Evolutionary Computation Based Optimization of Image Zernike Moments Shape Feature Vector

The image shape feature can be described by the image Zernike moments. In this paper, we points out the problem that the high dimension image Zernike moments shape feature vector can describe more detail of the original image but has too many elements making trouble for the next image analysis phases. Then the low dimension image Zernike moments shape feature vector should be improved and optimized to describe more detail of the original image. So the optimization algorithm based on evolutionary computation is designed and implemented in this paper to solve this problem. The experimental results demonstrate the feasibility of the optimization algorithm.

MRMR Based Feature Vector Design for Efficient Citrus Disease Detection

In recent times,the images and videos have emerged as one of the most important information source depicting the real time scenarios.Digital images nowadays serve as input for many applications and replacing the manual methods due to their capabilities of 3D scene representation in 2D plane.The capabilities of digital images along with utilization of machine learning methodologies are showing promising accuracies in many applications of prediction and pattern recognition.One of the application fields pertains to detection of diseases occurring in the plants,which are destroying the widespread fields.Traditionally the disease detection process was done by a domain expert using manual examination and laboratory tests.This is a tedious and time consuming process and does not suffice the accuracy levels.This creates a room for the research in developing automation based methods where the images captured through sensors and cameras will be used for detection of disease and control its spreading.The digital images captured from the field’s forms the dataset which trains the machine learning models to predict the nature of the disease.The accuracy of these models is greatly affected by the amount of noise and ailments present in the input images,appropriate segmentation methodology,feature vector development and the choice of machine learning algorithm.To ensure the high rated performance of the designed system the research is moving in a direction to fine tune each and every stage separately considering their dependencies on subsequent stages.Therefore the most optimum solution can be obtained by considering the image processing methodologies for improving the quality of image and then applying statistical methods for feature extraction and selection.The training vector thus developed is capable of presenting the relationship between the feature values and the target class.In this article,a highly accurate system model for detecting the diseases occurring in citrus fruits using a hybrid feature development approach is proposed.The overall improvement in terms of accuracy is measured and depicted.

A rapid audio event detection method by adopting 2D-Haar acoustic super feature vector

For accuracy and rapidity of audio event detection in the mass-data audio pro- cessing tasks, a generic method of rapidly recognizing audio event based on 2D-Haar acoustic super feature vector and AdaBoost is proposed. Firstly, it combines certain number of con- tinuous audio frames to be an ＂acoustic feature image＂, secondly, uses AdaBoost.MH or fast Random AdaBoost feature selection algorithm to select high representative 2D-Haar pattern combinations to construct super feature vectors; thirdly, analyzes the commonality and differ- ences between subcategories, then extracts common features and reduces different features to obtain a generic audio event template, which can support the accurate identification of multi- ple sub-classes and detect and locate the specific audio event from the audio stream accurately. Experimental results show that the use of 2D-Haar acoustic feature super vector can make recog- nition accuracy 5% higher than ones that MFCC, PLP, LPCC and other traditional acoustic features yielded, and can make tile training processing 7 20 times faster and the recognition processing 5-10 times faster, it can even achieve an average precision of 93.38%, an average recall of 95.03% under the optimal parameter configuration found by grid method. Above all, it can provide an accurate and fast mass-data processing method for audio event detection.

Feature Selection by Merging Sequential Bidirectional Search into Relevance Vector Machine in Condition Monitoring

For more accurate fault detection and diagnosis, there is an increasing trend to use a large number of sensors and to collect data at high frequency. This inevitably produces large-scale data and causes difficulties in fault classification. Actually, the classification methods are simply intractable when applied to high-dimensional condition monitoring data. In order to solve the problem, engineers have to resort to complicated feature extraction methods to reduce the dimensionality of data. However, the features transformed by the methods cannot be understood by the engineers due to a loss of the original engineering meaning. In this paper, other forms of dimensionality reduction technique（feature selection methods） are employed to identify machinery condition, based only on frequency spectrum data. Feature selection methods are usually divided into three main types： filter, wrapper and embedded methods. Most studies are mainly focused on the first two types, whilst the development and application of the embedded feature selection methods are very limited. This paper attempts to explore a novel embedded method. The method is formed by merging a sequential bidirectional search algorithm into scale parameters tuning within a kernel function in the relevance vector machine. To demonstrate the potential for applying the method to machinery fault diagnosis, the method is implemented to rolling bearing experimental data. The results obtained by using the method are consistent with the theoretical interpretation, proving that this algorithm has important engineering significance in revealing the correlation between the faults and relevant frequency features. The proposed method is a theoretical extension of relevance vector machine, and provides an effective solution to detect the fault-related frequency components with high efficiency.

