Ablation Experiments Research Articles

Cadherin 16 promotes sensory gating via the endocrine corpuscles of Stannius.

Sensory thresholds enable animals to regulate their behavioral responses to environmental threats. Despite the importance of sensory thresholds for animal behavior and human health, we do not yet have a full appreciation of the underlying molecular-genetic and circuit mechanisms. The larval zebrafish acoustic startle response provides a powerful system to identify molecular mechanisms underlying establishment of sensory thresholds and plasticity of thresholds through mechanisms like habituation. Using this system, we identify Cadherin 16 as a previously undescribed regulator of sensory gating. We demonstrate that Cadherin 16 regulates sensory thresholds via an endocrine organ, the corpuscle of Stannius (CS), which is essential in zebrafish for regulating Ca 2+ homeostasis. We further show that Cadherin 16 regulates whole-body calcium and ultimately behavior through the hormone Stanniocalcin 1L, and the IGF-regulatory metalloprotease, Papp-aa. Finally, we demonstrate the importance of the CS through ablation experiments that reveal its role in promoting normal acoustic sensory gating. Together, our results uncover a previously undescribed brain non-autonomous pathway for the regulation of behavior and establish Ca 2+ homeostasis as a critical process underlying sensory gating in vivo .

SDAM: A dual attention mechanism for high-quality fusion of infrared and visible images.

Image fusion of infrared and visible images to obtain high-quality fusion images with prominent infrared targets has important applications in various engineering fields. However, current fusion processes encounter problems such as unclear texture details and imbalanced infrared targets and texture detailed information, which lead to information loss. To address these issues, this paper proposes a method for infrared and visible image fusion based on a specific dual-attention mechanism (SDAM). This method employs an end-to-end network structure, which includes the design of channel attention and spatial attention mechanisms. Through these mechanisms, the method can fully exploit the texture details in the visible images while preserving the salient information in the infrared images. Additionally, an optimized loss function is designed to combine content loss, edge loss, and structure loss to achieve better fusion effects. This approach can fully utilize the texture detailed information of visible images and prominent information in infrared images, while maintaining better brightness and contrast, which improves the visual effect of fusion images. Through conducted ablation experiments and comparative evaluations on public datasets, our research findings demonstrate that the SDAM method exhibits superior performance in both subjective and objective assessments compared to the current state-of-the-art fusion methods.

Contact State Recognition for Dual Peg-in-Hole Assembly of Tightly Coupled Dual Manipulator

Contact state recognition is a critical technology for enhancing the robustness of robotic assembly tasks. There have been many studies on contact state recognition for single-manipulator, single peg-in-hole assembly tasks. However, as the number of pegs and holes increases, the contact state becomes significantly more complex. Additionally, when a tightly coupled multi-manipulator is required, the estimation errors in the contact forces between pegs and holes make contact state recognition challenging. The current state recognition methods have not been tested in such tasks. This paper tested Support Vector Machine (SVM) and several neural network models on these tasks and analyzed the recognition accuracy, precision, recall, and F1 score. An ablation experiment was carried out to test the contributions of force, image, and position to the recognition performance. The experimental results show that SVM has better performance than the neural network models. However, when the size of the dataset is limited, SVM still faces generalization issues. By applying heuristic action, this paper proposes a two-stage recognition strategy that can improve the recognition success rate of the SVM.

Tone classification of online medical services based on 1DCNN-BiLSTM

In order to improve the recognition rate of the tone classification of doctors in online medical services scenarios, we propose a model that integrates a one-dimensional convolutional neural network (1DCNN) with a bidirectional long short-term memory network (BiLSTM). Firstly, significant tone types within online medical services scenarios were identified through a survey questionnaire. Secondly, 68 features in both the time and frequency domains of doctors’ tone were extracted using Librosa, serving as the initial input for the model. We utilize the 1DCNN branch to extract local features in the time and frequency domains, while the BiLSTM branch captures the global sequential features of the audio, and a feature-level fusion is performed to enhance tone classification effectiveness. When applied in online medical services scenarios, experimental results show that the model achieved an average recognition rate of 84.4% and an F1 score of 84.4%, significantly outperforming other models and effectively improving the efficiency of doctor-patient communication. Additionally, a series of ablation experiments were conducted to validate the effectiveness of the 1DCNN and BiLSTM modules and the parameter settings.

