The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
We propose a parallel training framework of convolutional neural networks (CNNs) for small sample learning. In the framework we model the feature filter process and show Sadowsky energy distribution exists in the model. Using Sadowsky energy distribution, the weights in convolutional kernels can be rearranged after each update according to special cases. With this rearrangement, each CNNs in the framework...
The research using computational intelligence methods to improve bad debt recovery is imperative due to the rapid increase in the cost of healthcare in the U.S. This study explores effectiveness of using cost-sensitive learning methods to classify the unknown cases in imbalanced bad debt datasets and compares the results with those of two other methods: undersampling and oversampling, often used in...
In Substation Automation Systems, application functions such as monitoring, control, and protection are deployed in intelligent electronic devices (IEDs). Before the IEDs are installed in the substation, functions are tested by the manufactures to ensure that the functions operate properly as designed. A conventional function test platform is made of amplifiers with copper wire connection to the IEDs...
Science learned models based on limited data are usually fragile, researchers suggest the adoption of virtual samples to improve the prediction model. In this study, nonparametric statistical tool, Kolmogorov-Smirnov test, is introduced to examine the distribution of virtual samples without any assumption about the underlying population. The examination procedure would help control the quality of...
In hyerspectral remote sensing community, sparse representation based classification (SRC) is a novel concept — a testing pixel is linearly represented by labeled data, and weight coefficients are often solved by an ℓ1-norm minimization. In this work, an extension of SRC is proposed by imposing an adaptive similarity measurement between the testing pixel and labeled data on the ℓ1-norm penalty, named...
This paper presents a wireless, low power and low cost wearable for real time monitoring and analysis of bowling action in the game of cricket. Utilizing flex sensor as an enabling component, the device performs continuous measurement of arm angle within one degree accuracy. The wearable also utilizes a force sensor enabling it to detect the time instant at which the ball is released. The device wirelessly...
In June through October of 2014, power-hardware-in-the-loop (PHIL) simulation testing of a 1.2 MW, 4.16 kV AC / 1 kV DC power conversion module for naval applications was conducted. In these tests, the device-under-test (DUT) was interfaced to a virtual surrounding system that was generally representative of the power system of a future surface combatant. Tests were focused on demonstration of operation...
A promising solution to reduce the testing costs of analog/RF circuits is the alternate test strategy, which permits to replace costly specification measurements by simple low-cost indirect measurements. This approach has been widely explored and demonstrated in the literature on various case studies over the past twenty years. However it is clear that the efficiency of this strategy strongly depends...
Ulcerative colitis (UC) is a chronic inflammatory disease characterized by periods of relapses and remissions affecting more than 500,000 people in the United States. The therapeutic goals of UC are to first induce and then maintain disease remission. However, it is very difficult to evaluate the severity of UC objectively because of non-uniform nature of symptoms associated with UC, and large variations...
As unmanned aerial systems (UASs) become ever more ubiquitous with National Airspace (NAS) commercial and civilian operations, test sites and proving grounds need to be developed and heavily researched. Small UASs are being used as remote sensing systems, on demand, at the personal level, thus “personal remote sensing” scientific data drones urgently need Ground Truthing Test Sites beyond compliance...
With the development of sensing equipments, data from different modalities is available for gesture recognition. In this paper, we propose a novel multi-modal learning framework. A coupled hidden Markov model (CHMM) is employed to discover the correlation and complementary information across different modalities. In this framework, we use two configurations: one is multi-modal learning and multi-modal...
Congenital malformations (CM) are abnormalities of structures arising during the prenatal development and hampering body functions later in life. Causes of CM can be genetic, environmental or any kind of drug exposure during the pregnancy. CM is one of the most important causes of infant mortality in the developing countries. In Pakistan 6–9% of the perinatal deaths are attributed to CM, but a comprehensive...
Real Time Kinematic (RTK) Global Positioning System (GPS) uses carrier phase measurement from GPS signal and it has a high accuracy but has integer ambiguity resolution problem which causes cycle slips and requires good satellite visibility as well. RTK was originally developed for applications such as surveying; in our case the target application is the tracking and the control of a robot hexacopter...
Live streaming services have been developed prosperously in recent years. With live streaming services, broadcasters broadcast their videos to attract large numbers of viewers to watch. Some live streaming services also provide a platform for viewers gathering together to watch channels and interact with others. Over hundreds of videos broadcast every day, recommending channels are necessary to help...
Fault localization for power device is difficult due to their special structure with a thick metal layer on the surface as the testing terminal. This layer enhances the thermal diffusion and blocks the photon emission, which restricts the function of LC analysis, PEM or OBIRCH. The experiment shows that using the thinning layer like the barrier layer as the terminal after removing the most of the...
Pakistan faces heavy revenue losses in terms of one of its major cash crop i.e. Tobacco, due to the unavailability of accurate statistics of the total tobacco production. During the cropping season, there are many competing crops along with tobacco in the neighboring fields — making tobacco identification a challenging task. This study considers a pilot region of interest that spans over 64844 hectares,...
Improvement of classification accuracy is importance in data analysis problems. Enhancement of techniques have been proposed previously to address the problems as regard to classification performance, however, the issues of misclassification and noise elimination in the early stage of processing have been ignored by many researchers. If these problems were addressed, the performance of the classification...
Classifying cash crops through satellite based remote sensing has proved to be effective for reliable ground based agricultural statistics. In this study, frequently used simple and fast classification algorithms i.e., Mahalanobis Distance and Maximum Likelihood Classification (MLC) are compared for classifying tobacco crops by the end of June in north-western Pakistan. High Geometric Resolution imagery...
Identifying the mentor and the mentee in the online community is very difficult because of the hidden or lacking personal characteristics but it is very important for the organization. The new members in the organization probably will not only require the knowledge explicitly from their colleagues in the same department, but also the implicit knowledge from online community. The mentor and the mentee...
Most works related to convolutional neural networks (CNN) use the traditional CNN framework which extracts features in only one scale. We propose multi-scale convolutional neural networks (MSCNN) which can not only extract multi-scale features but also solve the issues of the previous methods which use CNN to extract multi-scale features. With the assumption of label-inheritable (LI) property, we...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.