Irrelevant Features Research Articles

PSSM-Sumo: deep learning based intelligent model for prediction of sumoylation sites using discriminative features

Post-translational modifications (PTMs) are fundamental to essential biological processes, exerting significant influence over gene expression, protein localization, stability, and genome replication. Sumoylation, a PTM involving the covalent addition of a chemical group to a specific protein sequence, profoundly impacts the functional diversity of proteins. Notably, identifying sumoylation sites has garnered significant attention due to their crucial roles in proteomic functions and their implications in various diseases, including Parkinson’s and Alzheimer’s. Despite the proposal of several computational models for identifying sumoylation sites, their effectiveness could be improved by the limitations associated with conventional learning methodologies. In this study, we introduce pseudo-position-specific scoring matrix (PsePSSM), a robust computational model designed for accurately predicting sumoylation sites using an optimized deep learning algorithm and efficient feature extraction techniques. Moreover, to streamline computational processes and eliminate irrelevant and noisy features, sequential forward selection using a support vector machine (SFS-SVM) is implemented to identify optimal features. The multi-layer Deep Neural Network (DNN) is a robust classifier, facilitating precise sumoylation site prediction. We meticulously assess the performance of PSSM-Sumo through a tenfold cross-validation approach, employing various statistical metrics such as the Matthews Correlation Coefficient (MCC), accuracy, sensitivity, specificity, and the Area under the ROC Curve (AUC). Comparative analyses reveal that PSSM-Sumo achieves an exceptional average prediction accuracy of 98.71%, surpassing existing models. The robustness and accuracy of the proposed model position it as a promising tool for advancing drug discovery and the diagnosis of diverse diseases linked to sumoylation sites.

SmokeFireNet: A Lightweight Network for Joint Detection of Forest Fire and Smoke

In recent years, forest fires have been occurring frequently around the globe, affected by extreme weather and dry climate, causing serious economic losses and environmental pollution. In this context, timely detection of forest fire smoke is crucial for realizing real-time early warning of fires. However, fire and smoke from forest fires can spread to cover large areas and may affect distant areas. In this paper, a lightweight joint forest fire and smoke detection network, SmokeFireNet, is proposed, which employs ShuffleNetV2 as the backbone for efficient feature extraction, effectively addressing the computational efficiency challenges of traditional methods. To integrate multi-scale information and enhance the semantic feature extraction capability, a feature pyramid network (FPN) and path aggregation network (PAN) are introduced in this paper. In addition, the FPN network is optimized by a lightweight DySample upsampling operator. The model also incorporates efficient channel attention (ECA), which can pay more attention to the detection of forest fires and smoke regions while suppressing irrelevant features. Finally, by embedding the receptive field block (RFB), the model further improves its ability to understand contextual information and capture detailed features of fire and smoke, thus improving the overall detection accuracy. The experimental results show that SmokeFireNet is better than other mainstream target detection algorithms in terms of average APall of 86.2%, FPS of 114, and GFLOPs of 8.4, and provides effective technical support for forest fire prevention work in terms of average precision, frame rate, and computational complexity. In the future, the SmokeFireNet model is expected to play a greater role in the field of forest fire prevention and make a greater contribution to the protection of forest resources and the ecological environment.

A Gaussian process embedded feature selection method based on automatic relevance determination

In Gaussian Process, feature importance is inversely proportional to the corresponding length scale when applying the Automatic Relevance Determination (ARD) structured kernel function. Features can be selected by ranking them according to their importance. Among the ARD-based feature selection methods, no uniform score exists for quantifying the output variation explained by feature subsets. This study proposes two feature selection approaches using two cumulative feature importance scores, one titled derivative decomposition ratio and the other normalized sensitivity, to determine the optimal feature subset. The performance of the approaches is assessed to test if irrelevant features are accurately identified and if the feature rankings are correct. The approaches are applied to identify relevant dimensionless inputs for a hybrid model estimating liquid entrainment fraction in two-phase flow. The results reveal that the proposed methods can identify the optimal feature subset for the hybrid model without significantly worsening its Root Mean Squared Error.

