, we conduct extensive experiments on a variety of datasets. The results demonstrate that our method outperforms the state-of-the-art competitors on effectiveness and robustness.

CATNet: Cross-modal fusion for audio–visual speech recognition

Automatic speech recognition (ASR) is a typical pattern recognition technology that converts human speeches into texts. With the aid of advanced deep learning models, the performance of speech recognition is significantly improved. Especially, the emerging Audio–Visual Speech Recognition (AVSR) methods achieve satisfactory performance by combining audio-modal and visual-modal information. However, various complex environments, especially noises, limit the effectiveness of existing methods. In response to the noisy problem, in this paper, we propose a novel cross-modal audio–visual speech recognition model, named CATNet. First, we devise a cross-modal bidirectional fusion model to analyze the close relationship between audio and visual modalities. Second, we propose an audio–visual dual-modal network to preprocess audio and visual information, extract significant features and filter redundant noises. The experimental results demonstrate the effectiveness of CATNet, which achieves excellent WER, CER and converges speeds, outperforms other benchmark models and overcomes the challenge posed by noisy environments.

Data-Driven Joint Fault Diagnosis Based on RMK-ASSA and DBSKNet for Blast Furnace Iron-Making Process

Blast furnace iron-making process (BFIP) is one of the most critical procedures in the iron and steel industry where timely detection and accurate classification of faults have always been of core focus. However, the coupling effects of system’s nonlinear and nonstationary characteristics often cause process consistent underlying information to be buried, allowing accurate extraction to be a significant challenge. This also complicates the development of BFIP fault diagnosis model. Therefore, we propose a novel data-driven joint fault diagnosis strategy that employs regularized mutual kernel analytic stationary subspace analysis (RMK-ASSA) and deep broad stationary kernel network (DBSKNet) to eliminate this interference. To develop this method, we first construct an RMK-ASSA approach to address the poor modeling accuracy caused by standard analytic stationary subspace analysis (ASSA)’s inability to handle complex process nonlinearity. Global and local kernels are utilized to account for multiple nonlinearities in BFIP data. The weight of different nonlinear data is calculated by regularized principal component analysis, and the main information is imported into ASSA to obtain more robust and accurate modeling results by eliminating the interference of redundant noise. Subsequently, we design a DBSKNet-based classifier to implement the fault diagnosis task. This network further considers the nonlinearity by boosting kernel structure in depth and width while distinguishing the respective contributions of different kernels to fault diagnosis results. Finally, a double-layer loop parameter optimization algorithm is used for optimizing. Simulated cases and practical BFIP tests validate that RMK-ASSA eliminates the negative impact caused by nonstationary data and that the proposed joint fault diagnosis strategy outperforms other methods. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —BFIP’s nonlinear and nonstationary coupling properties pose unique challenges in eliminating distractions, constructing fault classifiers and accurately detecting process anomalies. To tackle these challenges, this paper proposes a joint fault diagnosis strategy based on RMK-ASSA and DBSKNet. RMK-ASSA effectively estimates nonlinear consistent features, while DBSKNet mines rich deep nonlinear information, accurately distinguishing variations in BFIP data under different working conditions. Experimental results demonstrate that this data-driven strategy can perform high-quality fault diagnosis, enabling field engineers to execute operations efficiently.

A 28 nm CMOS low-noise amplifier with novel redundant noise cancellation technique beyond ultra-wideband for 6G-based wireless systems

In the current scenario, almost 5G-based wireless systems have been deployed everywhere but still performance trade-offs of RF amplifiers in the sub-nanometer regime are challenging. In this work, a high-performance low-noise amplifier (LNA) is realized in a 28 nm CMOS process with a novel redundant noise cancellation technique (RnC). The proposed technique improves the noise figure (NF) beyond the ultra-wideband of a low-noise amplifier (LNA) and minimizes the trade-off in the 28 nm process. An ultra-low NF is achieved in two approaches; Firstly, a current mirror network is employed in the primary path to cancel the thermal noise of the dominant transistor of a common gate-common source (CG-CS) without an extra power supply. Secondly, an auxiliary amplifier stage is introduced here to reduce the noise which contributes to the current mirror circuit and cancels the distortion in CG-CS topology without violating the traditional noise cancellation condition. In addition, an analytical approach is followed to optimize the input impedance, gain bandwidth and noise figure. Hence, the proposed RnC LNA benefits in achieving good tradeoffs among gain, bandwidth, NF, and power consumption in 28 nm technology node. The proposed RnC LNA is analyzed and fabricated using CMOS 28 nm technology, occupying an area of 0.011 mm2. The proposed design achieves an optimum performance: nearly flat gain of 15.3 dB, minimum NF of 1.7 dB over 1.7 to 12.52 GHz, and an IIP3 of − 2.6 dBm at 6.5 GHz. The proposed LNA consumes ultra-low power consumption of 1.8 mW under the power supply of 1 V.

