Abstract: Web mining is to discover and extract useful
Information. Different users may have different search goals when
they search by giving queries and submitting it to a search engine.
The inference and analysis of user search goals can be very useful for
providing an experience result for a user search query. In this project,
we propose a novel approach to infer user search goals by analyzing
search web logs. First, we propose a novel approach to infer user
search goals by analyzing search engine query logs, the feedback
sessions are constructed from user click-through logs and it
efficiently reflect the information needed for users. Second we
propose a preprocessing technique to clean the unnecessary data’s
from web log file (feedback session). Third we propose a technique
to generate pseudo-documents to representation of feedback sessions
for clustering. Finally we implement k-medoids clustering algorithm
to discover different user search goals and to provide a more optimal
result for a search query based on feedback sessions for the user.
Abstract: Advance in techniques of image and video processing has enabled the development of intelligent video surveillance systems. This study was aimed to automatically detect moving human objects and to analyze events of dual human interaction in a surveillance scene. Our system was developed in four major steps: image preprocessing, human object detection, human object tracking, and motion trajectory analysis. The adaptive background subtraction and image processing techniques were used to detect and track moving human objects. To solve the occlusion problem during the interaction, the Kalman filter was used to retain a complete trajectory for each human object. Finally, the motion trajectory analysis was developed to distinguish between the interaction and non-interaction events based on derivatives of trajectories related to the speed of the moving objects. Using a database of 60 video sequences, our system could achieve the classification accuracy of 80% in interaction events and 95% in non-interaction events, respectively. In summary, we have explored the idea to investigate a system for the automatic classification of events for interaction and non-interaction events using surveillance cameras. Ultimately, this system could be incorporated in an intelligent surveillance system for the detection and/or classification of abnormal or criminal events (e.g., theft, snatch, fighting, etc.).
Abstract: In this work, we explore the capability of the mean
shift algorithm as a powerful preprocessing tool for improving the
quality of spatial data, acquired from airborne scanners, from densely
built urban areas. On one hand, high resolution image data corrupted
by noise caused by lossy compression techniques are appropriately
smoothed while at the same time preserving the optical edges and, on
the other, low resolution LiDAR data in the form of normalized
Digital Surface Map (nDSM) is upsampled through the joint mean
shift algorithm. Experiments on both the edge-preserving smoothing
and upsampling capabilities using synthetic RGB-z data show that the
mean shift algorithm is superior to bilateral filtering as well as to
other classical smoothing and upsampling algorithms. Application of
the proposed methodology for 3D reconstruction of buildings of a
pilot region of Athens, Greece results in a significant visual
improvement of the 3D building block model.
Abstract: The edges of low contrast images are not clearly
distinguishable to human eye. It is difficult to find the edges and
boundaries in it. The present work encompasses a new approach for
low contrast images. The Chebyshev polynomial based fractional
order filter has been used for filtering operation on an image. The
preprocessing has been performed by this filter on the input image.
Laplacian of Gaussian method has been applied on preprocessed
image for edge detection. The algorithm has been tested on two test
images.
Abstract: The Simulation based VLSI Implementation of
FELICS (Fast Efficient Lossless Image Compression System)
Algorithm is proposed to provide the lossless image compression and
is implemented in simulation oriented VLSI (Very Large Scale
Integrated). To analysis the performance of Lossless image
compression and to reduce the image without losing image quality
and then implemented in VLSI based FELICS algorithm. In FELICS
algorithm, which consists of simplified adjusted binary code for
Image compression and these compression image is converted in
pixel and then implemented in VLSI domain. This parameter is used
to achieve high processing speed and minimize the area and power.
The simplified adjusted binary code reduces the number of arithmetic
operation and achieved high processing speed. The color difference
preprocessing is also proposed to improve coding efficiency with
simple arithmetic operation. Although VLSI based FELICS
Algorithm provides effective solution for hardware architecture
design for regular pipelining data flow parallelism with four stages.
With two level parallelisms, consecutive pixels can be classified into
even and odd samples and the individual hardware engine is
dedicated for each one. This method can be further enhanced by
multilevel parallelisms.
