Hoffmann's sign in cervical spondylotic myelopathy patients: pathological insights from neuroimaging.

OBJECTIVE: Hoffmann's sign testing is a commonly used physical examination in clinical practice for patients with cervical spondylotic myelopathy (CSM). However, the pathophysiological mechanisms underlying its occurrence and development have not been thoroughly investigated. Therefore, the present study aimed to explore whether a positive Hoffmann's sign (PHS) in CSM patients is associated with spinal cord and brain remodeling and to identify potential neuroimaging biomarkers with diagnostic value. METHODS: Seventy-six patients with CSM and 40 sex- and age-matched healthy controls (HCs) underwent multimodal MRI. Based on the results of the Hoffmann's sign examination, patients were divided into two groups: those with a PHS (n = 38) and those with a negative Hoffmann's sign (NHS; n = 38). Quantification of spinal cord and brain structural and functional parameters of the participants was performed using various methods, including functional connectivity analysis, voxel-based morphometry, and atlas-based analysis based on functional MRI and structural MRI data. Furthermore, this study conducted a correlation analysis between neuroimaging metrics and neurological function and utilized a support vector machine (SVM) algorithm for the classification of PHS and NHS. RESULTS: In comparison with the NHS and HC groups, PHS patients exhibited significant reductions in the cross-sectional area and fractional anisotropy (FA) of the lateral corticospinal tract (CST), reticulospinal tract (RST), and fasciculus cuneatus, concomitant with bilateral reductions in the volume of the lateral pallidum. The functional connectivity analysis indicated a reduction in functional connectivity between the left lateral pallidum and the right angular gyrus in the PHS group. The correlation analysis indicated a significant positive association between the CST and RST FA and the volume of the left lateral pallidum in PHS patients. Furthermore, all three variables exhibited a positive correlation with the patients' motor function. Finally, using multimodal neuroimaging metrics in conjunction with the SVM algorithm, PHS and NHS were classified with an accuracy rate of 85.53%. CONCLUSIONS: This research revealed a correlation between structural damage to the pallidum and RST and the presence of Hoffmann's sign as well as the motor function in patients with CSM. Features based on neuroimaging indicators have the potential to serve as biomarkers for assessing the extent of neuronal damage in CSM patients.

Machine Learning Data Augmentation Strategy for Electron Energy Loss Spectroscopy: Generative Adversarial Networks.

Recent advances in machine learning (ML) have highlighted a novel challenge concerning the quality and quantity of data required to effectively train algorithms in supervised ML procedures. This article introduces a data augmentation (DA) strategy for electron energy loss spectroscopy (EELS) data, employing generative adversarial networks (GANs). We present an innovative approach, called the data augmentation generative adversarial network (DAG), which facilitates data generation from a very limited number of spectra, around 100. Throughout this study, we explore the optimal configuration for GANs to produce realistic spectra. Notably, our DAG generates realistic spectra, and the spectra produced by the generator are successfully used in real-world applications to train classifiers based on artificial neural networks (ANNs) and support vector machines (SVMs) that have been successful in classifying experimental EEL spectra.

A practical online prediction platform to predict the survival status of laryngeal squamous cell carcinoma after 5 years.

OBJECTIVE: Currently, there are few practical tools for predicting the prognosis of laryngeal squamous cell carcinoma (LSCC). This study aims to establish a model and a convenient online prediction platform to predict whether LSCC patients will survive 5 years after diagnosis, providing a reference for further evaluation of patient prognosis. METHODS: This is a retrospective study based on data collected from two centers. Center 1 included 117 LSCC patients with survival prognosis data, and center 2 included 33 patients, totaling 150 patients. All data were divided into independent training sets (60 %) and testing sets (40 %). Eight machine learning (ML) algorithms were used to establish models with 11 clinical parameters as input features. The accuracy, sensitivity, specificity, and receiver operating characteristic curve (ROC) of the testing set were used to evaluate the models, and the best model was selected. The model was then developed into a website-based 5-year survival status prediction platform for LSCC. In addition, we also used the SHapley Additive exPlanations (SHAP) tool to conduct interpretability analysis on the parameters of the model. RESULTS: The LSCC 5-year survival status prediction model using the support vector machine (SVM) algorithm achieved the best results, with accuracy, sensitivity, specificity, and area under the ROC curve (AUC) of 85.0 %, 87.5 %, 75.0 %, and 81.2 % respectively. The online platform for predicting the 5-year survival status of LSCC based on this model was successfully established. The SHAP analysis shows that the clinical stage is the most important feature of the model. CONCLUSION: This study successfully established a ML model and a practical online prediction platform to predict the survival status of laryngeal cancer patients after 5 years, which may help clinicians to better evaluate the prognosis of LSCC.

