Search

We investigated the impact of window penetration loss (WinPL) on the frequency dependence of building entry loss (BEL) from 3.5 to 24 GHz. The WinPL characteristics of an ideal double-glazed glass and an actual double-glazed window were simulated and measured on-site, respectively, and both results showed almost the same oscillatory characteristics with respect to the frequency changes that occurred due to the impedance oscillation of the double glass-like multilayer dielectrics. Two BEL measurement scenarios were examined to analyze the frequency dependence of BEL in a traditional office building with double-glazed windows identical to those analyzed in the on-site WinPL measurements. The experiments included a complex propagation route (the first scenario) from the facade of the building to the corridors through windows and offices and a simple propagation route (the second scenario) through only windows lateral to the building. The two main findings are (i) BEL showed strong frequency-dependent behavior regardless of the propagation route and (ii) the WinPL characteristics of the outer double-glazed window were the main contributors to the frequency dependence of BEL.

We propose a novel monocular depth estimator, which improves the prediction accuracy on human regions by utilizing pose information. The proposed algorithm consists of two networks — PoseNet and DepthNet — to estimate keypoint heatmaps and a depth map, respectively. We incorporate the pose information from PoseNet to improve the depth estimation performance of DepthNet. Specifically, we develop the feature blending block, which fuses the features from PoseNet and DepthNet and feeds them into the next layer of DepthNet, to make the networks learn to predict the depths of human regions more accurately. Furthermore, we develop a novel joint training scheme using partially labeled datasets, which balances multiple loss functions effectively by adjusting weights. Experimental results demonstrate that the proposed algorithm can improve depth estimation performance significantly, especially around human regions. For example, the proposed algorithm improves the depth estimation performance on the human regions of ResNet-50 by 2.8% and 7.0% in terms of $\delta _{1}$ and RMSE, respectively, on the proposed HD + P dataset.

Permittivity sensing is commonly utilized in multiple fields for various applications. In this study, an enhanced RFID (Radio Frequency Identification) permittivity sensor system is designed. Additionally, we investigated the signal processing procedures in a stepwise manner to obtain the resultant graphs. For validation, a simplified system including a reader and a tag is tested. The reader in the system comprises a pulse generator and a pair of antennas connected to an oscilloscope, whereas the tag comprises an antenna and a delay line sensor. The pulse generator produces short pulses of less than 1 ns periodically, whereas the short-ended delay line on the tag acts as a sensor, wherein the delay time of the traversing wave is primarily associated with the relative permittivity of the material under test (MUT). We tested the system to derive an equation for the value of relative permittivity of the MUT using the measured signal. The system was calibrated by performing both unloaded and air tests to obtain measurement equations. Moreover, an additional test validated the water permittivity sensing, and the relative permittivity measured was 78.1. Considering the errors affecting the measurements, the measured relative permittivity of water concurs with the actual value.

Removing fog components from maritime images is more challenging than removing them from land images because of the complicated scattering effects. In this paper, we propose a single maritime image defogging algorithm based on illumination decomposition. First, we decompose a foggy input image into glow and glow-free layers by formulating an optimization problem and then solving it effectively, where the optimization variables are updated by closed-form solutions. Then, the fog components in the glow-free layer are removed using a defogging algorithm. Finally, the natural illumination in the glow layer is recovered using a compensation scheme to obtain the final fog-free image. Experimental results on real test images demonstrate that the proposed algorithm outperforms state-of-the-art algorithms in terms of both subjective and objective evaluation criteria.

High dynamic range (HDR) image and video technology can provide significant picture quality improvement over the standard dynamic range (SDR). However, when HDR content is represented on an SDR display, dynamic range compression may result in image quality deterioration. To address this problem, we propose an optimized human visual system (HVS) response model-based tone-mapping algorithm to preserve the perceptual responses between the HDR image and its tone-mapped image. First, we measure the HVS response differences using a 2D histogram when an HDR image is displayed on an HDR device and when its tone-mapped image is displayed on an SDR device. Then, we formulate an optimization problem to minimize the differences. By efficiently solving the optimization problem, we obtain an optimal tone-mapping curve. Experimental results on actual displays demonstrate that the proposed algorithm provides superior image quality compared with conventional algorithms in terms of both subjective and objective evaluations.

