Set Of Complementary Features Research Articles

Underwater Target Detection Using Side-Scan Sonar Images Based on Upsampling and Downsampling

Side-scan sonar (SSS) images present unique challenges to computer vision due to their lower resolution, smaller targets, and fewer features. Although the mainstream backbone networks have shown promising results on traditional vision tasks, they utilize traditional convolution to reduce the dimensionality of feature maps, which may cause information loss for small targets and decrease performance in SSS images. To address this problem, based on the yolov8 network, we proposed a new underwater target detection model based on upsampling and downsampling. Firstly, we introduced a new general downsampling module called shallow robust feature downsampling (SRFD) and a receptive field convolution (RFCAConv) in the backbone network. Thereby multiple feature maps extracted by different downsampling techniques can be fused to create a more robust feature map with a complementary set of features. Additionally, an ultra-lightweight and efficient dynamic upsampling module (Dysample) is introduced to improve the accuracy of the feature pyramid network (FPN) in fusing different levels of features. On the underwater shipwreck dataset, our improved model’s mAP50 increased by 4.4% compared to the baseline model.

Distributed Denial of Service Attack Detection in IoT Networks using Deep Learning and Feature Fusion: A Review

The explosive growth of Internet of Things (IoT) devices has led to escalating threats from distributed denial of service (DDoS) attacks. Moreover, the scale and heterogeneity of IoT environments pose unique security challenges, and intelligent solutions tailored for the IoT are needed to defend critical infrastructure. The deep learning technique shows great promise because automatic feature learning capabilities are well suited for the complex and high-dimensional data of IoT systems. Additionally, feature fusion approaches have gained traction in enhancing the performance of deep learning models by combining complementary feature sets extracted from multiple data sources. This paper aims to provide a comprehensive literature review focused specifically on deep learning techniques and feature fusion for DDoS attack detection in IoT networks. Studies employing diverse deep learning models and feature fusion techniques are analysed, highlighting key trends and developments in this crucial domain. This review provides several significant contributions, including an overview of various types of DDoS attacks, a comparison of existing surveys, and a thorough examination of recent applications of deep learning and feature fusion for detecting DDoS attacks in IoT networks. Importantly, it highlights the current challenges and limitations of these deep learning techniques based on the literature surveyed. This review concludes by suggesting promising areas for further research to enhance deep learning security solutions, which are specifically tailored to safeguarding the fast-growing IoT infrastructure against DDoS attacks.

Efficient Vertical Federated Unlearning via Fast Retraining

Vertical federated learning (VFL) revolutionizes privacy-preserved collaboration for small businesses, that have distinct but complementary feature sets. However, as the scope of VFL expands, the constant entering and leaving of participants, as well as the subsequent exercise of the “right to be forgotten” pose a great challenge in practice. The question of how to efficiently erase one’s contribution from the shared model remains largely unexplored in the context of vertical federated learning. In this paper, we introduce a vertical federated unlearning framework, which integrates model checkpointing techniques with a hybrid, first-order optimization technique. The core concept is to reduce backpropagation time and improve convergence/generalization by combining the advantages of the existing optimizers. We provide in-depth theoretical analysis and time complexity to illustrate the effectiveness of the proposed design. We conduct extensive experiments on 6 public datasets and demonstrate that our method could achieve up to 6.3 × speed-up compared to the baseline, with negligible influence on the original learning task.

A Robust Feature Downsampling Module for Remote-Sensing Visual Tasks

Remote sensing (RS) images present unique challenges for computer vision due to lower resolution, smaller objects, and fewer features. Mainstream backbone networks show promising results for traditional visual tasks. However, they use convolution to reduce feature map dimensionality, which can result in information loss for small objects in RS images and decreased performance. To address this problem, we propose a new and universal downsampling module named Robust Feature Downsampling (RFD). RFD fuses multiple feature maps extracted by different downsampling techniques, creating a more robust feature map with a complementary set of features. Leveraging this, we overcome the limitations of conventional convolutional downsampling, resulting in more accurate and robust analysis of RS images. We develop two versions of RFD module, Shallow RFD (SRFD) and Deep RFD (DRFD), tailored to adapt to different stages of feature capture and improve feature robustness. We replace the downsampling layers of existing mainstream backbones with RFD module and conduct comparative experiments on several public RS image datasets. The results show significant improvements compared to baseline approaches in RS image classification, object detection, and semantic segmentation. Specifically, our RFD module achieved an average performance gain of 1.5% on NWPU-RESISC45 classification dataset without utilizing any additional pretraining data, resulting in state-of-the-art performance on this dataset. Moreover, in detection and segmentation tasks on DOTA and iSAID datasets, our RFD module outperforms the baseline approaches by 2-7% when utilizing pretraining data from NWPU-RESISC45. These results highlight the value of RFD module in enhancing the performance of RS visual tasks.