Detection dataset of electric bicycles for lift control

Electric bicycle datasets for lift control have played a crucial role in the development of electric bicycle lift entry detection algorithms. However, existing datasets often encounter issues, including a small dataset size, a high false detection rate, and the absence of a publicly available benchmark dataset. This paper addresses these challenges by constructing a new electric bicycle detection dataset for lift control based on the research demands of the electric bicycle detection task for lift control. XHNet_EB, a car scene image dataset covering various types of electric bicycles, was constructed based on images taken by a camera from above. Segmented annotation was employed, framing the front and rear of the electric bicycle independently. This approach effectively addressed the problems of many irrelevant features and a high false detection rate caused by the use of whole-electric-bicycle annotations in mainstream datasets. AP_50, AP_75, the mAP, and the number of false detections in the images were used for quantitative analysis of the dataset. The experimental results indicated that the object detection accuracy of the XHNet_EB dataset was excellent. Quantitative analysis and evaluation of the number of false detections in images were conducted using four mainstream lightweight detection model algorithms. The results demonstrated that segmented annotation reduced the false detection rate more effectively than entire electric bicycle annotation. This study identified drawbacks in existing datasets. The dataset proposed in this paper overcomes the shortcomings of existing commercial data and solves problems such as the high false detection rate caused by the inclusion of many irrelevant features caused by the “whole-electric-bicycle annotation” method, which could help with the development of electric bicycle detection applications in lifts.

Stacked dynamic target regularization enhanced autoencoder for soft sensor in industrial processes

AbstractStacked autoencoders (SAEs) have great potential in developing soft sensors due to their excellent feature extraction capabilities. However, the pre‐training stage of SAE is unsupervised and some important information related to target variables may be discarded. Meanwhile, as the depth of the network increases, reconstruction errors continue to accumulate, resulting in incomplete feature representations of the original input. In addition, the dynamic nature of the data affects the predictive results of the model. To address these issues, the stacked dynamic target regularization enhanced autoencoder (SDTR‐EAE) method is proposed, which adds the DTR and the original input information layer by layer to enhance the feature extraction. To adapt to the dynamic changes in data and extract target‐related features, entropy weight grey relational analysis (EW‐GRA) is used as the DTR term to constrain the weight matrix and suppress irrelevant features. To reduce the accumulation of information loss during the reconstruction, an information enhancement layer is introduced, where the original inputs and the information of the hidden layers of previous DTR‐EAE units are added to the follow‐up DTR‐EAE unit. Finally, in the regression process, the DTR term is used again to fully utilize depth features for quality prediction and prevent overfitting. Experimental verifications using the debutanizer column and thermal power plant are conducted to validate the effectiveness of the proposed modelling method.

A stacking ensemble machine learning based approach for classification of plant diseases through leaf images

Diseases and pests in plants/crops are major causes of significant agricultural losses with economic, social and ecological impacts. Therefore, there is a need for early identification of plant diseases and pests through automated systems. Recently, machine learning-based methods have become popular in solving agricultural problems such as plant diseases faced by technically-noob farmers. This work proposes a novel method based on stacking ensemble machine learning to detect plant diseases in Uradbean precisely. Two classifiers: support vector machine (SVM), random forest (RF) are trained on a dataset consists of Uradbean infected and healthy leaf images. These classifiers are stacked with logistic regression (LR) classifier. In the diverse ensemble, LR classifier is used as a meta-learner which enhanced the precision of the disease classification. The fuzzy C-Means clustering with particle swarm optimization is used for image segmentation. Haralick, Hu Moments and color histogram methods are used in feature extraction. During the tests, the proposed model is also compared with pre-trained networks: DenseNet-201, ResNet-50, and VGG19. It achieved an impressive classification accuracy of 96.82 % which is higher than the individual classifiers and pre-trained networks. To validate model performance, it is evaluated on a benchmark public dataset consists of Apple leaf images and achieved 98.30% accuracy. It is observed that ensemble method reflects an advantage over individual models in increasing the classification rates and reducing the computational overhead in comparison to pre-trained networks which struggle due to the issues such as irrelevant features, generation of pertinent characteristics, and noise

Effective Reduction of Irrelevant Features in Complex Financial datasets using Hybrid Reverse Binary Optimisation Feature Reduction Methods

Effective Reduction of Irrelevant Features in Complex Financial datasets using Hybrid Reverse Binary Optimisation Feature Reduction Methods