Abstract: Color Histogram is considered as the oldest method
used by CBIR systems for indexing images. In turn, the global
histograms do not include the spatial information; this is why the
other techniques coming later have attempted to encounter this
limitation by involving the segmentation task as a preprocessing step.
The weak segmentation is employed by the local histograms while
other methods as CCV (Color Coherent Vector) are based on strong
segmentation. The indexation based on local histograms consists of
splitting the image into N overlapping blocks or sub-regions, and
then the histogram of each block is computed. The dissimilarity
between two images is reduced, as consequence, to compute the
distance between the N local histograms of the both images resulting
then in N*N values; generally, the lowest value is taken into account
to rank images, that means that the lowest value is that which helps to
designate which sub-region utilized to index images of the collection
being asked. In this paper, we make under light the local histogram
indexation method in the hope to compare the results obtained against
those given by the global histogram. We address also another
noteworthy issue when Relying on local histograms namely which
value, among N*N values, to trust on when comparing images, in
other words, which sub-region among the N*N sub-regions on which
we base to index images. Based on the results achieved here, it seems
that relying on the local histograms, which needs to pose an extra
overhead on the system by involving another preprocessing step
naming segmentation, does not necessary mean that it produces better
results. In addition to that, we have proposed here some ideas to
select the local histogram on which we rely on to encode the image
rather than relying on the local histogram having lowest distance with
the query histograms.
Abstract: Advances in the field of image processing envision a
new era of evaluation techniques and application of procedures in
various different fields. One such field being considered is the
biomedical field for prognosis as well as diagnosis of diseases. This
plethora of methods though provides a wide range of options to select
from, it also proves confusion in selecting the apt process and also in
finding which one is more suitable. Our objective is to use a series of
techniques on bone scans, so as to detect the occurrence of
rheumatoid arthritis (RA) as accurately as possible. Amongst other
techniques existing in the field our proposed system tends to be more
effective as it depends on new methodologies that have been proved
to be better and more consistent than others. Computer aided
diagnosis will provide more accurate and infallible rate of
consistency that will help to improve the efficiency of the system.
The image first undergoes histogram smoothing and specification,
morphing operation, boundary detection by edge following algorithm
and finally image subtraction to determine the presence of
rheumatoid arthritis in a more efficient and effective way. Using preprocessing
noises are removed from images and using segmentation,
region of interest is found and Histogram smoothing is applied for a
specific portion of the images. Gray level co-occurrence matrix
(GLCM) features like Mean, Median, Energy, Correlation, Bone
Mineral Density (BMD) and etc. After finding all the features it
stores in the database. This dataset is trained with inflamed and noninflamed
values and with the help of neural network all the new
images are checked properly for their status and Rough set is
implemented for further reduction.
Abstract: Real-time or in-line process monitoring frameworks are designed to give early warnings for a fault along with meaningful identification of its assignable causes. In artificial intelligence and machine learning fields of pattern recognition various promising approaches have been proposed such as kernel-based nonlinear machine learning techniques. This work presents a kernel-based empirical monitoring scheme for batch type production processes with small sample size problem of partially unbalanced data. Measurement data of normal operations are easy to collect whilst special events or faults data are difficult to collect. In such situations, noise filtering techniques can be helpful in enhancing process monitoring performance. Furthermore, preprocessing of raw process data is used to get rid of unwanted variation of data. The performance of the monitoring scheme was demonstrated using three-dimensional batch data. The results showed that the monitoring performance was improved significantly in terms of detection success rate of process fault.
Abstract: Reverse engineering of genetic regulatory network involves the modeling of the given gene expression data into a form of the network. Computationally it is possible to have the relationships between genes, so called gene regulatory networks (GRNs), that can help to find the genomics and proteomics based diagnostic approach for any disease. In this paper, clustering based method has been used to reconstruct genetic regulatory network from time series gene expression data. Supercoiled data set from Escherichia coli has been taken to demonstrate the proposed method.
