Search

Summary: Recently, researchers have placed a great deal of emphasis on modeling activity patterns to better understand human behavior. Several approaches have been researched so far to develop automatic human activity recognition systems that infer detailed semantics from visual images, aiming to understand real human behavior patterns. However, there is still a need for a cost effective solution to distinguish human actions in the real‐world environment. With this encouragement, a novel approach is proposed to recognize shoplifting acts by examining the posture evidence of the human being. This approach begins by obtaining the two‐dimensional pose reflecting human's body joints as a skeleton from the recorded frames. Subsequently, a preprocessing step is used to preprocess skeleton data, which can handle the occlusion too. Postural feature generation is then used to extract pertinent features from such preprocessed skeletons. Finally, feature deduction is performed to downsize the derived features to a smaller dimension, and activity classification is performed on such reduced features to identify shoplifting behaviors in real time. A synthetic shoplifting dataset and real store recorded videos are used to conduct the experiments, the findings of which appear more promising than those obtained using other cutting‐edge methods, with an accuracy of 97.36% and 91.66% for synthesized and real store recorded inputs. [ABSTRACT FROM AUTHOR]

Research in medical imaging focuses on methods useful in computer-aided diagnosis systems. In modern times, these systems often have automatic detection of regions of interest, and imaging technologies offer numerous advantages, like the possibility of developing reliable assisting algorithms. Magnetic Resonance Imaging (MRI) provides compelling features for brain tumor detection due to good soft tissue contrast and has important clinical value. To help clinicians in making diagnoses, current algorithms for processing and medical image classification may depend on intricate deep learning designs that demand large hardware resources and lengthy execution times. This is with no doubt helpful in understanding disease mechanisms and in labeling difficult instances for brain tumor identification. On the other hand, statistical low-dimension feature sets including co-occurrence-based ones could be useful in dealing with tumor detection avoiding possible complexity. In this paper, statistical approaches for feature extraction and reduction are analyzed for MRI brain tumor classification, and the evaluation of the results is presented on one of the publicly available brain tumor detection database commonly used for machine learning tasks. Bayes and kNN classifiers are applied for the analysis, as well as four distance metrics, and two methods for feature reduction. The results seem promising in developing a simple and less hardware-demanding procedure.

ABSTRACT: This study proposes an image classification methodology that automatically classifies human brain magnetic resonance (MR) images. The proposed methods contain four main stages: Data acquisition, preprocessing, feature extraction, feature reduction and classification, followed by evaluation. First stage starts by collecting MRI images from Harvard and our constructed Egyptian database. Second stage starts with noise reduction in MR images. Third stage obtains the features related to MRI images, using stationary wavelet transformation. In the fourth stage, the features of MR images have been reduced using principles of component analysis and kernel linear discriminator analysis (KLDA) to the more essential features. In last stage, the classification stage, two classifiers have been developed to classify subjects as normal or abnormal MRI human images. The first classifier is based on K‐Nearest Neighbor (KNN) on Euclidean distance. The second classifier is based on Levenberg‐Marquardt (LM‐ANN). Classification accuracy of 100% for KNN and LM‐ANN classifiers has been obtained. The result shows that the proposed methodologies are robust and effective compared with other recent works. [ABSTRACT FROM AUTHOR]

Falls are a serious public health problem and possibly life threatening for people in fall risk groups. We develop an automated fall detection system with wearable motion sensor units fitted to the subjects’ body at six different positions. Each unit comprises three tri-axial devices (accelerometer, gyroscope, and magnetometer/compass). Fourteen volunteers perform a standardized set of movements including 20 voluntary falls and 16 activities of daily living (ADLs), resulting in a large dataset with 2520 trials. To reduce the computational complexity of training and testing the classifiers, we focus on the raw data for each sensor in a 4 s time window around the point of peak total acceleration of the waist sensor, and then perform feature extraction and reduction. Most earlier studies on fall detection employ rule-based approaches that rely on simple thresholding of the sensor outputs. We successfully distinguish falls from ADLs using six machine learning techniques (classifiers): the k-nearest neighbor (k-NN) classifier, least squares method (LSM), support vector machines (SVM), Bayesian decision making (BDM), dynamic time warping (DTW), and artificial neural networks (ANNs). We compare the performance and the computational complexity of the classifiers and achieve the best results with the k-NN classifier and LSM, with sensitivity, specificity, and accuracy all above 99%. These classifiers also have acceptable computational requirements for training and testing. Our approach would be applicable in real-world scenarios where data records of indeterminate length, containing multiple activities in sequence, are recorded.

