Search results for " Methods"
showing 10 items of 4102 documents
Identification of Reading Difficulties by a Digital Game-Based Assessment Technology
2020
Computerized game-based assessment (GBA) system for screening reading difficulties may provide substantial time and cost benefits over traditional paper-and-pencil assessment while providing means also to individually adapt learning content in educational games. To study the reliability and validity of a GBA system to identify struggling readers performing below a standard deviation from mean in paper-and-pencil test either in raw scores and grade-normative scores, a large-scale study with first to fourth grade students ( N = 723) was conducted, where GBA was administrated as a group test by tablet devices. Overall, the results indicated that the GBA can be successfully used to identify st…
A kernel support vector machine based technique for Crohnâs disease classification in human patients
2017
In this paper a new technique for classification of patients affected by Crohnâs disease (CD) is proposed. The proposed technique is based on a Kernel Support Vector Machine (KSVM) and it adopts a Stratified K-Fold Cross-Validation strategy to enhance the KSVM classifier reliability. Traditional manual classification methods require radiological expertise and they usually are very time-consuming. Accordingly to three expert radiologists, a dataset composed of 300 patients has been selected for KSVM training and validation. Each patient was codified by 22 extracted qualitative features and classified as Positive or Negative as the related histological specimen result showed the CD. The eff…
Super-orthogonal space-time trellis codes with differential phase modulation for noncoherent mobile communication systems
2010
In this paper, we show how to design super-orthogonal space-time trellis codes (SOSTTCs) using the differential binary phase-shift keying (PSK) modulation for noncoherent communication systems, for which the knowledge of the channel state information (CSI) at the receiver is not necessary. Moreover, a new decoding algorithm with reduced decoding complexity is proposed. In all simulations, a geometric two-ring channel model is employed to evaluate the performance of the SOSTTCs. The simulation results show that the proposed decoding algorithm has the same decoding performance compared with the traditional decoding strategy, while the new algorithm reduces significantly the overall computing …
A Novel Angle Estimation for mmWave FMCW Radars Using Machine Learning
2021
In this article, we present a novel machine learning based angle estimation and field of view (FoV) enhancement techniques for mmWave FMCW radars operating in the frequency range of 77 - 81 GHz. Field of view is enhanced in both azimuth and elevation. The Elevation FoV enhancement is achieved by keeping the orientation of antenna elements in elevation. In this orientation, radar focuses the beam in vertical direction there by enhancing the elevation FoV. An Azimuth FoV enhancement is achieved by mechanically rotating the radar horizontally, which has antenna elements in the elevation. With the proposed angle estimation technique for such rotating radars, root mean square error (RMSE) of 2.5…
Editorial Article for Open Journal of Antennas and Propagation
2013
Antennas help communicate the World. Antennas make possible that millions of people can watch the Champions League. Antennas allow the positioning of billions of vehicles around our planet. And they also allow handling vehicles through our neighbor planets. By propagating waves through antennas you can send huge amounts of data in milliseconds. Besides, you can also tell somebody that you love him or her. Antennas have allowed communicate the people in these places where cables cannot. But antennas are not only used for communication. Antennas can be used for heating food, for detecting people, for guiding vessels, for founding treasures, for monitoring breath, for harvesting energy and so …
Detection of TV commercials
2004
This paper presents a system that labels TV shots either as commercial or program shots. The system uses two observations: logo presence and shot duration. These observations are modeled using HMMs, and a Viterbi decoder is finally used for shot labeling. The system has been tested on several hours of real video, achieving more than 99% correct labeling.
Learning Research Methods and Processes via Sharing Experience in a BLOG
2006
The goal is to increase knowledge about different research methods that have been employed in the information technology field by supporting the information exchange, collaboration, and cooperation between researchers. Well-designed, well-told stories can help others learn from past situations to respond more effectively in future situation. A blog is presented where PhD students and researchers are invited to collaborate by providing their stories, reading and commenting existing stories. This infrastructure allows researchers and PhD students to write the contents posing questions and finding answers on the relationship between research process and research results.
Evaluation of Ensemble Machine Learning Methods in Mobile Threat Detection
2017
The rapid growing trend of mobile devices continues to soar causing massive increase in cyber security threats. Most pervasive threats include ransom-ware, banking malware, premium SMS fraud. The solitary hackers use tailored techniques to avoid detection by the traditional antivirus. The emerging need is to detect these threats by any flow-based network solution. Therefore, we propose and evaluate a network based model which uses ensemble Machine Learning (ML) methods in order to identify the mobile threats, by analyzing the network flows of the malware communication. The ensemble ML methods not only protect over-fitting of the model but also cope with the issues related to the changing be…
The Elephant in the Machine: Proposing a New Metric of Data Reliability and its Application to a Medical Case to Assess Classification Reliability
2020
In this paper, we present and discuss a novel reliability metric to quantify the extent a ground truth, generated in multi-rater settings, as a reliable basis for the training and validation of machine learning predictive models. To define this metric, three dimensions are taken into account: agreement (that is, how much a group of raters mutually agree on a single case)
An Online Observer for Minimization of Pulsating Torque in SMPM Motors.
2015
A persistent problem of surface mounted permanent magnet (SMPM) motors is the non-uniformity of the developed torque. Either the motor design or the motor control needs to be improved in order to minimize the periodic disturbances. This paper proposes a new control technique for reducing periodic disturbances in permanent magnet (PM) electro-mechanical actuators, by advancing a new observer/estimator paradigm. A recursive estimation algorithm is implemented for online control. The compensating signal is identified and added as feedback to the control signal of the servo motor. Compensation is evaluated for different values of the input signal, to show robustness of the proposed method.