Abstract: In this paper, an efficient method for personal identification based on the pattern of human iris is proposed. It is composed of image acquisition, image preprocessing to make a flat iris then it is converted into eigeniris and decision is carried out using only reduction of iris in one dimension. By comparing the eigenirises it is determined whether two irises are similar. The results show that proposed method is quite effective.
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 feature selection methods to reduce the
dimensionality of the document-representation vector. In this paper,
we present three feature selection methods: Information Gain,
Support Vector Machine feature selection called (SVM_FS) and
Genetic Algorithm with SVM (called GA_SVM). We show that the
best results were obtained with GA_SVM method for a relatively
small dimension of the feature vector.
Abstract: An effective approach for extracting document images from a noisy background is introduced. The entire scheme is divided into three sub- stechniques – the initial preprocessing operations for noise cluster tightening, introduction of a new thresholding method by maximizing the ratio of stan- dard deviations of the combined effect on the image to the sum of weighted classes and finally the image restoration phase by image binarization utiliz- ing the proposed optimum threshold level. The proposed method is found to be efficient compared to the existing schemes in terms of computational complexity as well as speed with better noise rejection.
Abstract: We present a hardware oriented method for real-time
measurements of object-s position in video. The targeted application
area is light spots used as references for robotic navigation. Different
algorithms for dynamic thresholding are explored in combination
with component labeling and Center Of Gravity (COG) for highest
possible precision versus Signal-to-Noise Ratio (SNR). This method
was developed with a low hardware cost in focus having only one
convolution operation required for preprocessing of data.
Abstract: This paper presents a cold flow simulation study of a small gas turbine combustor performed using laboratory scale test rig. The main objective of this investigation is to obtain physical insight of the main vortex, responsible for the efficient mixing of fuel and air. Such models are necessary for predictions and optimization of real gas turbine combustors. Air swirler can control the combustor performance by assisting in the fuel-air mixing process and by producing recirculation region which can act as flame holders and influences residence time. Thus, proper selection of a swirler is needed to enhance combustor performance and to reduce NOx emissions. Three different axial air swirlers were used based on their vane angles i.e., 30°, 45°, and 60°. Three-dimensional, viscous, turbulent, isothermal flow characteristics of the combustor model operating at room temperature were simulated via Reynolds- Averaged Navier-Stokes (RANS) code. The model geometry has been created using solid model, and the meshing has been done using GAMBIT preprocessing package. Finally, the solution and analysis were carried out in a FLUENT solver. This serves to demonstrate the capability of the code for design and analysis of real combustor. The effects of swirlers and mass flow rate were examined. Details of the complex flow structure such as vortices and recirculation zones were obtained by the simulation model. The computational model predicts a major recirculation zone in the central region immediately downstream of the fuel nozzle and a second recirculation zone in the upstream corner of the combustion chamber. It is also shown that swirler angles changes have significant effects on the combustor flowfield as well as pressure losses.
Abstract: Classification is an important topic in machine learning
and bioinformatics. Many datasets have been introduced for
classification tasks. A dataset contains multiple features, and the quality of features influences the classification accuracy of the dataset.
The power of classification for each feature differs. In this study, we
suggest the Classification Influence Index (CII) as an indicator of classification power for each feature. CII enables evaluation of the
features in a dataset and improved classification accuracy by transformation of the dataset. By conducting experiments using CII
and the k-nearest neighbor classifier to analyze real datasets, we confirmed that the proposed index provided meaningful improvement
of the classification accuracy.
Abstract: This paper presents a implementation of an object tracking system in a video sequence. This object tracking is an important task in many vision applications. The main steps in video analysis are two: detection of interesting moving objects and tracking of such objects from frame to frame. In a similar vein, most tracking algorithms use pre-specified methods for preprocessing. In our work, we have implemented several object tracking algorithms (Meanshift, Camshift, Kalman filter) with different preprocessing methods. Then, we have evaluated the performance of these algorithms for different video sequences. The obtained results have shown good performances according to the degree of applicability and evaluation criteria.