In this paper, we propose three-dimensional (3D) photon counting double random phase encryption (DRPE) with enhanced visual quality and security level. Conventional 3D photon counting DRPE can quickly encrypt the data by using the 4f optical system and random phase masks with enhanced security because the 3D photon counting technique is used. 3D photon counting DRPE extracts photons from the encrypted data by using statistical methods such as the Poisson random process, and the visual quality of the decrypted data can be enhanced through the 3D reconstruction process. However, it still has a problem to visualize the data when we extract extremely a few photons. To improve the security and the visual quality of the decrypted data, we propose the random amplitude reconstruction process in the encryption stage. Our proposed method reconstructs the amplitude of the encrypted data at a random depth. Thus, the shifting pixel value and depth information can be another important key for decryption through the random process. Therefore, it can effectively decrypt data securely, and the visual quality of the decrypted data can be enhanced. Finally, through the random reconstruction process in the decryption stage, our proposed method can simultaneously enhance the security and visual quality. To verify our proposed method, we carry out the simulation and optical experiment.

In the era of the fourth industrial revolution (Industry 4.0) and the Internet of Things (IoT), real-time data is enormously collected and analyzed from mechanical equipment. By classifying and characterizing the measured signals, the fault condition of mechanical components could be identified. However, most current health monitoring techniques utilize time-consuming and labor-intensive feature engineering, i.e., feature extraction and selection, that are carried out by experts. This paper, on the contrary, deals with an automatic diagnosis method of machine monitoring using a convolutional neural network (CNN) with class activation maps (CAM). A class activation map enables us to discriminate the fault region in the images, thus allowing us to localize the fault precisely. The goal of the paper is to demonstrate how CNN and CAM could be employed to real-world vibration video to characterize the machine’s status, representing normal or fault conditions. The performance of the proposed model is validated with a base-excited cantilever beam dataset and a water pump dataset. This paper presents a novel industrial application by developing a promising method for automatic machine condition-based monitoring.

Knee osteoarthritis (KOA) is a leading cause of disability among elderly adults, and it causes pain and discomfort and limits the functional independence of such adults. The aim of this study was the development of an automated classification model for KOA, based on the Kellgren-Lawrence (KL) grading system, using radiographic imaging and gait analysis data. Gait features highly associated with the radiological severity of KOA identified from our previous study, in addition to radiographic image features extracted from a deep learning network, namely, Inception-ResNet-v2, were exploited using a support vector machine for KOA multi-classification. The area under the curve (AUC) of the receiver operating characteristic curve from KL Grades 0-4 were 0.93, 0.82, 0.83, 0.88, and 0.97, respectively. The sensitivity, precision, and F1-score of the model were 0.70, 0.76, and 0.71, respectively. The proposed model outperformed a common deep learning approach that is based on using only radiographic images as the input data. This result indicates that gait data and radiographic images are complementary with respect to KOA classification, and the use of both data can improve the accuracy of the automated diagnosis of multiclass KOA.

Continuous casting is the procedure of the successive casting for solidification of the steel, which contains several cooling processes along the caster to coagulate the molten steel. It is such a rule of thumb that strand surface quality and casting productivity is highly dependent on temperature control. A finite-difference method is one of estimating temperature distribution, yet it hinders the process control efficiently. Song, et al. suggest a multimodal deep learning approach for prediction of the temperature. However, sequential and transient phenomena of solidifying steel are not considered, which makes it difficult to estimate the sequential heat-transfer characteristics in the whole process of the steel concretion. Herein, a deep learning model is proposed to predict the temperature distribution by taking into account both transient and steady-state characteristics. The proposed model addresses both spatial and sequential information by incorporating a convolutional neural network (CNN) and a recurrent neural network (RNN). Our quantitative and qualitative results show considerable predictive performance improvement against baseline models. Furthermore, the proposed model is applicable in a real-world steel-making industry by providing real-time temperature prediction, whilst retaining a lower computational cost.

Detection and diagnosis of material degradation are of a complex and challenging task since it is presently hand-operated by a human. Therefore, it leads to misinterpretation and avoids correct classification and diagnosis. In this paper, we develop a computer-assisted detection method of material failure by utilizing a deep learning approach. A deep convolutional neural network (CNN) model, combined with an image processing technique, e.g., adaptive histogram equalization, is trained to classify a real-world turbine tube degradation image data set, which is retrieved from a power generation company. The experimental result demonstrates the effectiveness of the proposed approach with predictive classification accuracy is up to 99.99% in comparison with a shallow machine learning algorithm, e.g., linear SVM. Furthermore, performance evaluation of a deep CNN with and without an above-mentioned image processing technique is exhibited and benchmarked. We successfully demonstrate a novel application in constructing a deep-structure neural network model for material degradation diagnosis, which is not available in the current literature.