BANDRP: a bilinear attention network for anti-cancer drug response prediction based on fingerprint and multi-omics.

Predicting anti-cancer drug response can help with personalized cancer treatment and is an important topic in modern oncology research. Although some methods have been used for anti-cancer drug response prediction, how to effectively integrate various features related to cancer cell lines, drugs, and their known responses is still affected by the redundant information of input features and the complex interactions between features. In this study, we propose a bilinear attention model, named BANDRP, based on multiple omics data of cancer cell lines and multiple molecular fingerprints of drugs to predict potential anti-cancer drug responses. Compared with existing models, BANDRP uses gene expression data to calculate pathway enrichment scores to enrich the features of cancer cell lines and can automatically learn the interactive information of cancer cell lines and drugs through bilinear attention networks. Benchmarking and independent tests demonstrate that BANDRP surpasses baseline models and exhibits robust generalization performance. Ablation experiments affirm the optimality of the current model architecture and feature selection scheme for our prediction task. Furthermore, analytical experiments and case studies on unknown anti-cancer drug response predictions underscore BANDRP's potential as a potent and reliable framework for predicting anti-cancer drug response.

Global and local feature extraction based on convolutional neural network residual learning for MR image denoising.

Given the different noise distribution information of global and local magnetic resonance (MR) images, this study aims to extend the current work on convolutional neural networks that preserve global structure and local details in MR image denoising tasks. This study proposed a parallel and serial network for denoising 3D MR images, called 3D-PSNet. We use the residual depthwise separable convolution block to learn the local information of the feature map, reduce the network parameters, and thus improve the training speed and parameter efficiency. In addition, we consider the feature extraction of the global image and utilize residual dilated convolution to process the feature map to expand the receptive field of the network and avoid the loss of global information. Finally, we combine both of them to form a parallel network. What's more, we integrate reinforced residual convolution blocks with dense connections to form serial network branches, which can remove redundant information and refine features to further obtain accurate noise information. The peak signal-to-noise ratio, structural similarity index measure, and root mean square error metrics of 3D-PSNet are as high as 47.79%, 99.81%, and 0.40%, respectively, achieving competitive denoising effect on three public datasets. The ablation experiments demonstrated the effectiveness of all the designed modules regarding all the evaluated metrics in both datasets. The proposed 3D-PSNet takes advantage of multi-scale receptive fields, local feature extraction and residual dense connections to more effectively restore the global structure and local fine features in MR images, and is expected to help doctors quickly and accurately diagnose patients' conditions.

LesionMix data enhancement and entropy minimization for semi-supervised lesion segmentation of lung cancer

Determining the location and contour of the lesion is a crucial prerequisite for medical diagnosis, subsequent personalized treatment plan and prognostic prediction of lung cancer. Semi-supervised learning and data augmentation methods facilitate deep learning to be used in many fields of medical imaging. In this paper, we introduce a novel data enhancement technique called LesionMix. This method involves extracting and reusing lesions from a limited amount of labeled CT data, thereby enhancing the efficiency of utilizing those labeled data. Meanwhile, we propose a two-stage semi-supervised training strategy called Entropy Minimization LesionMix (EMLM). In the first stage, features containing lesion contour information are rapidly learned through LesionMix data augmentation. Entropy minimization strategy optimizes the model parameters to alleviate overfitting as much as possible in the second stage and improves prediction confidence. Our proposed method is validated on the public dataset LIDC-IDRI and the in-house dataset GDPHLUAD. Extensive experiments demonstrate that our method achieves promising performance and outperforms seven state-of-the-art semi-supervised models; Moreover, ablation experiments validate the effectiveness of various aspects of our approach.

