Significant full reference image segmentation evaluation: a survey in remote sensing field

Multimedia Tools and Applications - Image segmentation is a crucial step in remote sensing application, as it breaks down a larger image into smaller chunks, which contains useful information....     

Soil moisture estimates from TRMM Microwave Imager observations over the Southern United States

The lack of continuous soil moisture fields at large spatial scales, based on observations, has hampered hydrologists from understanding its role in weather and climate. The most readily available observations from which a surface wetness state could be derived is the Tropical Rainfall Measuring Mission (TRMM) Microwave Imager (TMI) observations at 10.65 GHz. This paper describes the first attempt to map daily soil moisture from space over an extended period of time. Methods to adjust for diurnal changes associated with this temporal variability and how to mosaic these orbits are presented. The algorithm for deriving soil moisture and temperature from TMI observations is based on a physical model of microwave emission from a layered soil-vegetation-atmosphere medium. An iterative, least-squares minimization method, which uses dual polarization observations at 10.65 GHz, is employed in the retrieval algorithm. Soil moisture estimates were compared with ground measurements over the U.S. Southern Great Plains (SGP) in Oklahoma and the Little River Watershed, Georgia. The soil moisture experiment in Oklahoma was conducted in July 1999 and Little River in June 2000. During both the experiments, the region was dry at the onset of the experiment, and experienced moderate rainfall during the course of the experiment. The regions experienced a quick dry-down before the end of the experiment. The estimated soil moisture compared well with the ground observations for these experiments (standard error of 2.5%). The TMI-estimated soil moisture during 6-22 July over Southern U.S. was analyzed and found to be consistent with the observed meteorological conditions.     

Con(dif)fused voice to convey secret: a dual-domain approach

Owing to the rapid development and advancements in the field of networks and communication, sharing of multimedia contents over insecure networks has becom     

Design and development of virtual instrument for fault diagnosis in fractal antenna array

This paper deals with the development of a virtual instrument for fault diagnosis in fractal antenna array using Lab‐VIEW software. Faults in antenna array are considered on the basis of the radiation pattern. In this study, theta and gain values of radiation patterns for each fault are used in Lab‐VIEW for curve fitting. An artificial neural network (ANN) has been developed for fitted data points using the Leavenberg Marquard algorithm in MATLAB software and mean square error (MSE) is minimized. The designed ANN model has been embedded in the virtual instrument. The proposed virtual instrument system gets test patterns as input and generates output for several faults present in antenna array. Simulated and measured results of the fractal antenna array are validated experimentally. This virtual instrument model has not been developed for fractal antenna array so far.     

DFuzzy: a deep learning-based fuzzy clustering model for large graphs

Graph clustering is successfully applied in various applications for finding similar patterns. Recently, deep learning- based autoencoder has been used efficiently for detecting disjoint clusters. However, in real-world graphs, vertices may belong to multiple clusters. Thus, it is obligatory to analyze the membership of vertices toward clusters. Furthermore, existing approaches are centralized and are inefficient in handling large graphs. In this paper, a deep learning-based model ‘DFuzzy’ is proposed for finding fuzzy clusters from large graphs in distributed environment. It performs clustering in three phases. In first phase, pre-training is performed by initializing the candidate cluster centers. Then, fine tuning is performed to learn the latent representations by mining the local information and capturing the structure using PageRank. Further, modularity is used to redefine clusters. In last phase, reconstruction error is minimized and final cluster centers are updated. Experiments are performed over real-life graph data, and the performance of DFuzzy is compared with four state-of-the-art clustering algorithms. Results show that DFuzzy scales up linearly to handle large graphs and produces better quality of clusters when compared to state-of-the-art clustering algorithms. It is also observed that deep structures can help in getting better graph representations and provide improved clustering performance.     

Big Data Framework for Zero-Day Malware Detection

Malware has already been recognized as one of the most dominant cyber threats on the Internet today. It is growing exponentially in terms of volume, variety, and velocity, and thus overwhelms the traditional approaches used for malware detection and classification. Moreover, with the advent of Internet of Things, there is a huge growth in the volume of digital devices and in such scenario, malicious binaries are bound to grow even faster making it a big data problem. To analyze and detect unknown malware on a large scale, security analysts need to make use of machine learning algorithms along with big data technologies. These technologies help them to deal with current threat landscape consisting of complex and large flux of malicious binaries. This paper proposes the design of a scalable architecture built on the top of Apache Spark which uses its scalable machine learning library (MLlib) for detecting zero-day malware. The proposed platform is tested and evaluated on a dataset comprising of 0.2 million files consisting of 0.05 million clean files and 0.15 million malicious binaries covering a large number of malware families over a period of 7 years starting from 2010.     

