As the number of high-rise buildings is increasing, more methods of exterior-wall cleaning are being developed. There are a few models based on artificial intelligence that determine the type and level of contaminatio...
详细信息
As the number of high-rise buildings is increasing, more methods of exterior-wall cleaning are being developed. There are a few models based on artificial intelligence that determine the type and level of contamination primarily by moving the cleaning area. In this study, we propose an system using YOLOv3 algorithm, color-detection, to install on facade cleaning robot and brightness-discrimination. There are three types of contaminant-detection parameters: size, color, and brightness, and these parameters are subjected to a robust optimization process to maintain a constant detection rate under different conditions. The three parameters are determined via Taguchi method with signal to noise ratio and noise factors. An environment for algorithm testing is established, and artificial contamination is implemented on the specimen. A field test with the detection algorithm shall be performed in the near future.
Background: Cervical vestibular evoked myogenic potentials (cVEMPs) are surface-recorded responses that reflect saccular function. Analysis of cVEMPs has focused, nearly exclusively, on time-domain waveform measuremen...
详细信息
Background: Cervical vestibular evoked myogenic potentials (cVEMPs) are surface-recorded responses that reflect saccular function. Analysis of cVEMPs has focused, nearly exclusively, on time-domain waveform measurements such as amplitude and latency of response peaks, but synchrony-based measures have not been previously reported. New Method: Time-frequency analyses were used to apply an objective response-detection algorithm and to quantify response synchrony. These methods are new to VEMP literature and have been adapted from previous auditory research. Air-conducted cVEMPs were elicited using a 500 Hz tone burst in twenty young, healthy participants. Results: Time-frequency characteristics of cVEMPs and time-frequency boundaries for response energy were established. An inter-trial coherence analysis approach revealed highly synchronous responses with representative inter-trial coherence values of approximately 0.7. Comparison with existing methods: Inter-trial coherence measures were highly correlated with conventional amplitude measures in this group of young, healthy adults (R2 = 0.91 - 0.94), although the frequencies at which these measures had their largest magnitude were unrelated (R2 =.02). Conventional measures of peak-to-peak amplitude and latency were consistent with previous literature. Interaural asymmetry ratios were comparable between amplitude- and synchrony-based measures. Conclusions: Synchrony-based time-frequency analyses were successfully applied to cVEMP data and this type of analysis may be helpful to differentiate synchrony from amplitude in populations with disrupted neural synchrony.
In the current context of intensive spectrum use by communications systems, WiFi systems have been allowed to use bands previously reserved for weather radars, as opportunity users. Some drawbacks in spectrum manageme...
详细信息
In the current context of intensive spectrum use by communications systems, WiFi systems have been allowed to use bands previously reserved for weather radars, as opportunity users. Some drawbacks in spectrum management make WiFi systems a source of interference that degrades the quality of observables obtained by C-band weather radars. In this work we present a strategy to detect these interfering WiFi packets at the output signal of the radar matched filter. The strategy is based on a delay and correlate algorithm that exploits the periodic structure of the WiFi packets preamble, periodicity that remains unchanged even though the signal is distorted when passing through the radar reception stages. We formulate the detection strategy as a hypothesis test that uses the squared modulus of the auto-correlation as the statistic, extended to a constant false alarm (CFAR) formulation to cope with the unknown noise power. We evaluate analytically and through numerical simulations the performance of the test in terms of detection probability. We also perform a series of controlled experiments using real-world weather radar data collected by Argentinian C-band RMA radars. The results show a high detection rate both when WiFi interference is in regions where there is only noise and when it is in regions where there is also a meteorological target. An algorithm for detecting WiFi packets in data acquired by weather radars operating in C-band is developed The detection algorithm leverages the periodic structure of the orthogonal frequency division multiplexing preamble at the beginning of Wi-Fi packets The performance of the developed algorithm is analyzed with both synthetic data and real data acquired by a weather radar Weather radars operating in the C-band currently experience interference from Wi-Fi access points operating in the 5 GHz band. This interference impacts the quality of weather radar products, making it challenging to accurately interpret weather conditions in
Wireless electrocardiogram (ECG) systems are responsible to collect and transmit the vital signals of cardiac patients wirelessly to medical centers for diagnostic and therapeutic purposes. ECG is a noninvasive techni...
详细信息
ISBN:
(纸本)9781479900664
Wireless electrocardiogram (ECG) systems are responsible to collect and transmit the vital signals of cardiac patients wirelessly to medical centers for diagnostic and therapeutic purposes. ECG is a noninvasive technique widely used in health care systems for diagnosis of heart diseases. However, the use of conventional ECG system is restricted by patient's mobility and the system's transmission capacity, and physical size. Aforementioned highlights the need and advantage of wireless ECG systems with low sampling-rate and low power consumption. With this in mind, Compressed Sensing (CS) procedure as a new sampling approach and the collaboration of wireless ECG framework is used to provide a robust high-resolution QRS detection algorithm in the hospitals and medical centers with high probability and enough accuracy. Advanced wireless ECG systems based on our approach will be able to deliver healthcare not only to patients in hospitals and medical centers;but also at their homes and workplaces thus offering cost saving, and improving the quality of life. Our simulation results for two records of ECG signals show an increment of 10% for sensitivity as well as 12% for the prediction level and good detection accuracy. The proposed algorithm also achieves significantly better detection rate in comparison with Empirical Mode Decomposition (EMD) method.
Roughness, as one of the evaluation indexes of processed surface quality, has a straight influence on the performance and life of products. Therefore, the roughness detection is of great significance for the control o...