Novel deep‐learning model for chemical process fault detection based on DCW transformer

AbstractIn this study, a double‐channel convolutional neural network and weighted (DCW) transformer model is proposed to address the problem of insufficient extraction of local information and no attention to channel‐step information in the traditional transformer model. First, a double‐channel information extraction method is proposed, so both the channel‐step and time‐step information achieve attention; second, the local information in the time and channel dimension of the data is extracted from deep and multiple scales, improving the feature extraction capability for local information; third, the long distance dependency relationship of the data is preserved by the attention mechanism, hence, the global correlation of the data is extracted effectively; finally, using the Gumbel‐SoftMax function, the weights of the time‐step and channel‐step feature information are assigned, so the extracted feature information has been optimized. The proposed method was applied for the penicillin fermentation process to verify its efficacy. Experimental results show that the proposed method achieved a better fault detection accuracy, outperforming the existing models. Further ablation experiments were conducted to demonstrate the effectiveness of each component of the proposed model.

Feature-Selection-Based Unsupervised Transfer Learning for Change Detection from VHR Optical Images

Accurate understanding of urban land use change information is of great significance for urban planning, urban monitoring, and disaster assessment. The use of Very-High-Resolution (VHR) remote sensing images for change detection on urban land features has gradually become mainstream. However, most existing transfer learning-based change detection models compute multiple deep image features, leading to feature redundancy. Therefore, we propose a Transfer Learning Change Detection Model Based on Change Feature Selection (TL-FS). The proposed method involves using a pretrained transfer learning model framework to compute deep features from multitemporal remote sensing images. A change feature selection algorithm is then designed to filter relevant change information. Subsequently, these change features are combined into a vector. The Change Vector Analysis (CVA) is employed to calculate the magnitude of change in the vector. Finally, the Fuzzy C-Means (FCM) classification is utilized to obtain binary change detection results. In this study, we selected four VHR optical image datasets from Beijing-2 for the experiment. Compared with the Change Vector Analysis and Spectral Gradient Difference, the TL-FS method had maximum increases of 26.41% in the F1-score, 38.04% in precision, 29.88% in recall, and 26.15% in the overall accuracy. The results of the ablation experiments also indicate that TL-FS could provide clearer texture and shape detections for dual-temporal VHR image changes. It can effectively detect complex features in urban scenes.

A frequency domain enhanced multi-view neural network approach to multiaxial fatigue life prediction for various metal materials

Fatigue damages and failure widely exist in engineering structures, particularly in industries such as aerospace, automotive, and construction, where components are often subjected to complex multiaxial loading conditions. Accurate prediction of fatigue life is critical for ensuring the safety and longevity of these structures. In this study, a novel multi-view deep learning model incorporating frequency domain analysis for fatigue life prediction is proposed. The proposed model integrates a Convolutional Neural Network (CNN), a Long Short-Term Memory Network (LSTM), and FNet that combines frequency domain analysis, in a parallel structure to extract features from the loading paths of materials. These extracted features are then connected to a fully connected neural network to predict fatigue life. The model was validated using fatigue data collected from 6 different materials, encompassing 17 loading paths and 336 samples. Additionally, ablation experiments were conducted, and the extrapolation capabilities were evaluated using specifically designed test sets. The results demonstrate that the proposed model exhibits excellent predictive performance and extrapolation capabilities. We anticipate that the multi-view approach, along with its accuracy and applicability, can offer potential applications in engineering fields that require reliable, data-driven models to assess material durability under complex loading scenarios.

Sensitivity Matrix Update Method for Electrical Resistance Tomography Based on Error-Constrained Cross Fusion Residual Attention Network

