Stacking Network Research Articles

A polyhedron-based metal-organic framework with electronegative donor sites for efficient C2H6/C2H4 separation

Ethylene is an important chemical raw material which is widely used in the production of chemical fibers, plastics, rubber, coatings, as well as medicines, and its separation from the gas mixtures of C2H6/C2H4 is of great importance but a challenging task due to their similar physical properties and molecular dimensions. Herein, we report the C2H6 and C2H4 sorption studies on a robust anionic metal-organic framework (MOF) {(NH2Me2)[Co3(μ3OH)(TPT)(TZB)3](H2O)6(DMA)6}n (Co-MOF) formed by connection of Co3(OH) clusters by two N-rich organic ligands 2,4,6-tri(4-pyridyl)-1,3,5-triazine (TPT) and 4-(1H-Tetrazol-5-yl)benzoic acid (H2TZB). The prepared Co-MOF features a polyhedron stacking network structure composed of trigonal bipyramidal cages and octahedral cage which both contribute to a high C2H6 uptake capacity of 6.48 mmol/g and a decent C2H6/C2H4 selectivity of 1.54 at 298 K and 1 bar. Grand Canonical Monte Carlo (GCMC) simulation results agree well with the experimental tendency, both in the adsorption isotherms and sorption heats, which demonstrated that the suitable pore surfaces with electronegative donor sites generated multiple CH ⋅⋅⋅O/N and CH ⋅⋅⋅π interactions between the framework and C2H6, resulting in a stronger interaction between the MOF skeleton and C2H6 molecule than C2H4 as reflected by the dispersion-corrected density functional theory (DFT) calculation.

π-π Stacking Network-Based Supramolecular Peptide Nanoprobe for Visualization of the ICB-Enhanced Ferroptosis Process.

The construction of coassembled peptide nanoprobes based on structural adaptation provides an effective template for stable monitoring of the molecular events in physiological and pathological processes. This also greatly expands their applications in biomedicine, such as multimodal combined diagnosis and treatment. However, the insufficient understanding of the physicochemical properties and structural features of different molecules still makes it difficult to construct the coassembled probes with mutually reinforcing functions, leading to unpredictable effects. Here, we showed how to utilize the π-π stacking network on β-sheets formed by PD-L1-targeting peptides to capture small molecules with ferroptosis functions, thus, coassembling them into a visual probe with synergistic effects. Compared with individual components, the coassembled strategy could significantly improve the stability of the nanoprobe, inducing stronger ferroptosis effects and immune checkpoint blocking effects, and track and reflect the process. This study provides new insights into the design of multicomponent collaborative coassembly systems with biological effects.

DMF2Net: Dynamic multi-level feature fusion network for heterogeneous remote sensing image change detection

With the rapid development of remote sensing data fusion technology, heterogeneous remote sensing image (HRSI) change detection (CD) has become a frontier field. The powerful nonlinear information processing capability of deep neural network provides the possibility for image domain conversion of HRSIs. However, the majority of existing methods rely on stacking network layers to extract deep high-level semantic features to accomplish the mutual conversion of image domains. The effective extraction and utilization of shallow features have not been fully considered. At the same time, the dependence between deep and shallow features has not been deeply explored. Therefore, these algorithms severely restrict the performance of CD. A new HRSI-CD network (DMF2Net) based on multi-level feature fusion is proposed in this paper to address these issues. DMF2Net uses central difference convolution to extract fine-grained features from shallow layers of images. It is capable of capturing the intrinsic detail features of image by aggregating intensity and gradient information. The dynamic multi-level feature fusion method is used to learn the fusion weights from the features, which are then used to guide the organic fusion of shallow and deep semantic features. This can preserve more position and detail features of the image, which can prevent the loss of small data during image conversion and enhance the model’s ability to detect subtle changes. On this basis, a new DMF2Net-based method for detecting change in bi-temporal HRSIs is proposed. We conducted extensive experiments on four publicly available HRSI-CD datasets. The experimental results showed that the proposed CD framework achieves significant improvement over the most advanced methods. The project file of the proposed framework will be obtained from https://github.com/cwlnnu/DMF2Net.

