Search

Driver fatigue is a contributing factor in about 20% of all fatal road crashes worldwide. Countermeasures are urgently needed and one of the most promising and currently available approaches for that are in-vehicle systems for driver fatigue detection. The main objective of this paper is to present a video-based driver sleepiness detection system set up as a two-stage model with (1) a generic deep feature extraction module combined with (2) a personalised sleepiness detection module. The approach was designed and evaluated using data from 13 drivers, collected during naturalistic driving conditions on a motorway in Sweden. Each driver performed one 90-minute driving session during daytime (low sleepiness condition) and one session during night-time (high sleepiness condition). The sleepiness detection model outputs a continuous output representing the Karolinska Sleepiness Scale (KSS) scale from 1-9 or a binary decision as alert (defined as KSS 1-6) or sleepy (defined as KSS 7-9). Continuous output modelling resulted in a mean absolute error (MAE) of 0.54 KSS units. Binary classification of alert or sleepy showed an accuracy of 92% (sensitivity = 91.7%, specificity = 92.3%, F1 score = 90.4%). Without personalisation, the corresponding accuracy was 72%, while a standard fatigue detection PERCLOS-based baseline method reached an accuracy of 68% on the same dataset. The developed real-time sleepiness detection model can be used in the management of sleepiness/fatigue by detecting precursors of severe fatigue, and ultimately reduce sleepiness-related road crashes by alerting drivers before high levels of fatigue are reached.

The accurate prediction of the remaining useful life (RUL) of rolling bearings is of immense importance in ensuring the safe and smooth operation of machinery and equipment. Although the prediction accuracy has been improved by a predictive model based on deep learning, it is still limited in engineering because lots of models use single-scale features to predict and assume that the degradation data of each bearing has a consistent distribution. In this paper, A deep convolutional migration network based on spatial pyramid pooling (SPP-CNNTL) is proposed to obtain higher prediction accuracy with self-extraction of multi-feature from the original vibrating signal. And to consider the differences of the data distribution in different failure types, transfer learning (TL) added with maximum mean difference (MMD) measurement function is used in the RUL prediction part. Finally, the data of IEEE PHM 2012 Challenge is used for verification, and the results show that the method in this paper has high prediction accuracy

Rolling bearing has been becoming an important part of human life and work. The working environment of rolling bearing is very complex and variable, which makes it difficult for fault diagnosis and monitor of rolling bearing from raw vibration data. Then, in this paper, a novel multi-feature learning-based extreme learning machine is proposed for rolling bearing fault diagnosis (FL-ELM). Extreme learning machine (ELM) is a fast and generalized algorithm proposed for training single-hidden-layer feed-forward networks (SLFNs), which has fast computing speed and small testing error. The novel architecture has two hidden layers and an experience pool sandwiched between two hidden layers. The first hidden layer consists of multi-feature learning methods. The experience pool is used to sort and choose new data, with old data being filtered out. Firstly, the first hidden layer is adopted for feature extraction. Secondly, the experience pool is used to rearrange and select data, which is extracted by first hidden layer. Thirdly, ELM is employed to further learn and classify. The proposed method (FL-ELM) is applied to the rolling bearing fault diagnosis. The results confirm that the proposed method is more effective than traditional methods and standard deep learning methods.

Background: Forecasting of time series stock data is important in financial related works. Stock data usually have multifeatures such as opening price, closing price and so on. The traditional forecast methods, however, is mainly applied to one feature – closing price, or a few, like four or five features. The massive information hidden in the multi-feature data is not thoroughly discovered and used. Objective: Find a method to make used of all information of multi-features and get a forecast model. Method: LSTM based models are introduced in this paper. For comparison, three models are used and they are single LSTM model, hybrid model of LSTM-CNN, and traditional ARIMA model. Results: Experiments with different models are performed on stock data with 50 and 230 features, respectively. Results show that MSE of single LSTM model is 2.4% lower than ARIMA model and MSE of LSTM-CNN model is 12.57% lower than that of single LSTM model on 50 features data. On 230 features data, LSTM-CNN model is found to be improved by 23.41% in forecast accuracy. Conclusion: In this paper, we use three different models – ARIMA, single LSTM and LSTM-CNN hybrid model – to forecast rise and fall of multi-features stock data. It’s found that single LSTM model is better than traditional ARIMA model on the average, and LSTM-CNN hybrid model is better than single LSTM model on 50-feature stock data. What’s more, we use LSTM-CNN model to perform experiments on stock data with 50 and 230 features, respectively. And is found that results of the same model on 230 features data is better than that on 50 features data. It’s proved in our work that the LSTM-CNN hybrid model is better than other models and experiments on stock data with more features could result in better outcomes. We’ll do more works on hybrid models next.