Fault Diagnosis Model Based on Feature Compression with Orthogonal Locality Preserving Projection

Based on feature compression with orthogonal locality preserving projection（OLPP）,a novel fault diagnosis model is proposed in this paper to achieve automation and high-precision of fault diagnosis of rotating machinery.With this model,the original vibration signals of training and test samples are first decomposed through the empirical mode decomposition（EMD）,and Shannon entropy is constructed to achieve high-dimensional eigenvectors.In order to replace the traditional feature extraction way which does the selection manually,OLPP is introduced to automatically compress the high-dimensional eigenvectors of training and test samples into the low-dimensional eigenvectors which have better discrimination.After that,the low-dimensional eigenvectors of training samples are input into Morlet wavelet support vector machine（MWSVM） and a trained MWSVM is obtained.Finally,the low-dimensional eigenvectors of test samples are input into the trained MWSVM to carry out fault diagnosis.To evaluate our proposed model,the experiment of fault diagnosis of deep groove ball bearings is made,and the experiment results indicate that the recognition accuracy rate of the proposed diagnosis model for outer race crack、inner race crack and ball crack is more than 90%.Compared to the existing approaches,the proposed diagnosis model combines the strengths of EMD in fault feature extraction,OLPP in feature compression and MWSVM in pattern recognition,and realizes the automation and high-precision of fault diagnosis.

Symbiotic Organisms Search with Deep Learning Driven Biomedical Osteosarcoma Detection and Classification

Osteosarcoma is one of the rare bone cancers that affect the individualsaged between 10 and 30 and it incurs high death rate. Early diagnosisof osteosarcoma is essential to improve the survivability rate and treatmentprotocols. Traditional physical examination procedure is not only a timeconsumingprocess, but it also primarily relies upon the expert’s knowledge.In this background, the recently developed Deep Learning (DL) models canbe applied to perform decision making. At the same time, hyperparameteroptimization of DL models also plays an important role in influencing overallclassification performance. The current study introduces a novel SymbioticOrganisms Search with Deep Learning-driven Osteosarcoma Detection andClassification (SOSDL-ODC) model. The presented SOSDL-ODC techniqueprimarily focuses on recognition and classification of osteosarcoma usinghistopathological images. In order to achieve this, the presented SOSDL-ODCtechnique initially applies image pre-processing approach to enhance the qualityof image. Also, MobileNetv2 model is applied to generate a suitable groupof feature vectors whereas hyperparameter tuning of MobileNetv2 modelis performed using SOS algorithm. At last, Gated Recurrent Unit (GRU)technique is applied as a classification model to determine proper class labels.In order to validate the enhanced osteosarcoma classification performance ofthe proposed SOSDL-ODC technique, a comprehensive comparative analysiswas conducted. The obtained outcomes confirmed the betterment of SOSDLODCapproach than the existing approaches as the former achieved a maximumaccuracy of 97.73%.

Robust Multi-Watermarking Algorithm for Medical Images Based on GoogLeNet and Henon Map

The field of medical images has been rapidly evolving since the advent of the digital medical information era.However,medical data is susceptible to leaks and hacks during transmission.This paper proposed a robust multi-watermarking algorithm for medical images based on GoogLeNet transfer learning to protect the privacy of patient data during transmission and storage,as well as to increase the resistance to geometric attacks and the capacity of embedded watermarks of watermarking algorithms.First,a pre-trained GoogLeNet network is used in this paper,based on which the parameters of several previous layers of the network are fixed and the network is fine-tuned for the constructed medical dataset,so that the pre-trained network can further learn the deep convolutional features in the medical dataset,and then the trained network is used to extract the stable feature vectors of medical images.Then,a two-dimensional Henon chaos encryption technique,which is more sensitive to initial values,is used to encrypt multiple different types of watermarked private information.Finally,the feature vector of the image is logically operated with the encrypted multiple watermark information,and the obtained key is stored in a third party,thus achieving zero watermark embedding and blind extraction.The experimental results confirmthe robustness of the algorithm from the perspective ofmultiple types of watermarks,while also demonstrating the successful embedding ofmultiple watermarks for medical images,and show that the algorithm is more resistant to geometric attacks than some conventional watermarking algorithms.