Landslide spatial prediction using cluster analysis

Temporal clustering is an intrinsic nature of landslide occurrences, therefore it should be considered in data-driven landslide spatial prediction (i.e., susceptibility assessment). However, it remains problematic regarding how to determine landslide temporal clusters and how to integrate susceptibility maps derived from different landslide temporal clusters. In this paper, a general framework of landslide spatial prediction model considering the temporal clustering of landslides is proposed. This novel framework first assesses landslide susceptibility separately based on each landslide temporal cluster identified by spatiotemporal clustering analysis and then integrates separate assessments by weighted averaging. In a case study, this general framework is implemented using the stacking network landslide susceptibility assessment method and used in the landslide spatial prediction of the Sanming City and Wenchuan seismic areas. The results show that the proposed framework outperformed traditional susceptibility models that do not consider landslide temporal clustering, and the integration of susceptibility models based on all landslide temporal clusters will promote the performance of landslide spatial prediction because levels of knowledge in long-term spatiotemporal landslide activities are considered. This novel general framework highlights the benefit of considering landslide temporal clustering in landslide spatial prediction and can provide better support for landslide risk management.

Enhanced Multigrained Scanning-Based Deep Stacking Network for Intrusion Detection in IoMT Networks

Enhanced Multigrained Scanning-Based Deep Stacking Network for Intrusion Detection in IoMT Networks

Single Image 3D Reconstruction Algorithm Based on Parallel Double-Branch Pyramid Stacking Network

Limited visual information contained in single images and complex motion models of objects may lead to severe fragmentation and confusion of model backbone in the 3D reconstruction of objects. In order to fully extract feature information in a single image and reduce noise interference caused by environmental factors in 3D reconstruction, a Parallel Dual-Branch Pyramid Stacking Network (PDB-PSN) model is proposed. A parallel dual-branch network model is used to construct an encoder-decoder framework based on cascaded feature extraction, encode/decode high and low-resolution features in a single image, and then convert from 2D to 3D through implicit functions to achieve the 3D reconstruction of target objects in a single image. A cascaded feature extraction network is used as a low-resolution feature extraction network to extract global features of objects. In the high-resolution feature extraction branch, three concatenated hourglass networks and dilated convolutions are used in the hourglass network to increase the receptive field and obtain more global information in order to maintain the integrity of the reconstructed object limbs. A threshold processing module is set to remove irrelevant information and ensure the integrity of global information, and meanwhile, to reduce the interference of irrelevant noise information. Simulation experiments on a self-built terracotta dataset show that the PDB-PSN model can completely reconstruct the 3D model in a single image and effectively eliminate model fragmentation in the reconstruction results.

Tuning electron delocalization of hydrogen-bonded organic framework cathode for high-performance zinc-organic batteries

Stable cathodes with multiple redox-active centres affording a high energy density, fast redox kinetics and a long life are continuous pursuits for aqueous zinc-organic batteries. Here, we achieve a high-performance zinc-organic battery by tuning the electron delocalization within a designed fully conjugated two-dimensional hydrogen-bonded organic framework as a cathode material. Notably, the intermolecular hydrogen bonds endow this framework with a transverse two-dimensional extended stacking network and structural stability, whereas the multiple C = O and C = N electroactive centres cooperatively trigger multielectron redox chemistry with super delocalization, thereby sharply boosting the redox potential, intrinsic electronic conductivity and redox kinetics. Further mechanistic investigations reveal that the fully conjugated molecular configuration enables reversible Zn2+/H+ synergistic storage accompanied by 10-electron transfer. Benefitting from the above synergistic effects, the elaborately tailored organic cathode delivers a reversible capacity of 498.6 mAh g−1 at 0.2 A g−1, good cyclability and a high energy density (355 Wh kg−1).