IoT Security Using Machine Learning Methods with Features Correlation

The Internet of Things (IoT) is an innovative technology that makes our environment smarter, with IoT devices as an integral part of home automation. Smart home systems are becoming increasingly popular as an IoT service in the home that connects via a network. Due to the security weakness of many devices, the malware is targeting IoT devices. After being infected with malicious attacks on smart devices, they act like bots that the intruders can control. Machine learning methods can assist in improving the attack detection process for these devices. However, the irrelevant features raise the computation time as well as affect the detection accuracy in the processing with many features. We proposed a machine learning-based IoT security framework using feature correlation. The feature extraction scheme, one-hot feature encoding, correlation feature selection, and attack detection implement an active detection mechanism. The results show that the implemented framework is not only for effective detection but also for lightweight performance. The proposed system outperforms the results with the selected features, which have almost 100% detection accuracy. It is also approved that the proposed system using CART is more suitable in terms of processing time and detection accuracy.

Utilizing Elephant Herd-Inspired Spiking Neural Networks for Enhanced Ship Detection and Classification in Marine Scene Matching

In the realm of marine intelligence, effective ship classification across vast oceanic expanses is pivotal. Despite strides in conventional identification techniques, existing methods exhibit limitations in terms of effectiveness, robustness, and overall performance. This paper introduces a novel Elephant Herd optimization based Spiking Neural Networks (EHO-SNN) for discerning large ships, small vessels, and the absence of ships. Initial satellite images from the Airbus dataset capture ships at sea, subjected to preprocessing via the wavelet transform-based Retinex algorithm (WRA) to eliminate noise and fog artifacts. Deep learning mobile net facilitates feature extraction, while the Elephant Herd algorithm culls irrelevant features, honing in on the most pertinent ones. Finally, the classification through a spiking neural network, distinguishing between large ships, small vessels, and the absence of ships. Detected large and small ships are accurately positioned within a selected scene, while the absence of a ship terminates the process. The Proposed EHO-SNN model attains an impressive classification accuracy of 99.10%. Notably, it surpasses OMRCNN-SHD, Efficient Net, and AN-YOLOv4 by 1.15%, 12.30%, and 7.79%, respectively, thereby advancing overall accuracy in ship classification.

Human Fall Detection with Ultra-Wideband Radar and Adaptive Weighted Fusion.

To address the challenges in recognizing various types of falls, which often exhibit high similarity and are difficult to distinguish, this paper proposes a human fall classification system based on the SE-Residual Concatenate Network (SE-RCNet) with adaptive weighted fusion. First, we designed the innovative SE-RCNet network, incorporating SE modules after dense and residual connections to automatically recalibrate feature channel weights and suppress irrelevant features. Subsequently, this network was used to train and classify three types of radar images: time-distance images, time-distance images, and distance-distance images. By adaptively fusing the classification results of these three types of radar images, we achieved higher action recognition accuracy. Experimental results indicate that SE-RCNet achieved F1-scores of 94.0%, 94.3%, and 95.4% for the three radar image types on our self-built dataset. After applying the adaptive weighted fusion method, the F1-score further improved to 98.1%.

MFNet: Multi-scale feature enhancement networks for wheat head detection and counting in complex scene

Developing a high-precision wheat head detection algorithm is challenging due to the dense distribution and diverse sizes of wheat head in the field, as well as serious coverage from weeds. In this work, we propose multi-scale feature enhancement networks for wheat head detection and counting in complex scene (MFNet). Firstly, we introduce a deformable spatial attention mechanism (DSAM) and embed it in the backbone network to enhance the extraction of wheat head features while suppressing irrelevant features, effectively improving detection of wheat head in occluded environments. Secondly, we design a multi-scale receptive field feature fusion (MRFF) module in combination with an improved light-weight feature pyramid module to achieve more accurate detection of wheat head of different sizes and improve localization accuracy simultaneously. Additionally, the modified detection head with deformable convolution is able to adapt to different shapes of wheat head features and accurately predict the bounding boxes. Our method achieves 94.2% AP@50 at a speed of 30 FPS on the GWHD dataset, and to verify the generalization of the proposed method, we constructed a dense wheat head detection (DWHD) dataset with annotations, conducted experiments on the DWHD and SPIKE datasets and compared them with state-of-the-art algorithms. The experimental results show that the proposed method outperformed most of the existing methods, which further proved the superiority and robustness of the proposed method, and demonstrated that our model possesses excellent adaptability, enabling it to flexibly cope with scenarios of significant scale differences and severe occlusion in complex field environments for wheat head, and provide a technological reference for monitoring the wheat phenotype.

