Enhancement Characteristics Research Articles

Multi-modal fusion and feature enhancement U-Net coupling with stem cell niches proximity estimation for voxel-wise GBM recurrence prediction.

Objective.We aim to develop a Multi-modal Fusion and Feature Enhancement U-Net (MFFE U-Net) coupling with stem cell niche proximity estimation to improve voxel-wise Glioblastoma (GBM) recurrence prediction.Approach.57 patients with pre- and post-surgery magnetic resonance (MR) scans were retrospectively solicited from 4 databases. Post-surgery MR scans included two months before the clinical diagnosis of recurrence and the day of the radiologicaly confirmed recurrence. The recurrences were manually annotated on the T1ce. The high-risk recurrence region was first determined. Then, a sparse multi-modal feature fusion U-Net was developed. The 50 patients from 3 databases were divided into 70% training, 10% validation, and 20% testing. 7 patients from the 4th institution were used as external testing with transfer learning. Model performance was evaluated by recall, precision, F1-score, and Hausdorff Distance at the 95% percentile (HD95). The proposed MFFE U-Net was compared to the support vector machine (SVM) model and two state-of-the-art neural networks. An ablation study was performed.Main results.The MFFE U-Net achieved a precision of 0.79 ± 0.08, a recall of 0.85 ± 0.11, and an F1-score of 0.82 ± 0.09. Statistically significant improvement was observed when comparing MFFE U-Net with proximity estimation couple SVM (SVMPE), mU-Net, and Deeplabv3. The HD95 was 2.75 ± 0.44 mm and 3.91 ± 0.83 mm for the 10 patients used in the model construction and 7 patients used for external testing, respectively. The ablation test showed that all five MR sequences contributed to the performance of the final model, with T1ce contributing the most. Convergence analysis, time efficiency analysis, and visualization of the intermediate results further discovered the characteristics of the proposed method.Significance. We present an advanced MFFE learning framework, MFFE U-Net, for effective voxel-wise GBM recurrence prediction. MFFE U-Net performs significantly better than the state-of-the-art networks and can potentially guide early RT intervention of the disease recurrence.

Exploring the Correlation between Morpho-physiological Traits and Growth Attributes Associated with Yield Characteristics in Rice (Oryza sativa L.)

This study aimed to identify the morpho-physiological and growth attributes, and yield associated with yield in rice genotypes. The experiment included 120 rice genotypes and 3 checks, conducted in an alpha lattice design with two replications at the Research Cum Instructional Farm in the Department of Plant Physiology, Indira Gandhi Krishi Vishawavidyalaya, Raipur, Chhattisgarh, during the two consecutive Kharif seasons of 2021-22 and 2022-23. Conventional spacing of 15 x 20 cm and recommended cultural practices were employed. The objective is to improve the overall efficiency and productivity of rice cultivation to meet the needs of a growing population. It is crucial to emphasize the comprehension and enhancement of the fundamental features associated with canopy structure and growth attributes. Improving these morpho-physiological traits is pivotal for boosting rice yield. By studying and refining the arrangement and growth of the rice plant's leaf canopy, the goal is to enhance the efficiency and productivity of rice cultivation. The results indicated that productive tillers (0.335**) and flag leaf area (0.213*) were positively correlated with higher yields. While leaf angles, specific leaf area, and days to panicle initiation showed negative correlations with yield. The leaf area index at flowering was positively correlated with specific leaf area (0.382***) but negatively with grain yield (-0.199*). Specific leaf weight was positively correlated with yield per hectare (0.178*). Understanding these relationships can guide the selection and breeding of rice genotypes with optimal traits for enhanced grain yield and crop performance.