Engine gas path component fault diagnosis based on a sparse deep stacking network

Accurate engine gas path component fault diagnosis methods are key to ensuring the reliability and safety of engine operations. At present, the effectiveness of the data-driven gas path component fault diagnosis methods has been widely verified in engineering applications. The deep stack neural network (DSN), as a common deep learning neural network, has been gaining more attention in gas path fault diagnosis studies. However, various gas path component faults with strong coupling effects could occur simultaneously, resulting the DSN method less effective for engine gas path fault diagnosis. In order to improve the prediction performance of the DSN handling multiple gas path component fault diagnosis, a sparse regularization and representation method was proposed. The sparse regularization term is used to expand the traditional deep stacking neural network in the sparse representation, and the predicted output tag is close to the target output tag through this term. The diagnosis performance of six different neural network methods were compared by various engine gas path component fault diagnosis types. The results show that the proposed sparse regularization method significantly improves the prediction performance of the DSN, with an accuracy rate 99.9% under various gas path component fault conditions, which is higher than other methods. The proposed engine gas path component fault diagnosis method can handle multiple coupling gas path faults, and help engine operators to develop maintenance plans for the purpose of engine health management.

A Comprehensive Review of Brain Tumour Detection Mechanisms

Abstract The brain is regarded as the central part of the human body and has a very complicated structure. The abnormal growth of tissue inside the brain is called a brain tumour. Tumour detection at an early stage is the most difficult task in the discipline of health. In this review article, the authors have deeply analysed and reviewed the brain tumour detection mechanisms which include manual, semi- and fully automated techniques. Today, fully automated mechanisms apply deep learning (DL) methods for tumour detection in brain magnetic resonance images (MRIs). This paper deals with previously published research articles relevant to various brain tumour detection techniques. Review of various types of tumours, MRI modalities, datasets, filters, segmentation methods and DL techniques like long short-term memory, gated recurrent unit network, convolution neural network, auto encoder, deep belief network, recurrent neural network, generative adverse network and deep stacking networks have been included in this paper. It has been observed from the analysis that the use of DL techniques in the detection of brain tumours improves accuracy. Finally, this paper reveals research gaps, limitations of existing methods, challenges in tumour detection and contributions of the proposed article.

Brain effective connectivity and functional connectivity as markers of lifespan vascular exposures in middle-aged adults: The Bogalusa Heart Study.

Effective connectivity (EC), the causal influence that functional activity in a source brain location exerts over functional activity in a target brain location, has the potential to provide different information about brain network dynamics than functional connectivity (FC), which quantifies activity synchrony between locations. However, head-to-head comparisons between EC and FC from either task-based or resting-state functional MRI (fMRI) data are rare, especially in terms of how they associate with salient aspects of brain health. In this study, 100 cognitively-healthy participants in the Bogalusa Heart Study aged 54.2 ± 4.3years completed Stroop task-based fMRI, resting-state fMRI. EC and FC among 24 regions of interest (ROIs) previously identified as involved in Stroop task execution (EC-task and FC-task) and among 33 default mode network ROIs (EC-rest and FC-rest) were calculated from task-based and resting-state fMRI using deep stacking networks and Pearson correlation. The EC and FC measures were thresholded to generate directed and undirected graphs, from which standard graph metrics were calculated. Linear regression models related graph metrics to demographic, cardiometabolic risk factors, and cognitive function measures. Women and whites (compared to men and African Americans) had better EC-task metrics, and better EC-task metrics associated with lower blood pressure, white matter hyperintensity volume, and higher vocabulary score (maximum value of p = 0.043). Women had better FC-task metrics, and better FC-task metrics associated with APOE-ε4 3-3 genotype and better hemoglobin-A1c, white matter hyperintensity volume and digit span backwards score (maximum value of p = 0.047). Better EC rest metrics associated with lower age, non-drinker status, and better BMI, white matter hyperintensity volume, logical memory II total score, and word reading score (maximum value of p = 0.044). Women and non-drinkers had better FC-rest metrics (value of p = 0.004). In a diverse, cognitively healthy, middle-aged community sample, EC and FC based graph metrics from task-based fMRI data, and EC based graph metrics from resting-state fMRI data, were associated with recognized indicators of brain health in differing ways. Future studies of brain health should consider taking both task-based and resting-state fMRI scans and measuring both EC and FC analyses to get a more complete picture of functional networks relevant to brain health.