m5U-SVM: identification of RNA 5-methyluridine modification sites based on multi-view features of physicochemical features and distributed representation.

BACKGROUND: RNA 5-methyluridine (m5U) modifications are obtained by methylation at the C5 position of uridine catalyzed by pyrimidine methylation transferase, which is related to the development of human diseases. Accurate identification of m5U modification sites from RNA sequences can contribute to the understanding of their biological functions and the pathogenesis of related diseases. Compared to traditional experimental methods, computational methods developed based on machine learning with ease of use can identify modification sites from RNA sequences in an efficient and time-saving manner. Despite the good performance of these computational methods, there are some drawbacks and limitations. RESULTS: In this study, we have developed a novel predictor, m5U-SVM, based on multi-view features and machine learning algorithms to construct predictive models for identifying m5U modification sites from RNA sequences. In this method, we used four traditional physicochemical features and distributed representation features. The optimized multi-view features were obtained from the four fused traditional physicochemical features by using the two-step LightGBM and IFS methods, and then the distributed representation features were fused with the optimized physicochemical features to obtain the new multi-view features. The best performing classifier, support vector machine, was identified by screening different machine learning algorithms. Compared with the results, the performance of the proposed model is better than that of the existing state-of-the-art tool. CONCLUSIONS: m5U-SVM provides an effective tool that successfully captures sequence-related attributes of modifications and can accurately predict m5U modification sites from RNA sequences. The identification of m5U modification sites helps to understand and delve into the related biological processes and functions.

Research on On-Line Monitoring of Grinding Wheel Wear Based on Multi-Sensor Fusion.

The state of a grinding wheel directly affects the surface quality of the workpiece. The monitoring of grinding wheel wear state can allow one to efficiently identify grinding wheel wear information and to timely and effectively trim the grinding wheel. At present, on-line monitoring technology using specific sensor signals can detect abnormal grinding wheel wear in a timely manner. However, due to the non-linearity and complexity of the grinding wheel wear process, as well as the interference and noise of the sensor signal, the accuracy and reliability of on-line monitoring technology still need to be improved. In this paper, an intelligent monitoring system based on multi-sensor fusion is established, and this system can be used for precise grinding wheel wear monitoring. The proposed system focuses on titanium alloy, a typical difficult-to-process aerospace material, and addresses the issue of low on-line monitoring accuracy found in traditional single-sensor systems. Additionally, a multi-eigenvalue fusion algorithm based on an improved support vector machine (SVM) is proposed. In this study, the mean square value of the wavelet packet decomposition coefficient of the acoustic emission signal, the grinding force ratio of the force signal, and the effective value of the vibration signal were taken as inputs for the improved support vector machine, and the recognition strategy was adjusted using the entropy weight evaluation method. A high-precision grinding machine was used to carry out multiple sets of grinding wheel wear experiments. After being processed by the multi-sensor integrated precision grinding wheel wear intelligent monitoring system, the collected signals can accurately reflect the grinding wheel wear state, and the monitoring accuracy can reach more than 92%.

Development of a Tremor Detection Algorithm for Use in an Academic Movement Disorders Center.

