Search

Addressing the critical issue of tire wear is essential for enhancing vehicle safety, performance, and maintenance. Worn-out tires often lead to accidents, underscoring the need for effective monitoring systems. This study is vital for several reasons: safety, as worn tires increase the risk of accidents due to reduced traction and longer braking distances; performance, as uneven tire wear affects vehicle handling and fuel efficiency; maintenance costs, as early detection can prevent more severe damage to suspension and alignment systems; and regulatory compliance, as ensuring tire integrity helps meet safety regulations imposed by transportation authorities. In response, this study systematically evaluates tire conditions at 25%, 50%, 75%, and 100% wear, with an intact tire as a reference, using vibration signals as the primary data source. The analysis employs statistical, histogram, and autoregressive–moving-average (ARMA) feature extraction techniques, followed by feature selection to identify key parameters influencing tire wear. CatBoost is used for feature classification, leveraging its adaptability and efficiency in distinguishing varying wear patterns. Additionally, the study incorporates feature fusion to combine different types of features for a more comprehensive analysis. The proposed methodology not only offers a robust framework for accurately classifying tire wear levels but also holds significant potential for real-time implementation, contributing to proactive maintenance practices, prolonged tire lifespan, and overall vehicular safety. [ABSTRACT FROM AUTHOR]

Introduction: With the development of artificial intelligence and autonomous driving technology, the application of motion recognition in automotive autonomous driving is becoming more and more important. The traditional feature extraction method uses adaptive search hybrid learning and needs to design the feature extraction process manually, which is difficult to meet the recognition requirements in complex environments. Methods: In this paper, a fusion algorithm is proposed to classify the driving characteristics through time-frequency analysis, and perform backpropagation operation in artificial neural network to improve the convergence speed of the algorithm. The performance analysis experiments of the study were carried out on Autov data sets, and the results were compared with those of the other three algorithms. Results: When the vehicle action coefficient is 227, the judgment accuracy of the four algorithms is 0.98, 0.94, 0.93 and 0.95, respectively, indicating that the fusion algorithm is stable. When the road sample is 547, the vehicle driving ability of the fusion algorithm is 4.7, which is the best performance among the four algorithms, indicating that the fusion algorithm has strong adaptability. Discussion: The results show that the fusion algorithm has practical significance in improving the autonomous operation ability of autonomous vehicles, reducing the frequency of vehicle accidents during driving, and contributing to the development of production, life and society. [ABSTRACT FROM AUTHOR]

With the continuous maturity of hyperspectral remote sensing imaging technology, it has been widely adopted by scholars to improve the performance of feature classification. However, due to the challenges in acquiring hyperspectral images and producing training samples, the limited training sample is a common problem that researchers often face. Furthermore, efficient algorithms are necessary to excavate the spatial and spectral information from these images, and then, make full use of this information with limited training samples. To solve this problem, a novel two-branch deep learning network model is proposed for extracting hyperspectral remote sensing features in this paper. In this model, one branch focuses on extracting spectral features using multi-scale convolution and a normalization-based attention module, while the other branch captures spatial features through small-scale dilation convolution and Euclidean Similarity Attention. Subsequently, pooling and layering techniques are employed to further extract abstract features after feature fusion. In the experiments conducted on two public datasets, namely, IP and UP, as well as our own labeled dataset, namely, YRE, the proposed DMAN achieves the best classification results, with overall accuracies of 96.74%, 97.4%, and 98.08%, respectively. Compared to the sub-optimal state-of-the-art methods, the overall accuracies are improved by 1.05, 0.42, and 0.51 percentage points, respectively. The advantage of this network structure is particularly evident in unbalanced sample environments. Additionally, we introduce a new strategy based on the RPNet, which utilizes a small number of principal components for feature classification after dimensionality reduction. The results demonstrate its effectiveness in uncovering compressed feature information, with an overall accuracy improvement of 0.68 percentage points. Consequently, our model helps mitigate the impact of data scarcity on model performance, thereby contributing positively to the advancement of hyperspectral remote sensing technology in practical applications. [ABSTRACT FROM AUTHOR]

A gearbox compound fault intelligent diagnosis method based on the period group sparse model is proposed for the problem that the fault features are coupled with each other and the fault components are superimposed on each other and difficult to be separated in the gearbox compound fault signal. Firstly, a binary sequence is constructed to embed the fault pulse period as a priori knowledge into the group sparse model to decouple and separate the composite fault signal while maintaining the amplitude and sparsity of the extracted features. Secondly, the wavelet packet energy features of the decoupled signals are extracted to improve the data quality while enhancing the characterization ability of the dictionary in the classification model. Finally, the wavelet packet energy features are imported into the sparse dictionary classification model, and the fault diagnosis is completed by outputting the fault categories using the self-driven characteristics of the data. The results show that the fault identification accuracy using the proposed method is 97%. In addition, the experimental validation under different states and working conditions with different rotational speeds allows the superiority and effectiveness of the algorithm in this paper to be tested and has the feasibility of a practical application in engineering. [ABSTRACT FROM AUTHOR]

Urban public open spaces (POS) are pivotal in sustainable urban planning, recognized for their positive impacts on the health of residents and environments. However, understanding their physical features in detail via remote sensing remains challenging due to the small and complex area characteristics. Advanced approaches struggle with the requirement for extensive training datasets, which are difficult to obtain and potentially inaccurate in certain settings. Sparse sampling of training data may offer a solution to these challenges, but its inability to consider useful contextual characteristics from objects remains as a significant barrier.To address these challenges, we propose an innovative methodology utilizing the Multivariate Long Short Term Memory–Fully Convolutional Network (MLSTM-FCN). This approach is adept at capturing subtle temporal and spectral variations from sparsely annotated data, making it particularly suited for optical remote sensing in urban POS. Our novel approach has achieved 97.86% accuracy in classifying POS features into 11 classes using only 1,870 annotated sample points and maintained over 90% of accuracy even with 187 samples or 10% of total samples, significantly outperform comparison models. This methodology allows for detailed and efficient monitoring of POS and enhances management strategies with minimal resources and effort. Our research opens new pathways for precise urban landscape study.

