Abstract: Most scientific programs have large input and output
data sets that require out-of-core programming or use virtual memory
management (VMM). Out-of-core programming is very error-prone
and tedious; as a result, it is generally avoided. However, in many
instance, VMM is not an effective approach because it often results
in substantial performance reduction. In contrast, compiler driven I/O
management will allow a program-s data sets to be retrieved in parts,
called blocks or tiles. Comanche (COmpiler MANaged caCHE) is a
compiler combined with a user level runtime system that can be used
to replace standard VMM for out-of-core programs. We describe
Comanche and demonstrate on a number of representative problems
that it substantially out-performs VMM. Significantly our system
does not require any special services from the operating system and
does not require modification of the operating system kernel.
Abstract: SQL injection on web applications is a very popular
kind of attack. There are mechanisms such as intrusion detection
systems in order to detect this attack. These strategies often rely on
techniques implemented at high layers of the application but do not
consider the low level of system calls. The problem of only
considering the high level perspective is that an attacker can
circumvent the detection tools using certain techniques such as URL
encoding. One technique currently used for detecting low-level
attacks on privileged processes is the tracing of system calls. System
calls act as a single gate to the Operating System (OS) kernel; they
allow catching the critical data at an appropriate level of detail. Our
basic assumption is that any type of application, be it a system
service, utility program or Web application, “speaks” the language of
system calls when having a conversation with the OS kernel. At this
level we can see the actual attack while it is happening. We conduct
an experiment in order to demonstrate the suitability of system call
analysis for detecting SQL injection. We are able to detect the attack.
Therefore we conclude that system calls are not only powerful in
detecting low-level attacks but that they also enable us to detect highlevel
attacks such as SQL injection.
Abstract: Research into the problem of classification of sonar signals has been taken up as a challenging task for the neural networks. This paper investigates the design of an optimal classifier using a Multi layer Perceptron Neural Network (MLP NN) and Support Vector Machines (SVM). Results obtained using sonar data sets suggest that SVM classifier perform well in comparison with well-known MLP NN classifier. An average classification accuracy of 91.974% is achieved with SVM classifier and 90.3609% with MLP NN classifier, on the test instances. The area under the Receiver Operating Characteristics (ROC) curve for the proposed SVM classifier on test data set is found as 0.981183, which is very close to unity and this clearly confirms the excellent quality of the proposed classifier. The SVM classifier employed in this paper is implemented using kernel Adatron algorithm is seen to be robust and relatively insensitive to the parameter initialization in comparison to MLP NN.
Abstract: Understanding proteins functions is a major goal in
the post-genomic era. Proteins usually work in context of other
proteins and rarely function alone. Therefore, it is highly relevant to
study the interaction partners of a protein in order to understand its
function. Machine learning techniques have been widely applied to
predict protein-protein interactions. Kernel functions play an
important role for a successful machine learning technique. Choosing
the appropriate kernel function can lead to a better accuracy in a
binary classifier such as the support vector machines. In this paper,
we describe a Bayesian kernel for the support vector machine to
predict protein-protein interactions. The use of Bayesian kernel can
improve the classifier performance by incorporating the probability
characteristic of the available experimental protein-protein
interactions data that were compiled from different sources. In
addition, the probabilistic output from the Bayesian kernel can assist
biologists to conduct more research on the highly predicted
interactions. The results show that the accuracy of the classifier has
been improved using the Bayesian kernel compared to the standard
SVM kernels. These results imply that protein-protein interaction can
be predicted using Bayesian kernel with better accuracy compared to
the standard SVM kernels.
Abstract: Emergence of smartphones brings to live the concept
of converged devices with the availability of web amenities. Such
trend also challenges the mobile devices manufactures and service
providers in many aspects, such as security on mobile phones,
complex and long time design flow, as well as higher development
cost. Among these aspects, security on mobile phones is getting more
and more attention. Microkernel based virtualization technology will
play a critical role in addressing these challenges and meeting mobile
market needs and preferences, since virtualization provides essential
isolation for security reasons and it allows multiple operating systems
to run on one processor accelerating development and cutting development
cost. However, virtualization benefits do not come for free.
As an additional software layer, it adds some inevitable virtualization
overhead to the system, which may decrease the system performance.