DE-Ada*: A novel model for breast mass classification using cross-modal pathological semantic mining and organic integration of multi-feature fusions

Computer-aided breast mass classification is an effective and widely used technology to assist pathologists in formulating clinical diagnoses and improving working efficiencies. Existing studies usually use a single image feature to perform breast mass classification. Herein, we propose a simple, yet effective, model called the DE-Ada*, which is an organic integration of multi-feature fusions, for breast mass classification. Firstly, we extract a set of complementary features, namely, scale-invariant feature transform (SIFT), GIST, histogram of oriented gradient (HOG), local binary pattern (LBP), residual network (ResNet), densely connected convolutional networks (DenseNet), and visual geometry group (VGG), to characterize mammograms from diverse perspectives. We attempt to mine the cross-modal pathological semantics among these features and complete their early fusion. The dynamic weight of any feature or cross-modal pathological semantics is computed and utilized to complete mid-level feature fusion. Finally, we design two voting-based ensemble learning strategies to implement late feature fusion. Our experiments demonstrate that the DE-Ada* model outperforms baselines on two well-known mammographic datasets. Our model encourages the use of cross-modal pathological semantics to deal with the overfitting problem.

A structure-guided approach to the prediction of natural image saliency

The structure of a scene provides global contextual information in directing gaze and complements local object information in saliency prediction. In this study, we explore how visual attention can be affected by scene structures, namely openness, depth and perspective. We first build an eye tracking dataset with 2500 natural scene images and collect gaze data via both eye tracking and mouse tracking. We make observations on scene layout properties and propose a set of scene structural features relating to visual attention. The set of complementary features are then integrated for saliency prediction. Our features are independent of and can work together with many computational modules, and this work demonstrates the use of Multiple kernel learning (MKL) as an example to integrate the features at low- and high-levels. Experimental results demonstrate that our model outperforms existing methods and our scene structural features can improve the performance of other saliency models in outdoor scenes.

Vehicle Collision Detection During Night Time

”Vehicle collision detection during night time” is an attempt to find an improved solution for vehicle detection problem, during night time. Night time vehicle detection is a challenging area since, the contrast between back ground and foreground is very less due to non uniform lighting, reflections, multiple light sources etc. This algorithm is a blend of night time image enhancement technique and fusion technique for fusing multiple features based on their weight. Image enhancement is an important aspect of the algorithm as it helps in improving the contrast between foreground and back ground as well as improving the lighting, so that it becomes easier to distinguish vehicle and other illuminated objects such as street lights. For improved reliability of the algorithm, set of complementary features - LBP (local binary pattern), HOG (Histogram of Oriented Gradients) and a CNN based feature - are used in the algorithm and are fused together using weighted fusion technique. For classification purpose, individual SVMs are trained for each feature and another SVM is trained for final rank based vehicle detection. Accurate region of interest in computed during detection phase, and is used for vehicle detection by trained SVM classifiers. Tail light detection is used for efficient region proposals. The algorithm is improved by leveraging the region proposals and high accuracy detection of Faster RCNN [10]. The algorithm detects multiple vehicles in single image frame and at possible multiple locations and distances within the frame.

Sparse3D: A new global model for matching sparse RGB-D dataset with small inter-frame overlap

We present a novel 3D global matching algorithm, Sparse3D, to handle the challenging reconstruction of RGB-D datasets whose inter-frame overlap is small due to insufficient temporal sampling or fast camera movement. To support a more reliable reconstruction, two major technical components are proposed: (1) pairwise alignment using a set of complementary features, and (2) a novel global model for alignment pruning and pose optimization. We examine the effectiveness of our algorithm on multiple benchmark datasets under various inter-frame overlap, and demonstrate it better reliability over existing RGB-D reconstruction algorithms.

Automated sleep staging of OSAs based on ICA preprocessing and consolidation of temporal correlations.