Purpose The major problem that limits the widespread use of WAAM technology is the forming quality. However, most of the current research focuses on post-process detections that are time-consuming, expensive and destructive. This paper aims to achieve the on-line detection and classification of the common defects, including hump, deposition collapse, deviation, internal pore and surface slag inclusion. Design/methodology/approach This paper proposes an in-process multi-feature data fusion nondestructive testing method based on the temperature field of the WAAM process. A thermal imager is used to collect the temperature data of the deposition layer in real-time. Efficient processing methods are proposed in this paper, such as the temperature stack algorithm, width extraction algorithm and a classification model based on a residual neural network. Some features closely related to the forming quality were extracted, containing the profile image and width curve of the deposition layer and abnormal temperature features in longitudinal and cross-sections. These features are used to achieve the detection and classification of defects. Findings Thermal non-destructive testing is a potentially superior technology for in-process detection in the industrial field. Based on the temperature field, extracting the most relevant features of the defect information is crucial. This paper pushes current infrared (IR) monitoring methods toward real-time detection and proposes an in-process multi-feature data fusion non-destructive testing method based on the temperature field of the WAAM process. Originality/value In this paper, the single-layer and multi-layer WAAM samples are preset with various defects, such as hump, deposition collapse, deviation, pore and slag inclusion. A multi-feature nondestructive testing methodology is proposed to realize the in-process detection and classification of the defects. A temperature stack algorithm is proposed, which improves the detection accuracy of profile change and solves the problem of uneven temperature from arc striking to arc extinguishing. The combination of residual neural network greatly improves the accuracy and efficiency of detection.

Diabetic Retinopathy (DR) is a severe complication of chronic diabetes causing significant visual deterioration and may lead to blindness with delay of being treated. Exudative diabetic maculopathy, a form of macular edema where hard exudates (HE) develop, is a frequent cause of visual deterioration in DR. The detection of HE comprises a significant role in the DR diagnosis. In this paper, an automatic exudates detection method based on superpixel multi-feature extraction and patch-based deep convolutional neural network is proposed. Firstly, superpixels, regarded as candidates, are generated on each resized image using the superpixel segmentation algorithm called Simple Linear Iterative Clustering (SLIC). Then, 25 features extracted from resized images and patches are generated on each feature. Patches are subsequently used to train a deep convolutional neural network, which distinguishes the hard exudates from the background. Experiments conducted on three publicly available datasets (DiaretDB1, e-ophtha EX and IDRiD) demonstrate that our proposed methodology achieved superior HE detection when compared with current state-of-art algorithms.

A speech emotion recognition algorithm based on multi-feature and Multi-lingual fusion is proposed in order to resolve low recognition accuracy caused bylack of large speech dataset and low robustness of acoustic features in the recognition of speech emotion. First, handcrafted and deep automatic features are extractedfrom existing data in Chinese and English speech emotions. Then, the various features are fused respectively. Finally, the fused features of different languages are fused again and trained in a classification model. Distinguishing the fused features with the unfused ones, the results manifest that the fused features significantly enhance the accuracy of speech emotion recognition algorithm. The proposedsolution is evaluated on the two Chinese corpus and two English corpus, and isshown to provide more accurate predictions compared to original solution. As a result of this study, the multi-feature and Multi-lingual fusion algorithm can significantly improve the speech emotion recognition accuracy when the dataset is small.