The lower limb exoskeleton technology is designed to facilitate the movement of human lower limbs. Significant progress has been made in this technology, which has important implications for rehabilitation patients and individuals who are eager to enhance their mobility. Electromyogram (EMG) signals, which encompass the complexity of human physiology, are integrated into lower limb exoskeletons due to their deep connection to movement and predictability before movement begins, and this integration is expected to enable intelligent control and improved human-computer interaction. This review explores a pattern based on EMG signals for identifying human motor intent in lower limb exoskeletons. Firstly, the development of lower limb exoskeleton and the existing lower limb exoskeleton products are systematically described. Combined with the intelligent control system of wearable device, the main methods and research progress of recognizing the motion intention of lower limb exoskeleton by surface EMG are discussed. It shows that the use of surface EMG can effectively improve the human-machine interaction of lower limb exoskeleton. Together, the study provides insight into the challenges that are hindering the commercialization of the market and provides a perspective on the future development of EMG signals.

The intelligent recognition of ship geometric features is a prerequisite for enabling computers to automatically generate and deform ship hull surfaces according to requirements, thereby replacing the work of human designers to improve design efficiency. This paper aims to research the recognition of geometric features in three-dimensional ship data using PointNet. To achieve this goal, we first construct two ship point cloud datasets suitable for global feature classification and feature part segmentation of three-dimensional hulls. Subsequently, we conducted recognition capability testing to determine the optimal hyperparameters for identifying ship feature networks. Finally, we employ ship models with non-standard positions to implement data augmentation, enhancing the network's robustness in recognizing the initial positions of ships and achieving rapid cognition of three-dimensional ship geometric features. The findings of this research will provide technical support for ship design based on artificial intelligence technology.

Pre-school education is an integral part of primary education, and with the development of digital technology, the integration of pre-school education and information technology development is deepening. The study first adds category constraints to the CycleGAN network to improve the efficiency of algorithm operations. The facial features of young children are extracted using the LBP method and recognized by improving the CycleGAN network after they are classified using the SOC classification method. On this basis, the improved model is applied to early childhood preschool education to explore the recognition of young children’s characteristics and educational effects. In this paper, the recognition accuracy of the improved CycleGAN network model is improved by 0.02~0.14 in the expression recognition accuracy of seven basic expressions. in early childhood education, the third round of test scores of the experimental group of young children is 93 compared to the first round of test improved by 34 points, compared with the control group scores improved by 15 points. This study provides practical and feasible development directions for constructing and reforming information technology in preschool education.

The use of infrared thermography (IRT) technique combining other remoting sensing techniques such as photogrammetry and unmanned aerial vehicle (UAV) platforms to perform geotechnical studies has been attempted by several previous researchers and encouraging results were obtained. However, studies using time-lapse IRT survey via a UAV equipped with a thermal camera are limited. Given the unique setting of Hong Kong, which has a high population living in largely hilly terrain with little natural flat land, steep man-made slopes and natural hillsides have caused significant geotechnical problems which pose hazards to life and facilities. This paper presents the adoption of a time-lapse IRT survey using a UAV in such challenging geotechnical conditions. Snapshot and time-lapse IRT studies of a selected site in Hong Kong, where landslides had occurred were carried out, and visual inspection, photogrammetry, and IRT techniques were also conducted. 3D terrain models of the selected sites were created by using data collected from the photogrammetry and single (snapshot) and continuous monitoring (time-lapse) infrared imaging methods applied in this study. The results have successfully identified various thermal infrared signatures attributed to the existence of moisture patches, seepage, cracks/discontinuities, vegetation, and man-made structures. Open cracks/discontinuities, moisture, vegetation, and rock surfaces with staining can be identified in snapshot thermal image, while the gradient of temperature decay plotted in ln(T) vs. ln(t) enables quantifiable identifications of the above materials via time-lapse thermography and analysis. [ABSTRACT FROM AUTHOR]

Abstract The quantitative feature classification of breast ultrasound images can explore the intrinsic connection between image features and lesions, and become an important basis for the diagnosis of tumor nature in clinical medicine. However, the tumor features extracted from breast ultrasound images are generally based on the overall situation, which has an impact on the classification of features in ultrasound images. Therefore, a quantitative feature classification algorithm for breast ultrasound images using improved Naive Bayes (NB) is proposed. First, histogram features, grayscale co‐generation matrix and other texture features are extracted from the ultrasound image. Second, NB is combined with decision tree calculation to improve the traditional NB algorithm. Finally, feature classification is optimized using improved NB algorithm to achieve high accuracy in the classification of ultrasound images. The results show that the contour of the lesion recognition results obtained by the proposed algorithm is the most complete, and the other regions can maximize the retention of the texture features of the original image. The classification accuracy is high, and the classification time of quantitative features of breast ultrasound images is short. It has application value in the field of breast ultrasound diagnosis.

With the continuous maturity of hyperspectral remote sensing imaging technology, it has been widely adopted by scholars to improve the performance of feature classification. However, due to the challenges in acquiring hyperspectral images and producing training samples, the limited training sample is a common problem that researchers often face. Furthermore, efficient algorithms are necessary to excavate the spatial and spectral information from these images, and then, make full use of this information with limited training samples. To solve this problem, a novel two-branch deep learning network model is proposed for extracting hyperspectral remote sensing features in this paper. In this model, one branch focuses on extracting spectral features using multi-scale convolution and a normalization-based attention module, while the other branch captures spatial features through small-scale dilation convolution and Euclidean Similarity Attention. Subsequently, pooling and layering techniques are employed to further extract abstract features after feature fusion. In the experiments conducted on two public datasets, namely, IP and UP, as well as our own labeled dataset, namely, YRE, the proposed DMAN achieves the best classification results, with overall accuracies of 96.74%, 97.4%, and 98.08%, respectively. Compared to the sub-optimal state-of-the-art methods, the overall accuracies are improved by 1.05, 0.42, and 0.51 percentage points, respectively. The advantage of this network structure is particularly evident in unbalanced sample environments. Additionally, we introduce a new strategy based on the RPNet, which utilizes a small number of principal components for feature classification after dimensionality reduction. The results demonstrate its effectiveness in uncovering compressed feature information, with an overall accuracy improvement of 0.68 percentage points. Consequently, our model helps mitigate the impact of data scarcity on model performance, thereby contributing positively to the advancement of hyperspectral remote sensing technology in practical applications.