An automated sleep staging based on analyzing long-range time correlations in EEG is proposed. These correlations, indicating time-scale invariant property or self-similarity at different time scales, are known to be salient dynamical characteristics of stage succession for a sleeping brain even when the subject suffers a destructive disorder such as Obstructive Sleep Apnea (OSA). The goal is to extract a set of complementary features from cerebral sources mapped onto the scalp electrodes or from a number of denoised EEG channels. For this purpose, source localization/extraction and noise reduction approaches based on Independent Component Analysis were used prior to correlation analysis. Feature extracted segments were then classified in one of the five classes including WAKE, STAGE1, STAGE2, SWS and REM via an ensemble neuro-fuzzy classifier. Some techniques were employed to improve the classifier's performance including Scaled Conjugate Gradient Method to speed up learning the ANFIS classifiers, a pruning algorithm to eliminate irrelevant fuzzy rules and the 10-fold cross-validation technique to train and test the system more efficiently. The performance of classification for two strategies including (1) feature extraction from effective cerebral sources and (2) feature extraction from selected channels of denoised EEG signals was compared and contrasted in terms of training errors and test accuracies. The first and second strategies achieved 92.23 and 88.74% agreement with human expert respectively which indicates the effectiveness of the staging system based on cerebral sources of activity. Our results further indicate that the misclassification rates were almost below 10%. The proposed automated sleep staging system is reliable due to the fact that it is based on the underlying dynamics of sleep staging which is less likely to be affected by sleep fragmentations occurred repeatedly in OSA.

An object-based approach for mapping forest structural types based on low-density LiDAR and multispectral imagery

Mapping forest structure variables provides important information for the estimation of forest biomass, carbon stocks, pasture suitability or for wildfire risk prevention and control. The optimization of the prediction models of these variables requires an adequate stratification of the forest landscape in order to create specific models for each structural type or strata. This paper aims to propose and validate the use of an object-oriented classification methodology based on low-density LiDAR data (0.5 m−2) available at national level, WorldView-2 and Sentinel-2 multispectral imagery to categorize Mediterranean forests in generic structural types. After preprocessing the data sets, the area was segmented using a multiresolution algorithm, features describing 3D vertical structure were extracted from LiDAR data and spectral and texture features from satellite images. Objects were classified after feature selection in the following structural classes: grasslands, shrubs, forest (without shrubs), mixed forest (trees and shrubs) and dense young forest. Four classification algorithms (C4.5 decision trees, random forest, k-nearest neighbour and support vector machine) were evaluated using cross-validation techniques. The results show that the integration of low-density LiDAR and multispectral imagery provide a set of complementary features that improve the results (90.75% overall accuracy), and the object-oriented classification techniques are efficient for stratification of Mediterranean forest areas in structural- and fuel-related categories. Further work will be focused on the creation and validation of a different prediction model adapted to the various strata.

Fusion of Local and Global Feature Extraction Based on Uniform LBP and DCT for Traffic Sign Recognition

Automatic traffic sign recognition has been converted to a real challenge for high performance of computer vision and machine learning techniques. It is an important issue, in particular for vehicle safety applications. In this paper the fusion of two discriminative and complementary feature sets, i.e., the Discrete Cosine Transform and the Uniform block based Local Binary Pattern has been presented. The DCT descriptor is used to extract the global gray-scale features of the whole image whereas the ULBP descriptor is able to capture the local gray-scale features of the traffic sign image and are insensitive to illumination variations which contributes most to traffic sign recognition. Principal Component Analysis is used for dimensionality reduction. We have analyzed the performance of this method under different distance classifiers like City-block and Euclidean distances. Experimental results on GTSRB and BTSC databases show that the proposed fusion method has an obvious performance improvement compared with the other classical recognition methods.

Persian Handwritten Digit Recognition Using Ensemble Classifiers

Abstract Optical character recognition (OCR) includes three main sections, pre-processing, feature extraction and classification. The purpose of the pre-processing is to remove noise, smooth and normalize the input data, which can have a significant role in better differentiating patterns in the feature space. In the feature extraction, a feature vector is assigned to each sample which represents the sample in the related feature space and thus makes it distinct from the other samples. Feature extraction has significant effect on classification of sample class. In the classification stage, correct boundaries should be made between feature vectors, so that the samples of each pattern are separated from other samples by clear boundaries. Persian handwritten digits recognition is a branches of pattern recognition. In this paper, a method is proposed to recognize Persian handwritten digits. The proposed framework includes three main sections, pre-processing, feature extraction and classification. In the feature extraction stage, an appropriate and complementary set of features consist of 115 features extracted from Persian handwritten digits. In the classification stage, the ensemble classifier algorithm is used to separate the samples’ classes from each other. Estimation of results was performed on TMU (Tarbiat Modares University) digits database and the best recognition rate of Persian handwritten digits, was 95.280%.