Adaptive VMD-K-SVD-Based Rolling Bearing Fault Signal Enhancement Study.

To address the challenges associated with nonlinearity, non-stationarity, susceptibility to redundant noise interference, and the difficulty in extracting fault feature signals from rolling bearing signals, this study introduces a novel combined approach. The proposed method utilizes the variational mode decomposition (VMD) and K-singular value decomposition (K-SVD) algorithms to effectively denoise and enhance the collected rolling bearing signals. Initially, the VMD method is employed to separate the overall noise into intrinsic mode functions (IMFs), reducing the noise content within each IMF. To optimize the mode component, K, and the penalty factor, α, in VMD, an improved arithmetic optimization algorithm (IAOA) is employed. This ensures the selection of optimal parameters and the decomposition of the signal into a set of IMFs, forming the original dictionary. Subsequently, the signals are decomposed into multiple IMFs using VMD, and an original dictionary is constructed based on these IMFs. K-SVD is then applied to the original dictionary to further reduce the noise in each IMF, resulting in a denoised and enhanced signal. To validate the efficacy of the proposed method, rolling bearing signals collected from Case Western Reserve University (CWRU) and thrust bearing test rigs were utilized. The experimental results demonstrate the feasibility and effectiveness of the proposed approach in denoising and enhancing the rolling bearing signals.

SiamCCF: Siamese visual tracking via cross‐layer calibration fusion

AbstractSiamese networks have attracted wide attention in visual tracking due to their competitive accuracy and speed. However, the existing Siamese trackers usually leverage a fixed linear aggregation of feature maps, which does not effectively fuse the different layers of features with attention. Besides, most of Siamese trackers calculate the similarity between the template and the search region through a cross‐correlation operation between the features of the last blocks from the two branches, which might introduce the redundant noise information. In order to solve these problems, this study proposes a novel Siamese visual tracking method via cross‐layer calibration fusion, termed SiamCCF. An attention‐based feature fusion module is employed using local attention and non‐local attention to fuse the features from the deep and shallow layers, so as to capture both local details and high‐level semantic information. Moreover, a cross‐layer calibration module can use the fused features to calibrate the features of the last network blocks and build the cross‐layer long‐range spatial and inter‐channel dependencies around each spatial location. Extensive experiments demonstrate that the proposed method has achieved competitive tracking performance compared with state‐of‐the‐art trackers on challenging benchmarks, including OTB100, OTB2013, UAV123, UAV20L, and LaSOT.

Inferring Gene Regulatory Networks via Ensemble Path Consistency Algorithm Based on Conditional Mutual Information.

Utilizing gene expression data to infer gene regulatory networks has received great attention because gene regulation networks can reveal complex life phenomena by studying the interaction mechanism among nodes. However, the reconstruction of large-scale gene regulatory networks is often not ideal due to the curse of dimensionality and the impact of external noise. In order to solve this problem, we introduce a novel algorithms called ensemble path consistency algorithm based on conditional mutual information (EPCACMI), whose threshold of mutual information is dynamically self-adjusted. We first use principal component analysis to decompose a large-scale network into several subnetworks. Then, according to the absolute value of coefficient of each principal component, we could remove a large number of unrelated nodes in every subnetwork and infer the relationships among these selected nodes. Finally, all inferred subnetworks are integrated to form the structure of the complete network. Rather than inferring the whole network directly, the influence of a mass of redundant noise could be weakened. Compared with other related algorithms like MRNET, ARACNE, PCAPMI and PCACMI, the results show that EPCACMI is more effective and more robust when inferring gene regulatory networks with more nodes.