Abstract Electrical resistance tomography (ERT) is an imaging technique of conductivity distribution. The image reconstruction algorithm based on the empty field sensitivity matrix is widely used because it provides an approximate solution to the complex ERT inverse problems. However, due to the soft field effect, the sensitivity matrix changes with the media distribution, leading to significant errors in image reconstruction. To address this issue, an error-constrained deep learning scheme for bubble flow, namely cross fusion residual attention network (CFRA-Net) is designed to update the sensitivity matrix during gas-liquid-solid fluidized bed operation. CFRA-Net employs a multi-head self-attention mechanism to enhance bubble features in boundary measurements, a multilevel cross fusion module to fuse empty field strength and boundary measurement information, and a novel serial-channel residual spatial attention block to boost the feature extraction capability of the model. A weighted loss function is designed to give more weight to the gas phase distribution region. Additionally, this paper establishes a dataset for gas-liquid-solid three-phase flow, considering background field conductivity variations. Validation and reliability of the proposed method are assessed through ablation, comparison, and noise experiments. The experimental results demonstrate that CFRA-Net achieves rapid updates of the sensitivity matrix, high imaging accuracy, and robust noise immunity.

On ablation characteristics based on two-temperature model involving a multivariate lattice heat capacity by ultrashort laser-irradiated in zirconia

To explore the mechanism of material removal, this paper conducts a systematic study on picosecond laser processing of zirconia by using both theory and experiment. Comparing the multivariate lattice heat capacity of the Einstein and Debye models, two-temperature model (TTM) is developed to improve the accuracy of the temperature field. Then, to verify the effectiveness of TTM proposed, ablation experiments are performed by single-pulse picosecond laser on zirconia at different laser energy density. The results show that the measured craters profiles are well agree with the simulated melting/vaporization temperature distribution. Micro-morphology is significantly affected by phase transition induced by temperature rise. Moreover, the results confirmed that increased temperature can lead to transition in zirconia crystal structure and oxygen vacancies. Finally, the effect of coupling temperature variations on the elemental and physical phase variations are focused to investigate, which can help to optimize the processing quality due to crystalline phase transitions. This study provides guidance for optimizing picosecond laser processing of zirconia.

A Robot Ground Medium Classification Algorithm Based on Feature Fusion and Adaptive Spatio-Temporal Cascade Networks

With technological advancements and scientific progress, mobile robots have found widespread applications across various fields. To enable robots to perform tasks safely and effectively in diverse and unknown environments, this paper proposes a ground medium classification algorithm for robots based on feature fusion and an adaptive spatio-temporal cascade network. Specifically, the original directional features in the dataset are first transformed into quaternion form. Then, spatio-temporal forward and reverse neighbors are identified using KD trees, and their connection strengths are evaluated via a kernel density estimation algorithm to determine the final set of neighbors. Subsequently, based on the connection strengths determined in the previous step, we perform noise reduction on the features using discrete wavelet transform. The noise-reduced features are then weighted and fused to generate a new feature representation.After feature fusion, the Adaptive Dynamic Convolutional Neural Network (ADC) proposed in this paper is cascaded with the Long Short-Term Memory (LSTM) network to further extract hybrid spatio-temporal feature information from the dataset, culminating in the final terrain classification. Experiments on the terrain type classification dataset demonstrate that our method achieves an average accuracy of 97.46% and an AUC of 99.80%, significantly outperforming other commonly used algorithms in the field. Furthermore, the effectiveness of each module in the proposed method is further demonstrated through ablation experiments.

Recognition of vehicle license plates in highway scenes with deep fusion network and connectionist temporal classification

AbstractLicense plate recognition is crucial in Intelligent Transportation Systems (ITS) for vehicle management, traffic monitoring, and security inspection. In highway scenarios, this task faces challenges such as diversity, blurriness, occlusion, and illumination variation of license plates. This article explores Recurrent Neural Networks based on Connectionist Temporal Classification (RNN‐CTC) for license plate recognition in challenging highway conditions. Four neural network models: ResNet50, ResNeXt, InceptionV3, and SENet, all combined with RNN‐CTC are comparatively evaluated. Furthermore, a novel architecture named ResNet50 Deep Fusion Network using Connectionist Temporal Classification (ResNet50‐DFN‐CTC) is proposed. Comparative and ablation experiments are conducted using the Highway License Plate Dataset of Southeast University (HLPD‐SU). Results demonstrate the superior performance of ResNet50‐DFN‐CTC in challenging highway conditions, achieving 93.158% accuracy with a processing time of 7.91 ms, outperforming other tested models. This research contributes to advancing license plate recognition technology for real‐world highway applications under adverse conditions.