Segmentation and range sensing using a moving-aperture lens

The use of a novel motorized lens to perform segmentation of image sequences is presented in this paper. The lens has the effect of introducing small, repeating movements of the camera center so that objects appear to translate in the image by an amount that depends on the distance from the plane of focus. For a stationary scene, optical flow magnitudes are therefore directly related to three-dimensional object distance from the observer. We describe a segmentation procedure that exploits these controlled observer movements and present experimental results that demonstrate the successful extraction of objects at different depths. Potential applications of our approach include image compositing, teleconferencing, and range estimation.Received: 4 July 2002, Accepted: 16 December 2002, Published online: 23 July 2003 Correspondence to: Amy E. Bell     

“When Is Short,Sweet?” Selection Uncertainty and Online Review Presentations

Online customer reviews are an important part of e-commerce product selection. When used effectively, online reviews may reduce the uncertainty inherent in making product selection decisions online, but how best to deal with thousands of online customer reviews? Past research considers online review summarization, where reviews are reduced to numeric ratings, key phrases, keywords or product characteristics. However, in their original form, online reviews contain the carefully crafted narratives of past customers, elements of which may not be amenable to summarization. In this research, we present findings of a laboratory experiment which examines the impact of review summarization when evaluating different types of products online. Key findings include evidence that perceptions of product selection uncertainty depend on online review presentation format and the category of the product under consideration. Additionally, the study provides evidence that the e-commerce retailers may benefit from varying online review presentations across specific types of products.     

How to Better Use Expert Advice

This work is concerned with online learning from expert advice. Extensive work on this problem generated numerous expert advice algorithms whose total loss is provably bounded above in terms of the loss incurred by the best expert in hindsight. Such algorithms were devised for various problem variants corresponding to various loss functions. For some loss functions, such as the square, Hellinger and entropy losses, optimal algorithms are known. However, for two of the most widely used loss functions, namely the 0/1 and absolute loss, there are still gaps between the known lower and upper bounds.In this paper we present two new expert advice algorithms and prove for them the best known 0/1 and absolute loss bounds. Given an expert advice algorithm ALG, the goal is to form an upper bound on the regret L _ALG – L* of ALG, where L _ALG is the loss of ALG and L* is the loss of the best expert in hindsight. Typically, regret bounds of a canonical form C · are sought where N is the number of experts and C is a constant. So far, the best known constant for the absolute loss function is C = 2.83, which is achieved by the recent IAWM algorithm of Auer et al. (2002). For the 0/1 loss function no bounds of this canonical form are known and the best known regret bound is , where C ₁ = e – 2 and C ₂ = 2 . This bound is achieved by a P-norm algorithm of Gentile and Littlestone (1999). Our first algorithm is a randomized extension of the guess and double algorithm of Cesa-Bianchi et al. (1997). While the guess and double algorithm achieves a canonical regret bound with C = 3.32, the expected regret of our randomized algorithm is canonically bounded with C = 2.49 for the absolute loss function. The algorithm utilizes one random choice at the start of the game. Like the deterministic guess and double algorithm, a deficiency of our algorithm is that it occasionally restarts itself and therefore forgets what it learned. Our second algorithm does not forget and enjoys the best known asymptotic performance guarantees for both the absolute and 0/1 loss functions. Specifically, in the case of the absolute loss, our algorithm is canonically bounded with C approaching and in the case of the 0/1 loss, with C approaching 3/ . In the 0/1 loss case the algorithm is randomized and the bound is on the expected regret.     

Special sensor microwave imager data in field experiments: FIFE-1987

Estimation of regional soil moisture is of importance to the hydrological modelling community for validating the accuracy of model predictions and to the climate community for use in regional and global climate models. Soil moisture estimation is done in two ways, viz., estimation using models and estimation using satellite data. Both these methods have to be corroborated using in situ field data. The present paper examines the feasibility of using observations of brightness temperature from the Special Sensor Microwave Imager (SSM/I) for small scale/catchment scale studies. The simulations of the 19 and 37 GHz brightness temperatures are carried out for a period of 13 days between 6 and 21 August 1987. The comparisons between the simulated and the observed brightness temperatures are good and the errors can be explained based on the atmospheric and surface conditions. Sensitivity analysis of the brightness temperatures to leaf area index, soil moisture and soil temperatures shows interesting characteristics. The errors in the simulated brightness temperatures can be explained by variability in the input parameters. This study shows that such an approach holds promise for local and regional studies of the land surface.