In order to solve the problem of crop disease detection in large-scale planting, a new crop disease detection algorithm based on multi-feature decision fusion is proposed. This paper proposes a multi-feature decision fusion disease discrimination algorithm (PD R-CNN) based on machine vision on crop surfaces. The algorithm is based on the machine vision processing model of R-CNN and integrates a disease discrimination algorithm on the basis of R-CNN. After training on crop image data sets, PD R-CNN can reach the goal of identifying crop surface lesions. This paper uses machine vision image acquisition, image processing and analysis technology to collect and analyze the growth of cucumber seedlings. The research results show that compared with manual judgment, PD R-CNN reduces the workload and can effectively distinguish crop diseases. Through experiments, during the occurrence of pests and diseases, PD R-CNN has a monitoring accuracy of 88.0% for mosaic disease, 92.0% for root rot, 88.0% for powdery mildew, and 86.0% for aphids, indicating that there are errors in actual monitoring, but the accuracy exceeds 85.0% can be put into use.

The quality of "non-landslide' samples data impacts the accuracy of geological hazard risk assessment. This research proposed a method to improve the performance of support vector machine (SVM) by perfecting the quality of `non-landslide' samples in the landslide susceptibility evaluation model through fuzzy c-means (FCM) cluster to generate more reliable susceptibility maps. Firstly, three sample selection scenarios for `non-landslide' samples include the following principles: 1) select randomly from low-slope areas (scenario-SS), 2) select randomly from areas with no hazards (scenarioRS), 3) obtain samples from the optimal FCM model (scenario-FCM), and then three sample scenarios are constructed with 10,193 landslide positive samples. Next, we have compared and evaluated the performance of three sample scenarios in the SVM models based on the statistical indicators such as the proportion of disaster points, density of disaster points precision, receiver operating characteristic (ROC) curve, and area under the ROC curve (AUC). Finally, The evaluation results show that the `non-landslide' negative samples based on the FCM model are more reasonable. Furthermore, the hybrid method supported by SVM and FCM models exhibits the highest prediction efficiency. Scenario FCM produces an overall accuracy of approximately 89.7% (AUC), followed by scenario-SS (86.7%) and scenario-RS (85.6%).

Graphical abstract, As a novel lactate-derived post-translational modification (PTM), lysine lactylation (Kla) is involved in diverse biological processes, and participates in human tumorigenesis. Identification of Kla substrates with their exact sites is crucial for revealing the molecular mechanisms of lactylation. In contrast with labor-intensive and time-consuming experimental approaches, computational prediction of Kla could provide convenience and increased speed, but is still lacking. In this work, although current identified Kla sites are limited, we constructed the first Kla benchmark dataset and developed a few-shot learning-based architecture approach to leverage the power of small datasets and reduce the impact of imbalance and overfitting. A maximum 11.7% (0.745 versus 0.667) increase of area under the curve (AUC) value was achieved in contrast to conventional machine learning methods. We conducted a comprehensive survey of the performance by combining 8 sequence-based features and 3 structure-based features and tailored a multi-feature hybrid system for synergistic combination. This system achieved >16.2% improvement of the AUC value (0.889 versus 0.765) compared with single feature-based models for the prediction of Kla sites in silico. Taken few-shot learning and hybrid system together, we present our newly designed predictor named FSL-Kla, which is not only a cutting-edge tool for Kla site profile but also could generate candidates for further experimental approaches. The webserver of FSL-Kla is freely accessible for academic research at http://kla.zbiolab.cn/.

The effect of motion posture recognition hinges on the accurate description of motion postures with effective feature information. This study introduces Wronskian function to improve the denoising ability of visual background extractor (ViBe) algorithm, and thus acquires relatively clear motion targets. Then, a multi-feature fusion motion posture feature model was developed based on genetic algorithm (GA). Specifically, GA was called to optimize and fuse the extracted feature information, while a fitness function was constructed based on the mean variance ratio, and used to select the feature information with high inter-class discriminability. Taking support vector machine (SVM) as the classifier, a multi-class classifier was designed by one-to-one method for the classification and recognition of motion postures. Through experiments, our model was proved highly accurate in motion posture recognition.