Deep stacked pinball transfer matrix machine with its application in roller bearing fault diagnosis

At present, the matrix-based classification methods have played an extremely important role to mechanical fault diagnosis. However, the traditional matrix-based classification methods are mostly shallow classifiers, which are difficult to obtain the deep-seated sensitive features of vibration signals. To learn and extract low-rank structure information, a new deep stacked pinball transfer matrix machine (DSPTMM) is proposed to enhance the performance of traditional shallow matrix-based classifiers, which takes the stacking generalization principle as the main idea. In DSPTMM, a pinball transfer module (PTM) is constructed as the basic module of deep stacking network, in which the pinball loss is used to achieve an enhanced noise robustness. Specifically, PTM performs the function to obtain the weak prediction of the previous module, and the original results of previous weak prediction are modified by random projection and then will be input as a new feature set in the next module. Therefore, DSPTMM has a better classification performance and can modeled without enough annotation samples. Extensive experiments are carried out on two different datasets of roller bearing, and the results of experiment show that the proposed DSPTMM can use limited samples to establish the accurate model.

Recent Landscape of Deep Learning Intervention and Consecutive Clustering on Biomedical Diagnosis

Background: Consecutive Clustering is one type of learning method that is built on neural network. It is frequently used in different domains including biomedical research. It is very useful for consecutive clustering (adjacent clustering). Adjacent clustering is highly used where there are various specific locations or addresses denoting each individual features in the data that need to be grouped consecutively. One of the useful consecutive clustering in the field of biomedical research is differentially methylated region (DMR) finding analysis on various CpG sites (features). Method: So far, many researches have been carried out on deep learn- ing and consecutive clustering in biomedical domain. But for epigenetics study, very limited survey papers have been published till now where con- secutive clustering has been demonstrated together. Hence, in this study, we contributed a comprehensive survey on several fundamental categories of consecutive clustering, e.g., Convolutional Neural Network(CNN) Auto- Encoder (AE), Restricted Boltzmann Machines (RBM) and Deep Belief Net- work (DBN), Recurrent Neural Network (RNN), Deep Stacking Networks (DSN), Long Short Term Memory (LSTM) / Gated Recurrent Unit (GRU) Network etc., along with their applications, advantages and disadvantages. Different forms of consecutive clustering algorithms are covered in the second section (viz., supervised and unsupervised DMR finding methods) used for DNA methylation data have been described here along with their advantages, shortcomings and overall performance estimation (power, time). Conclusion: Our survey paper provides a latest research work that have been done for consecutive clustering algorithms for healthcare purposes. All the usages, benefits and shortcomings along with their performance evaluation of each algorithm has been elaborated in our manuscript by which new biomedical researchers can understand and use those tools and algorithms for their research prospective.

LWSNet - a novel deep-learning architecture to segregate Covid-19 and pneumonia from x-ray imagery.

Automatic detection of lung diseases using AI-based tools became very much necessary to handle the huge number of cases occurring across the globe and support the doctors. This paper proposed a novel deep learning architecture named LWSNet (Light Weight Stacking Network) to separate Covid-19, cold pneumonia, and normal chest x-ray images. This framework is based on single, double, triple, and quadruple stack mechanisms to address the above-mentioned tri-class problem. In this framework, a truncated version of standard deep learning models and a lightweight CNN model was considered to conviniently deploy in resource-constraint devices. An evaluation was conducted on three publicly available datasets alongwith their combination. We received 97.28%, 96.50%, 97.41%, and 98.54% highest classification accuracies using quadruple stack. On further investigation, we found, using LWSNet, the average accuracy got improved from individual model to quadruple model by 2.31%, 2.55%, 2.88%, and 2.26% on four respective datasets.