Improved Facial Expression Recognition Algorithm Based on Local Feature Enhancement and Global Information Association

Facial expression recognition is the key area of research in computer vision, enabling intelligent devices to understand human emotions and intentions. However, recognition of facial expressions in natural scenes presents challenges due to environmental factors like occlusion and pose variations. To address this, we propose a novel approach that combines local feature enhancement and global information correlation. This method allows the model to learn both local and global facial features along with contextual information. By enhancing salient local features and exploring multi-scale facial expression features, our model effectively mitigates the impact of occlusion and pose variations, improving recognition accuracy. Experimental results demonstrate that our adapted model outperforms alternative algorithms in recognizing facial expressions under challenging environments, achieving recognition accuracies of 85.07% and 99.35% on the RAF-DB and CK+ datasets, respectively.

High-performance real-time fire detection and forecasting framework for industrial cables

In industrial scenarios, cable fires have always been the most common threat, and traditional fire detection systems often rely on a large number of sensors, and the detection range is very limited, and it is impossible to effectively predict the fire situation in time. In this paper, we propose a detection and prediction scheme for industrial cable fire, which breaks the limitations of the previous research on multi-sensor signal input, and highly couples the detection and prediction modules to realize fire prediction based on video image input only. In fire detection, we design an object detection model using HSV for flame feature enhancement based on YOLOv8, and in fire prediction aspect, we use iTransformer as a time series prediction model to mine the correlation between various parameters to predict the spread of fire. In the experiments, the average absolute percentage error of the flame detection model for the detection of flame height, width and longitudinal position was 3.49%–10.64 %, 2.45%–8.89 % and 1.61%–9.31 %, respectively, and the MAPE of the time series prediction model for the above three parameters was 11.18%–15.06 % and 4.35%–8.18 %, 3.37%–6.62 %.The results of the above experiments verify that the proposed model has the ability to quantitatively analyze the fire spread trend in the actual fire and help firefighters make decisions.

Multi-Frequency Spectral–Spatial Interactive Enhancement Fusion Network for Pan-Sharpening

The objective of pan-sharpening is to effectively fuse high-resolution panchromatic (PAN) images with limited spectral information and low-resolution multispectral (LR-MS) images, thereby generating a fused image with a high spatial resolution and rich spectral information. However, current fusion techniques face significant challenges, including insufficient edge detail, spectral distortion, increased noise, and limited robustness. To address these challenges, we propose a multi-frequency spectral–spatial interaction enhancement network (MFSINet) that comprises the spectral–spatial interactive fusion (SSIF) and multi-frequency feature enhancement (MFFE) subnetworks. The SSIF enhances both spatial and spectral fusion features by optimizing the characteristics of each spectral band through band-aware processing. The MFFE employs a variant of wavelet transform to perform multiresolution analyses on remote sensing scenes, enhancing the spatial resolution, spectral fidelity, and the texture and structural features of the fused images by optimizing directional and spatial properties. Moreover, qualitative analysis and quantitative comparative experiments using the IKONOS and WorldView-2 datasets indicate that this method significantly improves the fidelity and accuracy of the fused images.

LHFFNet: A hybrid feature fusion method for lane detection

Lane line images have the essential attribute of large-scale variation and complex scene information, and the similarity between adjacent lane lines is high, which can easily cause classification errors. And remote lane lines are difficult to recognize due to visual angle changes in width. To address this issue, this paper proposes an effective lane detection framework, which is a hybrid feature fusion network that enhances multiple spatial features and distinguishes key features throughout the entire lane line segment. It enhances and fuses lane line features at multiscale to enhance the feature representation of lane line images, especially at the far end. Firstly, in order to enhance the correlation of multiscale lane features, a multi-head self attention is used to construct a multi-space attention enhancement module for feature enhancement in multispace. Secondly, a spatial separable convolutional branch is designed for the jumping layer structure connecting multiscale lane line features. While retaining feature information of different scales, important lane areas in multiscale feature information are emphasized through the allocation of spatial attention weights. Finally, considering that lane lines are elongated areas in the image, and the background information in the image is much more abundant than lane line information, the flexibility of traditional pooling operations in capturing widely existing anisotropic contexts in actual environments is limited. Therefore, before embedding feature output branches, strip pooling is introduced to refine the representation of lane line information and optimize model performance. The experimental results show that the accuracy on the TuSimple dataset reaches 96.84%, and the F1 score on the CULane dataset reaches 75.9%.