PurposeWorkpiece sorting is a key link in industrial production lines. The vision-based workpiece sorting system is non-contact and widely applicable. The detection and recognition of workpieces are the key technologies of the workpiece sorting system. To introduce deep learning algorithms into workpiece detection and improve detection accuracy, this paper aims to propose a workpiece detection algorithm based on the single-shot multi-box detector (SSD).Design/methodology/approachPropose a multi-feature fused SSD network for fast workpiece detection. First, the multi-view CAD rendering images of the workpiece are used as deep learning data sets. Second, the visual geometry group network was trained for workpiece recognition to identify the category of the workpiece. Third, this study designs a multi-level feature fusion method to improve the detection accuracy of SSD (especially for small objects); specifically, a feature fusion module is added, which uses “element-wise sum” and “concatenation operation” to combine the information of shallow features and deep features.FindingsExperimental results show that the actual workpiece detection accuracy of the method can reach 96% and the speed can reach 41 frames per second. Compared with the original SSD, the method improves the accuracy by 7% and improves the detection performance of small objects.Originality/valueThis paper innovatively introduces the SSD detection algorithm into workpiece detection in industrial scenarios and improves it. A feature fusion module has been added to combine the information of shallow features and deep features. The multi-feature fused SSD network proves the feasibility and practicality of introducing deep learning algorithms into workpiece sorting.

The area of fingerprint image collected by mobile intelligent device is small, which will lead to the lack of extracted fingerprint feature information. In this study, a small area fingerprint encryption algorithm based on fingerprint mosaic was proposed. The experimental results on the real fingerprint database show that the proposed fingerprint mosaic method can significantly improve the performance of the small area fingerprint encryption algorithm, the acquisition failure rate decreased from 39% to 8%, and the correct acceptance rate increased from 48% to 69%. The algorithm uses fingerprint feature mosaic technology and fingerprint image mosaic technology to effectively increase fingerprint feature information.

Medical image segmentation is a challenging task especially in multimodality medical image analysis. In this paper, an improved pulse coupled neural network based on multiple hybrid features grey wolf optimizer (MFGWO-PCNN) is proposed for multimodality medical image segmentation. Specifically, a two-stage medical image segmentation method based on bionic algorithm is presented, including image fusion and image segmentation. The image fusion stage fuses rich information from different modalities by utilizing a multimodality medical image fusion model based on maximum energy region. In the stage of image segmentation, an improved PCNN model based on MFGWO is proposed, which can adaptively set the parameters of PCNN according to the features of the image. Two modalities of FLAIR and T1C brain MRIs are applied to verify the effectiveness of the proposed MFGWO-PCNN algorithm. The experimental results demonstrate that the proposed method outperforms the other seven algorithms in subjective vision and objective evaluation indicators.

Image alignment and colour consistency are two challenging tasks for image stitching. Traditional point correspondence methods are difficult to achieve good alignments due to their insufficiency and unreliability. The results are prone to errors and distortions. On the other hand, the problem of colour inconsistency in overlapping area between image pairs is still difficult to solve, especially when the illumination difference between images is large. To solve these problems, the authors integrate point features and line features into a warping model through a designed energy function. Line features will provide geometric constraints for image stitching, and remedy the defect of point correspondences in low‐textured image stitching. A global colour consistency optimization method with colour mapping via a histogram extreme point‐matching algorithm is proposed. The colour characteristic of reference images will be transferred to the others to achieve a global colour consistency. The proposed method is evaluated on a series of images, and compared with other methods. The experiments demonstrate that the proposed method provides convincing stitching results and achieves satisfied colour consistency results.