Research and Application for Corrosion Rate Prediction of Natural Gas Pipelines Based on a Novel Hybrid Machine Learning Approach

An accurate and stable prediction of the corrosion rate of natural gas pipelines has a major impact on pipeline material selection, inhibitor filling process, and maintenance schedules. At present, corrosion data are impacted by non-linearity and noise interference. The traditional corrosion rate prediction methods often ignore noise data, and only a small number of researchers have carried out in-depth research on non-linear data processing. Therefore, an innovative hybrid prediction model has been proposed with four processes: data preprocessing, optimization, prediction, and evaluation. In the proposed model, a decomposing algorithm is applied to eliminate redundant noise and to extract the primary characteristics of the corrosion data. Stratified sampling is applied to separate the training set and the test set to avoid deviation due to the sampling randomness of small samples. An improved particle swarm optimization algorithm is applied to optimize the parameters of support vector regression. A comprehensive evaluation of this framework is also conducted. For natural gas pipelines in southwest China, the coefficient of determination and mean absolute percentage error of the proposed hybrid model are 0.925 and 5.73%, respectively, with better prediction performance compared to state-of-the-art models. The results demonstrate the best approach for improving the prediction accuracy of the proposed hybrid model. This can be applied to improve the corrosion control effect and to support the digital transformation of the corrosion industry.

Extraction of cardiac-related signals from a suprasternal pressure sensor during sleep

Objective. The accurate detection of respiratory effort during polysomnography is a critical element in the diagnosis of sleep-disordered breathing conditions such as sleep apnea. Unfortunately, the sensors currently used to estimate respiratory effort are either indirect and ignore upper airway dynamics or are too obtrusive for patients. One promising alternative is the suprasternal notch pressure (SSP) sensor: a small element placed on the skin in the notch above the sternum within an airtight capsule that detects pressure swings in the trachea. Besides providing information on respiratory effort, the sensor is sensitive to small cardiac oscillations caused by pressure perturbations in the carotid arteries or the trachea. While current clinical research considers these as redundant noise, they may contain physiologically relevant information. Approach. We propose a method to separate the signal generated by cardiac activity from the one caused by breathing activity. Using only information available from the SSP sensor, we estimate the heart rate and track its variations, then use a set of tuned filters to process the original signal in the frequency domain and reconstruct the cardiac signal. We also include an overview of the technical and physiological factors that may affect the quality of heart rate estimation. The output of our method is then used as a reference to remove the cardiac signal from the original SSP pressure signal, to also optimize the assessment of respiratory activity. We provide a qualitative comparison against methods based on filters with fixed frequency cutoffs. Main results. In comparison with electrocardiography (ECG)-derived heart rate, we achieve an agreement error of 0.06 ± 5.09 bpm, with minimal bias drift across the measurement range, and only 6.36% of the estimates larger than 10 bpm. Significance. Together with qualitative improvements in the characterization of respiratory effort, this opens the development of novel portable clinical devices for the detection and assessment of sleep disordered breathing.

Intelligent detection of IT assets in power grid enterprises based on signal processing and cyberspace

Signal processing can complete the processing of various types of signals to obtain key data. Signal processing can also filter out redundant noise signals and ensure the quality of source signals. Due to the various functions of signal processing technology, it is widely used in network security, especially in IT asset detection and other aspects. Cyberspace is a general concept, which represents all devices associated with network connections. Detecting network assets in cyberspace means finding all networked devices. The detection of IT assets for power grid enterprises can help power grid enterprise IT administrators understand enterprise IT assets. At the same time, it can also discover the security loopholes existing in the operation of the current enterprise IT assets, and use the detection results to fix the loopholes as soon as possible to prevent the occurrence of network security incidents. This paper firstly sorts out the concepts of signal processing, cyberspace and power grid IT assets, then combines CNN and signal processing technology to design an intelligent detection strategy for power grid IT assets, and compares the designed strategy with the efficiency and other indicators of traditional detection methods. In contrast, finally, a cyberspace-based IT asset intelligent detection strategy was designed, and a power grid enterprise IT asset intelligent detection system was designed. Through the deployment strategy test environment, a test case was written in Python language, and the cyberspace-based IT asset intelligent detection was found. Compared with the traditional power grid enterprise IT asset detection scheme, the strategy has better performance in all aspects. The research adopts the method of modeling and analysis to calculate the signal values of the IT assets involved as much as possible, thereby greatly reducing the possible errors in the evaluation of enterprise IT assets. The test of the results obtained by the formula shows that the IT asset detection combined with the cyberspace search method shows superiority in different indicators.