A two-stream-network based steganalysis network: TSNet

The three-stage framework consisting of preprocessing, feature extraction and classification is the most commonly used structure in traditional deep learning based steganalysis networks (SNs). Preprocessing, as the core part of the three-stage framework, typically adopts fixed high-pass filters to generate filter residuals, and exploits a feature enhancement module following high-pass filters to improve signal-to-noise ratio of the stego signal, thus strengthening the expression of steganographic features. However, fixed high-pass filters can only provide filter residuals through the linear relationships, rather than complex dependencies automatically learned, among local pixels, which suggests that fixed high-pass filters lack powerful ability of extracting comprehensive steganographic features from the beginning of SNs. Inspired by the motivation, a two-stream-network based SN called TSNet is proposed to extract comprehensive steganographic features from two different perspectives, namely automatic learning and fixed filtering. The discrete cosine transform attention mechanism (DCTAM)-based fusion module (DCTAM-FM) with considering the steganalysis properties is proposed to fuse two streams and enhance channel representation using DCTAM, which is conductive to improving the detection accuracy. Two streams aim to explore different types of residuals from two perspectives, but inevitably lead to a considerable number of parameters and high computational complexity. To this end, the feature extraction stage contains lightweight depthwise separable convolution blocks and the linearly increasing style of the number of channels. Combining the two-stream network, DCTAM-FM as well as the lightweight feature extraction stage, TSNet obtains deep composite features, which can fully express the comprehensive steganographic features, and thus brings a high detection accuracy. Experimental results from three benchmark datasets demonstrate that TSNet outperforms current state-of-the-art methods in detection accuracy and has an acceptable computational complexity.

Event-driven weakly supervised video anomaly detection

Inspired by the observations of human working manners, this work proposes an event-driven method for weakly supervised video anomaly detection. Complementary to the conventional snippet-level anomaly detection, this work designs an event analysis module to predict the event-level anomaly scores as well. It first generates event proposals simply via a temporal sliding window and then constructs a cascaded causal transformer to capture temporal dependencies for potential events of varying durations. Moreover, a dual-memory augmented self-attention scheme is also designed to capture global semantic dependencies for event feature enhancement. The network is learned with a standard multiple instance learning (MIL) loss, together with normal-abnormal contrastive learning losses. During inference, the snippet- and event-level anomaly scores are fused for anomaly detection. Experiments show that the event-level analysis helps to detect anomalous events more continuously and precisely. The performance of the proposed method on three public datasets demonstrates that the proposed approach is competitive with state-of-the-art methods.

Multi-query and multi-level enhanced network for semantic segmentation

Plain transformer-based methods have achieved promising performance on semantic segmentation recently. These methods adopt a single set of class queries to predict masks of different semantic categories based on multi-level feature maps. We argue that this single-query design cannot fully exploit diverse information of different levels for improved semantic segmentation. To address this issue, we propose a multi-query and multi-level enhanced network for semantic segmentation (named QLSeg). Our QLSeg first performs multi-level feature enhancement on plain transformer to improve feature discriminability. Afterwards, we introduce multi-query decoder to respectively extract feature embeddings and predict mask logits at different levels, where feature embeddings are adaptively merged for classification and mask logits are summed for output masks. In addition, we introduce masked attention-to-mask to focus on local regions with the same class. We perform the experiments on three widely-used semantic segmentation datasets: ADE20K, COCO-Stuff-10K, and PASCAL-Context. Our proposed QLSeg achieves competitive results on all these three datasets.