At present, the recognition method based on character segmentation is not effective in recognizing English text, and the traditional methods are based on the structural features and statistical characteristics of strokes. In order to improve the recognition effect of in English text, from the perspective of machine learning, this study introduces multi-features to improve the lack of information caused by the small Chinese data set. Moreover, this study disassembles the character recognition problem into a text matching problem of question and answer, and the textual entailment problem of answer and standard answer and continues training on the data set of short text score. The final result has a certain improvement, which proves the usability of the mechanism designed in this paper. In order to study the performance of the model proposed in this paper, the model proposed in this paper and the neural network recognition model are compared in terms of recognition accuracy and recognition speed. The research results show that the algorithm proposed in this paper has a certain effect.

On-time recovery and treatment of disease is always desirable. The use of Machine learning in health-care has grown very fast to diagnosis the different kinds of diseases in the past few years. In such a diagnosis, past and real-time data are playing very crucial role in using data mining techniques. Still, we are lacking in diagnosing the emotional mental disturbance accurately in the early stages. Thus,the initial diagnosis of depression expressively stances a great problem for both,researchers and clinical professionals. We have addressed the said problem in our proposed work using Pipeline Machine Learning technique where people based on emotional stages have been effectively classified into different groups in e-healthcare. To implement Hybrid classification, a well known machine learning multi-feature hybrid classifier is used by having the emotional stimulation in form of negative or positive people. In order to improve classification, an Ensemble Learning Algorithm is used which helps in choosing the more suitable features from the available genres-emotion data on online media. Additionally, Hold out validation method has been to split the dataset for training and testing of the predictive model. Further, performance evaluation measures have been applied to check the proposed system evaluation. This study is done on Genres-Tags MovieLens dataset. The experimental results show that applied ensemble method provides optimal classification performance by choosing the best subset of features. The said results proved the excellency of the proposed system which comes from the choosing most related features selected by the Integrated Learning algorithm. Additionally, suggested approach is used to accurately and effectively diagnose the depression in its early stage. It will help in recovery and treatment of depressed people. We conclude that use of the suggested method is highly suitable in all aspects of e-healthcare for depress stimulation.

The Qomolangma National Nature Reserve (QNNR) has complex geomorphological characteristics of the high altitude Tibetan Plateau and aunique plateau wetland environment. In order to extract the wetl...

Single-feature methods are unable to effectively track a target in an underground coal mine video due to the high background noise, low and uneven illumination, and drastic light fluctuation in the video. In this study, we propose an underground coal mine personnel target tracking method using multi-feature joint sparse representation. First, with a particle filter framework, the global and local multiple features of the target template and candidate particles are extracted. Second, each of the candidate particles is sparsely represented by a dictionary template, and reconstruction is achieved after solving the sparse coefficient. Last, the particle with the lowest reconstruction error is deemed the tracking result. To validate the effectiveness of the proposed algorithm, we compare the proposed method with three commonly employed tracking algorithms. The results show that the proposed method is able to reliably track the target in various scenarios, such as occlusion and illumination change, which generates better tracking results and validates the feasibility and effectiveness of the proposed method.

This study aims to analyze the potential of the computer vision (CV) approach to classify eight canola varieties. The input images of eight canola varieties were CON-I, CON-II, CON-III, Pakola, Canola Raya, Rainbow, PARC Canola Hybrid, and Tarnab-III. A digital camera acquired these images on an open sunny day without any complex laboratory setup. First-order histogram features, second-order statistical texture features, binary features, spectral features of three bands were, blue (B), green (G), and red (R), were employed in the artificial neural network (ANN). A 10-fold stratified cross-validation method was used for classification. The best results with accuracy ranging from 95% to 98% observed when the data of regions of interest (512 × 512) deployed to the classifier.

The changing dynamics of life and other activities has encouraged the human society to move or migrate between regions of any country. The population in different region and state of India gets increasing and it is necessary for the planning commission to monitor the migrations incur in every year. Number of approaches available for the prediction and analysis of migrations to perform several decision making but suffer to achieve higher performance. In this paper, an efficient time variant multi feature census analysis algorithm is presented. The method keeps track of migrations made in every time stamp. The reasons and purpose of migration also being recorded every year like study, business, work, marriage and others. Using these features the method performs analysis on the ratio of migration in different aspects and predicts the ratio of migration. The result of analysis would be used to perform several planning activities by the government. The method introduces higher performance in migration prediction.