Effective Connectivity Is A More Promising Biomarker for Brain Health in Middle‐Aged Adults Than Functional Connectivity: Bogalusa Heart Study

AbstractBackgroundEffective connectivity, the causal influence that functional activity in a source brain location exerts over functional activity in a target brain location, has the potential to provide richer information about brain networks than functional connectivity, which only quantifies activity synchrony between regions. However, head‐to‐head comparisons of effective and functional connectivity from functional MRI data are rare, especially among diverse cognitively healthy middle aged and older adults.Method100 Bogalusa Heart Study participants performed a Stroop task during functional MRI (Table 1). Effective connectivity and functional connectivity among 24 regions of interest (ROIs) previously identified as activated by this task [1] were calculated using deep stacking networks [2] and Pearson correlation, respectively. Graph metrics were then calculated from directed graphs resulting from effective connectivity and undirected graphs resulting from functional connectivity. Linear regression models related graph metrics to demographic, cardiometabolic, and cognitive measures.ResultFigure 1 shows the group‐consensus effective and functional connectivity graphs. Systolic blood pressure (SBP) was associated with effective connectivity based characteristic path length (Pearson’s r = 0.22, p‐value = 0.038) and modularity (r = 0.25, p‐value = 0.02) (Figure 2). Diastolic blood pressure (DBP) was associated with effective connectivity based degree, density, clustering coefficient, modularity, transitivity, characteristic path length, and global efficiency (|r| = 0.26 ‐ 0.35, maximum p‐value = 0.013) (Figure 2). Word reading and vocabulary scores from the Wide Range Achievement Test (WRAT) were associated with effective connectivity based degree, density, clustering coefficient, transitivity, characteristic path length, modularity, and global efficiency (|r| = 0.21 ‐ 0.27, maximum p‐value = 0.049). Logical Memory II Recognition scores associated with effective connectivity based assortativity (r = 0.24, p‐value = 0.025). Associations between functional connectivity based graph metrics and demographic, cardiometabolic, and cognitive measures were not significant.ConclusionIn a diverse, cognitively healthy, middle‐aged community sample, graph metrics derived from effective connectivity based directed graphs tracked more closely with recognized indicators of brain health than traditional functional connectivity based undirected graph metrics.

Effective Connectivity Is A More Promising Biomarker for Brain Health in Middle‐Aged Adults Than Functional Connectivity: Bogalusa Heart Study

AbstractBackgroundEffective connectivity, the causal influence that functional activity in a source brain location exerts over functional activity in a target brain location, has the potential to provide richer information about brain networks than functional connectivity, which only quantifies activity synchrony between regions. However, head‐to‐head comparisons of effective and functional connectivity from functional MRI data are rare, especially among diverse cognitively healthy middle aged and older adults.Method100 Bogalusa Heart Study participants performed a Stroop task during functional MRI (Table 1). Effective connectivity and functional connectivity among 24 regions of interest (ROIs) previously identified as activated by this task [1] were calculated using deep stacking networks [2] and Pearson correlation, respectively. Graph metrics were then calculated from directed graphs resulting from effective connectivity and undirected graphs resulting from functional connectivity. Linear regression models related graph metrics to demographic, cardiometabolic, and cognitive measures.ResultFigure 1 shows the group‐consensus effective and functional connectivity graphs. Systolic blood pressure (SBP) was associated with effective connectivity based characteristic path length (Pearson’s r = 0.22, p‐value = 0.038) and modularity (r = 0.25, p‐value = 0.02) (Figure 2). Diastolic blood pressure (DBP) was associated with effective connectivity based degree, density, clustering coefficient, modularity, transitivity, characteristic path length, and global efficiency (|r| = 0.26 ‐ 0.35, maximum p‐value = 0.013) (Figure 2). Word reading and vocabulary scores from the Wide Range Achievement Test (WRAT) were associated with effective connectivity based degree, density, clustering coefficient, transitivity, characteristic path length, modularity, and global efficiency (|r| = 0.21 ‐ 0.27, maximum p‐value = 0.049). Logical Memory II Recognition scores associated with effective connectivity based assortativity (r = 0.24, p‐value = 0.025). Associations between functional connectivity based graph metrics and demographic, cardiometabolic, and cognitive measures were not significant.ConclusionIn a diverse, cognitively healthy, middle‐aged community sample, graph metrics derived from effective connectivity based directed graphs tracked more closely with recognized indicators of brain health than traditional functional connectivity based undirected graph metrics.