Adaptive Optimal Resonance Fault Feature Enhancement for Wind Turbine Based on Frequency Search and Uncertainty Analysis

The wind turbine fault feature has strong uncertainty due to various factors such as wind speed and equipment parameters. Based on the analysis of the vibration characteristics of wind turbines with unknown prior conditions, this paper conducts research on the enhancement method of fault features. First, analyzing the change in fault features caused by the change in operating conditions to lay the foundation for subsequent research; Second, for the uncertainty of wind turbine fault feature frequency, searching for fault features by constructing the energy in each spectral interval, then use signal noise optimal resonance to transfer noise energy to low frequency fault features to achieve the purpose of adaptive optimal resonance enhancement of fault feature; Finally, validation of the proposed method by simulation experiments and fault signals of actual wind turbine rolling bearings. The case shows that the proposed algorithm can effectively realize the uncertain fault feature of wind turbines search and enhancement. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

SCECNet: self-correction feature enhancement fusion network for remote sensing scene classification

SCECNet: self-correction feature enhancement fusion network for remote sensing scene classification

DEM super-resolution guided by shaded relief using attention-based fusion

Deep-learning based approaches have been proven effective for Digital Elevation Model (DEM) super-resolution (SR) tasks. Previous networks typically treat DEM elevation values as single-channel image for input. However, DEM images alone cannot fully capture spatial and terrain features. Shaded relief images (SRIs), derived from DEMs, serve as crucial visual cues that intuitively convey terrain characteristics, addressing the limitations of DEM images and providing synergistic benefits for training DL models. The primary challenge in utilizing SRIs for guiding DEM SR lies in accurately selecting a consistent structure to extract and effectively integrate features from SRIs and DEMs. In this study, we propose an Attention-based Hierarchical Terrain Fusion (AHTF) framework for guided DEM SR. Specifically, an Attention-based Feature Fusion Module (AFFM) is designed to efficiently fuse relevant information from LR DEM and SRI, which includes a feature enhancement block to select valuable features and a feature recalibration block to fuse diverse terrain features. Additionally, we optimize the loss function from the perspectives of terrain analysis and visual effects. We validate AHTF on our newly constructed real-world Shade-DEM SR dataset and two open-source DEM SR datasets. Compared to the current state-of-the-art methods, our AHTF achieves the best results in terms of root mean square error (RMSE) for elevation, slope, and aspect. Furthermore, the extracted stream networks are closer to real-world conditions. This study offers new insights and methods for further research and application in the field of DEM super-resolution. Our dataset can be obtained at https://doi.org/10.6084/m9.figshare.25590945.

Feature-Enhanced Multi-Task Learning for Speech Emotion Recognition Using Decision Trees and LSTM

Speech emotion recognition (SER) plays an important role in human-computer interaction (HCI) technology and has a wide range of application scenarios in medical medicine, psychotherapy, and other applications. In recent years, with the development of deep learning, many researchers have combined feature extraction technology with deep learning technology to extract more discriminative emotional information. However, a single speech emotion classification task makes it difficult to effectively utilize feature information, resulting in feature redundancy. Therefore, this paper uses speech feature enhancement (SFE) as an auxiliary task to provide additional information for the SER task. This paper combines Long Short-Term Memory Networks (LSTM) with soft decision trees and proposes a multi-task learning framework based on a decision tree structure. Specifically, it trains the LSTM network by computing the distances of features at different leaf nodes in the soft decision tree, thereby achieving enhanced speech feature representation. The results show that the algorithm achieves 85.6% accuracy on the EMO-DB dataset and 81.3% accuracy on the CASIA dataset. This represents an improvement of 11.8% over the baseline on the EMO-DB dataset and 14.9% on the CASIA dataset, proving the effectiveness of the method. Additionally, we conducted cross-database experiments, real-time performance analysis, and noise environment analysis to validate the robustness and practicality of our method. The additional analyses further demonstrate that our approach performs reliably across different databases, maintains real-time processing capabilities, and is robust to noisy environments.