SimpleTrackV2: Rethinking the Timing Characteristics for Multi-Object Tracking.

Multi-object tracking tasks aim to assign unique trajectory codes to targets in video frames. Most detection-based tracking methods use Kalman filtering algorithms for trajectory prediction, directly utilizing associated target features for trajectory updates. However, this approach often fails, with camera jitter and transient target loss in real-world scenarios. This paper rethinks state prediction and fusion based on target temporal features to address these issues and proposes the SimpleTrackV2 algorithm, building on the previously designed SimpleTrack. Firstly, to address the poor prediction performance of linear motion models in complex scenes, we designed a target state prediction algorithm called LSTM-MP, based on long short-term memory (LSTM). This algorithm encodes the target's historical motion information using LSTM and decodes it with a multilayer perceptron (MLP) to achieve target state prediction. Secondly, to mitigate the effect of occlusion on target state saliency, we designed a spatiotemporal attention-based target appearance feature fusion (TSA-FF) target state fusion algorithm based on the attention mechanism. TSA-FF calculates adaptive fusion coefficients to enhance target state fusion, thereby improving the accuracy of subsequent data association. To demonstrate the effectiveness of the proposed method, we compared SimpleTrackV2 with the baseline model SimpleTrack on the MOT17 dataset. We also conducted ablation experiments on TSA-FF and LSTM-MP for SimpleTrackV2, exploring the optimal number of fusion frames and the impact of different loss functions on model performance. The experimental results show that SimpleTrackV2 handles camera jitter and target occlusion better, achieving improvements of 1.6%, 3.2%, and 6.1% in MOTA, IDF1, and HOTA, respectively, compared to the SimpleTrack algorithm.

Underwater organisms detection algorithm based on multi‐scale perception and representation enhancement

AbstractTo address issues such as object‐background confusion and difficulties in multi‐scale object feature extraction in underwater scenarios, this article proposes an underwater organisms detection algorithm based on multi‐scale perception and representation enhancement. The key innovation of the proposed algorithm is the perception improvement of the deep learning model for underwater multi‐scale objects. First, for underwater large‐scale objects, omni‐dimensional dynamic convolution is embedded as an attention mechanism (AM) into the deep network to improve the network's sensitivity to large‐scale underwater objects. For underwater small‐scale objects, an information retention downsampling module is designed to reduce the effects of serious information loss. Then, a contextual transformer as an AM is introduced into shallow networks to strengthen the network's ability to extract features from small objects. The second innovation of the proposed algorithm is an underwater spatial pooling pyramid module which enhances the representation ability of the model. Furthermore, a lightweight decoupled head is designed to eliminate the conflict between classification and localization. The ablation experiment on the URPC dataset shows that the proposed models are effective for underwater object detection. The comparative experiments on the URPC and DUT‐USEG datasets demonstrate that the proposed algorithm achieves an advantage in detection performance compared with the mainstream detection algorithms and underwater detection algorithms.

A multi‐objective optimization model for RSU deployment in intelligent expressways based on traffic adaptability

AbstractThe intelligent expressway exemplifies a prominent application of intelligent transportation systems. Roadside units (RSUs), strategically deployed alongside roadways, serve as pivotal infrastructure in facilitating interactions within intelligent expressways. A well‐planned RSU deployment strategy is crucial for enhancing service quality, it necessitates balancing performance improvements with significant financial costs due to the limited transmission range and high deployment expenses of RSUs. To tackle these challenges, an adaptive approach for RSU deployment is proposed, which takes into account economic feasibility, service requirements, and dynamic traffic demands. A traffic adaptability‐based RSU deployment (TARD) model, which integrates factors such as deployment cost, the effectiveness of information coverage, road network topology, and traffic flow characteristics have been devised. The TARD aims to minimize deployment expenses while maximizing the benefits of information coverage and alignment with road traffic demands. The Non‐dominated Sorting Genetic Algorithm II (NSGA‐II) is employed to solve this optimization model. To validate its efficacy, simulations are conducted on the G2 expressway in Shandong Province, China, demonstrating the superior performance of the TARD compared to three other deployment strategies. Ablation experiments further underscore the critical role of tunnel deployments and comprehensive coverage along long sections in bolstering network connectivity and elevating service quality.