A Cotraining-Based Semisupervised Approach for Remaining-Useful-Life Prediction of Bearings.

The failure of bearings can have a significant negative impact on the safe operation of equipment. Recently, deep learning has become one of the focuses of RUL prediction due to its potent scalability and nonlinear fitting ability. The supervised learning process in deep learning requires a significant quantity of labeled data, but data labeling can be expensive and time-consuming. Cotraining is a semisupervised learning method that reduces the quantity of required labeled data through exploiting available unlabeled data in supervised learning to boost accuracy. This paper innovatively proposes a cotraining-based approach for RUL prediction. A CNN and an LSTM were cotrained on large amounts of unlabeled data to obtain a health indicator (HI), then the monitoring data were entered into the HI and the RUL prediction was realized. The effectiveness of the proposed approach was compared and analyzed against individual CNN and LSTM and the stacking networks SAE+LSTM and CNN+LSTM in the existing literature using RMSE and MAPE values on a PHM 2012 dataset. The results demonstrate that the RMSE and MAPE value of the proposed approach are superior to individual CNN and LSTM, and the RMSE value of the proposed approach is 54.72, which is significantly lower than SAE+LSTM (137.12), and close to CNN+LSTM (49.36). The proposed approach has also been tested successfully on a real-world task and thus has strong application value.

Soil classification in a seismically active environment based on join analysis of seismic parameters

BACKGROUND AND OBJECTIVES: The increase in the number of vehicles has several negative impacts, including traffic congestion, air pollution, noise levels, and the availability of parking spaces. Drivers looking for parking spaces can cause traffic jams and air pollution. The solution offered at this time is the development of a smart parking system to overcome these problems. The smart parking system offers a parking availability information feature in a parking area to break up congestion in the parking space. Deep learning is a successful method to solve parking space classification problems. It is known that this method requires a large computational process. Th aims of this study are to modified the architecture of Convolutional Neural Networks, part of deep learning to classify parking spaces. Modification of the Convolutional Neural Networks architecture is assumed to increase the work efficiency of the smart parking system in processing parking availability information.METHODS: Research is focusing on developing parking space classification techniques using camera sensors due to the rapid advancement of technology and algorithms in computer vision. The input image has 3x3 dimensions. The first convolution layer accepts the input image and converts it into 56x56 dimensions. The second convolution layer is composed in the same way as the first layer with dimensions of 25x25. The third convolution layer employs a 3 x 3 filter matrix with padding of up to 15 and converts it into 10x10 dimensions. The fourth layer is composed in the same way as the third layer, but with the addition of maximum pooling. The software used in the test is Python with a Python framework.FINDINGS: The proposed architecture is the Efficient Parking Network or EfficientParkingNet. It can be shown that this architecture is more efficient in classifying parking spaces compared to some other architectures, such as the mini–Alex Network (mAlexnet) and the Grassmannian Deep Stacking Network with Illumination Correction (GDSN-IC). EfficientParkingNet has not been able to pass the accuracy of Yolo Mobile Network (Yolo+MobileNet). Furthermore, Yolo+MobileNet has so many parameters that it cannot be used on low computing devices. Selection of EfficientParkingNet as a lightweight architecture tailored to the needs of use. EfficientParkingNet's lightweight computing architecture can increase the speed of information on parking availability to users.CONCLUSION: EfficientParkingNet is more efficient in determining the availability of parking spaces compared to mAlexnet, but still cannot match Yolo+MobileNet. Based on the number of parameters, EfficientParkingNet uses half of the number of parameters of mAlexnet and is much smaller than Yolo+MobileNet. EfficientParkingNet has an accuracy rate of 98.44% for the National Research Council parking dataset and higher than other architectures. EfficientParkingNet is suitable for use in parking systems with low computing devices such as the Raspberry Pi because of the small number of parameters.