A gearbox compound fault intelligent diagnosis method based on the period group sparse model is proposed for the problem that the fault features are coupled with each other and the fault components are superimposed on each other and difficult to be separated in the gearbox compound fault signal. Firstly, a binary sequence is constructed to embed the fault pulse period as a priori knowledge into the group sparse model to decouple and separate the composite fault signal while maintaining the amplitude and sparsity of the extracted features. Secondly, the wavelet packet energy features of the decoupled signals are extracted to improve the data quality while enhancing the characterization ability of the dictionary in the classification model. Finally, the wavelet packet energy features are imported into the sparse dictionary classification model, and the fault diagnosis is completed by outputting the fault categories using the self-driven characteristics of the data. The results show that the fault identification accuracy using the proposed method is 97%. In addition, the experimental validation under different states and working conditions with different rotational speeds allows the superiority and effectiveness of the algorithm in this paper to be tested and has the feasibility of a practical application in engineering.

Today, closed-circuit television (CCTV) is widely used in various fields. If authorized by law, CCTV can be used to identify drug users in public places or specific areas. It can estimate the drug population and determine the hot spots of drug proliferation to comprehend and control the overall drug situation in a region. Based on the GoogLeNet network of deep learning, this work integrated image processing, face detection, data augmentation, and transfer learning to establish a special face image recognition framework that could differentiate drug users from nonusers. The facial database with drug addicts and nonaddicts used in the experiment was obtained from the Internet, face benchmarks, and police agencies. This facial database was diverse and included different genders, ages, and races. The experimental results showed that the model accuracy in this study reached 87.14%, implying that the model could learn the low-dimensional facial discrimination features of drug addicts. The three classification performances, precision, recall, and F1-score reached 87.32%, also representing a good overall classification performance of the model. In addition, we also confirmed that adjusting the activation function and the dropout probability could further optimize the model's performance. [ABSTRACT FROM AUTHOR]

The prompt and accurate diagnosis of breast lesions, including the distinction between cancer, non-cancer, and suspicious cancer, plays a crucial role in the prognosis of breast cancer. In this paper, we introduce a novel method based on feature extraction and reduction for the detection of breast cancer in mammography images. First, we extract features from multiple pre-trained convolutional neural network (CNN) models, and then concatenate them. The most informative features are selected based on their mutual information with the target variable. Subsequently, the selected features can be classified using a machine learning algorithm. We evaluate our approach using four different machine learning algorithms: neural network (NN), k-nearest neighbor (kNN), random forest (RF), and support vector machine (SVM). Our results demonstrate that the NN-based classifier achieves an impressive accuracy of 92% on the RSNA dataset. This dataset is newly introduced and includes two views as well as additional features like age, which contributed to the improved performance. We compare our proposed algorithm with state-of-the-art methods and demonstrate its superiority, particularly in terms of accuracy and sensitivity. For the MIAS dataset, we achieve an accuracy as high as 94.5%, and for the DDSM dataset, an accuracy of 96% is attained. These results highlight the effectiveness of our method in accurately diagnosing breast lesions and surpassing existing approaches. [ABSTRACT FROM AUTHOR]

This paper provides a survey of apparent personality trait analysis based on multimodal trait prediction and optimization of multimodal output parameters. This paper analyzes, synthesizes, and compares the development of different methods of Personality computing based on the personality trait analysis within the Big Five model (OCEAN model) and based on audio, visual and textual inputs. The results of the trait analysis and detection are different for different methods, from trait extracted from handwriting with an accuracy of 62-83%, trait extracted from with 56-62%, trait extracted from audio with 70%, trait extracted from visual element images and videos 87-91%, from aggregation function min and max 52 - 81%, mean and median 85%, and methods based on robustness and Huber function 72 - 77 %. Trait analysis is a problem with numerous real-life applications. Accurate trait recognition and analysis of various human traits are tasks that have been studied for a very long time in the field of psychology and lately represent an important area of study in the field of computer science and computing. The best results in the field of apparent personality trait analysis were achieved with convolutional neural networks. Multimodal trait prediction will give a better prediction than prediction based on a single modality, and optimization with aggregation functions and robust methods can achieve a better prediction of the models.

The quantitative feature classification of breast ultrasound images can explore the intrinsic connection between image features and lesions, and become an important basis for the diagnosis of tumor nature in clinical medicine. However, the tumor features extracted from breast ultrasound images are generally based on the overall situation, which has an impact on the classification of features in ultrasound images. Therefore, a quantitative feature classification algorithm for breast ultrasound images using improved Naive Bayes (NB) is proposed. First, histogram features, grayscale co‐generation matrix and other texture features are extracted from the ultrasound image. Second, NB is combined with decision tree calculation to improve the traditional NB algorithm. Finally, feature classification is optimized using improved NB algorithm to achieve high accuracy in the classification of ultrasound images. The results show that the contour of the lesion recognition results obtained by the proposed algorithm is the most complete, and the other regions can maximize the retention of the texture features of the original image. The classification accuracy is high, and the classification time of quantitative features of breast ultrasound images is short. It has application value in the field of breast ultrasound diagnosis. [ABSTRACT FROM AUTHOR]

Brain–computer interface (BCI) can obtain text information by decoding language induced electroencephalogram (EEG) signals, so as to restore communication ability for patients with language impairment. At present, the BCI system based on speech imagery of Chinese characters has the problem of low accuracy of features classification. In this paper, the light gradient boosting machine (LightGBM) is adopted to recognize Chinese characters and solve the above problems. Firstly, the Db4 wavelet basis function is selected to decompose the EEG signals in six-layer of full frequency band, and the correlation features of Chinese characters speech imagery with high time resolution and high frequency resolution are extracted. Secondly, the two core algorithms of LightGBM, gradient-based one-side sampling and exclusive feature bundling, are used to classify the extracted features. Finally, we verify that classification performance of LightGBM is more accurate and applicable than the traditional classifiers according to the statistical analysis methods. We evaluate the proposed method through contrast experiment. The experimental results show that the average classification accuracy of the subjects' silent reading of Chinese characters "左(left)", "壹(one)" and simultaneous silent reading is improved by 5.24%, 4.90% and 12.44% respectively. [ABSTRACT FROM AUTHOR]