DGM-Flow: Appearance flow estimation for virtual try-on via dynamic graph matching

A virtual-image try-on is aimed at warping the target garment image to align with structure of the human body. In recent studies, flexible flow field estimation has been employed via feature matching between the garment and the human body to simulate garment deformation. However, currently available methods for estimating appearance flow rely on a direct comparison of feature descriptors between the source garment and the target pose, while neglecting the surrounding information. This limitation is prone to noisy feature matching, resulting in low accuracy for complex deformations. To overcome this challenge, herein we propose a novel framework named DGM-Flow that exploits the neighbor structure invariance of key features for feature matching, thus improving the estimation accuracy of the appearance flow. Specifically, DGM-Flow models higher-order geometric similarity information between the source garment and the target pose via dynamic graph matching. Moreover, considering the incomplete mapping of garment features before and after deformation, DGM-Flow is used to estimate a hard attention mask matrix to filter irrelevant features using cross-graph matching. Experiments conducted on both the VITON and VITON-HD datasets revealed that DGM-Flow affords better performance than the current leading algorithms, especially when dealing with intricate clothing deformations.

An improved equilibrium optimization algorithm for feature selection problem in network intrusion detection

In this paper, an enhanced equilibrium optimization (EO) version named Levy-opposition-equilibrium optimization (LOEO) is proposed to select effective features in network intrusion detection systems (IDSs). The opposition-based learning (OBL) approach is applied by this algorithm to improve the diversity of the population. Also, the Levy flight method is utilized to escape local optima. Then, the binary rendition of the algorithm called BLOEO is employed to feature selection in IDSs. One of the main challenges in IDSs is the high-dimensional feature space, with many irrelevant or redundant features. The BLOEO algorithm is designed to intelligently select the most informative subset of features. The empirical findings on NSL-KDD, UNSW-NB15, and CIC-IDS2017 datasets demonstrate the effectiveness of the BLOEO algorithm. This algorithm has an acceptable ability to effectively reduce the number of data features, maintaining a high intrusion detection accuracy of over 95%. Specifically, on the UNSW-NB15 dataset, BLOEO selected only 10.8 features on average, achieving an accuracy of 97.6% and a precision of 100%.

X Bot Detection Using One-Class Classification Methods with Isolation Forest Algorithm

X bots pose a significant issue in the social media landscape, with many shared links originating from bot-like accounts. This study introduces the application of the Isolation Forest algorithm, aimed explicitly at identifying anomalies such as bots by analyzing X account details. This study utilizes a dataset that merges data from Botometer with supplementary metrics like ‘average tweets per day’ and ‘account age in days’, contributed by David Martín Gutiérrez. This approach was adopted due to the increasing difficulties accessing the X API. The dataset comprises 37,438 instances, with 25,013 labeled human accounts and 12,425 labeled bot accounts. Pre-processing is performed to remove irrelevant features, and the dataset is split into Training, Validation, and Test sets in a 70:15:15 ratio. The training set undergoes hyperparameter and threshold tuning to identify the best configuration for this specific dataset (n_estimators: 50, contamination: 0.5, bootstrap: True), achieving a training set F1-score of 0.211001. Despite these optimization efforts, the Isolation Forest model's performance remains relatively low. The Test set evaluation yields modest precision, recall, and F1-score values (0.1801, 0.2795, and 0.2190, respectively), with a ROC AUC score of 0.3272. While the Isolation Forest algorithm shows promise in detecting X bots, its performance on this specific dataset is limited. Isolation Forest may not be the most suitable algorithm for this particular bot detection task on this dataset. Future work will explore techniques to enhance the performance of bot detection for a more comprehensive analysis.