In this paper, the problem of image speckle removal is addressed. To alleviate the pepper–salt remainder in the speckled image, we propose to utilize the nonlocal means filtering, where the weighting coefficients are derived based on the maximum a posteriori estimation with the total variation image prior. As a result, the objective function of the pixel fitting term plus the total variation regularizer is formulated, and it is solved with the majorization–minimization approach. To avoid the computationally intractable step size selection in the huge-scale gradient-based optimization, we split and solve the variables in the pixel fitting term and regularizer by means of the alternating direction method of multipliers. Performance analysis is performed for the Rayleigh and Gamma distributed signal models. The simulation and experimental results show the superior performance compared with other image despeckling methods in terms of various metrics and visual perception.

We propose the property-specific aesthetic assessment (PSAA) algorithm with unsupervised aesthetic property discovery. The proposed PSAA algorithm uses an aesthetic feature extractor, an aesthetic property classifier, and multiple property-specific assessment networks. The aesthetic feature extractor analyzes aesthetics of images to generate features. Using such aesthetic features, we discover diverse aesthetic properties in an unsupervised manner and develop the aesthetic property classifier to predict the aesthetic property of each image. For each discovered aesthetic property, we train a property-specific assessment network. Thus, we can assess the aesthetic quality of an image using the property-specific network that corresponds to its property. Experimental results on a large dataset show that the proposed PSAA algorithm achieves state-of-the-art aesthetic assessment performance. Furthermore, we demonstrate that PSAA is useful for improving aesthetic qualities of images in two applications: contrast enhancement and image cropping.

In this paper, a tri-band Gysel power divider (PD) based on zero-degree composite right-/left-handed (CRLH) transmission lines (TLs) is presented. Compared to the generalized design methods in which multiple passbands are realized by replacing conventional impedance transformers with quarter-wavelength CRLH-TLs, the employed zero-degree CRLH-TLs include high design flexibility for the characteristic impedance and phase responses of the composed left-handed and right-handed TLs, which can be used to separately control the bandwidths of the three passbands. In addition, the microstrip-to-slotline transition is utilized to replace the conventional 180° TL, which can expand the realizable range of the three center frequencies and reduce the circuit size, as well. The proposed theory is validated using two designs: One involves a broadband PD with a center frequency of 2.5 GHz, while the other is a tri-band PD centered at 3.5 GHz, 2.5 GHz, and 1.5 GHz. Good agreement between the simulated and measured results are obtained; for the first PD, a fractional 3-dB bandwidth of up to 116% is achieved, whereas, for the tri-band PD, a size reduction of 80% is achieved with good impedance matching and isolation performance.

Autonomous cars are currently widely studied in the automotive and robotics industries because autonomous driving can satisfy the needs of human drivers regarding safety, efficiency, and comfortable driving. Behavior and motion planning for an autonomous car is one of the main requirements of autonomous driving. For autonomous cars, a local route along with its road geometry and attributes of the area is required. There are two ways to obtain the local route: perception-based local route (PBLR) and precise map-based local route (MBLR) methods. First, this paper analyzes the characteristic of both the PBLR and MBLR inference methods. Then based on this analysis, this paper proposes a hybrid local route generation algorithm that chooses the best local route between the PBLR and MBLR options, according to the perceived performance and the precise map availability. To effectively create an expensive precise map, a mapping region classification algorithm is presented to selectively choose the mapping area, where the precise map must be constructed for the MBLR inference. The hybrid local route generation algorithm with the mapping region classification allows the area used for autonomous driving to be extended while reducing the cost due to the precise map. The advantages of the proposed algorithm were verified with experiments in real traffic conditions.

In this paper, a size-reduced tri-band Gysel power divider (PD) with ultra-wideband harmonics suppression performance, simple structure, high-power handling capability, and independently controllable bandwidth is first presented. The three passbands are introduced by two tri-band biasing networks whose impedances can also be utilized to control the bandwidths of the three passbands independently. With the introduction of slow-wave transmission lines and coupled lines with series open-circuited stubs, a reduced size and ultra-wide stopband can be obtained, respectively. Detailed closed-form design equations are derived and validated with a design of PD operating at 2.0, 2.5, and 3.0 GHz. Also, two additional circuits are designed, simulated, and fabricated. One is utilized to obtain the optional range of the three passbands, and the other is to make a comparison with the proposed PD. All the measured results agree well with the corresponding simulated ones. Proper impedance matching, isolation, and a wider 3-dB fractional bandwidth can be obtained, which is 18.5%, 20.7%, and 13.0%, respectively, at each passband. In addition, more bands can be easily extended to the proposed PD by introducing more open-circuited stubs in the tri-band biasing networks.