Search

The accurate estimation of clutter covariance matrix (CCM) is essential in designing a radar detector/filter to suppress sea clutter. This estimation might not be easily accomplished because of the scarcity of valid training vectors adjacent to the range cell under test (CUT). We propose a new CCM estimation algorithm that is derived by modeling time-series clutter returns into a clutter Doppler spectrum in the frequency domain and exploiting mutual independence among spectral components. To justify its excellence over the conventional sample covariance matrix (SCM) algorithm, we design two filters—a maximum signal-to-interference-plus-noise ratio (SINR)-based filter and a whitening filter—that use the estimated CCMs and compare their performance in a numerically simulated sea clutter scenario. Comparisons are made by showing the eigenvector spectra of the estimated CCMs and the frequency responses and outputs of the filters. Moreover, SINRs at the target Doppler bin are examined and compared with a theoretical, analytically derived SINR.

Ensemble deep learning methods have demonstrated significant improvements in forecasting the solar panel power generation using historical time-series data. Although many studies have used ensemble deep learning methods with various data partitioning strategies, most have only focused on improving the predictive methods by associating several different models or combining hyperparameters and interactions. In this study, we contend that we can enhance the precision of power generation forecasting by identifying a suitable data partition strategy and establishing the ideal number of partitions and subset sizes. Thus, we propose a feasibility study of the influence of data partition strategies on ensemble deep learning. We selected five time-series data partitioning strategies—window, shuffle, pyramid, vertical, and seasonal—that allow us to identify different characteristics and features in the time-series data. We conducted various experiments on two sources of solar panel datasets collected in Seoul and Gyeongju, South Korea. Additionally, LSTM-based bagging ensemble models were applied to combine the advantages of several single LSTM models. The experimental results reveal that the data partition strategies positively influence the forecasting of power generation. Specifically, the results demonstrate that ensemble models with data partition strategies outperform single LSTM models by approximately 4–11% in terms of the coefficient of determination (R2) score.

CT volumetry (CTV) has been widely used for pre-operative graft weight (GW) estimation in living-donor liver transplantation (LDLT), and the use of a deep-learning algorithm (DLA) may further improve its efficiency. However, its accuracy has not been well determined. To evaluate the efficiency and accuracy of DLA-assisted CTV in GW estimation, we performed a retrospective study including 581 consecutive LDLT donors who donated a right-lobe graft. Right-lobe graft volume (GV) was measured on CT using the software implemented with the DLA for automated liver segmentation. In the development group (n = 207), a volume-to-weight conversion formula was constructed by linear regression analysis between the CTV-measured GV and the intraoperative GW. In the validation group (n = 374), the agreement between the estimated and measured GWs was assessed using the Bland–Altman 95% limit-of-agreement (LOA). The mean process time for GV measurement was 1.8 ± 0.6 min (range, 1.3–8.0 min). In the validation group, the GW was estimated using the volume-to-weight conversion formula (estimated GW [g] = 206.3 + 0.653 × CTV-measured GV [mL]), and the Bland–Altman 95% LOA between the estimated and measured GWs was −1.7% ± 17.1%. The DLA-assisted CT volumetry allows for time-efficient and accurate estimation of GW in LDLT.

Air pollution is a critical problem that is of major concern worldwide. South Korea is one of the countries most affected by air pollution. Rapid urbanization and industrialization in South Korea have induced air pollution in multiple forms, such as smoke from factories and exhaust from vehicles. In this paper, we perform a comparative analysis of predictive models for fine particulate matter in Daejeon, the fifth largest city in South Korea. This study is conducted for three purposes. The first purpose is to determine the factors that may cause air pollution. Two main factors are considered: meteorological and traffic. The second purpose is to find an optimal predictive model for air pollutant concentration. We apply machine learning and deep learning models to the collected dataset to predict hourly air pollutant concentrations. The accuracy of the deep learning models is better than that of the machine learning models. The third purpose is to analyze the influence of road conditions on predicting air pollutant concentration. Experimental results demonstrate that considering wind direction and wind speed could significantly decrease the error rate of the predictive models.

The design and application of eddy current brakes (ECBs) should be simple; further, ECBs should be used semi-permanently. This study aimed to determine major parameters for designing an ECB that can be applied to a small-scale wind turbine generator. To this end, an ECB was developed that could actuate without additional power, thus improving the efficiency of the generator. A series of simulations were conducted for a parametric study to pre-design ECBs suitable for small wind turbines. The six parameters chosen were disk thickness, number of magnets, radial location of magnets from center of disk, magnet pole arrangement, magnetic flux density, and rotational speed. The simulations were conducted on COMSOL Multiphysics. The results indicated that the number of magnets and magnet pole arrangements can significantly affect the performance curve of ECBs. Moreover, the disk thickness and rotational speed are linearly proportional to the braking torque.