In this paper we evaluate and analyze the virtualization performance
cost of L4 microkernel based virtualization on a competitive mobile
phone by comparing the L4Linux, a para-virtualized Linux on top of
L4 microkernel, with the native Linux performance using lmbench
and a set of typical mobile phone applications.
Abstract: Speedups from mapping four real-life DSP
applications on an embedded system-on-chip that couples coarsegrained
reconfigurable logic with an instruction-set processor are
presented. The reconfigurable logic is realized by a 2-Dimensional
Array of Processing Elements. A design flow for improving
application-s performance is proposed. Critical software parts, called
kernels, are accelerated on the Coarse-Grained Reconfigurable
Array. The kernels are detected by profiling the source code. For
mapping the detected kernels on the reconfigurable logic a prioritybased
mapping algorithm has been developed. Two 4x4 array
architectures, which differ in their interconnection structure among
the Processing Elements, are considered. The experiments for eight
different instances of a generic system show that important overall
application speedups have been reported for the four applications.
The performance improvements range from 1.86 to 3.67, with an
average value of 2.53, compared with an all-software execution.
These speedups are quite close to the maximum theoretical speedups
imposed by Amdahl-s law.
Abstract: Drying characteristics of rough rice (variety of lenjan) with an initial moisture content of 25% dry basis (db) was studied in a hot air dryer assisted by infrared heating. Three arrival air temperatures (30, 40 and 500C) and four infrared radiation intensities (0, 0.2 , 0.4 and 0.6 W/cm2) and three arrival air speeds (0.1, 0.15 and 0.2 m.s-1) were studied. Bending strength of brown rice kernel, percentage of cracked kernels and time of drying were measured and evaluated. The results showed that increasing the drying arrival air temperature and radiation intensity of infrared resulted decrease in drying time. High bending strength and low percentage of cracked kernel was obtained when paddy was dried by hot air assisted infrared dryer. Between this factors and their interactive effect were a significant difference (p
Abstract: Text categorization is the problem of classifying text documents into a set of predefined classes. After a preprocessing step the documents are typically represented as large sparse vectors. When training classifiers on large collections of documents, both the time and memory restrictions can be quite prohibitive. This justifies the application of features selection methods to reduce the dimensionality of the document-representation vector. Four feature selection methods are evaluated: Random Selection, Information Gain (IG), Support Vector Machine (called SVM_FS) and Genetic Algorithm with SVM (GA_FS). We showed that the best results were obtained with SVM_FS and GA_FS methods for a relatively small dimension of the features vector comparative with the IG method that involves longer vectors, for quite similar classification accuracies. Also we present a novel method to better correlate SVM kernel-s parameters (Polynomial or Gaussian kernel).
Abstract: Unlike general-purpose processors, digital signal
processors (DSP processors) are strongly application-dependent. To
meet the needs for diverse applications, a wide variety of DSP
processors based on different architectures ranging from the
traditional to VLIW have been introduced to the market over the
years. The functionality, performance, and cost of these processors
vary over a wide range. In order to select a processor that meets the
design criteria for an application, processor performance is usually
the major concern for digital signal processing (DSP) application
developers. Performance data are also essential for the designers of
DSP processors to improve their design. Consequently, several DSP
performance benchmarks have been proposed over the past decade or
so. However, none of these benchmarks seem to have included recent
new DSP applications.
In this paper, we use a new benchmark that we recently developed
to compare the performance of popular DSP processors from Texas
Instruments and StarCore. The new benchmark is based on the
Selectable Mode Vocoder (SMV), a speech-coding program from the
recent third generation (3G) wireless voice applications. All
benchmark kernels are compiled by the compilers of the respective
DSP processors and run on their simulators. Weighted arithmetic
mean of clock cycles and arithmetic mean of code size are used to
compare the performance of five DSP processors.
In addition, we studied how the performance of a processor is
affected by code structure, features of processor architecture and
optimization of compiler. The extensive experimental data gathered,
analyzed, and presented in this paper should be helpful for DSP
processor and compiler designers to meet their specific design goals.