Considering that the kidneys segmentation challenge for image processing because of the gray level from abdominal computer tomography (CT) scans is a great similarity of adjacent organs, partial volume effects and so on, a novel multi-feature sparse constraints strategy is proposed to diagnose the benign and malignant renal tumors, which can improve the accuracy and reliability of segmentation. The weighted sparse measure is defined by introducing weights in the l1-norm of vectors. The weight is inversely proportional to the similarity between data, therefore the weighted l1-norm penalty on the linear representation coefficients tends to force similar data be involved while dissimilar data uninvolved in the linear representation of a datum. The resulted representation can overcome the drawbacks of l1-norm penalty that the presentation coefficients are usually over sparse and not robust for highly correlated data. Experimental results and objective assessment indexes show that the proposed method can effectively segment CT images with good visual consistency. In addition, the dice coefficients of renal and renal tumors were 0.933 and 0.854, respectively. In addition, our method can also be used for the diagnosis of renal tumors, and has also achieved good performance.

The Unmanned Aerial Vehicle (UAV) and Google Earth (GE) RGB images have ultra-high spatial resolution. But it is difficult to get a high classification accuracy due to the poor spectral resolution....

Background: RNA methylation is a reversible post-transcriptional modification involving numerous biological processes. Ribose 2'-O-methylation is part of RNA methylation. It has shown that ribose 2'-O-methylation plays an important role in immune recognition and other pathogenesis. Objective: We aim to design a computational method to identify 2'-O-methylation. Methods: Different from the experimental method, we propose a computational workflow to identify the methylation site based on the multi-feature extracting algorithm. Results: With a voting procedure based on 7 best feature-classifier combinations, we achieved Accuracy of 76.5% in 10-fold cross-validation. Furthermore, we optimized features and input the optimized features into SVM. As a result, the AUC reached to 0.813. Conclusion: The RNA sample, especially the negative samples, used in this study are more objective and strict, so we obtained more representative results than state-of-arts studies.

Ribosomes are a kind of organelle in cells, which are mainly involved in the translation process of genetic materials, but the underlying mechanisms associated with ribosome stalling are not fully understood. Thanks to the development of biological experimental techniques, many ribosome footprintings are generated, which can help us to study ribosome stalling. Effectively obtaining a precise ribosome stalling site will be helpful for the treatment of the related diseases, however there is still much room for the improvement of ribosome stalling prediction. In this study, we propose a new deep neural network model named DeepRibSt for the prediction of ribosome stalling sites. We first process the ribosome footprinting data to the training set. Then three new features, including evolutionary conservation, hydrophobicity, and amino dissociation constant, along with the previous sequence features, are extracted as input to the network. To improve the performance of the algorithm in ribosome stalling prediction, we use two convolutional layers and three fully connected layers to design a new network architecture. To verify the validity of our proposed DeepRibSt, we compare DeepRibSt with four popular deep neural networks, i.e., AlexNet, LeNet, ResNet, and LSTM on human (i.e., Battle2015 and Stumpf13) and yeast (i.e., Pop2014, Young15, and Brar12) data. To further demonstrate the effectiveness of DeepRibS, we compare DeepRibSt with the state-of-the-art method. The experimental results show that DeepRibSt outperforms all other methods and achieves the state-of-the-art performance in accuracy, recall, specificity, F1-score, and the area under the receiver operating characteristic curve (AUC).

Building information is an essential part of geographic information system (GIS) applications in urban planning and management. However, it changes rapidly with economic growth. Unmanned aerial veh...

