Wardmcguire7061

Human activity recognition (HAR) systems combined with machine learning normally serve users based on a fixed sensor position interface. Variations in the installing position will alter the performance of the recognition and will require a new training dataset. Therefore, we need to understand the role of sensor position in HAR system design to optimize its effect. In this paper, we designed an optimization scheme with virtual sensor data for the HAR system. The system is able to generate the optimal sensor position from all possible locations under a given sensor number. Utilizing virtual sensor data, the training dataset can be accessed at low cost. The system can help the decision-making process of sensor position selection with great accuracy using feedback, as well as output the classifier at a lower cost than a conventional training model.The analysis of data from sensors in structures subjected to extreme conditions such as the ones used in smelting processes is a great decision tool that allows knowing the behavior of the structure under different operational conditions. In this industry, the furnaces and the different elements are fully instrumented, including sensors to measure variables such as temperature, pressure, level, flow, power, electrode positions, among others. From the point of view of engineering and data analytics, this quantity of data presents an opportunity to understand the operation of the system under normal conditions or to explore new ways of operation by using information from models provided by using deep learning approaches. Although some approaches have been developed with application to this industry, it is still an open research area. As a contribution, this paper presents an applied deep learning temperature prediction model for a 75 MW electric arc furnace, which is used for ferronickel production. In general, the methodology proposed considers two steps first, a data cleaning process to increase the quality of the data, eliminating both redundant information as well as atypical and unusual data, and second, a multivariate time series deep learning model to predict the temperatures in the furnace lining. The developed deep learning model is a sequential one based on GRU (gated recurrent unit) layer plus a dense layer. The GRU + Dense model achieved an average root mean square error (RMSE) of 1.19 °C in the test set of 16 different thermocouples radially distributed on the furnace.The recent explosive growth in the number of smart technologies relying on data collected from sensors and processed with machine learning classifiers made the training data imbalance problem more visible than ever before. find more Class-imbalanced sets used to train models of various events of interest are among the main reasons for a smart technology to work incorrectly or even to completely fail. This paper presents an attempt to resolve the imbalance problem in sensor sequential (time-series) data through training data augmentation. An Unrolled Generative Adversarial Networks (Unrolled GAN)-powered framework is developed and successfully used to balance the training data of smartphone accelerometer and gyroscope sensors in different contexts of road surface monitoring. Experiments with other sensor data from an open data collection are also conducted. It is demonstrated that the proposed approach allows for improving the classification performance in the case of heavily imbalanced data (the F1 score increased from 0.69 to 0.72, p less then 0.01, in the presented case study). However, the effect is negligible in the case of slightly imbalanced or inadequate training sets. The latter determines the limitations of this study that would be resolved in future work aimed at incorporating mechanisms for assessing the training data quality into the proposed framework and improving its computational efficiency.Rotary left ventricular assist devices (LVAD) have emerged as a long-term treatment option for patients with advanced heart failure. LVADs need to maintain sufficient physiological perfusion while avoiding left ventricular myocardial damage due to suction at the LVAD inlet. To achieve these objectives, a control algorithm that utilizes a calculated suction index from measured pump flow (SIMPF) is proposed. This algorithm maintained a reference, user-defined SIMPF value, and was evaluated using an in silico model of the human circulatory system coupled to an axial or mixed flow LVAD with 5-10% uniformly distributed measurement noise added to flow sensors. Efficacy of the SIMPF algorithm was compared to a constant pump speed control strategy currently used clinically, and control algorithms proposed in the literature including differential pump speed control, left ventricular end-diastolic pressure control, mean aortic pressure control, and differential pressure control during (1) rest and exercise states; (2) rapid, eight-fold augmentation of pulmonary vascular resistance for (1); and (3) rapid change in physiologic states between rest and exercise. Maintaining SIMPF simultaneously provided sufficient physiological perfusion and avoided ventricular suction. Performance of the SIMPF algorithm was superior to the compared control strategies for both types of LVAD, demonstrating pump independence of the SIMPF algorithm.The resolution of planar-Hall magnetoresistive (PHMR) sensors was investigated in the frequency range from 0.5 Hz to 200 Hz in terms of its sensitivity, average noise level, and detectivity. Analysis of the sensor sensitivity and voltage noise response was performed by varying operational parameters such as sensor geometrical architectures, sensor configurations, sensing currents, and temperature. All the measurements of PHMR sensors were carried out under both constant current (CC) and constant voltage (CV) modes. In the present study, Barkhausen noise was revealed in 1/f noise component and found less significant in the PHMR sensor configuration. Under measured noise spectral density at optimized conditions, the best magnetic field detectivity was achieved better than 550 pT/√Hz at 100 Hz and close to 1.1 nT/√Hz at 10 Hz for a tri-layer multi-ring PHMR sensor in an unshielded environment. Furthermore, the promising feasibility and possible routes for further improvement of the sensor resolution are discussed.In the actual fault diagnosis process of an analog circuit, there is often a problem due to the lack of fault samples, leading to the low-accuracy of diagnostic models. Therefore, using positive samples that are easy to obtain to establish diagnostic models became a research hotspot in the field of analog circuit fault diagnosis. This paper proposes a method based on Support Vector Data Description (SVDD) and Dempster-Shafer evidence theory (D-S evidence theory) for fault diagnosis of modular analog circuit. Firstly, the principle of circuit module partition is proposed to divide the analog circuit under test, and the output port of each module is selected as test point. Secondly, the paper extracts the feature of the time-domain and frequency-domain output signals of the circuit module through Principal Component Analysis (PCA). Thirdly, four state detection models based on SVDD are established to judge the working state of each circuit module, including TSG, TSP, FSG, and FSP state detection model. Finally, the D-S theory is introduced to integrate the test results of each model for locating fault circuit module. To verify the effectiveness of the proposed method, the dual bandpass filter circuit is selected for simulation and hardware experiment. The results show that the proposed method can locate the analog fault effectively and has a higher diagnosis accuracy.Power conversion efficiency (PCE) has been one of the key concerns for power management circuits (PMC) due to the low output power of the vibrational energy harvesters. This work reports a dynamic threshold cancellation technique for a high-power conversion efficiency CMOS rectifier. The proposed rectifier consists of two stages, one passive stage with a negative voltage converter, and another stage with an active diode controlled by a threshold cancellation circuit. The former stage conducts the signal full-wave rectification with a voltage drop of 1 mV, whereas the latter reduces the reverse leakage current, consequently enhancing the output power delivered to the ohmic load. As a result, the rectifier can achieve a voltage and power conversion efficiency of over 99% and 90%, respectively, for an input voltage of 0.45 V and for low ohmic loads. The proposed circuit is designed in a standard 130 nm CMOS process and works for an operating frequency range from 800 Hz to 51.2 kHz, which is promising for practical applications.This paper proposes a novel wideband leaf-shaped printed dipole antenna sensor that uses a parasitic element to improve the impedance matching bandwidth characteristics for high-power jamming applications. The proposed antenna sensor consists of leaf-shaped dipole radiators, matching posts, rectangular slots, and a parasitic loop element. The leaf-shaped dipole radiators are designed with exponential curves to obtain a high directive pattern and are printed on a TLY-5 substrate for high-power durability. The matching posts, rectangular slots, and a parasitic loop element are used to enhance the impedance matching characteristics. The proposed antenna sensor has a measured fractional bandwidth of 66.7% at a center frequency of 4.5 GHz. To confirm the array antenna sensor characteristics, such as its active reflection coefficients (ARCs) and beam steering gains, the proposed single antenna sensor is extended to an 11 × 1 uniform linear array. The average values of the simulated and measured ARCs from 4.5 to 6 GHz are -13.4 dB and -14.7 dB. In addition, the measured bore-sight array gains of the co-polarization are 13.4 dBi and 13.7 dBi at 4 GHz and 5 GHz, while those of the cross-polarizations are -4.9 dBi and -3.4 dBi, respectively. When the beam is steered at a steering angle, θ0, of 15°, the maximum measured array gains of the co-polarization are 12.2 dBi and 10.3 dBi at 4 GHz and 5 GHz, respectively.The advances in the miniaturisation of electronic devices and the deployment of cheaper and faster data networks have propelled environments augmented with contextual and real-time information, such as smart homes and smart cities. These context-aware environments have opened the door to numerous opportunities for providing added-value, accurate and personalised services to citizens. In particular, smart healthcare, regarded as the natural evolution of electronic health and mobile health, contributes to enhance medical services and people's welfare, while shortening waiting times and decreasing healthcare expenditure. However, the large number, variety and complexity of devices and systems involved in smart health systems involve a number of challenging considerations to be considered, particularly from security and privacy perspectives. To this aim, this article provides a thorough technical review on the deployment of secure smart health services, ranging from the very collection of sensors data (either related to the medical conditions of individuals or to their immediate context), the transmission of these data through wireless communication networks, to the final storage and analysis of such information in the appropriate health information systems. As a result, we provide practitioners with a comprehensive overview of the existing vulnerabilities and solutions in the technical side of smart healthcare.