Abstract: This paper presents the development of a wavelet
based algorithm, for distinguishing between magnetizing inrush
currents and power system fault currents, which is quite adequate,
reliable, fast and computationally efficient tool. The proposed
technique consists of a preprocessing unit based on discrete wavelet
transform (DWT) in combination with an artificial neural network
(ANN) for detecting and classifying fault currents. The DWT acts as
an extractor of distinctive features in the input signals at the relay
location. This information is then fed into an ANN for classifying
fault and magnetizing inrush conditions. A 220/55/55 V, 50Hz
laboratory transformer connected to a 380 V power system were
simulated using ATP-EMTP. The DWT was implemented by using
Matlab and Coiflet mother wavelet was used to analyze primary
currents and generate training data. The simulated results presented
clearly show that the proposed technique can accurately discriminate
between magnetizing inrush and fault currents in transformer
protection.
Abstract: Medical image segmentation based on image smoothing followed by edge detection assumes a great degree of importance in the field of Image Processing. In this regard, this paper proposes a novel algorithm for medical image segmentation based on vigorous smoothening by identifying the type of noise and edge diction ideology which seems to be a boom in medical image diagnosis. The main objective of this algorithm is to consider a particular medical image as input and make the preprocessing to remove the noise content by employing suitable filter after identifying the type of noise and finally carrying out edge detection for image segmentation. The algorithm consists of three parts. First, identifying the type of noise present in the medical image as additive, multiplicative or impulsive by analysis of local histograms and denoising it by employing Median, Gaussian or Frost filter. Second, edge detection of the filtered medical image is carried out using Canny edge detection technique. And third part is about the segmentation of edge detected medical image by the method of Normalized Cut Eigen Vectors. The method is validated through experiments on real images. The proposed algorithm has been simulated on MATLAB platform. The results obtained by the simulation shows that the proposed algorithm is very effective which can deal with low quality or marginal vague images which has high spatial redundancy, low contrast and biggish noise, and has a potential of certain practical use of medical image diagnosis.
Abstract: In Geographic Information System, one of the sources
of obtaining needed geographic data is digitizing analog maps and
evaluation of aerial and satellite photos. In this study, a method will
be discussed which can be used to extract vectorial features and
creating vectorized drawing files for aerial photos. At the same time
a software developed for these purpose. Converting from raster to
vector is also known as vectorization and it is the most important step
when creating vectorized drawing files. In the developed algorithm,
first of all preprocessing on the aerial photo is done. These are;
converting to grayscale if necessary, reducing noise, applying some
filters and determining the edge of the objects etc. After these steps,
every pixel which constitutes the photo are followed from upper left
to right bottom by examining its neighborhood relationship and one
pixel wide lines or polylines obtained. The obtained lines have to be
erased for preventing confusion while continuing vectorization
because if not erased they can be perceived as new line, but if erased
it can cause discontinuity in vector drawing so the image converted
from 2 bit to 8 bit and the detected pixels are expressed as a different
bit. In conclusion, the aerial photo can be converted to vector form
which includes lines and polylines and can be opened in any CAD
application.
Abstract: The frontal area in the brain is known to be involved in
behavioral judgement. Because a Kanji character can be discriminated
visually and linguistically from other characters, in Kanji character
discrimination, we hypothesized that frontal event-related potential
(ERP) waveforms reflect two discrimination processes in separate
time periods: one based on visual analysis and the other based
on lexcical access. To examine this hypothesis, we recorded ERPs
while performing a Kanji lexical decision task. In this task, either a
known Kanji character, an unknown Kanji character or a symbol was
presented and the subject had to report if the presented character was
a known Kanji character for the subject or not. The same response
was required for unknown Kanji trials and symbol trials. As a preprocessing
of signals, we examined the performance of a method
using independent component analysis for artifact rejection and found
it was effective. Therefore we used it. In the ERP results, there
were two time periods in which the frontal ERP wavefoms were
significantly different betweeen the unknown Kanji trials and the
symbol trials: around 170ms and around 300ms after stimulus onset.
This result supported our hypothesis. In addition, the result suggests
that Kanji character lexical access may be fully completed by around
260ms after stimulus onset.