The human society has been identified as more prone for diseases. Various drugs with different compounds are available to treat the diseases. However, the medical practitioner cannot be sure about the application of the drug and what would be exact drug should be feed to the patient. To hook this, a multi feature drug compound analysis model is presented in this paper. The method keeps track of medical records related to various patients and the details of drugs being provided to them. Using these treatment data set, the method applies machine learning techniques to generate and predict the success rate of different drugs. To perform this, the method first split the records based on the disease and for each of them the list of medicines and compounds given has been identified. Based on these data, a set of patterns are generated according to various compounds of drug provided. Further, the method estimates the success influence measure (SIM) for different drug components. Estimated success influence measure is used to generate the fuzzy rules. Based on the rule generated, the method performs success rate prediction for various drug compounds. The method produces noticeable growth in the success rate prediction.

Glaucoma is a chronic and irreversible eye disease leading to blindness, and early detection is particularly important for its diagnosis and treatment. To improve the performance of automatic glaucoma diagnosis, a method based on multi-feature and multi-classifier is proposed. Firstly, an average histogram is obtained for each channel and ophthalmic condition, and 6 features are extracted from the average histogram with the average count of pixels and their maximum intensity value. Secondly, the optimal features combination is screened for each classifier with 10-fold cross-validation. Finally, the three optimal classifiers and their optimal features combination are fused with the principle of democratic voting. With the 10-fold cross-validation algorithm, the fusion model was evaluated on Local and HRF dataset, that achieved accuracy of 91.8% and 93.3%, sensitivity of 86.9% and 86.7%, specificity of 96.7% and 100%, AUC of 0.953 and 0.978, time cost of 1.0 s and 3.9 s per image, respectively. Simulation results show that the proposed method is of high accuracy and generality. It can effectively classify the retinal fundus images and provide technical support for the clinical diagnosis of retinal diseases.

In this paper, a novel approach is proposed for Synthetic Aperture Radar (SAR) target classification based on multi-aspect multi-feature collaborative representation. Firstly, principal component a...

When bug reports are submitted through bug tracking systems, they are analysed manually to identify their severity levels. A severity level specifies the negative impact of a bug on a system. With the huge number of submitted reports, setting the severity class manually is tedious and time consuming. Moreover, some bug types are reported more often than other types, which leads to imbalanced bug repositories. This paper proposes a multi-feature approach for automatic severity assignment, which leverages lexical, semantic, and categorical properties of the bug reports. The proposed approach utilizes word embeddings, topic model, vector space model, and an adapted K-Nearest Neighbour technique. Moreover, the impact of utilizing two sampling techniques, namely SMOTE and cluster-based under-sampling (CBU), were investigated. Experiments over two open source repositories, Eclipse and Mozilla, demonstrated that the proposed approach is superior to two previous studies.

In this new era, the advancement towards the diagnosis of disease in its early-stage has improved. The medical field is not only equipped with the new generation devices but also the approach. The ultimate aim of this research is to diagnose a Glaucoma disorder in the optical never of the eye. Glaucoma diagnosis is a complex process as it produces no sign until it affects the eye and causes a loss of vision partially or entirely. This research provides a solution to find this disorder at the early stage by analysis the retinal parameters or features extracted using high-resolution imaging process. In this screening process, the hunt for diseases such as retinal detachment, retinopathy, retinoblastoma, and age-related molecular degeneration is processed. The classification of these diseases is complicated as many of these diseases share identical characteristics which cause the doctors to confuse in identifying the particular illness for the treatment. In this research, the multi-feature analysis methodology of classification is introduced enhanced with the machine learning algorithm and a DWT (discrete wavelet transform) to classify the diseases for the unique treatment procedures. This research shows promising results as the methodology provides more than 95 percentage of Accuracy for the Glaucoma identification.

To address the low accuracy problem of playground detection under complex background, the accurate playground localization based on multi-feature extraction and cascade classifier is proposed in th...