The use of infrared thermography (IRT) technique combining other remoting sensing techniques such as photogrammetry and unmanned aerial vehicle (UAV) platforms to perform geotechnical studies has been attempted by several previous researchers and encouraging results were obtained. However, studies using time-lapse IRT survey via a UAV equipped with a thermal camera are limited. Given the unique setting of Hong Kong, which has a high population living in largely hilly terrain with little natural flat land, steep man-made slopes and natural hillsides have caused significant geotechnical problems which pose hazards to life and facilities. This paper presents the adoption of a time-lapse IRT survey using a UAV in such challenging geotechnical conditions. Snapshot and time-lapse IRT studies of a selected site in Hong Kong, where landslides had occurred were carried out, and visual inspection, photogrammetry, and IRT techniques were also conducted. 3D terrain models of the selected sites were created by using data collected from the photogrammetry and single (snapshot) and continuous monitoring (time-lapse) infrared imaging methods applied in this study. The results have successfully identified various thermal infrared signatures attributed to the existence of moisture patches, seepage, cracks/discontinuities, vegetation, and man-made structures. Open cracks/discontinuities, moisture, vegetation, and rock surfaces with staining can be identified in snapshot thermal image, while the gradient of temperature decay plotted in ln(T) vs. ln(t) enables quantifiable identifications of the above materials via time-lapse thermography and analysis.

Reliable assessment of an individual’s driving skills is very important. The growing population of unskilled drivers will result in disastrous and fatal road accidents. Current situation demands better and accurate automated assessment technique for driver performance. This research aims to development a portable independent assessment system which can be installed in any vehicle. This system will monitor and understand the driver’s skills based on the data from sensors and access their performance using machine learning algorithm. Machine learning based classifiers with more than 90% accuracy are developed for classifying the driver skills. This proposed system will ensure one from possibilities of beaching the formal process and getting the license without qualification, it is a suggestion to the conventional method of assessment. This system could help in building better-skilled driver on the road for a healthy road environment.

Ovarian cancer (OC) is one kind of tumour that impacts women's ovaries and is hard to diagnose in the initial phase as a primary cause of cancer death. The ovarian cancer information generated by the Clinical Network has been used, and the Self Organizing Map (SOM) and Optimized Neural Networks have suggested a new method for the distinction between ovarian cancer and remaining cancer. Feature optimization and identification of the ovarian cancer (FOI‐OV) framework are proposed in this research. The SOM algorithm has also been used separately to improve the functional subset, with understandable and intriguing information from participants' health information steps. The SOM‐based collection appears to be tolerable in guided learning strategies due to the lack of different classifiers, which would direct the quest for knowledge specific to the classification algorithm. The classification technique will classify data from ovarian cancer as benign/malignant. By optimizing Neural Network configuration, Advanced Harmony Searching Optimization (AHSO) can enhance the ovarian cancer detection method compared with other methods. This research's suggested model can also diagnose cancer with high precision, and low root means square error (RMSE) early. With 94% precision and 0.029%, RMSE, SOM, and NN techniques have shown identification and precision in ovarian cancer. Optimization (AHSO) has provided an efficient classification approach with a better failure rate. [ABSTRACT FROM AUTHOR]

Over the past decade, the fresh white mulberry (Morus alba L.) fruit has gained growing interest due to its superior health and nutritional characteristics. While white mulberry is consumed as fresh fruit in several countries, it is also popular in dried form as a healthy snack food. One of the main challenges that have prevented a wider consumer uptake of this nutritious fruit is the non-uniformity in its quality grading. Therefore, identifying a reliable quality grading tool can greatly benefit the relevant stakeholders. The present research addresses this need by developing a novel machine vision system that combines the key strengths of image processing and artificial intelligence. Two grades (i.e., high- and low-quality) of white mulberry were imaged using a digital camera and 285 colour and textural features were extracted from their RGB images. Using the quadratic sequential feature selection method, a subset of 23 optimum features was identified to classify samples into two grades using artificial neural networks (ANN) and support vector machine (SVM) classifiers. The developed system under both classifiers achieved the highest correct classification rate (CCR) of 100%. Indeed, the latter approach offered a smaller mean squared error for the training and test sets. The developed model's high accuracy confirms the machine vision's suitability as a reliable, low-cost, rapid, and intelligent tool for quality monitoring of dried white mulberry. [ABSTRACT FROM AUTHOR]

The behaviours of the pig are often closely related to their health. Pig recognition is very important for pig behaviour analysis and digital breeding. Currently, the early signs and abnormal behaviours of sick pigs in breeding farms are mainly completed by human observation. However, visual inspection is labour intensive and time-consuming, and it suffers from the problems of individual experiences and varying environments. An improved ResNet model was proposed and applied to detect individual pigs in this study based on deep learning knowledge. The developed model captured the features of pigs applying across layer connections, and the ability of feature expression was improved by adding a new residual module. The number of layers was reduced to minimise the net complexity. Generally, the ResNet frame was developed by reducing the number of convolution layers, constructing different types of the residual module and adding the number of convolution kernels. The training accuracy and testing accuracy reached 98.2% and 96.4%, respectively, when using the improved model. The experiment results showed that the method proposed in this paper for checking living situations and disease prevention of commercial pigs in pig farms is potential.

The prompt and accurate diagnosis of breast lesions, including the distinction between cancer, non-cancer, and suspicious cancer, plays a crucial role in the prognosis of breast cancer. In this paper, we introduce a novel method based on feature extraction and reduction for the detection of breast cancer in mammography images. First, we extract features from multiple pre-trained convolutional neural network (CNN) models, and then concatenate them. The most informative features are selected based on their mutual information with the target variable. Subsequently, the selected features can be classified using a machine learning algorithm. We evaluate our approach using four different machine learning algorithms: neural network (NN), k-nearest neighbor (kNN), random forest (RF), and support vector machine (SVM). Our results demonstrate that the NN-based classifier achieves an impressive accuracy of 92% on the RSNA dataset. This dataset is newly introduced and includes two views as well as additional features like age, which contributed to the improved performance. We compare our proposed algorithm with state-of-the-art methods and demonstrate its superiority, particularly in terms of accuracy and sensitivity. For the MIAS dataset, we achieve an accuracy as high as 94.5%, and for the DDSM dataset, an accuracy of 96% is attained. These results highlight the effectiveness of our method in accurately diagnosing breast lesions and surpassing existing approaches.