Modeling a Novel Hyper-Parameter Tuned Deep Learning Enabled Malaria Parasite Detection and Classification

A theoretical methodology is suggested for finding the malaria parasites’presence with the help of an intelligent hyper-parameter tuned Deep Learning(DL)based malaria parasite detection and classification(HPTDL-MPDC)in the smear images of human peripheral blood.Some existing approaches fail to predict the malaria parasitic features and reduce the prediction accuracy.The trained model initiated in the proposed system for classifying peripheral blood smear images into the non-parasite or parasite classes using the available online dataset.The Adagrad optimizer is stacked with the suggested pre-trained Deep Neural Network(DNN)with the help of the contrastive divergence method to pre-train.The features are extracted from the images in the proposed system to train the DNN for initializing the visible variables.The smear images show the concatenated feature to be utilized as the feature vector in the proposed system.Lastly,hyper-parameters are used to fine-tune DNN to calculate the class labels’probability.The suggested system outperforms more modern methodologies with an accuracy of 91%,precision of 89%,recall of 93%and F1-score of 91%.The HPTDL-MPDC has the primary application in detecting the parasite of malaria in the smear images of human peripheral blood.

A Hand Gesture Recognition Method Based on SVM

A hand gesture recognition method is presented for human-computer interaction, which is based on fingertip localization. First, hand gesture is segmented from the background based on skin color characteristics. Second, feature vectors are selected with equal intervals on the boundary of the gesture, and then gestures＇ length normalization is accomplished. Third, the fingertip positions are determined by the feature vectors＇ parameters, and angles of feature vectors are normalized. Finally the gestures are classified by support vector machine. The experimental results demonstrate that the proposed method can recognize 9 gestures with an accuracy of 94.1%.

Implementation of Texture Based Image Retrieval Using M-band Wavelet Transform

Wavelet transform has attracted attention because it is a very useful tool for signal analyzing. As a fundamental characteristic of an image, texture traits play an important role in the human vision system for recognition and interpretation of images. The paper presents an approach to implement texture-based image retrieval using M-band wavelet transform. Firstly the traditional 2-band wavelet is extended to M-band wavelet transform. Then the wavelet moments are computed by M-band wavelet coefficients in the wavelet domain. The set of wavelet moments forms the feature vector related to the texture distribution of each wavelet images. The distances between the feature vectors describe the similarities of different images. The experimental result shows that the M-band wavelet moment features of the images are effective for image indexing. The retrieval method has lower computational complexity, yet it is capable of giving better retrieval performance for a given medical image database.

ILipo-PseAAC: Identification of Lipoylation Sites Using Statistical Moments and General PseAAC

Lysine Lipoylation is a protective and conserved Post Translational Modification(PTM)in proteomics research like prokaryotes and eukaryotes.It is connected with many biological processes and closely linked with many metabolic diseases.To develop a perfect and accurate classification model for identifying lipoylation sites at the protein level,the computational methods and several other factors play a key role in this purpose.Usually,most of the techniques and different traditional experimental models have a very high cost.They are time-consuming;so,it is required to construct a predictor model to extract lysine lipoylation sites.This study proposes a model that could predict lysine lipoylation sites with the help of a classification method known as Artificial Neural Network(ANN).The ANN algorithm deals with the noise problem and imbalance classification in lipoylation sites dataset samples.As the result shows in ten-fold cross-validation,a brilliant performance is achieved through the predictor model with an accuracy of 99.88%,and also achieved 0.9976 as the highest value of MCC.So,the predictor model is a very useful and helpful tool for lipoylation sites prediction.Some of the residues around lysine lipoylation sites play a vital part in prediction,as demonstrated during feature analysis.The wonderful results reported through the evaluation and prediction of this model can provide an informative and relative explanation for lipoylation and its molecular mechanisms.

A new parallel algorithm for image matching based on entropy

Presents a new parallel image matching algorithm based on the concept of entropy feature vector and suitable to SIMD computer, which, in comparison with other algorithms, has the following advantages:(1)The spatial information of an image is appropriately introduced into the definition of image entropy. (2) A large number of multiplication operations are eliminated, thus the algorithm is sped up. (3) The shortcoming of having to do global calculation in the first instance is overcome, and concludes the algorithm has very good locality and is suitable for parallel processing.