Depth-Enhanced Deep Learning Approach For Monocular Camera Based 3D Object Detection

Automatic 3D object detection using monocular cameras presents significant challenges in the context of autonomous driving. Precise labeling of 3D object scales requires accurate spatial information, which is difficult to obtain from a single image due to the inherent lack of depth information in monocular images, compared to LiDAR data. In this paper, we propose a novel approach to address this issue by enhancing deep neural networks with depth information for monocular 3D object detection. The proposed method comprises three key components: 1)Feature Enhancement Pyramid Module: We extend the conventional Feature Pyramid Networks (FPN) by introducing a feature enhancement pyramid network. This module fuses feature maps from the original pyramid and captures contextual correlations across multiple scales. To increase the connectivity between low-level and high-level features, additional pathways are incorporated. 2)Auxiliary Dense Depth Estimator: We introduce an auxiliary dense depth estimator that generates dense depth maps to enhance the spatial perception capabilities of the deep network model without adding computational burden. 3)Augmented Center Depth Regression: To aid center depth estimation, we employ additional bounding box vertex depth regression based on geometry. Our experimental results demonstrate the superiority of the proposed technique over existing competitive methods reported in the literature. The approach showcases remarkable performance improvements in monocular 3D object detection, making it a promising solution for autonomous driving applications.

An Improved Underwater Visual SLAM through Image Enhancement and Sonar Fusion

To enhance the performance of visual SLAM in underwater environments, this paper presents an enhanced front-end method based on visual feature enhancement. The method comprises three modules aimed at optimizing and improving the matching capability of visual features from different perspectives. Firstly, to address issues related to insufficient underwater illumination and uneven distribution of artificial light sources, a brightness-consistency recovery method is proposed. This method employs an adaptive histogram equalization algorithm to balance the brightness of images. Secondly, a method for denoising underwater suspended particulates is introduced to filter out noise from images. After image-level processing, a combined underwater acousto–optic feature-association method is proposed, which associates acoustic features from sonar with visual features, thereby providing distance information for visual features. Finally, utilizing the AFRL dataset, the improved system incorporating the proposed enhancement methods is evaluated for its performance against the OKVIS framework. The system achieves a better trajectory estimation accuracy compared to OKVIS and demonstrates robustness in underwater environments.

The Effect of Social Factors, Prices, and Product Features on Purchase Intention of Yamaha NMAX Motorcycles at State Polytechnic of Bengkalis Students

The development of the business world in the current era of globalization is increasingly sharpening competition, especially in the management of automotive company units. One type of automotive that is widely favored by Indonesians is motorcycles. This study aims to determine the Effect Social Factors, Prices, and Product Features on Purchase Intention of Yamaha NMAX Motorcycles at State Polytechnic of Bengkalis Students. This study uses quantitative methods, data collection techniques are carried out by distributing online questionnaires with a sample of 100 respondents. The sampling technique used non- probability sampling method, data analysis used is descriptive statistics, classical assumption test, multiple regression analysis, data conclusion with T test, F test and the coefficient of determination (R2), while data processing used SPSS version 26 program. The findings indicate that social factors and product features variables have an effect, meanwhile the prices variable does not have an effect on purchase intention of Yamaha NMAX motorcycles at State Polytechnic of Bengkalis students. This study provides the insight that Yamaha can direct efforts and resources towards social marketing and product feature enhancement rather than focusing on price adjustment strategies.