Data quality estimation has become an important research axis in applications when defining useful information is required. Determining useful information is an essential task in the learning process. One important aspect thereby is to find optimal and sufficient information that has a good quality and which is complimentary to improve the performance of the decision-making system. In this paper, a survey of data quality is operated in the possibilistic framework. The main objective of this work is the development of a possibilistic approach that aims to extract useful information from imperfect knowledge. The new method consists of two main steps, the classification of feature quality and the determination of the optimal feature subset. The optimal feature subset is deduced according to the feature classification technique and the feature complementarity. To show the performance of the proposed approach, the new method has been evaluated, firstly, on a synthetic dataset, and then on different benchmark databases. Later, the new method is evaluated on two real databases to gain a better insight into the performance of this method. Experiments showed the effectiveness of the proposed method in extracting useful information using the optimal feature subset. Experimental results illustrate significant accuracy rates compared with different earlier methods, especially when the system complexity increases. • This work aims to develop a possibilistic approach for extracting useful data. • Our method involves classifying features based on their quality and defining the optimal subset • Our method is evaluated on synthetic dataset, benchmark databases and two real databases. [ABSTRACT FROM AUTHOR]

Requirements Engineering in the industry is expertise-driven, heavily manual, and centered around various types of requirement specification documents being prepared and maintained. These specification documents are in diverse formats and vary depending on whether it is a business requirement document, functional specification, interface specification, client specification, and so on. These diverse specification documents embed crucial product knowledge such as functional decomposition of the domain into features, feature hierarchy, feature types and their specific feature characteristics, dependencies, business context, etc. Moreover, in a product development scenario, thousands of pages of requirement specification documentation is created over the years. Comprehending functionality and its associated context from large volumes of specification documents is a highly complex task. To address this problem, we propose to digitalize the requirement specification documents into processable models. This paper discusses the salient aspects involved in the digitalization of requirements knowledge from diverse requirement specification documents. It proposes an AI engine for the automatic transformation of diverse text-based requirement specifications into machine-processable models using NLP techniques and the generation of context-sensitive user stories. The paper describes the key requirement abstractions and concepts essential in an industrial scenario, the conceptual meta-model, and DizReq engine (AI engine for digitalizing requirements) implementation for automatically transforming diverse requirement specifications into user stories embedding the business context. The evaluation results from digitalizing specifications of an IT product suite are discussed: mean feature extraction efficiency is 40 features/file, mean user story extraction efficiency is 71 user stories/file, feature extraction accuracy is 94%, and requirement extraction accuracy is 98%. [ABSTRACT FROM AUTHOR]

Brain-computer interface (BCI) based on electroencephalogram (EEG) signals can provide a way for human to communicate with the outside world. This approach is independent of the body's peripheral nerves and muscle tissue. The brain-controlled robot is a new technology based on the brain-computer interface technology and the robot control technology. This technology allows the human brain to control a robot to perform a series of actions. The processing of EEG signals plays a vital role in the technology of brain-controlled robots. In this paper, the methods of EEG signal processing in recent years are summarized. In order to better develop the EEG signal processing methods in brain-controlled robots, this paper elaborate on three parts: EEG signal pre-processing, feature extraction and feature classification. At the same time, the correlation analysis methods and research contents are introduced. The advantages and disadvantages of these methods are analyzed and compared in this paper. Finally, this article looks forward to the EEG signal processing methods in the process of brain-controlled robots.

Context: Quality Control (QC) has been constantly an essential concern in many fields like food industry production, medical drugs, environmental protection, and so on. An odor or flavor, as a global fingerprint, can be implemented as a non-invasive mechanism for quality assurance. This computer-based approach can assure accurate detection and precise identification of the product quality or manufactured goods. Objective: This paper aims to achieve a systematic review about e-nose by introducing the achievements made by researchers in this area, to summarize their findings, to provide motivations and challenges to new researchers in the field of e-nose. Methods: The articles that were being utilized in the e-nose field were systematically achieved using three search engines: The online library of IEEE Explore, Web of Science and Science Direct for time span of 7 years (from 2013 to 2020). Both medical literature reviews and technical reviews were considered in the criteria of the research for wider understanding in the field of e-nose. The articles were categorized according to the objective of the research and projected into four classes. Upon completion of screening process 333 research papers using the exclusion and inclusion conditions, as the final set 54 articles were selected. Results: The taxonomy of this research was classified into four categories. The first one included the suggested methods that introduced the utilization of the e-nose for classification purposes (9/54 papers). The second category comprises the methods related to the development of e-nose (24/54 papers). The third one included the review studies about the e-nose (8/54 papers). The fourth group comprises comparative studies and evaluation (13/54 papers). Discussion: This systematic review contributes for a clearer understanding and a full insight in the e- nose research field by surveying and categorizing pertinent research efforts. Conclusion: This review paper will help to address the up-to-date research opportunities, challenges, problems, motivations and recommendations related to the utilization of e-nose in all fields of sciences and industries.

In the intelligent fault diagnosis of rotating machinery, it is difficult to extract early weak fault impact features of rotating machinery under the interference of strong background noise, which makes the accuracy of fault identification low. In order to effectively identify the early faults of rotating machinery, an intelligent fault diagnosis method of rotating machinery based on an optimized adaptive learning dictionary and one-dimensional convolution neural network (1DCNN) is proposed in this paper. First of all, based on the original signal, a redundant dictionary with impact components is constructed by K-singular value decomposition (K-SVD), and the sparse coefficients are solved by an optimized orthogonal matching pursuit (OMP) algorithm. The sparse representation of fault impact features is realized, and the reconstructed signal with a concise fault impact feature structure is obtained. Secondly, the reconstructed signal is normalized, and the experimental dataset is divided into samples. Finally, the training set is input into the 1DCNN model for model training, and the test set is input into the trained model for classification and detection to complete the intelligent fault classification diagnosis of rotating machinery. This method is applied to the fault diagnosis of bearing data of Case Western Reserve University and worm gear reducer data of Shanghai University of Technology. Compared with other methods and models, the results show that the diagnosis method proposed in this paper can achieve higher diagnosis accuracy and better generalization ability than other diagnosis models under different datasets. [ABSTRACT FROM AUTHOR]

Over the past decade, the fresh white mulberry (Morus alba L.) fruit has gained growing interest due to its superior health and nutritional characteristics. While white mulberry is consumed as fresh fruit in several countries, it is also popular in dried form as a healthy snack food. One of the main challenges that have prevented a wider consumer uptake of this nutritious fruit is the non-uniformity in its quality grading. Therefore, identifying a reliable quality grading tool can greatly benefit the relevant stakeholders. The present research addresses this need by developing a novel machine vision system that combines the key strengths of image processing and artificial intelligence. Two grades (i.e., high- and low-quality) of white mulberry were imaged using a digital camera and 285 colour and textural features were extracted from their RGB images. Using the quadratic sequential feature selection method, a subset of 23 optimum features was identified to classify samples into two grades using artificial neural networks (ANN) and support vector machine (SVM) classifiers. The developed system under both classifiers achieved the highest correct classification rate (CCR) of 100%. Indeed, the latter approach offered a smaller mean squared error for the training and test sets. The developed model’s high accuracy confirms the machine vision’s suitability as a reliable, low-cost, rapid, and intelligent tool for quality monitoring of dried white mulberry.