Tremor, defined as an "involuntary, rhythmic, oscillatory movement of a body part", is a key feature of many neurological conditions including Parkinson's disease and essential tremor. Clinical assessment continues to be performed by visual observation with quantification on clinical scales. Methodologies for objectively quantifying tremor are promising but remain non-standardized across centers. Our center performs full-body behavioral testing with 3D motion capture for clinical and research purposes in patients with Parkinson's disease, essential tremor, and other conditions. The objective of this study was to assess the ability of several candidate processing pipelines to identify the presence or absence of tremor in kinematic data from patients with confirmed movement disorders and compare them to expert ratings from movement disorders specialists. We curated a database of 2272 separate kinematic data recordings from our center, each of which was contemporaneously annotated as tremor present or absent by a movement physician. We compared the ability of six separate processing pipelines to recreate clinician ratings based on F1 score, in addition to accuracy, precision, and recall. The performance across algorithms was generally comparable. The average F1 score was 0.84±0.02 (mean ± SD; range 0.81-0.87). The second highest performing algorithm (cross-validated F1=0.87) was a hybrid that used engineered features adapted from an algorithm in longstanding clinical use with a modern Support Vector Machine classifier. Taken together, our results suggest the potential to update legacy clinical decision support systems to incorporate modern machine learning classifiers to create better-performing tools.

Classification of Sand-Binder Mixtures from the Foundry Industry Using Electrical Impedance Spectroscopy and Support Vector Machines.

Molding sand mixtures used in the foundry industry consist of various sands (quartz sands, chromite sands, etc.) and additives such as bentonite. The optimum control of the processes involved in using the mixtures and in their regeneration after the casting requires an efficient in-line monitoring method that is not available today. We are investigating whether such a method can be based on electrical impedance spectroscopy (EIS). To establish a database, we have characterized various sand mixtures by EIS in the frequency range from 0.5 kHz to 1 MHz under laboratory conditions. Attempts at classifying the different molding sand mixtures by support vector machines (SVM) show encouraging results. Already high assignment accuracies (above 90%) could even be improved with suitable feature selection (sequential feature selection). At the same time, the standard uncertainty of the SVM results is low, i.e., data assigned to a class by the presented SVMs have a high probability of being assigned correctly. The application of EIS with subsequent evaluation by machine learning (machine-learning-enhanced EIS, MLEIS) in the field of bulk material monitoring in the foundry industry appears possible.

A SMART methodology for assessment of hexanal in potato crisps using electronic nose technology: sensor screening by scalar machine learning classifier method.

There is a pertinent need to develop a rapid and accurate methodology for the detection of the onset and the progression of rancidity in the most popular savory product worldwide, viz. fried potato crisps for food safety and health concerns. Rancidity in the fried crisps-one set prepared using C18:2-lean deodorized virgin coconut oil under modified deep frying conditions (140 °C, 5 min),-and another set deep fried (170 °C, 3 min) in C18:2-rich oil (simulating commercial frying conditions) was determined by 'rancidity indices' generated (using Mahalanobis distance) from the data obtained by MO-based electronic nose analysis of hexanal (in Likens-Nickerson extract of volatiles from potato crisps), the most prominent rancidity marker, using screened sensors calibrated with standard hexanal, and classified using support vector machine. This also allowed unambiguous discrimination of the two sets of potato fries. The correlation of hexanal contents with the said indices yielded robust regression models which could accurately predict rancidity status of the crisps, forgoing GC-FID analysis of rancidity marker in the same. The 'SMART' models developed would allow rapid-cum-accurate detection of the onset and progression of rancidity in fried potato crisps on an industrial scale, forgoing the need to conduct biochemical analyses. Supplementary Information: The online version contains supplementary material available at 10.1007/s13197-023-05831-y.

Parkinsonian daytime sleep-wake classification using deep brain stimulation lead recordings.