Binaural Speech Separation Algorithm Based on Long and Short Time Memory Networks

Speaker separation in complex acoustic environment is one of challenging tasks in speech separation.In practice,speakers are very often unmoving or moving slowly in normal communication.In this case,the spatial features among the consecutive speech frames become highly correlated such that it is helpful for speaker separation by providing additional spatial information.To fully exploit this information,we design a separation system on Recurrent Neural Network(RNN)with long short-term memory(LSTM)which effectively learns the temporal dynamics of spatial features.In detail,a LSTM-based speaker separation algorithm is proposed to extract the spatial features in each time-frequency(TF)unit and form the corresponding feature vector.Then,we treat speaker separation as a supervised learning problem,where a modified ideal ratio mask(IRM)is defined as the training function during LSTM learning.Simulations show that the proposed system achieves attractive separation performance in noisy and reverberant environments.Specifically,during the untrained acoustic test with limited priors,e.g.,unmatched signal to noise ratio(SNR)and reverberation,the proposed LSTM based algorithm can still outperforms the existing DNN based method in the measures of PESQ and STOI.It indicates our method is more robust in untrained conditions.

ROBUST ZERO-WATERMARK ALGORITHMS BASED ON NUMERICAL RELATIONSHIP BETWEEN ADJACENT BLOCKS

In this paper, three robust zero-watermark algorithms named Direct Current coefficient RElationship (DC-RE), CUmulant combined Singular Value Decomposition (CU-SVD), and CUmulant combined Singular Value Decomposition RElationship (CU-SVD-RE) are proposed. The algorithm DC-RE gets the feature vector from the relationship of DC coefficients between adjacent blocks, CU-SVD gets the feature vector from the singular value of third-order cumulants, while CU-SVD-RE combines the essence of the first two algorithms. Specially, CU-SVD-RE gets the feature vector from the relationship between singular values of third-order cumulants. Being a cross-over studying field of watermarking and cryptography, the zero-watermark algorithms are robust without modifying the carrier. Numerical simulation obviously shows that, under geometric attacks, the performance of CU-SVD-RE and DC-RE algorithm are better and all three proposed algorithms are robust to various attacks, such as median filter, salt and pepper noise, and Gaussian low-pass filter attacks.

Historical Arabic Images Classification and Retrieval Using Siamese Deep Learning Model

Classifying the visual features in images to retrieve a specific image is a significant problem within the computer vision field especially when dealing with historical faded colored images.Thus,there were lots of efforts trying to automate the classification operation and retrieve similar images accurately.To reach this goal,we developed a VGG19 deep convolutional neural network to extract the visual features from the images automatically.Then,the distances among the extracted features vectors are measured and a similarity score is generated using a Siamese deep neural network.The Siamese model built and trained at first from scratch but,it didn’t generated high evaluation metrices.Thus,we re-built it from VGG19 pre-trained deep learning model to generate higher evaluation metrices.Afterward,three different distance metrics combined with the Sigmoid activation function are experimented looking for the most accurate method formeasuring the similarities among the retrieved images.Reaching that the highest evaluation parameters generated using the Cosine distance metric.Moreover,the Graphics Processing Unit(GPU)utilized to run the code instead of running it on the Central Processing Unit(CPU).This step optimized the execution further since it expedited both the training and the retrieval time efficiently.After extensive experimentation,we reached satisfactory solution recording 0.98 and 0.99 F-score for the classification and for the retrieval,respectively.

Cross-task emotion recognition using EEG measures: first step towards practical application

Electroencephalographic(EEG)-based emotion recognition has received increasing attention in the field of human-computer interaction(HCI)recently,there however remains a number of challenges in building a generalized emotion recognition model,one of which includes the difficulty of an EEG-based emotion classifier trained on a specific task to handle other tasks.Lit-tle attention has been paid to this issue.The current study is to determine the feasibility of coping with this challenge using feature selection.12 healthy volunteers were emotionally elicited when conducting picture induced and videoinduced tasks.Firstly,support vector machine(SVM)classifier was examined under within-task conditions(trained and tested on the same task)and cross-task conditions(trained on one task and tested on another task)for pictureinduced and videoinduced tasks.The within-task classification performed fairly well(classification accuracy:51.6%for picture task and 94.4%for video task).Cross-task classification,however,deteriorated to low levels(around 44%).Trained and tested with the most robust feature subset selected by SVM-recursive feature elimination(RFE),the performance of cross-task classifier was significantly improved to above 68%.These results suggest that cross-task emotion recognition is feasible with proper methods and bring EEG-based emotion recognition models closer to being able to discriminate emotion states for any tasks.