Dual-dual subspace learning with low-rank consideration for feature selection

The performance of machine learning algorithms can be affected by redundant features of high-dimensional data. Furthermore, these irrelevant features increase the time of computation for learning model. These problems can be addressed by leveraging different techniques including feature selection and dimensionality reduction. Unsupervised feature selection has drawn increased attention due to the difficulty of label collection for supervised feature selection. To this end, we developed an innovative approach based on nonnegative matrix factorization (NMF) to remove redundant information. In this technique, for the first time, the local information preserving regularization and global information preserving regularization are applied for both feature weight matrix and representation matrix which is why we called Dual-Dual regularized feature selection. Furthermore, Schatten p-norm is utilized to extract inherent low-rank properties of data. To demonstrate the effectiveness of the proposed method, experimental studies are conducted on six benchmark datasets. The computational results show that the proposed method in comparison with state-of-the-art unsupervised feature selection techniques is more efficient for feature selection.

Dual Contrastive Learning Network for Graph Clustering.

Graph representation is an important part of graph clustering. Recently, contrastive learning, which maximizes the mutual information between augmented graph views that share the same semantics, has become a popular and powerful paradigm for graph representation. However, in the process of patch contrasting, existing literature tends to learn all features into similar variables, i.e., representation collapse, leading to less discriminative graph representations. To tackle this problem, we propose a novel self-supervised learning method called dual contrastive learning network (DCLN), which aims to reduce the redundant information of learned latent variables in a dual manner. Specifically, the dual curriculum contrastive module (DCCM) is proposed, which approximates the node similarity matrix and feature similarity matrix to a high-order adjacency matrix and an identity matrix, respectively. By doing this, the informative information in high-order neighbors could be well collected and preserved while the irrelevant redundant features among representations could be eliminated, hence improving the discriminative capacity of the graph representation. Moreover, to alleviate the problem of sample imbalance during the contrastive process, we design a curriculum learning strategy, which enables the network to simultaneously learn reliable information from two levels. Extensive experiments on six benchmark datasets have demonstrated the effectiveness and superiority of the proposed algorithm compared with state-of-the-art methods.

Towards intrusion detection in fog environments using generative adversarial network and long short-term memory network

Recently, fog computing has been developed to complement cloud computing, which can provide cloud services at the edge of the network with real-time processing. However, the computational power of fog nodes is limited and this leads to security issues. On the other hand, cyber-attacks have become common with the exponential growth of Internet of Things (IoT) connected devices. This fact necessitates the development of Intrusion Detection Systems (IDSs) in fog environments with the aim of detecting attacks. In this paper, we develop an IDS named GAN-LSTM for fog environments that uses Generative Adversarial Networks (GANs) and Long Short-Term Memory Networks (LSTMs). GAN-LSTM is used to identify anomalies in network traffic to specific types of attacks or non-attacks. In general, GAN-LSTM consists of three components: data preprocessing, generation of real traffic patterns, and sequence analysis of real traffic data. Data preprocessing ensures data quality by removing noise and irrelevant features. The pre-processed data is fed to the GAN to generate real traffic as a baseline for normal behavior. Finally, the LSTM component is applied to detect anomalous anomalies in fog computing. The proposed algorithm was evaluated on public databases and experimental results showed that GAN-LSTM improves the accuracy of attack detection compared to equivalent approaches.

Causality-inspired Domain Expansion network for single domain generalization

Most existing single domain generalization (SDG) methods focus on extending the distribution of the training data to achieve good generalizability in the target domain by synthesizing out-of-domain data. However, in practice, the generated data are insufficient to cover all possible shifts. When the target distributions are not covered, the spurious associations between irrelevant features and labels captured by a model will deteriorate the generalization performance. To alleviate this problem, in this paper, we first analyze that augmenting the source domain with samples of new styles (e.g., different backgrounds) can mitigate spurious associations between irrelevant features and labels from a causal perspective, which can reduce the interference of non-causal features on the classification labels then propose a novel Causality-inspired Domain Expansion Network (CDEN) for SDG. Specifically, CDEN contains a domain augmentation subnetwork and a representation learning subnetwork. The former uses a special style generator module AdaIN∗ to generate out-of-domain data with the same semantic information but different styles from the source domain data to help the model capture true associations between discriminative features and labels. The latter introduces a novel class-level contrastive learning, instance-level contrastive learning, and invariant risk minimization to help the model further eliminate spurious associations. CDEN progressively generates diverse style data and learns domain invariant representations containing few spurious associations by optimizing the two subnetworks in an adversarial learning manner. We conduct extensive experiments on three benchmark datasets to evaluate the superiority of CDEN, comparing it to fifteen state-of-the-art methods.