Radiomics-based researches have shown predictive abilities with machine-learning approaches. However, it is still unknown whether different radiomics strategies affect the prediction performance. The aim of this study was to compare the prediction performance of frequently utilized radiomics feature selection and classification methods in glioma grading. Quantitative radiomics features were extracted from tumor regions in 210 Glioblastoma (GBM) and 75 low-grade glioma (LGG) MRI subjects. Then, the diagnostic performance of sixteen feature selection and fifteen classification methods were evaluated by using two different test modes: ten-fold cross-validation and percentage split. Balanced accuracy and area under the curve (AUC) of the receiver operating characteristic were used to evaluate prediction performance. In addition, the roles of the number of selected features, feature type, MRI modality, and tumor sub-region were compared to optimize the radiomics-based prediction. The results indicated that the combination of feature selection method L1-based linear support vector machine (L1-SVM) and classifier multi-layer perceptron (MLPC) achieved the best performance in the differentiation of GBM and LGG in both ten-fold cross validation (balanced accuracy:0.944, AUC:0.986) and percentage split (balanced accuracy:0.953, AUC:0.981). For radiomics feature extraction, the enhancing tumor region (ET) combined with necrotic and non-enhancing tumor (NCR/NET) regions in T1 post-contrast (T1-Gd) modality provided more considerable tumor-related phenotypes than other combinations of tumor region and MRI modality. Our comparative investigation indicated that both feature selection methods and machine learning classifiers affected the predictive performance in glioma grading. Also, the cross-combination strategy for comparison of radiomics feature selection and classification methods provided a way of searching optimal machine learning model for future radiomics-based prediction.

Abstract Every day, new applications arise relying on the use of high-resolution road maps in both academic and industrial environments. Autonomous vehicles rely on digital maps to navigate when optical sensors cannot be trusted, such as heavy rainfalls, snowy conditions, fog, and other situations. These situations increase the risks of accidents and disable the potentials of real-time mapping sensors. To tackle those problems, we present a methodology to automatically map anomalies on the road, namely speed bumps in this study, using an off-the-shelf camera (GoPro) and Machine Learning (ML) algorithms. We acquired data over a series of differently shaped speed bumps and applied three classification techniques: Naive Bayes, Multi-Layer Perceptron, and Random Forest (RF). With over 96% of classification accuracy, then RF was able to identify speed bumps on a GoPro dataset automatically. The results show a potential of the proposed methodology to be developed in surveying vehicles to produce highly-detailed maps of vertical road anomalies with a fast and accurate update rate.

Cardiovascular diseases (CVDs) are the leading cause of death today. The current identification method of the diseases is analyzing the Electrocardiogram (ECG), which is a medical monitoring technology recording cardiac activity. Unfortunately, looking for experts to analyze a large amount of ECG data consumes too many medical resources. Therefore, the method of identifying ECG characteristics based on machine learning has gradually become prevalent. However, there are some drawbacks to these typical methods, requiring manual feature recognition, complex models, and long training time. This paper proposes a robust and efficient 12-layer deep one-dimensional convolutional neural network on classifying the five micro-classes of heartbeat types in the MIT- BIH Arrhythmia database. The five types of heartbeat features are classified, and wavelet self-adaptive threshold denoising method is used in the experiments. Compared with BP neural network, random forest, and other CNN networks, the results show that the model proposed in this paper has better performance in accuracy, sensitivity, robustness, and anti-noise capability. Its accurate classification effectively saves medical resources, which has a positive effect on clinical practice.

Cardiovascular diseases (CVDs) are the leading cause of death today. The current identification method of the diseases is analyzing the Electrocardiogram (ECG), which is a medical monitoring technology recording cardiac activity. Unfortunately, looking for experts to analyze a large amount of ECG data consumes too many medical resources. Therefore, the method of identifying ECG characteristics based on machine learning has gradually become prevalent. However, there are some drawbacks to these typical methods, requiring manual feature recognition, complex models, and long training time. This paper proposes a robust and efficient 12-layer deep one-dimensional convolutional neural network on classifying the five micro-classes of heartbeat types in the MIT- BIH Arrhythmia database. The five types of heartbeat features are classified, and wavelet self-adaptive threshold denoising method is used in the experiments. Compared with BP neural network, random forest, and other CNN networks, the results show that the model proposed in this paper has better performance in accuracy, sensitivity, robustness, and anti-noise capability. Its accurate classification effectively saves medical resources, which has a positive effect on clinical practice. [ABSTRACT FROM AUTHOR]

Abstract We propose the first non-invasive three-layer architecture in literature based on neural networks that aims to determine the Big Five personality traits of an individual by analyzing offline handwriting. We also present the first database in literature that links the Big Five personality type with the handwriting features collected from 128 subjects containing both predefined and random texts. Testing our novel architecture on this database, we show that the predefined texts add more value if enforced on writers in the training stage, offering accuracies of 84.4% in intra-subject tests and 80.5% in inter-subject tests when the random dataset is used for testing purposes, up to 7% higher than when random datasets are used in the training phase. We obtain the highest prediction accuracy for Openness to Experience, Extraversion, and Neuroticism (over 84%), while for Conscientiousness and Agreeableness, the prediction accuracy is around 77%. Overall, our approach offers the highest accuracy compared with other state-of-the-art methods and results are computed in maximum 90 s, making the approach faster than the questionnaire or psychological interviews currently used for determining the Big Five personality traits. Our research also shows there are relationships between specific handwriting features and prediction with high accuracy of specific personality traits and this can be further exploited for improving, even more, the prediction accuracy of the proposed architecture.