An Intelligent Methodology for Railways Monitoring Using Ultrasonic Guided Waves

It is far from trivial to inspect railways for defections. In particular, for the foot area of the rail non destructive testing methods are known to be difficult to apply. In this paper, an ultrasonic guided wave method is considered along with classification methods for automated rail foot defect detection. In effect, given a set of gathered ultrasonic signals, multiple features are extracted from time-, frequency- and time–frequency domains. Next, a robust feature selection method is performed, to collect a small set of complementary features. The classification task is accomplished by means of a kernel-based support vector machine. To demonstrate the performance capabilities of our approach, an extensive experimental setup is designed under representative environmental and operational conditions. The sensitivity and the resolution of the proposed defect detection system are reported. A study on the influence of rail fastening on the proposed method is also reported where robust defect detection rates, greater than 93 %, are achieved assuming that a compact feature subset is considered. However, it is evident in experiments that even in the case of large defects, changes in the environmental conditions (temperature and humidity) increase the interpretation of the acquired signals, thus making the detection task more difficult.

Social video annotation by combining features with a tri-adaptation approach

Online social video websites such as YouTube allow users to manually annotate their video documents with textual labels. These labels can be used as indexing keywords to facilitate search and organization of video data. However, manual video annotation is usually a labor-intensive and time-consuming process. In this work, we propose a novel social video annotation approach that combines multiple feature sets based on a tri-adaptation approach. For the shots in each video, they are annotated by aggregating models that are learned from three complementary feature sets. Meanwhile, the models are collaboratively adapted by exploring unlabeled shots. In this sense, the method can be viewed as a novel semi-supervised algorithm that explores three complementary views. Our approach also exploits the temporal smoothness of video labels by applying a label correction strategy. Experiments on a web video dataset demonstrate the effectiveness of the proposed approach.

Complementary feature sets for optimal face recognition

Abstract In face recognition tasks, one kind of feature set is not adequate to generate superior results; thus, selection and combination of complementary features are crucial steps. In this paper, the fusion of two useful descriptors, i.e., the Zernike moments (ZMs) and the local binary pattern (LBP)/local ternary pattern (LTP), has been proposed. The ZM descriptor consists of good global image representation capabilities besides being invariant to image rotation and noise, while the LBP/LTP descriptors capture the innate details within some local parts of face image and are insensitive to illumination variations. The fusion of these two is observed to incorporate the traits of both of these individual descriptors. Subsequently, in this work, the performance of diverse feature sets of ZMs (i.e., magnitude features, magnitude plus phase features, and the real plus imaginary component features) combined with the LBP/LTP descriptor is analyzed on FERET, Yale, and ORL face databases. The recognition results achieved by the proposed method are approximately 10 to 30% higher than those obtained with these descriptors separately. Recognition rates of the proposed method are also found to be significantly better (i.e., by 8 to 24%) in case of single example image per person in the training.

Techniques for vertical handoff decision across wireless heterogeneous networks: A survey

The dawn of the next generation wireless networks will be characterized by the ability to integrate currently available heterogeneous networks. Network integration will not only bring about the realization of ubiquitous connectivity (anytime, anywhere), it will also achieve the dream of always best connected (ABC). This is because these heterogeneous networks are complementary, for example, the universal mobile telecommunications system (UMTS) networks have wide coverage area but with low data rate. On the other hand, wide local area network (WLAN) with high data rate suffers from limited coverage area. Again, worldwide interoperability for microwave access (WiMAX) networks have emerged with a different set of complementary features. Only through the technology of network integration will a user derive the best that these networks have to offer at anywhere and at anytime. The glue for the integration of these networks is the process called vertical handoff (VHO). VHO is the seamless transfer of an ongoing user session between different heterogeneous radio access technologies. The success of any VHO process depends largely on the ability to make accurate and precise decisions about available wireless networks for connection. A considerable number of works have appeared in literature, each proposing techniques for VHO decision. These works have considered different number of decision policies under different scenarios. They used different approaches to demonstrate their solutions. A number of them made many useful contributions; however, there remain some limitations. This survey paper seeks to provide a comprehensive exposition into the various decision making policies used in the VHO decision phase. Key words: Vertical handoff, networks, decision.