Abstract: In this paper, in order to categorize ORL database face
pictures, principle Component Analysis (PCA) and Kernel Principal
Component Analysis (KPCA) methods by using Elman neural
network and Support Vector Machine (SVM) categorization methods
are used. Elman network as a recurrent neural network is proposed
for modeling storage systems and also it is used for reviewing the
effect of using PCA numbers on system categorization precision rate
and database pictures categorization time. Categorization stages are
conducted with various components numbers and the obtained results
of both Elman neural network categorization and support vector
machine are compared. In optimum manner 97.41% recognition
accuracy is obtained.
Abstract: A study was carried out at the Rice Research Institute of Iran (RRII) to investigate the effect of rollers differential peripheral speed of commercial rubber roll husker and paddy moisture content on the husking index and percentage of broken rice. The experiment was conducted at six levels of rollers differential speed (1.5, 2.2, 2.9, 3.6, 4.3 and 5 m/s) and three levels of paddy moisture content (8-9, 10-11 and 12-13% w.b.). Two common paddy varieties namely, Binam and Khazer, were selected for this study. Results revealed that the effect of rollers differential speed and moisture content significantly (P
Abstract: Intelligent systems based on machine learning
techniques, such as classification, clustering, are gaining wide spread
popularity in real world applications. This paper presents work on
developing a software system for predicting crop yield, for example
oil-palm yield, from climate and plantation data. At the core of our
system is a method for unsupervised partitioning of data for finding
spatio-temporal patterns in climate data using kernel methods which
offer strength to deal with complex data. This work gets inspiration
from the notion that a non-linear data transformation into some high
dimensional feature space increases the possibility of linear
separability of the patterns in the transformed space. Therefore, it
simplifies exploration of the associated structure in the data. Kernel
methods implicitly perform a non-linear mapping of the input data
into a high dimensional feature space by replacing the inner products
with an appropriate positive definite function. In this paper we
present a robust weighted kernel k-means algorithm incorporating
spatial constraints for clustering the data. The proposed algorithm
can effectively handle noise, outliers and auto-correlation in the
spatial data, for effective and efficient data analysis by exploring
patterns and structures in the data, and thus can be used for
predicting oil-palm yield by analyzing various factors affecting the
yield.
Abstract: A self tuning PID control strategy using reinforcement
learning is proposed in this paper to deal with the control of wind
energy conversion systems (WECS). Actor-Critic learning is used to
tune PID parameters in an adaptive way by taking advantage of the
model-free and on-line learning properties of reinforcement learning
effectively. In order to reduce the demand of storage space and to
improve the learning efficiency, a single RBF neural network is used
to approximate the policy function of Actor and the value function of
Critic simultaneously. The inputs of RBF network are the system
error, as well as the first and the second-order differences of error.
The Actor can realize the mapping from the system state to PID
parameters, while the Critic evaluates the outputs of the Actor and
produces TD error. Based on TD error performance index and
gradient descent method, the updating rules of RBF kernel function
and network weights were given. Simulation results show that the
proposed controller is efficient for WECS and it is perfectly
adaptable and strongly robust, which is better than that of a
conventional PID controller.
Abstract: We have previously introduced an ultrasonic imaging
approach that combines harmonic-sensitive pulse sequences with a
post-beamforming quadratic kernel derived from a second-order
Volterra filter (SOVF). This approach is designed to produce images
with high sensitivity to nonlinear oscillations from microbubble
ultrasound contrast agents (UCA) while maintaining high levels of
noise rejection. In this paper, a two-step algorithm for computing the
coefficients of the quadratic kernel leading to reduction of tissue
component introduced by motion, maximizing the noise rejection and
increases the specificity while optimizing the sensitivity to the UCA
is presented. In the first step, quadratic kernels from individual
singular modes of the PI data matrix are compared in terms of their
ability of maximize the contrast to tissue ratio (CTR). In the second
step, quadratic kernels resulting in the highest CTR values are
convolved. The imaging results indicate that a signal processing
approach to this clinical challenge is feasible.