With the rapid increase in automobiles, the importance of reducing low-frequency noise is being emphasized for a comfortable urban environment. Helmholtz resonators are widely used to attenuate low-frequency noise over a narrow range. In this study, a slit-type soundproof panel is designed to achieve low-frequency noise attenuation in the range of 500 Hz to 1000 Hz with the characteristics of a Helmholtz resonator and the ability to pass air through the slits on the panel surface for reducing wind load. The basic dimension of the soundproof panel is determined using the classical formula and numerical analysis using a commercial program, COMSOL Multiphysics, for transmission loss prediction. From the numerical study, it is identified that the transmission loss performance is improved compared to the basic design according to the shape change and configuration method of the Helmholtz resonator. Although the correlation according to the shape change and configuration method cannot be derived, it is confirmed that it can be used as an effective method for deriving a soundproof panel design that satisfies the basic performance.

For an open-deck steel plate girder railway bridge with rail joints, frequent damage to the bridge members and a high level of noise and vibration occur. By installing continuous welded rail (CWR) to the bridge, it is possible to reduce the noise and impact force of the bridge. However, current girder–sleeper fasteners have low lateral resistance in nature and track buckling can occur when CWR is used on such a bridge. Therefore, a new girder-sleeper fastener with proper lateral resistance to prevent CWR track buckling is needed. In this study, the lateral resistance requirements of a girder-sleeper fastener are investigated through a series of finite element (FE) analyses and parametric study. The effect of peak lateral resistance of the fastener, curve radius, girder length, and lateral displacement of girder are examined. From the analysis results, the peak lateral resistance criterion of the girder–sleeper fastener is proposed for the design of a new fastener for CWR tracks on an open-deck steel plate girder bridge.

With the advent of artificial intelligence, the research paradigm in natural language processing has been transitioned from statistical methods to machine learning-based approaches. One application is to develop a deep learning-based language model that helps software engineers write code faster. Although there have already been many attempts to develop code auto-completion functionality from different research groups, a need to establish an in-house code has been identified for the following reasons: (1) a security-sensitive company (e.g., Samsung Electronics) may not want to utilize commercial tools given that there is a risk of leaked source codes and (2) commercial tools may not be applicable to the specific domain (e.g., SSD firmware development) especially if one needs to predict unique code patterns and style. This research proposes a hybrid approach that harnesses the synergy between machine learning techniques and advanced design methods aiming to develop a code auto-completion framework that helps firmware developers write code in a more efficient manner. The sensitivity analysis results show that the deterministic design results in reducing prediction accuracy as it generates output in some unexpected ways, while the probabilistic design provides a list of reasonable next code elements in which one could select it manually to increase prediction accuracy.

In this article, a CMOS multistandard wireless direct-conversion receiver is designed. The receiver is composed of three components: low noise amplifier, voltage-controlled oscillator, and mixer. In details, the designed receiver adopts direct-conversion architecture and accommodates three standards: WCDMA, Wibro (or mobile WIMAX), and CDMA 2000 1×: 1.84–2.4 GHz. The designed mixer is a passive sub-harmonic doubly balanced structure, the VCO is a back-gate coupling quadrature VCO, and the LNA is a differential structure. Each component is designed with relevance to direct-conversion architecture. The designed mixer has no flicker noise theoretically because the mixing transistors operate in the triode region. Also, DC offset problem is avoided, because local oscillator frequency is half of RF frequency and the port isolation is improved by the innate characteristic of a balanced structure. The VCO generates a quadrature signal and the oscillation frequency is half of RF frequency to drive designed sub-harmonic mixer. No coupling transistors are needed due to the use of back-gate coupling to reduce flicker noise. Back-gate coupling means that the body of a transistor is used as another gate. The LNA, which adopts a well-known cascade structure, is designed as a differential structure to suppress common mode noise and to drive a doubly balanced mixer. All designed components are fabricated by the TSMC 0.18-μm RF CMOS process. © 2010 Wiley Periodicals, Inc. Microwave Opt Technol Lett 52: 718–721, 2010; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/mop.24989 [ABSTRACT FROM AUTHOR]

The Lavic Road Bridge in San Bernardino County, California, was severely damaged during the October 16, 1999, Hector Mine Earthquake (7.1 Mw). The earthquake epicenter was approximately 16 km (10 mi) south-southwest of the structure’s location on Interstate 40. Prior to the earthquake, periodic modal field tests were being conducted on the structure to evaluate the impact of on-going reactive-aggregate induced structural deterioration. A scheduled field test was performed on the structure two weeks prior to the event. A second, unscheduled field test was performed three days after the event in order to capture any changes in the structure’s modal properties that might have resulted from damage incurred as a result of the earthquake. This paper provides a visible description of the damage sustained by the structure, documents the field test procedures used to determine modal properties (preevent and postevent modal frequencies, damping, and mode shapes), and discusses the changes observed in the preevent and postevent modal properties. The extracted modal results indicated that lower-mode natural frequencies decreased 18% relative to preevent values, that the frequency order of modes did not change, and that the modal damping levels increased by 25% relative to preevent levels. [ABSTRACT FROM AUTHOR]