详细信息
Roughness, as one of the evaluation indexes of processed surface quality, has a straight influence on the performance and life of products. Therefore, the roughness detection is of great significance for the control of product quality. At present, image-based roughness detection has become the mainstream technology with its advantage of high detection efficiency, large amount of information collection, and high measurement accuracy. From the perspective of image acquisition, preprocessing, and detection algorithms,this paper summarizes the existing typical methods, compares and analyzes them, and gives the challenges and future development direction of detection technology.
Relevant physiological studies have revealed that the response of the classical receptive field (CRF) to visual stimuli could be suppressed by non-CRF (nCRF) inhibition of the kernel in the primary visual cortex (V1)....
详细信息
Relevant physiological studies have revealed that the response of the classical receptive field (CRF) to visual stimuli could be suppressed by non-CRF (nCRF) inhibition of the kernel in the primary visual cortex (V1). Based on this mechanism, many bio-inspired contour detection models have been proposed, which are mainly achieved through CRF responses and nCRF surround inhibition calculation. In fact, the dynamic characteristics of neurons play an important role in contour detection in biological vision. Inspired by these visual mechanisms, the authors propose a contour detection model that emulates these dynamic characteristics. By introducing a multi-bandwidth Gabor filter, according to the target image, they can effectively adjust the weight ratios of the filter to protect the contours and filter the background textures in the calculation of CRF responses. Additionally, they logarithmically modulate the nCRF inhibition kernel to make texture suppression more flexible and effective, thus improving the accuracy of detection algorithm as a whole. Compared with existing bio-inspired contour detection models, the proposed model is more effective at contour detection, which will aid engineering applications that utilise pattern recognition in machine vision.
Massive multi-input multi-output (MIMO) technology is one of the most promising concepts in 5G wireless system. Grounded on the fact that the channel matrix in massive MIMO system is large dimensional, classical MIMO ...
详细信息
ISBN:
(纸本)9783319908021;9783319908014
Massive multi-input multi-output (MIMO) technology is one of the most promising concepts in 5G wireless system. Grounded on the fact that the channel matrix in massive MIMO system is large dimensional, classical MIMO detection algorithms are not appropriate for large scaled antennas. In this paper, a low-complexity discrete gbest-guided artificial bee colony (DGABC) detection algorithm is proposed for massive MIMO uplink, chaotic maps for parameter adaptation is also proposed in order to improve the convergence characteristic of the DGABC algorithm and to prevent the algorithm from getting stuck in local solutions. Experiments show that the proposed DGABC detection algorithm outperforms both the original ABC algorithm and MMSE detection with a relatively low complexity.
Aviation security X-ray equipment currently searches objects through primary screening, in which the screener has to re-search a baggage/person to detect the target object from overlapping objects. The advancements of...
详细信息
Aviation security X-ray equipment currently searches objects through primary screening, in which the screener has to re-search a baggage/person to detect the target object from overlapping objects. The advancements of computer vision and deep learning technology can be applied to improve the accuracy of identifying the most dangerous goods, guns and knives, from X-ray images of baggage. Artificial intelligence-based aviation security X-rays can facilitate the high-speed detection of target objects while reducing the overall security search duration and load on the screener. Moreover, the overlapping phenomenon was improved by using raw RGB images from X-rays and simultaneously converting the images into grayscale for input. An O-Net structure was designed through various learning rates and dense/depth-wise experiments as an improvement based on U-Net. Two encoders and two decoders were used to incorporate various types of images in processing and maximize the output performance of the neural network, respectively. In addition, we proposed U-Net segmentation to detect target objects more clearly than the You Only Look Once (YOLO) of Bounding-box (Bbox) type through the concept of a "confidence score". Consequently, the comparative analysis of basic segmentation models such as Fully Convolutional Networks (FCN), U-Net, and Segmentation-networks (SegNet) based on the major performance indicators of segmentation-pixel accuracy and mean-intersection over union (m-IoU)-revealed that O-Net improved the average pixel accuracy by 5.8%, 2.26%, and 5.01% and the m-IoU was improved by 43.1%, 9.84%, and 23.31%, respectively. Moreover, the accuracy of O-Net was 6.56% higher than that of U-Net, indicating the superiority of the O-Net architecture.
This paper presents a new algorithm for the detection of ferroresonance oscillations in medium voltage (MV) power systems. The proposed method is based on an analysis of estimated flux resulting from the voltage in op...
详细信息
This paper presents a new algorithm for the detection of ferroresonance oscillations in medium voltage (MV) power systems. The proposed method is based on an analysis of estimated flux resulting from the voltage in open delta voltage transformer (VT) connection. The testing results proved that the new solution is capable of identifying quickly and reliably ferroresonance oscillations and it does not maloperate during faults. In addition, this method is simple for hardware implementation. The developed solution has been thoroughly tested on simulation runs (from the MATLAB2019b/Simulink program), as well as recorded signals.
High sleep quality enhances life while helping to improve health. Sleep quality increases with fewer sleep disorders such as in-sleep activity is assessed based on such sleep disorders as indicators. In this context, ...
详细信息
ISBN:
(纸本)9781728163321
High sleep quality enhances life while helping to improve health. Sleep quality increases with fewer sleep disorders such as in-sleep activity is assessed based on such sleep disorders as indicators. In this context, the measurement of in-sleep activity will enable the analysis of sleep quality. This study suggests an algorithm to measure the number of in-sleep activity using a pressure sensor. Movements are detected using the vibration data that is measured from the sensor during tossing and turning, and the pattern of changing pressure according to person's posture in sleep is analyzed. Measuring in-sleep activity using this algorithm will enable the evaluation of sleep quality. Also, to evaluate the algorithm, an actual test environment was constructed where in-sleep activities were measured, and it was determined whether they were counted accurately. As a result, it presented an average cognitive accuracy of 98.6%, and the availability of the algorithm was confirmed.
暂无评论