Abstract: This paper describes an optimal approach for feature
subset selection to classify the leaves based on Genetic Algorithm
(GA) and Kernel Based Principle Component Analysis (KPCA). Due
to high complexity in the selection of the optimal features, the
classification has become a critical task to analyse the leaf image
data. Initially the shape, texture and colour features are extracted
from the leaf images. These extracted features are optimized through
the separate functioning of GA and KPCA. This approach performs
an intersection operation over the subsets obtained from the
optimization process. Finally, the most common matching subset is
forwarded to train the Support Vector Machine (SVM). Our
experimental results successfully prove that the application of GA
and KPCA for feature subset selection using SVM as a classifier is
computationally effective and improves the accuracy of the classifier.
Abstract: Many-core GPUs provide high computing ability and
substantial bandwidth; however, optimizing irregular applications
like SpMV on GPUs becomes a difficult but meaningful task. In this
paper, we propose a novel method to improve the performance of
SpMV on GPUs. A new storage format called HYB-R is proposed to
exploit GPU architecture more efficiently. The COO portion of the
matrix is partitioned recursively into a ELL portion and a COO
portion in the process of creating HYB-R format to ensure that there
are as many non-zeros as possible in ELL format. The method of
partitioning the matrix is an important problem for HYB-R kernel, so
we also try to tune the parameters to partition the matrix for higher
performance. Experimental results show that our method can get
better performance than the fastest kernel (HYB) in NVIDIA-s
SpMV library with as high as 17% speedup.
Abstract: CT assessment of postoperative spine is challenging in the presence of metal streak artifacts that could deteriorate the
quality of CT images. In this paper, we studied the influence of different acquisition parameters on the magnitude of metal streaking.
A water-bath phantom was constructed with metal insertion similar with postoperative spine assessment. The phantom was scanned with
different acquisition settings and acquired data were reconstructed
using various reconstruction settings. Standardized ROIs were defined within streaking region for image analysis. The result shows
increased kVp and mAs enhanced SNR values by reducing image
noise. Sharper kernel enhanced image quality compared to smooth
kernel, but produced more noise in the images with higher CT fluctuation. The noise between both kernels were significantly
different (P
Abstract: In many data mining applications, it is a priori known
that the target function should satisfy certain constraints imposed
by, for example, economic theory or a human-decision maker. In this
paper we consider partially monotone prediction problems, where the
target variable depends monotonically on some of the input variables
but not on all. We propose a novel method to construct prediction
models, where monotone dependences with respect to some of
the input variables are preserved by virtue of construction. Our
method belongs to the class of mixture models. The basic idea is to
convolute monotone neural networks with weight (kernel) functions
to make predictions. By using simulation and real case studies,
we demonstrate the application of our method. To obtain sound
assessment for the performance of our approach, we use standard
neural networks with weight decay and partially monotone linear
models as benchmark methods for comparison. The results show that
our approach outperforms partially monotone linear models in terms
of accuracy. Furthermore, the incorporation of partial monotonicity
constraints not only leads to models that are in accordance with the
decision maker's expertise, but also reduces considerably the model
variance in comparison to standard neural networks with weight
decay.
Abstract: In this paper, a recursive algorithm for the
computation of 2-D DCT using Ramanujan Numbers is proposed.
With this algorithm, the floating-point multiplication is completely
eliminated and hence the multiplierless algorithm can be
implemented using shifts and additions only. The orthogonality of
the recursive kernel is well maintained through matrix factorization
to reduce the computational complexity. The inherent parallel
structure yields simpler programming and hardware implementation
and provides
log 1
2
3
2 N N-N+
additions and
N N
2 log
2 shifts which is
very much less complex when compared to other recent multiplierless
algorithms.
Abstract: The amount of the information being churned out by the field of biology has jumped manifold and now requires the extensive use of computer techniques for the management of this information. The predominance of biological information such as protein sequence similarity in the biological information sea is key information for detecting protein evolutionary relationship. Protein sequence similarity typically implies homology, which in turn may imply structural and functional similarities. In this work, we propose, a learning method for detecting remote protein homology. The proposed method uses a transformation that converts protein sequence into fixed-dimensional representative feature vectors. Each feature vector records the sensitivity of a protein sequence to a set of amino acids substrings generated from the protein sequences of interest. These features are then used in conjunction with support vector machines for the detection of the protein remote homology. The proposed method is tested and evaluated on two different benchmark protein datasets and it-s able to deliver improvements over most of the existing homology detection methods.