Principal component analysis (PCA) and its modified methods have been widely applied in industrial process monitoring. In practice, industrial processes are with disparate characteristics, the process monitoring system should consider as many process characteristics as possible, such as dynamic and nonlinear characteristics. In this paper, a multi-feature extraction technique based on PCA is proposed for nonlinear dynamic process monitoring. The proposed method integrates dynamic inner PCA (DiPCA), PCA and kernel PCA (KPCA) methods through a serial structure to extract the dynamic, linear and nonlinear features among the process data. Along with the proposed method, the original data space is decomposed into several orthogonal subspaces, in which abnormal variations of different features can be monitored. For real-time process monitoring, a combined Hotelling’s T2 statistic based on the extracted multi-feature and a squared prediction error (SPE or Q) statistic are established. Case studies on a numerical example and the Tennessee Eastman process are carried out to demonstrate the superior process monitoring performance of the proposed method compared with other relevant methods.

Various UNet architecture-based image change detection algorithms promote the development of image change detection, but there are still some defects. First, under the encoder–decoder framework, the low-level features are extracted many times in multiple dimensions, which generates redundant information; second, the relationship between each feature layer is not modeled so sufficiently that it cannot produce the optimal feature differentiation representation. This paper proposes a remote image change detection algorithm based on the multi-feature self-attention fusion mechanism UNet network, abbreviated as MFSAF UNet (multi-feature self-attention fusion UNet). We attempt to add multi-feature self-attention mechanism between the encoder and decoder of UNet to obtain richer context dependence and overcome the two above-mentioned restrictions. Since the capacity of convolution-based UNet network is directly proportional to network depth, and a deeper convolutional network means more training parameters, so the convolution of each layer of UNet is replaced as a separated convolution, which makes the entire network to be lighter and the model’s execution efficiency is slightly better than the traditional convolution operation. In addition to these, another innovation point of this paper is using preference to control loss function and meet the demands for different accuracies and recall rates. The simulation test results verify the validity and robustness of this approach.

Discriminating the homology and heterogeneity of two documents in information retrieval is very important and difficult step. Existing methods mainly focus on word-based document duplicate checking or sentence pairs matching except manual verification which need a lot of human resource cost. The word-based document duplicate checking can not judge the similarity of two documents from the semantic level and the matching sentence pair methods can not effectively mine the semantic information from a long text which is frequent retrieval results. A concept-based Multi-Feature Semantic Fusion Model (MFSFM) is proposed. It employs multi-feature enhanced semantics to construct a concept map for represent the document, and employs a multi-convolution mixed residual CNN module to introduce local attention mechanism for improve the sensitivity of conceptual boundary information. To improve the feasibility of the proposed MFSFM based on concept maps, two multi-feature document data sets are set up. Each of them consists of about 500 actual scientific and technological project feasibility reports. Experimental results based on the actual datasets show that the proposed MFSFM converges quickly while expanding the latest methods of natural language matching at the accuracy rate.

A multi-feature broad learning system (MFBLS) is proposed to improve the image classification performance of broad learning system (BLS) and its variants. The model is characterized by two major characteristics: multi-feature extraction method and parallel structure. Multi-feature extraction method is utilized to improve the feature-learning ability of BLS. The method extracts four features of the input image, namely convolutional feature, K-means feature, HOG feature and color feature. Besides, a parallel architecture that is suitable for multi-feature extraction is proposed for MFBLS. There are four feature blocks and one fusion block in this structure. The extracted features are used directly as the feature nodes in the feature block. In addition, a “stacking with ridge regression” strategy is applied to the fusion block to get the final output of MFBLS. Experimental results show that MFBLS achieves the accuracies of 92.25%, 81.03%, and 54.66% on SVHN, CIFAR-10, and CIFAR-100, respectively, which outperforms BLS and its variants. Besides, it is even superior to the deep network, convolutional deep belief network, in both accuracy and training time on CIFAR-10. Code for the paper is available at https://github.com/threedteam/mfbls .

Fully polarimetric synthetic aperture radar (PolSAR) technology performs well in oil spill detection because of its rich target scattering information. Aiming at the problem that oil spill detection scheme based on polarization feature and deep learning has large sample requirements and high information redundancy, we propose a classification scheme combining with RBFSVM classifier and VGG16 based on transfer network. The ability of our method to distinguish different oil films is analyzed through a radarsat-2 POLSAR image of the North Sea oil spill experiment.