Unsupervised Feature Selection to Identify Important ICD-10 and ATC Codes for Machine Learning on a Cohort of Patients With Coronary Heart Disease: Retrospective Study.

The application of machine learning in health care often necessitates the use of hierarchical codes such as the International Classification of Diseases (ICD) and Anatomical Therapeutic Chemical (ATC) systems. These codes classify diseases and medications, respectively, thereby forming extensive data dimensions. Unsupervised feature selection tackles the "curse of dimensionality" and helps to improve the accuracy and performance of supervised learning models by reducing the number of irrelevant or redundant features and avoiding overfitting. Techniques for unsupervised feature selection, such as filter, wrapper, and embedded methods, are implemented to select the most important features with the most intrinsic information. However, they face challenges due to the sheer volume of ICD and ATC codes and the hierarchical structures of these systems. The objective of this study was to compare several unsupervised feature selection methods for ICD and ATC code databases of patients with coronary artery disease in different aspects of performance and complexity and select the best set of features representing these patients. We compared several unsupervised feature selection methods for 2 ICD and 1 ATC code databases of 51,506 patients with coronary artery disease in Alberta, Canada. Specifically, we used the Laplacian score, unsupervised feature selection for multicluster data, autoencoder-inspired unsupervised feature selection, principal feature analysis, and concrete autoencoders with and without ICD or ATC tree weight adjustment to select the 100 best features from over 9000 ICD and 2000 ATC codes. We assessed the selected features based on their ability to reconstruct the initial feature space and predict 90-day mortality following discharge. We also compared the complexity of the selected features by mean code level in the ICD or ATC tree and the interpretability of the features in the mortality prediction task using Shapley analysis. In feature space reconstruction and mortality prediction, the concrete autoencoder-based methods outperformed other techniques. Particularly, a weight-adjusted concrete autoencoder variant demonstrated improved reconstruction accuracy and significant predictive performance enhancement, confirmed by DeLong and McNemar tests (P<.05). Concrete autoencoders preferred more general codes, and they consistently reconstructed all features accurately. Additionally, features selected by weight-adjusted concrete autoencoders yielded higher Shapley values in mortality prediction than most alternatives. This study scrutinized 5 feature selection methods in ICD and ATC code data sets in an unsupervised context. Our findings underscore the superiority of the concrete autoencoder method in selecting salient features that represent the entire data set, offering a potential asset for subsequent machine learning research. We also present a novel weight adjustment approach for the concrete autoencoders specifically tailored for ICD and ATC code data sets to enhance the generalizability and interpretability of the selected features.

The role of task on the human brain's responses to, and representation of, visual regularity defined by reflection and rotation

Identifying and segmenting objects in an image is generally achieved effortlessly and is facilitated by the presence of symmetry: a principle of perceptual organisation used to interpret sensory inputs from the retina into meaningful representations. However, while imaging studies show evidence of symmetry selective responses across extrastriate visual areas in the human brain, whether symmetry is processed automatically is still under debate. We used functional Magnetic Resonance Imaging (fMRI) to study the response to and representation of two types of symmetry: reflection and rotation. Dot pattern stimuli were presented to 15 human participants (10 female) under stimulus-relevant (symmetry) and stimulus-irrelevant (luminance) task conditions. Our results show that symmetry-selective responses emerge from area V3 and extend throughout extrastriate visual areas. This response is largely maintained when participants engage in the stimulus irrelevant task, suggesting an automaticity to processing visual symmetry. Our multi-voxel pattern analysis (MVPA) results extend these findings by suggesting that not only spatial organisation of responses to symmetrical patterns can be distinguished from that of non-symmetrical (random) patterns, but also that representation of reflection and rotation symmetry can be differentiated in extrastriate and object-selective visual areas. Moreover, task demands did not affect the neural representation of the symmetry information. Intriguingly, our MVPA results show an interesting dissociation: representation of luminance (stimulus irrelevant feature) is maintained in visual cortex only when task relevant, while information of the spatial configuration of the stimuli is available across task conditions. This speaks in favour of the automaticity for processing perceptual organisation: extrastriate visual areas compute and represent global, spatial properties irrespective of the task at hand.