Excessive daytime sleepiness is a recognized non-motor symptom that adversely impacts the quality of life of people with Parkinson's disease (PD), yet effective treatment options remain limited. Deep brain stimulation (DBS) of the subthalamic nucleus (STN) is an effective treatment for PD motor signs. Reliable daytime sleep-wake classification using local field potentials (LFPs) recorded from DBS leads implanted in STN can inform the development of closed-loop DBS approaches for prompt detection and disruption of sleep-related neural oscillations. We performed STN DBS lead recordings in three nonhuman primates rendered parkinsonian by administrating neurotoxin 1-methyl-4-phenyl-1,2,3,6-tetrahydropyridine (MPTP). Reference sleep-wake states were determined on a second-by-second basis by video monitoring of eyes (eyes-open, wake and eyes-closed, sleep). The spectral power in delta (1-4 Hz), theta (4-8 Hz), low-beta (8-20 Hz), high-beta (20-35 Hz), gamma (35-90 Hz), and high-frequency (200-400 Hz) bands were extracted from each wake and sleep epochs for training (70% data) and testing (30% data) a support vector machines classifier for each subject independently. The spectral features yielded reasonable daytime sleep-wake classification (sensitivity: 90.68 ± 1.28; specificity: 88.16 ± 1.08; accuracy: 89.42 ± 0.68; positive predictive value; 88.70 ± 0.89, n = 3). Our findings support the plausibility of monitoring daytime sleep-wake states using DBS lead recordings. These results could have future clinical implications in informing the development of closed-loop DBS approaches for automatic detection and disruption of sleep-related neural oscillations in people with PD to promote wakefulness.

Classification of breast tumors by using a novel approach based on deep learning methods and feature selection.

PURPOSE: Cancer is one of the most insidious diseases that the most important factor in overcoming the cancer is early diagnosis and detection. The histo-pathological images are used to determine whether the tissue is cancerous and the type of cancer. As the result of examination on tissue images by the expert personnel, the cancer type, and stage of the tissue can be determined. However, this situation can cause both time and energy loss as well as personnel-related inspection errors. By the increased usage of computer-based decision methods in the last decades, it would be more efficient and accurate to detect and classify the cancerous tissues with computer-aided systems. METHODS: As classical image processing methods were used for cancer-type detection in early studies, advanced deep learning methods based on recurrent neural networks and convolutional neural networks have been used more recently. In this paper, popular deep learning methods such as ResNet-50, GoogLeNet, InceptionV3, and MobilNetV2 are employed by implementing novel feature selection method in order to classify cancer type on a local binary class dataset and multi-class BACH dataset. RESULTS: The classification performance of the proposed feature selection implemented deep learning methods follows as for the local binary class dataset 98.89% and 92.17% for BACH dataset which is much better than most of the obtained results in literature. CONCLUSION: The obtained findings on both datasets indicates that the proposed methods can detect and classify the cancerous type of a tissue with high accuracy and efficiency.

Ceusia-Breast: computer-aided diagnosis with contrast enhanced ultrasound image analysis for breast lesions.

BACKGROUND: In recent years, contrast-enhanced ultrasonography (CEUS) has been used for various applications in breast diagnosis. The superiority of CEUS over conventional B-mode imaging in the ultrasound diagnosis of the breast lesions in clinical practice has been widely confirmed. On the other hand, there have been many proposals for computer-aided diagnosis of breast lesions on B-mode ultrasound images, but few for CEUS. We propose a semi-automatic classification method based on machine learning in CEUS of breast lesions. METHODS: The proposed method extracts spatial and temporal features from CEUS videos and breast tumors are classified as benign or malignant using linear support vector machines (SVM) with combination of selected optimal features. In the proposed method, tumor regions are extracted using the guidance information specified by the examiners, then morphological and texture features of tumor regions obtained from B-mode and CEUS images and TIC features obtained from CEUS video are extracted. Then, our method uses SVM classifiers to classify breast tumors as benign or malignant. During SVM training, many features are prepared, and useful features are selected. We name our proposed method "Ceucia-Breast" (Contrast Enhanced UltraSound Image Analysis for BREAST lesions). RESULTS: The experimental results on 119 subjects show that the area under the receiver operating curve, accuracy, precision, and recall are 0.893, 0.816, 0.841 and 0.920, respectively. The classification performance is improved by our method over conventional methods using only B-mode images. In addition, we confirm that the selected features are consistent with the CEUS guidelines for breast tumor diagnosis. Furthermore, we conduct an experiment on the operator dependency of specifying guidance information and find that the intra-operator and inter-operator kappa coefficients are 1.0 and 0.798, respectively. CONCLUSION: The experimental results show a significant improvement in classification performance compared to conventional classification methods using only B-mode images. We also confirm that the selected features are related to the findings that are considered important in clinical practice. Furthermore, we verify the intra- and inter-examiner correlation in the guidance input for region extraction and confirm that both correlations are in strong agreement.