Timestamp Feature Variation based Weather Prediction Using Multi-Perception Neural Classification for Successive Crop Recommendation in Big Data Analysis

The recent generation has a lot of information for analysing growth in future prediction. Especially India is an extensive agricultural resource for the world's expansive economic growth. But in extensive data analysis, a problem for the recommendation of the seasonal crop is tedious because of improper feature analysis due to varying periods in weather conditions. So time variation-based big data analysis is essential for research improvement. To resolve this problem, we propose a Timestamp feature variation-based weather prediction using multi-perception neural classification (TFV-MPNC) for successive crop recommendation in big data analysis. Initially, the pre-processing was carried out to prepare the redundant noise dataset for fast prediction. Initially, the Preprocessing ensures the Contemporary Forecasting rate (CFR) for predicting the previous deficiency rate. Based on that Time stamp feature analysis (TSFA). The Dense region harvest rate (DRHR) was evaluated, and features were decision using Fuzzy intensive decision Function (FIDF), selected the scaled features and trained with multi-perception neural classification (MPNN). The proposed system produces higher forecasting by prediction features as well supportive to the weather dependences related to higher classification rate in precision, and recall has the best classification result.

NCT:noise-control multi-object tracking

AbstractMulti-Object Tracking (MOT) is an important topic in computer vision. Recent MOT methods based on the anchor-free paradigm trade complicated hierarchical structures for tracking performance. However, existing anchor-free MOT methods ignore the noise in detection, data association, and trajectory reconnection stages, which results in serious problems, such as missing detection of small objects, insufficient motion information, and trajectory drifting. To solve these problems, this paper proposes Noise-Control Tracker (NCT), which focuses on the noise-control design of detection, association, and reconnection. First, a prior depth denoise method is introduced to suppress the fusion feature redundant noise, which can recover the gradient information of the heatmap fusion features. Then, the Smoothing Gain Kalman filter is designed, which combines the Gaussian function with the adaptive observation coefficient matrix to stabilize the mutation noise of Kalman gain. Finally, to address the drift noise issue, the gradient boosting reconnection context mechanism is designed, which realizes adaptive trajectory reconnection to effectively fill the gaps in trajectories. With the assistance of the plug-and-play noise-control method, the experimental results on MOTChallenge 16 &amp;17 datasets indicate that the NCT can achieve better performance than other state-of-the-art trackers.

Illumination Guided Attentive Wavelet Network for Low-Light Image Enhancement

Deep convolutional neural networks have recently been applied to improve the quality of low-light images and have achieved promising results. However, most existing methods cannot suppress noise during the enhancement process effectively, resulting in unknown artifacts and color distortions. In addition, these methods do not fully utilize illumination information and perform poorly under extremely low-light condition. To alleviate these problems, we propose the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">illumination guided attentive wavelet network</i> (IGAWN) for low-light image enhancement (LLIE). Considering that the wavelet transform can separate high-frequency noise and desired low-frequency content effectively, we enhance low-light images in the frequency domain. By integrating attention mechanisms with wavelet transform, we develop the attentive wavelet transform to capture more important wavelet features, which enables the desired content to be enhanced and the redundant noise to be suppressed. To improve the image enhancement performance under extremely low-light environment, we extract illumination information from the input images and exploit it as the guidance for image enhancement through the frequency feature transform (FFT) layer. The proposed FFT layer generates frequency-aware affine transformation from the estimated illumination information, which can adaptively modulate the image features of different frequencies. Extensive experiments on synthetic and real-world datasets demonstrate that our IGAWN performs favorably against state-of-the-art LLIE methods.

Part-Aware Framework for Robust Object Tracking.

The local parts of the target are vitally important for robust object tracking. Nevertheless, existing excellent context regression methods involving siamese networks and discrimination correlation filters mostly represent the target appearance from the holistic model, showing high sensitivity in scenarios with partial occlusion and drastic appearance changes. In this paper, we address this issue by proposing a novel part-aware framework based on context regression, which simultaneously considers the global and local parts of the target and fully exploits their relationship to be collaboratively aware of the target state online. To this end, the spatial-temporal measure among context regressors corresponding to multiple parts is designed to evaluate the tracking quality of each part regressor by solving the imbalance among global and local parts. The coarse target locations provided by part regressors are further aggregated by treating their measures as weights to refine the final target location. Furthermore, the divergence of multiple part regressors in each frame reveals the interference degree of background noise, which is quantified to control the proposed combination window functions in part regressors to adaptively filter redundant noise. Besides, the spatial-temporal information among part regressors is also leveraged to assist in accurately estimating the target scale. Extensive evaluations demonstrate that the proposed framework help many context regression trackers achieve performance improvements and perform favorably against state-of-the-art methods on the popular benchmarks: OTB, TC128, UAV, UAVDT, VOT, TrackingNet, GOT-10k, LaSOT.