Advanced Multi-Label Fire Scene Image Classification via BiFormer, Domain-Adversarial Network and GCN

Detecting wildfires presents significant challenges due to the presence of various potential targets in fire imagery, such as smoke, vehicles, and people. To address these challenges, we propose a novel multi-label classification model based on BiFormer’s feature extraction method, which constructs sparse region-indexing relations and performs feature extraction only in key regions, thereby facilitating more effective capture of flame characteristics. Additionally, we introduce a feature screening method based on a domain-adversarial neural network (DANN) to minimize misclassification by accurately determining feature domains. Furthermore, a feature discrimination method utilizing a Graph Convolutional Network (GCN) is proposed, enabling the model to capture label correlations more effectively and improve performance by constructing a label correlation matrix. This model enhances cross-domain generalization capability and improves recognition performance in fire scenarios. In the experimental phase, we developed a comprehensive dataset by integrating multiple fire-related public datasets, and conducted detailed comparison and ablation experiments. Results from the tenfold cross-validation demonstrate that the proposed model significantly improves recognition of multi-labeled images in fire scenarios. Compared with the baseline model, the mAP increased by 4.426%, CP by 4.14% and CF1 by 7.04%.

The ablation behavior of diamond/Cu composites by infrared nanosecond pulsed laser

This paper investigates the material removal behavior of diamond/Cu composites by multi-passes infrared nanosecond pulsed laser ablation, focusing on the formed surface cracks, periodic ripples, profile evolution and deposition. Combining nanosecond laser ablation experiments with simulations based on thermophysical properties is then undertaken to effectively reduce the maximum thermal stress and inhibit crack initiation and propagation. Three types of cracks were identified in nanosecond laser ablation, which were influenced by the diverse thermophysical properties of the material and the temperature gradient. The periodic ripples of 300–1800 nm on the sidewalls of the machined groove on diamond grains were induced when the laser fluence approached the ablation threshold, which did not even appear on the copper matrix as the thermal effects dominate. The groove profile showed a limited change as the ablation passes further increase to be over 40 due to the plasma shielding effect inside the groove, the laser defocusing phenomenon and the increased difficulty of sputtering the molten material. In addition, the different ablation mechanisms of diamond and copper resulted in the formation of overlapping deposition layers with changed surface characteristics at varying laser energy densities. The uneven island-like recast layer affected the uniformity of the ablated grooves, which was dependent on the material microstructure and accumulated laser energy.

Density-guided and Adaptive Update Strategy for Multi-objective Particle Swarm Optimization

Abstract As a powerful optimization technique, multi-objective particle swarm optimization (MOPSO) has been paid more and more attention by scientists. However, in more complex problems, MOPSO faces the challenges of weak global search ability and easy to fall into local optimality. To address these challenges and obtain better solutions, people have proposed many variants. In this study, a density-guided and adaptive update strategy for multi-objective particle swarm optimization (DAMOPSO) is proposed. First, an adaptive grid is used to determine the mutation particles and guides. Then the Cauchy mutation operator is performed for the poorly distributed particles to expand the search space of the population. Additionally, the strategy of non-dominated sorting and hyper-region density are devised for maintaining external archives, which contribute to the uniform distribution of optimal solutions. Finally, an adaptive detection strategy based on the adjustment coefficient and conversion efficiency is designed to update the flight parameters. These approaches not only speed up the convergence of algorithms, but also balance exploitation and exploration more effectively. The proposed algorithm is compared with several representative multi-objective optimization algorithms on 22 benchmark functions; meanwhile, statistical tests, ablation experiments, analysis of stability and complexity are also performed. The experimental results demonstrate DAMOPSO is more competitive than other comparison algorithms.