The operating condition of rolling bearings affects productivity and quality in the rotating machine process. Developing an effective rolling bearing condition monitoring approach is critical to accurately identify the operating condition. In this paper, a hybrid generalized hidden Markov model-based condition monitoring approach for rolling bearings is proposed, where interval valued features are used to efficiently recognize and classify machine states in the machine process. In the proposed method, vibration signals are decomposed into multiple modes with variational mode decomposition (VMD). Parameters of the VMD, in the form of generalized intervals, provide a concise representation for aleatory and epistemic uncertainty and improve the robustness of identification. The multi-scale permutation entropy method is applied to extract state features from the decomposed signals in different operating conditions. Traditional principal component analysis is adopted to reduce feature size and computational cost. With the extracted features' information, the generalized hidden Markov model, based on generalized interval probability, is used to recognize and classify the fault types and fault severity levels. Finally, the experiment results show that the proposed method is effective at recognizing and classifying the fault types and fault severity levels of rolling bearings. This monitoring method is also efficient enough to quantify the two uncertainty components. [ABSTRACT FROM AUTHOR]

In recent years, there has been a growing interest in the use of fault analysis techniques in unmanned marine vehicles (UMVs) owing to their significant impact on marine operations. This study presents a novel approach to the diagnosis of unbalanced load (blades damage) faults in an electric thruster motor in UMV propulsion systems based on orthogonal fuzzy neighbourhood discriminative analysis for feature dimensionality reduction. The diagnosis approach is based on the use of discrete wavelet transforms as a feature extraction tool and the optimal number of mother wavelet function and levels of resolution by analysing the vibration and current signals. As a result of analysis and comparisons, the Deubechies 12 (db12) wavelet and level 8 were chosen. A dynamic recurrent neural network was chosen for fault classification and level of fault severity prediction was implemented. Four faulty conditions were analysed under laboratory conditions and these were recreated by damaging the blades of a motor. The results obtained from the simulation demonstrate the effectiveness and reliability of the proposed methodology in classifying the different faults with greater speed and accuracy compared to existing methods. [ABSTRACT FROM AUTHOR]

Wearable devices for fall detection have received attention in academia and industry, because falls are very dangerous, especially for elderly people, and if immediate aid is not provided, it may result in death. However, some predictive devices are not easily worn by elderly people. In this work, a huge dataset, including 2520 tests, is employed to determine the best sensor placement location on the body and to reduce the number of sensor nodes for device ergonomics. During the tests, the volunteer's movements are recorded with six groups of sensors each with a triaxial (accelerometer, gyroscope and magnetometer) sensor, which is placed tightly on different parts of the body with special straps: head, chest, waist, right-wrist, right-thigh and right-ankle. The accuracy of individual sensor groups with their location is investigated with six machine learning techniques, namely the k-nearest neighbor (k-NN) classifier, Bayesian decision making (BDM), support vector machines (SVM), least squares method (LSM), dynamic time warping (DTW) and artificial neural networks (ANNs). Each technique is applied to single, double, triple, quadruple, quintuple and sextuple sensor configurations. These configurations create 63 different combinations, and for six machine learning techniques, a total of 63 ? 6 = 378 combinations is investigated. As a result, the waist region is found to be the most suitable location for sensor placement on the body with 99.96% fall detection sensitivity by using the k-NN classifier, whereas the best sensitivity achieved by the wrist sensor is 97.37%, despite this location being highly preferred for today's wearable applications. [ABSTRACT FROM AUTHOR]

The integrity of machining tools is important to maintain a high level of surface quality. The wear of the tool can lead to poor surface quality of the workpiece and even to damage of the machine. Furthermore, in some applications such as aeronautics and precision engineering, it is preferable to change the tool earlier rather than to loose the workpiece because of its high price compared to the tool's one. Thus, to maintain a high quality of the manufactured pieces, it is necessary to assess and predict the level of wear of the cutting tool. This can be done by using condition monitoring and prognostics. The aim is then to estimate and predict the amount of wear and calculate the remaining useful life (RUL) of the cutting tool. This paper presents a method for tool condition assessment and life prediction. The method is based on nonlinear feature reduction and support vector regression. The number of original features extracted from the monitoring signals is first reduced. These features are then used to learn nonlinear regression models to estimate and predict the level of wear. The method is applied on experimental data taken from a set of cuttings and simulation results are given. These results show that the proposed method is suitable for assessing the wear evolution of the cutting tools and predicting their RUL. This information can then be used by the operators to take appropriate maintenance actions. [ABSTRACT FROM AUTHOR]