Evaluation of machine learning approaches for prediction of pigeon pea yield based on weather parameters in India.

Pigeon pea is the second most important grain legume in India, primarily grown under rainfed conditions. Any changes in agro-climatic conditions will have a profound influence on the productivity of pigeon pea (Cajanus cajan) yield and, as a result, the total pulse production of the country. In this context, weather-based crop yield prediction will enable farmers, decision-makers, and administrators in dealing with hardships. The current study examines the application of the stepwise linear regression method, supervised machine learning algorithms (support vector machines (SVM) and random forest (RF)), shrinkage regression approaches (least absolute shrinkage and selection operator (LASSO) or elastic net (ENET)), and artificial neural network (ANN) model for pigeon pea yield prediction using long-term weather data. Among the approaches, ANN resulted in a higher coefficient of determination (R2 = 0.88-0.99), model efficiency (0.88-1.00) with subsequent lower normalised root mean square error (nRMSE) during calibration (1.13-12.55%), and validation (0.33-21.20%) over others. The temperature alone or its interaction with other weather parameters was identified as the most influencing variables in the study area. The Pearson correlation coefficients were also determined for the observed and predicted yield. Those values also showed ANN as the best model with correlation values ranging from 0.939 to 0.999 followed by RF (0.955-0.982) and LASSO (0.880-0.982). However, all the approaches adopted in the study were outperformed the statistical method, i.e. stepwise linear regression with lower error values and higher model efficiency. Thus, these approaches can be effectively used for precise yield prediction of pigeon pea over different districts of Karnataka in India.

Using Support Vector Machines for Facet Partitioning in Multidimensional Scaling.

In this article we focus on interpreting multidimensional scaling (MDS) configurations using facet theory. The facet theory approach is attempting to partition a representational space, facet by facet, into regions with certain simplifying constraints on the regions' boundaries (e.g., concentric circular sub-spaces). A long-standing problem has been the lack of computational methods for optimal facet-based partitioning. We propose using support vector machines (SVM) to perform this task. SVM is highly attractive for this purpose as they allow for linear as well as nonlinear classification boundaries in any dimensionality. Using various classical examples from the facet theory literature we elaborate on the combined use of MDS and SVM for facet-based partitioning. Different types of MDS are discussed, and options for SVM kernel specification, tuning, and performance evaluation are illustrated.

IoT Solutions and AI-Based Frameworks for Masked-Face and Face Recognition to Fight the COVID-19 Pandemic.

A global health emergency resulted from the COVID-19 epidemic. Image recognition techniques are a useful tool for limiting the spread of the pandemic; indeed, the World Health Organization (WHO) recommends the use of face masks in public places as a form of protection against contagion. Hence, innovative systems and algorithms were deployed to rapidly screen a large number of people with faces covered by masks. In this article, we analyze the current state of research and future directions in algorithms and systems for masked-face recognition. First, the paper discusses the importance and applications of facial and face mask recognition, introducing the main approaches. Afterward, we review the recent facial recognition frameworks and systems based on Convolution Neural Networks, deep learning, machine learning, and MobilNet techniques. In detail, we analyze and critically discuss recent scientific works and systems which employ machine learning (ML) and deep learning tools for promptly recognizing masked faces. Also, Internet of Things (IoT)-based sensors, implementing ML and DL algorithms, were described to keep track of the number of persons donning face masks and notify the proper authorities. Afterward, the main challenges and open issues that should be solved in future studies and systems are discussed. Finally, comparative analysis and discussion are reported, providing useful insights for outlining the next generation of face recognition systems.