The convolutional neural network (CNN) model is an active research topic in the field of EEG signals analysis. However, the classification effect of CNN on EEG signals of amnestic mild cognitive impairment (aMCI) with type 2 diabetes mellitus (T2DM) is not ideal. Even if EEG signals are transformed into multispectral images that are more closely matched with the model, the best classification performance can not be achieved. Therefore, to improve the performance of CNN toward EEG multispectral image classification, a multi-view convolutional neural network (MVCNN) classification model based on inceptionV1 is designed in this study. This model mainly improves and optimizes the convolutional layers and stochastic gradient descent (SGD) in the convolutional architecture model. Firstly, based on the discreteness of EEG multispectral image features, the multi-view convolutional layer structure was proposed. Then the learning rate change function of the SGD was optimized to increase the classification performance. The multi-view convolutional nerve was used in an EEG multispectral classification task involving 19 aMCI with T2DM and 20 normal controls. The results showed that compared with the traditional classification models, MVCNN had a better stability and accuracy. Therefore, MVCNN could be used as an effective feature classification method for aMCI with T2DM. [ABSTRACT FROM AUTHOR]

In real-time applications, a fast and robust visual tracker should generally have the following important properties: 1) feature representation of an object that is not only efficient but also has a good discriminative capability and 2) appearance modeling which can quickly adapt to the variations of foreground and backgrounds. However, most of the existing tracking algorithms cannot achieve satisfactory performance in both of the two aspects. To address this issue, in this paper, we advocate a novel and efficient visual tracker by exploiting the excellent feature learning and classification capabilities of an emerging learning technique, that is, extreme learning machine (ELM). The contributions of the proposed work are as follows: 1) motivated by the simplicity and learning ability of the ELM autoencoder (ELM-AE), an ELM-AE-based feature extraction model is presented, and this model can provide a compact and discriminative representation of the inputs efficiently and 2) due to the fast learning speed of an ELM classifier, an ELM-based appearance model is developed for feature classification, and is able to rapidly distinguish the object of interest from its surroundings. In addition, in order to cope with the visual changes of the target and its backgrounds, the online sequential ELM is used to incrementally update the appearance model. Plenty of experiments on challenging image sequences demonstrate the effectiveness and robustness of the proposed tracker. [ABSTRACT FROM AUTHOR]

Accurate and early detection of the brain tumor region has a great impact on the choice of treatment, its success rate, and the follow‐up of the disease process over time. This study presents a new bioinspired technique for the early detection of the brain tumor area to improve the chance of completely healing. The study presents a multistep technique to detect the brain tumor area. Herein, after image preprocessing and image feature extraction, an artificial neural network is used to determine the tumor area in the image. The method is based on using an improved version of the whale optimization algorithm for optimal selection of the features and optimizing the artificial neural network weights for classification. Simulation results of the proposed method are applied to FLAIR, T1, and T2 datasets and are compared with different algorithms. Three performance indexes including correct detection rate, false acceptance rate, and false rejection rate are selected for the system performance analysis. Final results showed the superiority of the proposed method toward the other similar methods. [ABSTRACT FROM AUTHOR]

In the intelligent fault diagnosis of rotating machinery, it is difficult to extract early weak fault impact features of rotating machinery under the interference of strong background noise, which makes the accuracy of fault identification low. In order to effectively identify the early faults of rotating machinery, an intelligent fault diagnosis method of rotating machinery based on an optimized adaptive learning dictionary and one-dimensional convolution neural network (1DCNN) is proposed in this paper. First of all, based on the original signal, a redundant dictionary with impact components is constructed by K-singular value decomposition (K-SVD), and the sparse coefficients are solved by an optimized orthogonal matching pursuit (OMP) algorithm. The sparse representation of fault impact features is realized, and the reconstructed signal with a concise fault impact feature structure is obtained. Secondly, the reconstructed signal is normalized, and the experimental dataset is divided into samples. Finally, the training set is input into the 1DCNN model for model training, and the test set is input into the trained model for classification and detection to complete the intelligent fault classification diagnosis of rotating machinery. This method is applied to the fault diagnosis of bearing data of Case Western Reserve University and worm gear reducer data of Shanghai University of Technology. Compared with other methods and models, the results show that the diagnosis method proposed in this paper can achieve higher diagnosis accuracy and better generalization ability than other diagnosis models under different datasets.

3D mesh denoising plays an important role in 3D model pre-processing and repair. A fundamental challenge in the mesh denoising process is to accurately extract features from the noise and to preserve and restore the scene structure features of the model. In this paper, we propose a novel feature-preserving mesh denoising method, which was based on robust guidance normal estimation, accurate feature point extraction and an anisotropic vertex denoising strategy. The methodology of the proposed approach is as follows: (1) The dual weight function that takes into account the angle characteristics is used to estimate the guidance normals of the surface, which improved the reliability of the joint bilateral filtering algorithm and avoids losing the corner structures; (2) The filtered facet normal is used to classify the feature points based on the normal voting tensor (NVT) method, which raised the accuracy and integrity of feature classification for the noisy model; (3) The anisotropic vertex update strategy is used in triangular mesh denoising: updating the non-feature points with isotropic neighborhood normals, which effectively suppressed the sharp edges from being smoothed; updating the feature points based on local geometric constraints, which preserved and restored the features while avoided sharp pseudo features. The detailed quantitative and qualitative analyses conducted on synthetic and real data show that our method can remove the noise of various mesh models and retain or restore the edge and corner features of the model without generating pseudo features.