Clustering feature decision trees for semi-supervised classification from high-speed data streams

Most stream data classification algorithms apply the supervised learning strategy which requires massive labeled data.Such approaches are impractical since labeled data are usually hard to obtain in reality.In this paper,we build a clustering feature decision tree model,CFDT,from data streams having both unlabeled and a small number of labeled examples.CFDT applies a micro-clustering algorithm that scans the data only once to provide the statistical summaries of the data for incremental decision tree induction.Micro-clusters also serve as classifiers in tree leaves to improve classification accuracy and reinforce the any-time property.Our experiments on synthetic and real-world datasets show that CFDT is highly scalable for data streams while gener-ating high classification accuracy with high speed.

Unmanned vehicle dynamic obstacle detection,tracking and recognition method based on laser sensor

Purpose-In response to these shortcomings,this paper proposes a dynamic obstacle detection and tracking method based on multi-feature fusion and a dynamic obstacle recognition method based on spatio-temporal feature vectors.Design/methodology/approach-The existing dynamic obstacle detection and tracking methods based on geometric features have a high false detection rate.The recognition methods based on the geometric features and motion status of dynamic obstacles are greatly affected by distance and scanning angle,and cannot meet the requirements of real traffic scene applications.Findings-First,based on the geometric features of dynamic obstacles,the obstacles are considered The echo pulse width feature is used to improve the accuracy of obstacle detection and tracking;second,the space-time feature vector is constructed based on the time dimension and space dimension information of the obstacle,and then the support vector machine method is used to realize the recognition of dynamic obstacles to improve the obstacle The accuracy of object recognition.Finally,the accuracy and effectiveness of the proposed method are verified by real vehicle tests.Originality/value-The paper proposes a dynamic obstacle detection and tracking method based on multi-feature fusion and a dynamic obstacle recognition method based on spatio-temporal feature vectors.The accuracy and effectiveness of the proposed method are verified by real vehicle tests.

Diagnosing Traffic Anomalies Using a Two-Phase Model

Network traffic anomalies are unusual changes in a network,so diagnosing anomalies is important for network management.Feature-based anomaly detection models （ab）normal network traffic behavior by analyzing packet header features.PCA-subspace method （Principal Component Analysis） has been verified as an efficient feature-based way in network-wide anomaly detection.Despite the powerful ability of PCA-subspace method for network-wide traffic detection,it cannot be effectively used for detection on a single link.In this paper,different from most works focusing on detection on flow-level traffic,based on observations of six traffic features for packet-level traffic,we propose a new approach B6SVM to detect anomalies for packet-level traffic on a single link.The basic idea of B6-SVM is to diagnose anomalies in a multi-dimensional view of traffic features using Support Vector Machine （SVM）.Through two-phase classification,B6-SVM can detect anomalies with high detection rate and low false alarm rate.The test results demonstrate the effectiveness and potential of our technique in diagnosing anomalies.Further,compared to previous feature-based anomaly detection approaches,B6-SVM provides a framework to automatically identify possible anomalous types.The framework of B6-SVM is generic and therefore,we expect the derived insights will be helpful for similar future research efforts.

Two-Stream Temporal Convolutional Networks for Skeleton-Based Human Action Recognition

With the growing popularity of somatosensory interaction devices,human action recognition is becoming attractive in many application scenarios.Skeleton-based action recognition is effective because the skeleton can represent the position and the structure of key points of the human body.In this paper,we leverage spatiotemporal vectors between skeleton sequences as input feature representation of the network,which is more sensitive to changes of the human skeleton compared with representations based on distance and angle features.In addition,we redesign residual blocks that have different strides in the depth of the network to improve the processing ability of the temporal convolutional networks(TCNs)for long time dependent actions.In this work,we propose the two-stream temporal convolutional networks(TSTCNs)that take full advantage of the inter-frame vector feature and the intra-frame vector feature of skeleton sequences in the spatiotemporal representations.The framework can integrate different feature representations of skeleton sequences so that the two feature representations can make up for each other’s shortcomings.The fusion loss function is used to supervise the training parameters of the two branch networks.Experiments on public datasets show that our network achieves superior performance and attains an improvement of 1.2%over the recent GCN-based(BGC-LSTM)method on the NTU RGB+D dataset.