CTSF: An Intrusion Detection Framework for Industrial Internet Based on Enhanced Feature Extraction and Decision Optimization Approach.

The traditional Transformer model primarily employs a self-attention mechanism to capture global feature relationships, potentially overlooking local relationships within sequences and thus affecting the modeling capability of local features. For Support Vector Machine (SVM), it often requires the joint use of feature selection algorithms or model optimization methods to achieve maximum classification accuracy. Addressing the issues in both models, this paper introduces a novel network framework, CTSF, specifically designed for Industrial Internet intrusion detection. CTSF effectively addresses the limitations of traditional Transformers in extracting local features while compensating for the weaknesses of SVM. The framework comprises a pre-training component and a decision-making component. The pre-training section consists of both CNN and an enhanced Transformer, designed to capture both local and global features from input data while reducing data feature dimensions. The improved Transformer simultaneously decreases certain training parameters within CTSF, making it more suitable for the Industrial Internet environment. The classification section is composed of SVM, which receives initial classification data from the pre-training phase and determines the optimal decision boundary. The proposed framework is evaluated on an imbalanced subset of the X-IIOTID dataset, which represent Industrial Internet data. Experimental results demonstrate that with SVM using both "linear" and "rbf" kernel functions, CTSF achieves an overall accuracy of 0.98875 and effectively discriminates minor classes, showcasing the superiority of this framework.

Advancing Network Security with AI: SVM-Based Deep Learning for Intrusion Detection.

With the rapid growth of social media networks and internet accessibility, most businesses are becoming vulnerable to a wide range of threats and attacks. Thus, intrusion detection systems (IDSs) are considered one of the most essential components for securing organizational networks. They are the first line of defense against online threats and are responsible for quickly identifying potential network intrusions. Mainly, IDSs analyze the network traffic to detect any malicious activities in the network. Today, networks are expanding tremendously as the demand for network services is expanding. This expansion leads to diverse data types and complexities in the network, which may limit the applicability of the developed algorithms. Moreover, viruses and malicious attacks are changing in their quantity and quality. Therefore, recently, several security researchers have developed IDSs using several innovative techniques, including artificial intelligence methods. This work aims to propose a support vector machine (SVM)-based deep learning system that will classify the data extracted from servers to determine the intrusion incidents on social media. To implement deep learning-based IDSs for multiclass classification, the CSE-CIC-IDS 2018 dataset has been used for system evaluation. The CSE-CIC-IDS 2018 dataset was subjected to several preprocessing techniques to prepare it for the training phase. The proposed model has been implemented in 100,000 instances of a sample dataset. This study demonstrated that the accuracy, true-positive recall, precision, specificity, false-positive recall, and F-score of the proposed model were 100%, 100%, 100%, 100%, 0%, and 100%, respectively.

A Support Vector Machine-Based Approach for Bolt Loosening Monitoring in Industrial Customized Vehicles.

Machine learning techniques have progressively emerged as important and reliable tools that, when combined with machine condition monitoring, can diagnose faults with even superior performance than other condition-based monitoring approaches. Furthermore, statistical or model-based approaches are often not applicable in industrial environments with a high degree of customization of equipment and machines. Structures such as bolted joints are a key part of the industry; therefore, monitoring their health is critical to maintaining structural integrity. Despite this, there has been little research on the detection of bolt loosening in rotating joints. In this study, vibration-based detection of bolt loosening in a rotating joint of a custom sewer cleaning vehicle transmission was performed using support vector machines (SVM). Different failures were analyzed for various vehicle operating conditions. Several classifiers were trained to evaluate the influence of the number and location of accelerometers used and to determine the best approach between specific models for each operating condition or a single model for all cases. The results showed that using a single SVM model with data from four accelerometers mounted both upstream and downstream of the bolted joint resulted in more reliable fault detection, with an overall accuracy of 92.4%.