In the recent year's many approaches have been made that uses image processing algorithms to detect traffic sign boards. Edge detection is used to avoid segmentation problems of the existing method. Color based segmentation faces the challenge of adaptive thresholding which fails in real time scenarios. This proposed algorithm is yet another approach to detect traffic sign boards from video sequences. The first step of this work is the pre-processing of the video frame which is achieved by the gray scale conversion and edge detection and the second step is the extraction of the objects. Hough Transform algorithm is then applied to measure properties of image regions for further analysis. The different feature points which include perimeter, area, filled area, solidity and centroid are extracted for the detection of the traffic sign board. Feature generation and classification are done on the recognition side to get the class of the detected object. The input for the project is video sequences taken from a camera placed on the vehicle. [ABSTRACT FROM AUTHOR]

Detecting cracks within reinforced concrete is still a challenging problem, owing to the complex disturbances from the background noise. In this work, we advocate a new concrete crack damage detection model, based upon multilayer sparse feature representation and an incremental extreme learning machine (ELM), which has both favorable feature learning and classification capabilities. Specifically, by cropping and using a sliding window operation and image rotation, a large number of crack and non-crack patches are obtained from the collected concrete images. With the existing image patches, the defect region features can be quickly calculated by the multilayer sparse ELM autoencoder networks. Then, the online incremental ELM classified network is used to recognize the crack defect features. Unlike the commonly-used deep learning-based methods, the presented ELM-based crack detection model can be trained efficiently without tediously fine-tuning the entire-network parameters. Moreover, according to the ELM theory, the proposed crack detector works universally for defect feature extraction and detection. In the experiments, when compared with other recently developed crack detectors, the proposed concrete crack detection model can offer outstanding training efficiency and favorable crack detecting accuracy. [ABSTRACT FROM AUTHOR]

The retrieval of features in a large-scale image database can improve the degree of visualization of images. The conventional method of feature-retrieval is a time-consuming process because it retrieves by searching the keywords. In this paper, a rapid feature retrieval method based on granular computing is proposed for use in a large-scale image database. In this method, we first collect and process the images from the database. Next, we construct a binary tree to realize the multi-class classification of the image features and complete the feature retrieval using support vector machines. The experimental results demonstrate that the proposed method can effectively retrieve the features in the large-scale image database. The effectiveness of retrieval can reach more than 95%. [ABSTRACT FROM AUTHOR]

Objective: Up to 10% of free flap cases are compromised, and without prompt intervention, amputation and even death can occur. Hourly monitoring improves salvage rates, but the gold standard for monitoring requires experienced personnel to operate and suffers from high false-positive rates as high as 31% that result in costly and unnecessary surgeries. In this paper, we investigate free flap patency monitoring using automatic hardware-only classification systems that eliminate the need for experienced personnel. The expected flow ranges of the antegrade and retrograde veins for breast reconstruction are studied using a syringe pump to create the laminar flow seen in veins. Methods: Feature data extracted from the Doppler blood flow signals are analyzed for sensitivity, specificity, and false-positive rates. Hardware is built to perform the classification automatically in real-time and output a decision at the end of the observation period. Results: Experimental results using the hardware-only classifier for a 50 ms window size show high sensitivity (96.75%), specificity (90.20%), and low false-positive rate (9.803%). The experimental and theoretical classification results show close agreement. Conclusion: This work indicates that automatic hardware-only classifiers can eliminate the need for experienced personnel to monitor free flap patency. Significance: The hardware-only classification is amenable to a monolithic implementation and future studies should study a totally implantable wirelessly-powered blood flow classifier. The high classifier performance in a short window period indicates that duty-cycled powering can be used to extend the safe operational depth of an implant. This is particularly relevant for the difficult buried free flap applications. [ABSTRACT FROM AUTHOR]

Advances in the eye care telemedicine system aid the diabetic patients in remote areas to stop the unwanted visit to ophthalmologist, reduces overall cost, time and money. Diabetic retinopathy, which is the primary cause of sight loss, has the most common symptoms like microaneurysms, haemorrhages, cotton‐wool spots, exudates and drusen. In this work, an efficient approach for the automatic detection of haemorrhages in colour retinal images is proposed and validated. The colour retinal images captured from the diabetic patients are enhanced by an effective pre‐processor. A bag of features based on intensity, colour and texture are extracted. Finally, the features are classified with the help of partial least square classifier. The classifier performance is validated on two publicly available databanks. The developed method obtains an area under receiver operating characteristic curve of 0.98 with an average execution time of 6 s. This application outperforms the existing approaches with high robustness and efficiency. [ABSTRACT FROM AUTHOR]

The aim of this study is to determine if navigation movements, used in surgical training, follow a particular power law which describes the relationship between the hand trajectory's curvature, torsion, and speed. Based on this approach, this study proposes the affine velocity as an appropriate classification feature to solve the surgical movement recognition problem. Eight subjects with different surgical experience were involved in the experiments. They were asked to do two kinds of movements that involve depth perception skills with their right arm. Using six video cameras and an instrumented laparoscope, the 3D trajectory of the end effector was recorded for each participant. A power law was used to fit the data sets and the exponents that relate the torsion, curvature, and speed were calculated. The exponents involved and the affine velocity for each trajectory were then computed, using a multi‐variable linear regression, and compared between participants. It is shown that fitting residual follows a normal distribution indicating no regression biases. Finally, it is presented that an affine velocity analysis could be able to classify between both trajectories showing a correlation with the surgical skills and a clear difference for people with some surgical training. [ABSTRACT FROM AUTHOR]

License plate recognition (LPR) system plays a vital role in security applications which include road traffic monitoring, street activity monitoring, identification of potential threats, and so on. Numerous methods were adopted for LPR but still, there is enough space for a single standard approach which can be able to deal with all sorts of problems such as light variations, occlusion, and multi‐views. The proposed approach is an effort to deal under such conditions by incorporating multiple features extraction and fusion. The proposed architecture is comprised of four primary steps: (i) selection of luminance channel from CIE‐Lab colour space, (ii) binary segmentation of selected channel followed by image refinement, (iii) a fusion of Histogram of oriented gradients (HOG) and geometric features followed by a selection of appropriate features using a novel entropy‐based method, and (iv) features classification with support vector machine (SVM). To authenticate the results of proposed approach, different performance measures are considered. The selected measures are False positive rate (FPR), False negative rate (FNR), and accuracy which is achieved maximum up to 99.5%. Simulation results reveal that the proposed method performs exceptionally better compared with existing works. [ABSTRACT FROM AUTHOR]

During the last decades, many researches and applications have been conducted on machining features modeling and classification. Although several approaches have been used in the domain of Computer-Aided Process Planning (CAPP), the consideration of freeform shapes has not been well explored at present. This paper aims to provide an up-to-date review of machining features and its conformance with STEP-NC (STEP compliant Numerical Control). A new method based on discrete shape representation, differential geometry and graph theory is developed for freeform machining feature characterization and classification. The effectiveness of the proposed method is demonstrated through an example of a blade part. [ABSTRACT FROM AUTHOR]