Wearable devices for fall detection have received attention in academia and industry, because falls are very dangerous, especially for elderly people, and if immediate aid is not provided, it may result in death. However, some predictive devices are not easily worn by elderly people. In this work, a huge dataset, including 2520 tests, is employed to determine the best sensor placement location on the body and to reduce the number of sensor nodes for device ergonomics. During the tests, the volunteer’s movements are recorded with six groups of sensors each with a triaxial (accelerometer, gyroscope and magnetometer) sensor, which is placed tightly on different parts of the body with special straps: head, chest, waist, right-wrist, right-thigh and right-ankle. The accuracy of individual sensor groups with their location is investigated with six machine learning techniques, namely the k-nearest neighbor (k-NN) classifier, Bayesian decision making (BDM), support vector machines (SVM), least squares method (LSM), dynamic time warping (DTW) and artificial neural networks (ANNs). Each technique is applied to single, double, triple, quadruple, quintuple and sextuple sensor configurations. These configurations create 63 different combinations, and for six machine learning techniques, a total of 63 × 6 = 378 combinations is investigated. As a result, the waist region is found to be the most suitable location for sensor placement on the body with 99.96% fall detection sensitivity by using the k-NN classifier, whereas the best sensitivity achieved by the wrist sensor is 97.37%, despite this location being highly preferred for today’s wearable applications.

Falls are a serious public health problem and possibly life threatening for people in fall risk groups. We develop an automated fall detection system with wearable motion sensor units fitted to the subjects' body at six different positions. Each unit comprises three tri-axial devices (accelerometer, gyroscope, and magnetometer/compass). Fourteen volunteers perform a standardized set of movements including 20 voluntary falls and 16 activities of daily living (ADLs), resulting in a large dataset with 2520 trials. To reduce the computational complexity of training and testing the classifiers, we focus on the raw data for each sensor in a 4 s time window around the point of peak total acceleration of the waist sensor, and then perform feature extraction and reduction. Most earlier studies on fall detection employ rule-based approaches that rely on simple thresholding of the sensor outputs. We successfully distinguish falls from ADLs using six machine learning techniques (classifiers): the k-nearest neighbor (k-NN) classifier, least squares method (LSM), support vector machines (SVM), Bayesian decision making (BDM), dynamic time warping (DTW), and artificial neural networks (ANNs). We compare the performance and the computational complexity of the classifiers and achieve the best results with the k-NN classifier and LSM, with sensitivity, specificity, and accuracy all above 99%. These classifiers also have acceptable computational requirements for training and testing. Our approach would be applicable in real-world scenarios where data records of indeterminate length, containing multiple activities in sequence, are recorded. [ABSTRACT FROM AUTHOR]

The operating condition of rolling bearings affects productivity and quality in the rotating machine process. Developing an effective rolling bearing condition monitoring approach is critical to accurately identify the operating condition. In this paper, a hybrid generalized hidden Markov model-based condition monitoring approach for rolling bearings is proposed, where interval valued features are used to efficiently recognize and classify machine states in the machine process. In the proposed method, vibration signals are decomposed into multiple modes with variational mode decomposition (VMD). Parameters of the VMD, in the form of generalized intervals, provide a concise representation for aleatory and epistemic uncertainty and improve the robustness of identification. The multi-scale permutation entropy method is applied to extract state features from the decomposed signals in different operating conditions. Traditional principal component analysis is adopted to reduce feature size and computational cost. With the extracted features' information, the generalized hidden Markov model, based on generalized interval probability, is used to recognize and classify the fault types and fault severity levels. Finally, the experiment results show that the proposed method is effective at recognizing and classifying the fault types and fault severity levels of rolling bearings. This monitoring method is also efficient enough to quantify the two uncertainty components., Competing Interests: The authors declare no conflict of interest.