MCCA-Net: Multi-color convolution and attention stacked network for Underwater image classification

Underwater images are serious problems affected by the absorption and scattering of light. At present, the existing sharpening methods can't effectively solve all underwater image degradation problems, thus it is necessary to propose a specific solution to the degradation problem. To solve the above problems, the Multi-Color Convolutional and Attentional Stacking Network (MCCA-Net) for Underwater image classification are proposed in this paper. First, an underwater image is converted to HSV and Lab color spaces and fused to achieve a refined image. Then, the attention mechanism module is used to fine the extracted image features. At last, the vertically stacked convolution module fully utilizes different levels of feature information, which realizes the fusion of convolution and attention mechanism, optimizes feature extraction and parameter reduction, and improves the classification performance of the MCCA-Net model. Extensive experiments on underwater degraded image classification show that our MCCA-Net model and method outperform other models and improve the accuracy of underwater degraded image classification. Our image fusion method can achieve 96.39% accuracy on other models, and the MCCA-Net model achieves 97.38% classification accuracy.

Deep Stacking Network for Intrusion Detection.

Preventing network intrusion is the essential requirement of network security. In recent years, people have conducted a lot of research on network intrusion detection systems. However, with the increasing number of advanced threat attacks, traditional intrusion detection mechanisms have defects and it is still indispensable to design a powerful intrusion detection system. This paper researches the NSL-KDD data set and analyzes the latest developments and existing problems in the field of intrusion detection technology. For unbalanced distribution and feature redundancy of the data set used for training, some training samples are under-sampling and feature selection processing. To improve the detection effect, a Deep Stacking Network model is proposed, which combines the classification results of multiple basic classifiers to improve the classification accuracy. In the experiment, we screened and compared the performance of various mainstream classifiers and found that the four models of the decision tree, k-nearest neighbors, deep neural network and random forests have outstanding detection performance and meet the needs of different classification effects. Among them, the classification accuracy of the decision tree reaches 86.1%. The classification effect of the Deeping Stacking Network, a fusion model composed of four classifiers, has been further improved and the accuracy reaches 86.8%. Compared with the intrusion detection system of other research papers, the proposed model effectively improves the detection performance and has made significant improvements in network intrusion detection.

Audio Classification for Noise Filtering Using Convolutional Neural Network Approach

In each part of daily routine, sound assumes a significant part. From discrete security features to basic reconnaissance, a sound is a vivacious component to create automated frameworks for these fields. Scarcely any frameworks are now on the lookout, yet their effectiveness is a concerned point for their execution, real-time conditions. The learning capacities of Deep learning designs can be utilized to create sound characterization frameworks increase the impact of sound classification. Our main aim in this paper is to implement deep learning networks for filtering the nose and arrangement of these sound created by the natural phenomenon’s according to the spectrograms that are created accordingly. The spectrograms of these natural sounds are utilized for the preparation of the Convolutional neural network (CNN) and Tensor Deep Stacking Network (TDSN). The utilized datasets for analysis and creation of the networks are ESC-10 and ESC-50. These frameworks produced from these datasets were efficient in accomplishment of filtering the audio and recognizing the audio of the natural sound. The precision obtained from the developed system is 80% for CNN and 70% for TDSN. Form the implemented framework, it is presumed that proposed approach for sound filtering and recognition through the utility spectrogram of their subsequent sounds can be productively used to create efficient frameworks for audio classification and recognition based on neural networks.