Deep learning (DL) methods have brought world-shattering breakthroughs, especially in computer vision and classification problems. Yet, the design and deployment of DL methods in time series prediction and nonlinear system identification applications still need more progress. In this paper, we present DL frameworks that are developed to provide novel approaches as solutions to the aforementioned engineering problems. The proposed DL frameworks leverage the advantages of autoencoders and long-short term memory network, which are known being data compression and recurrent structures, respectively, to design Deep Neural Networks (DNN) for modeling time series and nonlinear systems with high performance. We provide recommendations on how deep AEs and LSTMs should be utilized to end up with efficient Prediction-focused (Pf) and Simulation-focused (Sf) DNNs for time series and system identification problems. We present systematic learning methods for the DL frameworks that allow straightforward learning of Pf-DNN and Sf-DNN models in detail. To demonstrate the efficiency of the developed DNNs, we present various comparative results conducted on the benchmark and real-world datasets in comparison with their conventional, shallow, and deep neural network counterparts. The results clearly show that the deployment of the proposed DL frameworks results with DNNs that have high accuracy, even with a low dimensional feature vector.
Recognizing people by gait promises to be useful for identifying individuals from a distance; in this regard, improved techniques
are under development. In this paper, an improved method for gait recognition is proposed. Binarized silhouette of a motion
object is first represented by four 1-D signals that are the basic image features called the distance vectors. The distance
vectors are differences between the bounding box and silhouette, and extracted using four projections to silhouette. Fourier
Transform is employed as a preprocessing step to achieve translation invariant for the gait patterns accumulated from silhouette
sequences that are extracted from the subjects’ walk in different speed and/or different time. Then, eigenspace transformation
is applied to reduce the dimensionality of the input feature space. Support vector machine (SVM)-based pattern classification
technique is then performed in the lower-dimensional eigenspace for recognition. The input feature space is alternatively
constructed by using two different approaches. The four projections (1-D signals) are independently classified in the first
approach. A fusion task is then applied to produce the final decision. In the second approach, the four projections are concatenated
to have one vector and then pattern classification with one vector is performed in the lower-dimensional eigenspace for recognition.
The experiments are carried out on the most well-known public gait databases: the CMU, the USF, SOTON, and NLPR human gait
databases. To effectively understand the performance of the algorithm, the experiments are executed and presented as increasing
amounts of the gait cycles of each person available during the training procedure. Finally, the performance of the proposed
algorithm is comparatively illustrated to take into consideration the published gait recognition approaches. 相似文献
The achievement of governmental transformation through the use of electronically delivered services is a worthy goal that requires significant planning and research to achieve. In order to reach transformational paradigm shifts in governmental operation, it will first be necessary to understand and optimize present governmental e-Service provisions. Of these, the revenue function of taxation is paramount. This paper describes factors related to the use and acceptance by accounting professionals of information technology intended to facilitate electronic tax filing systems. Though tested in the context of governmental tax management systems in Turkey, our findings on the use and acceptance of e-Tax systems are relevant and applicable to a great number of nations and contexts as the ongoing electronic transformation of the governmental revenue system contributes to efforts to transform governments through alternative services delivery venues and channels. We discover that intention to use automated systems as part of the governmental treasury function transformation is hindered by factors that mediate actual plans to do so, mostly in terms of normative pressures and perceptions of behavioral control, which training and education may well ameliorate. Hence, transformation of the treasury function in Turkey is only partially complete and will require additional support, direction and training on the part of the government in its interactions with the tax professionals who interact with the emergent automated system. 相似文献
Reconstructing high dynamic range (HDR) images of a complex scene involving moving objects and dynamic backgrounds is prone to artifacts. A large number of methods have been proposed that attempt to alleviate these artifacts, known as HDR deghosting algorithms. Currently, the quality of these algorithms are judged by subjective evaluations, which are tedious to conduct and get quickly outdated as new algorithms are proposed on a rapid basis. In this paper, we propose an objective metric which aims to simplify this process. Our metric takes a stack of input exposures and the deghosting result and produces a set of artifact maps for different types of artifacts. These artifact maps can be combined to yield a single quality score. We performed a subjective experiment involving 52 subjects and 16 different scenes to validate the agreement of our quality scores with subjective judgements and observed a concordance of almost 80%. Our metric also enables a novel application that we call as hybrid deghosting, in which the output of different deghosting algorithms are combined to obtain a superior deghosting result. 相似文献