A Model for Urban Environment Instance Segmentation with Data Fusion.

Fine-grained urban environment instance segmentation is a fundamental and important task in the field of environment perception for autonomous vehicles. To address this goal, a model was designed with LiDAR pointcloud data and camera image data as the subject of study, and the reliability of the model was enhanced using dual fusion at the data level and feature level. By introducing the Markov Random Field algorithm, the Support Vector Machine classification results were optimized according to the spatial contextual linkage while providing the model with the prerequisite of the differentiation of similar but foreign objects, and the object classification and instance segmentation of 3D urban environments were completed by combining the Mean Shift. The dual fusion approach in this paper is a method for the deeper fusion of data from different sources, and the model, designed more accurately, describes the categories of items in the environment with a classification accuracy of 99.3%, and segments the different individuals into groups of the same kind of objects without instance labels. Moreover, our model does not have high computational resource and time cost requirements, and is a lightweight, efficient, and accurate instance segmentation model.

HOMLC-Hyperparameter Optimization for Multi-Label Classification of Intrusion Detection Data for Internet of Things Network.

The comparison of low-rank-based learning models for multi-label categorization of attacks for intrusion detection datasets is presented in this work. In particular, we investigate the performance of three low-rank-based machine learning (LR-SVM) and deep learning models (LR-CNN), (LR-CNN-MLP) for classifying intrusion detection data: Low Rank Representation (LRR) and Non-negative Low Rank Representation (NLR). We also look into how these models' performance is affected by hyperparameter tweaking by using Guassian Bayes Optimization. The tests has been run on merging two intrusion detection datasets that are available to the public such as BoT-IoT and UNSW- NB15 and assess the models' performance in terms of key evaluation criteria, including precision, recall, F1 score, and accuracy. Nevertheless, all three models perform noticeably better after hyperparameter modification. The selection of low-rank-based learning models and the significance of the hyperparameter tuning log for multi-label classification of intrusion detection data have been discussed in this work. A hybrid security dataset is used with low rank factorization in addition to SVM, CNN and CNN-MLP. The desired multilabel results have been obtained by considering binary and multi-class attack classification as well. Low rank CNN-MLP achieved suitable results in multilabel classification of attacks. Also, a Gaussian-based Bayesian optimization algorithm is used with CNN-MLP for hyperparametric tuning and the desired results have been achieved using c and γ for SVM and α and ß for CNN and CNN-MLP on a hybrid dataset. The results show the label UDP is shared among analysis, DoS and shellcode. The accuracy of classifying UDP among three classes is 98.54%.

Working Mode Recognition of Non-Specific Radar Based on ResNet-SVM Learning Framework.

Mode recognition is a basic task to interpret the behavior of multi-functional radar. The existing methods need to train complex and huge neural networks to improve the recognition ability, and it is difficult to deal with the mismatch between the training set and the test set. In this paper, a learning framework based on residual neural network (ResNet) and support vector machine (SVM) is designed, to solve the problem of mode recognition for non-specific radar, called multi-source joint recognition framework (MSJR). The key idea of the framework is to embed the prior knowledge of radar mode into the machine learning model, and combine the manual intervention and automatic extraction of features. The model can purposefully learn the feature representation of the signal on the working mode, which weakens the impact brought by the mismatch between training and test data. In order to solve the problem of difficult recognition under signal defect conditions, a two-stage cascade training method is designed, to give full play to the data representation ability of ResNet and the high-dimensional feature classification ability of SVM. Experiments show that the average recognition rate of the proposed model, with embedded radar knowledge, is improved by 33.7% compared with the purely data-driven model. Compared with other similar state-of-the-art reported models, such as AlexNet, VGGNet, LeNet, ResNet, and ConvNet, the recognition rate is increased by 12%. Under the condition of 0-35% leaky pulses in the independent test set, MSJR still has a recognition rate of more than 90%, which also proves its effectiveness and robustness in the recognition of unknown signals with similar semantic characteristics.