Sparse norm regularized attribute selection for graph neural networks

Graph Neural Networks (GNNs) have been widely used for graph learning tasks. The main aspect of GNN’s layer-wise message passing is conducting attribute/feature propagation on graph. Most existing GNNs generally conduct feature propagation across all feature dimensions. However, in many real applications, attributes usually contain irrelevant and redundant noise. In this case, attribute/feature selection is desired to extract meaningful features and eliminate noisy ones for GNN’s layer-wise propagation. Based on this observation, in this paper, we combine ℓ2,1/ℓ1-norm regularized attribute selection and GNNs together and propose a novel Attribute selection guided GNNs (AsGNNs) for graph data representation.AsGNNs aim to adaptively select some desired meaningful features/attributes that best serve GNNs. Moreover, an effective optimization framework has also been derived to train the proposed AsGNNs. The proposed AsGNNs provide a general framework which can incorporate any GNNs to conduct feature selection for layer-wise propagation. In this paper, we implement AsGNNs on both graph convolutional network (GCN) and graph attention network (GAT) and develop AsGCN and AsGAT for graph learning. Experimental results on several benchmark datasets demonstrate the effectiveness of the proposed AsGNNs (AsGCN, AsGAT) on semi-supervised learning tasks.

LightFGCNet: A Lightweight and Focusing on Global Context Information Semantic Segmentation Network for Remote Sensing Imagery

Convolutional neural networks have attracted much attention for their use in the semantic segmentation of remote sensing imagery. The effectiveness of semantic segmentation of remote sensing images is significantly influenced by contextual information extraction. The traditional convolutional neural network is constrained by the size of the convolution kernel and mainly concentrates on local contextual information. We suggest a new lightweight global context semantic segmentation network, LightFGCNet, to fully utilize the global context data and to further reduce the model parameters. It uses an encoder–decoder architecture and gradually combines feature information from adjacent encoder blocks during the decoding upsampling stage, allowing the network to better extract global context information. Considering that the frequent merging of feature information produces a significant quantity of redundant noise, we build a unique and lightweight parallel channel spatial attention module (PCSAM) for a few critical contextual features. Additionally, we design a multi-scale fusion module (MSFM) to acquire multi-scale feature target information. We conduct comprehensive experiments on the two well-known datasets ISPRS Vaihingen and WHU Building. The findings demonstrate that our suggested strategy can efficiently decrease the number of parameters. Separately, the number of parameters and FLOPs are 3.12 M and 23.5 G, respectively, and the mIoU and IoU of our model on the two datasets are 70.45% and 89.87%, respectively, which is significantly better than what the conventional convolutional neural networks for semantic segmentation can deliver.

A multi-dimensional residual shrinking network combined with a long short-term memory network for state of charge estimation of Li-ion batteries

The multi-dimensional interaction and noise interference of the original data increase the difficulty of state-of-charge (SoC) estimation. Meanwhile the existing SoC estimators prefer to estimate the SoC of consecutive time steps, which may lead to cumulative errors and data leakage. To solve these problems, a fusion network combining a multi-dimensional residual shrinkage network (MRSN) with a long short-term memory network (LSTM) is proposed for SoC estimation. Meanwhile, a sequence-to-point processing method is utilized to avoid data leakage, which is based on historical input data for estimating SoC at a single time step. Specifically, MRSN uses small sub-networks to remove redundant noise and extracts multi-scale local features on different channels to obtain stronger correlation features. LSTM uses historical inputs to obtain multi-scale temporal correlation. After that the features extracted by both networks are fused in the channel dimension to enhance the accuracy of SoC estimation. Experiments on the public dataset show that the mean absolute error (MAE) of the results is kept within 0.5 % under four different temperature conditions. Furthermore, the MAE is 0.18 % at 25 degrees, which verifies that the proposed network could significantly improve the accuracy of the estimation.