This paper presents a wavelet-based kernel Principal Component Analysis (PCA) method by integrating the Daubechies wavelet representation of palm images and the kernel PCA method for palmprint recognition. Kernel PCA is a technique for nonlinear dimension reduction of data with an underlying nonlinear spatial structure. The intensity values of the palmprint image are first normalized by using mean and standard deviation. The palmprint is then transformed into the wavelet domain to decompose palm images and the lowest resolution subband coeffcients are chosen for palm representation. The kernel PCA method is then applied to extract non-linear features from the subband coeffcients. Finally, similarity measurement is accomplished by using weighted Euclidean linear distance-based nearest neighbor classifier. Experimental results on PolyU Palmprint Databases demonstrate that the proposed approach achieves highly competitive performance with respect to the published palmprint recognition approaches. 相似文献
Healthcare facilities are often complex and overwhelming for visitors, and wayfinding in healthcare facilities can be challenging. As there is an increasing number of global citizens who travel to seek medical care in another country, it is critical to make wayfinding easy for visitors who are not familiar with the language in a foreign country. Among many wayfinding aids, symbols are helpful for those visitors who have limited ability to understand written language. This study tested universal healthcare symbols in the United States, South Korea, and Turkey to compare the comprehension of symbols cross-country and identify predictors of the correct comprehension. To explore statistically significant relationships between symbol comprehension and countries, Pearson's Chi-square tests, logistic regression, and ANOVA were conducted. The test results showed that ten symbols among 14 tested have significant relationship with countries. Results of this study demonstrate that symbol comprehension can be varied significantly in different countries. 相似文献
Multimedia Tools and Applications - The accurate separation of ECG signals has become crucial to identify heart diseases. Machine learning methods are widely used to separate ECG signals. The aim... 相似文献
In this study, multiwall carbon nanotube (MCNT)‐supported Pd (Pd/MWCNT) catalysts are prepared by using NaBH4 reduction method. In order to maximize the oxidation and reduction of H2SO4, synthesis conditions (Pd ratio, molar ratio of NaBH4/K2PdCl4, volume of deionized water, and duration of agitation) are optimized by using response surface methodology (RSM). The optimum synthesis conditions are determined as 58.2% of Pd by weight, 154.6 molar ratio of NaBH4 to K2PdCl4, 19.48 mL of deionized water, and 186.16 min of agitation duration. The effect of electrochemical measurement conditions on the oxidation kinetics of Pd/MWCNT is also investigated by RSM. The optimum electrochemical measurement conditions are found as 10 μL of catalyst mixture, 90°C of H2SO4 solution, and 5.5 M H2SO4. The Pd/MWCNT, Pd50Ag50/MWCNT, and Pd65.6Ag33.6Cr0.80/MWCNT catalysts prepared under optimized conditions are characterized by using X‐ray diffraction, transmission electron microscopy, N2 adsorption‐desorption, and inductively coupled plasma mass spectrometry. The crystallite sizes of these catalysts are found as 4.85, 5.66, and 5.26 nm for Pd/MWCNT, Pd50Ag50/MWCNT, and Pd65.6Ag33.6Cr0.80/MWCNT catalysts, respectively. Isotherms of all these catalysts are found to be similar to Type V isotherms with H3 hysteresis loop. The average particle size of Pd50Ag50/MWCNT and Pd65.6Ag33.6Cr0.80/MWCNT catalysts are determined as 5.2 and 9.2 nm, respectively. Electrochemical performance of as‐prepared catalysts is evaluated by using cyclic voltammetry and chronoamperometry. The formic acid electrooxidation (FAEO) activities are found as 18.9, 27.8, and 51.6 mA/cm2 for Pd/MWCNT, Pd50Ag50/MWCNT, and Pd65.6Ag33.6Cr0.80/MWCNT, respectively. Pd65.6Ag33.6Cr0.80/MWCNT shows the highest activity and stability. Optimization of synthesis conditions and electrochemical measurement parameters allow us to obtain very good electrochemical activity and stability for FAEO reaction compared with anode catalysts in the literature. 相似文献
An efficient disparity estimation algorithm for multi-view video sequences, recorded by a two-dimensional camera array in which the cameras are spaced equidistantly, is presented. Because of the strong geometrical relationship among views, the disparity vectors of a certain view can for most blocks be derived from the disparity vectors of other views. A frame constructed using that idea is called a D frame in this work. Three new prediction schemes which contain D frames are proposed for encoding 5 × 3 multi-view video sequences. The schemes are applied to several multi-view image sequences taken from a camera-array and they are compared in terms of quality, bit-rate and complexity. The experimental results show that the proposed prediction schemes significantly decrease the complexity of the encoder at a very low cost of quality and/or bit-rate. 相似文献