Face-based multiple instance analysis for smart electronics billboard

This paper introduces a visual-based system, which can count the number of viewers and recognize their gender in front of an electronic billboard in real-time video streams. The viewers actually watching an advertisement are captured via frontal face detection techniques. To count the number of viewer precisely, the problem of occlusions between viewers is tackled. Besides, a complementary set of features is extracted from the torso of a viewer due to the fact that the part of the body contains relatively rich discriminative information than other body parts. In addition, for conducting robust viewer recognition, an online classifier trained by AdaBoost is developed. To recognize the gender of the counted viewers, an approach based on spatiotemporal probabilistic framework is proposed. Our experimental results demonstrate the robustness of the proposed system for the viewer counting and gender recognition tasks.

Statistical Motion Information Extraction and Representation for Semantic Video Analysis

In this paper, an approach to semantic video analysis that is based on the statistical processing and representation of the motion signal is presented. Overall, the examined video is temporally segmented into shots and for every resulting shot appropriate motion features are extracted; using these, hidden Markov models (HMMs) are employed for performing the association of each shot with one of the semantic classes that are of interest. The novel contributions of this paper lie in the areas of motion information processing and representation. Regarding the motion information processing, the kurtosis of the optical flow motion estimates is calculated for identifying which motion values originate from true motion rather than measurement noise. Additionally, unlike the majority of the approaches of the relevant literature that are mainly limited to global- or camera-level motion representations, a new representation for providing local-level motion information to HMMs is also presented. It focuses only on the pixels where true motion is observed. For the selected pixels, energy distribution-related information, as well as a complementary set of features that highlight particular spatial attributes of the motion signal, are extracted. Experimental results, as well as comparative evaluation, from the application of the proposed approach in the domains of <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Tennis</i> , <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">News</i> and <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Volleyball</i> broadcast video, and <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Human Action</i> video demonstrate the efficiency of the proposed method.

Multi-level learning: improving the prediction of protein, domain and residue interactions by allowing information flow between levels

BackgroundProteins interact through specific binding interfaces that contain many residues in domains. Protein interactions thus occur on three different levels of a concept hierarchy: whole-proteins, domains, and residues. Each level offers a distinct and complementary set of features for computationally predicting interactions, including functional genomic features of whole proteins, evolutionary features of domain families and physical-chemical features of individual residues. The predictions at each level could benefit from using the features at all three levels. However, it is not trivial as the features are provided at different granularity.ResultsTo link up the predictions at the three levels, we propose a multi-level machine-learning framework that allows for explicit information flow between the levels. We demonstrate, using representative yeast interaction networks, that our algorithm is able to utilize complementary feature sets to make more accurate predictions at the three levels than when the three problems are approached independently. To facilitate application of our multi-level learning framework, we discuss three key aspects of multi-level learning and the corresponding design choices that we have made in the implementation of a concrete learning algorithm. 1) Architecture of information flow: we show the greater flexibility of bidirectional flow over independent levels and unidirectional flow; 2) Coupling mechanism of the different levels: We show how this can be accomplished via augmenting the training sets at each level, and discuss the prevention of error propagation between different levels by means of soft coupling; 3) Sparseness of data: We show that the multi-level framework compounds data sparsity issues, and discuss how this can be dealt with by building local models in information-rich parts of the data. Our proof-of-concept learning algorithm demonstrates the advantage of combining levels, and opens up opportunities for further research.AvailabilityThe software and a readme file can be downloaded at . The programs are written in Java, and can be run on any platform with Java 1.4 or higher and Apache Ant 1.7.0 or higher installed. The software can be used without a license.

Enhancement of GMM speaker identification performance using complementary feature sets

This paper describes a way of enhancing speaker identification (SiD) performance using N-best list method which utilises complementary feature sets. The SiD process is first done by training the Gaussian mixture model (GMM) classifier using paramcterised feature sets (PFS) to form speaker models. During testing, the likelihood of a speaker, given a set of speaker models is her score. Performance scores of SiD system is normally degraded as the population of speakers increases. This paper addresses this problem by using linear prediction cepstral coefficients (LPCC) to complement the results obtained from the PFS and the final identification is performed on a smaller population set. Results obtained using 2-best list indicate performance improvement.