EMCFN: Edge-based Multi-scale Cross Fusion Network for video frame interpolation

Video frame interpolation (VFI) is used to synthesize one or more intermediate frames between two frames in a video sequence to improve the temporal resolution of the video. However, many methods still face challenges when dealing with complex scenes involving high-speed motion, occlusions, and other factors. To address these challenges, we propose an Edge-based Multi-scale Cross Fusion Network (EMCFN) for VFI. We integrate a feature enhancement module (FEM) based on edge information into the U-Net architecture, resulting in richer and more complete feature maps, while also enhancing the preservation of image structure and details. This contributes to generating more accurate and realistic interpolated frames. At the same time, we use a multi-scale cross fusion frame synthesis model (MCFM) composed of three GridNet branches to generate high-quality interpolation frames. We have conducted a series of experiments and the results show that our model exhibits satisfactory performance on different datasets compared with the state-of-the-art methods.

Fault diagnosis of induction motor in the cooling water supply system using a multi-channel data fusion transformer with limited sample conditions*

Abstract Induction motors play a vital role in the cooling water supply system of hydropower facilities. However, it is not feasible to collect sufficient fault samples in a hydropower station. The scarcity of labeled samples poses a challenge in developing powerful diagnostic models with high classification accuracy. To address this challenge, this paper proposes a multi-channel data fusion strategy based on a transformer for feature enhancement. Initially, the original signals are transferred into non-overlapping single-channel data patches to preserve correlation features across different channels. Next, temporal and spatial attention modules are applied to process the data patches, which can learn and fuse temporal and spatial information, respectively. Subsequently, the data patches are embedded to retain position information and represent fault-related features through class embedding, which are further processed by a transformer encoder with self-attention mechanisms. Finally, the classification task is achieved by using a multilayer perceptron layer connected to the class embedding. While dealing with limited training samples, the proposed method can learn robust features that are beneficial to improve the fault diagnosis ability of induction motors. The comparison of the proposed method with three basic models and two improved methods demonstrates the superiority of the proposed method in accuracy and feature clustering performance under limited sample conditions. In addition, ablation experiments demonstrate the necessity of each module in the proposed method.

Review Paper on Properties of Concrete using Grind Fish Scale in Different forms Replacing Fine Aggregate and Cement

This study intends the use waste Fish scale powder as an alternative material for cement and fish scales as an alternative material for fine aggregates in concrete production. Different partial replacements of fish scale powder and fish scales (0%, 2%, 4%, and 6%) and (0%, 5%, 10%, and 15%) by volume of cement and fine aggregate are cast and test such as compressive strength is to be performed on concrete. Experimental research illustrates the enhancement of mechanical features in concrete due to the replacement of fish scale powder and fish scale concrete. A compression test will be carried out to evaluate the strength properties of concrete at the age of the 3rd, 7th, and 28th day

Self-Training-Transductive-Learning Broad Learning System (STTL-BLS): A model for effective and efficient image classification

A novel model called Self-Training-Transductive-Learning Broad Learning System (STTL-BLS) is proposed for image classification. The model consists of two key blocks: Feature Block (FB) and Enhancement Block (EB). The FB utilizes the Proportion of Large Values Attention (PLVA) technique and an Encoder for feature extraction. Multiple FBs are cascaded in the model to learn discriminative features. The Enhancement Block (EB) enhances feature learning and prevents under-fitting on complex datasets. Additionally, an architecture that combines characteristics of Broad Learning System (BLS) and gradient descent is designed for STTL-BLS, enabling the model to leverage the advantages of both BLS and Convolutional Neural Networks (CNNs). Moreover, a training algorithm (STTL) that combines self-training and transductive learning is presented for the model to improve its generalization ability. Experimental results demonstrate that the accuracy of the proposed model surpasses all compared BLS variants and performs comparably or even superior to deep networks: on small-scale datasets, STTL-BLS has an average accuracy improvement of 14.82 percentage points compared to other models; on large-scale datasets, 12.95 percentage points. Notably, the proposed model exhibits low time complexity, particularly with the shortest testing time on the small-scale datasets among all compared models: it has an average testing time of 46.4 s less than other models. It proves to be an additional valuable solution for image classification tasks on both small- and large-scale datasets. The source code for this paper can be accessed at https://github.com/threedteam/sttl_bls.