Abstract: Machine Translation (MT) between the Thai and English languages has been a challenging research topic in natural language processing. Most research has been done on English to Thai machine translation, but not the other way around. This paper presents a Thai to English Machine Translation System that translates a Thai sentence into interlingua of a Thai LFG tree using LFG grammar and a bottom up parser. The Thai LFG tree is then transformed into the corresponding English LFG tree by pattern matching and node transformation. Finally, an equivalent English sentence is created using structural information prescribed by the English LFG tree. Based on results of experiments designed to evaluate the performance of the proposed system, it can be stated that the system has been proven to be effective in providing a useful translation from Thai to English.
Abstract: A welded structure must be inspected to guarantee that the weld quality meets the design requirements to assure safety and reliability. However, X-ray image analyses and defect recognition with the computer vision techniques are very complex. Most difficulties lie in finding the small, irregular defects in poor contrast images which requires pre processing to image, extract, and classify features from strong background noise. This paper addresses the issue of designing methodology to extract defect from noisy background radiograph with image processing. Based on the use of actives contours this methodology seems to give good results
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: 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: Determining depth of anesthesia is a challenging problem
in the context of biomedical signal processing. Various methods
have been suggested to determine a quantitative index as depth of
anesthesia, but most of these methods suffer from high sensitivity
during the surgery. A novel method based on energy scattering of
samples in the wavelet domain is suggested to represent the basic
content of electroencephalogram (EEG) signal. In this method, first
EEG signal is decomposed into different sub-bands, then samples
are squared and energy of samples sequence is constructed through
each scale and time, which is normalized and finally entropy of the
resulted sequences is suggested as a reliable index. Empirical Results
showed that applying the proposed method to the EEG signals can
classify the awake, moderate and deep anesthesia states similar to
BIS.
Abstract: In this paper, an automatic detecting algorithm for
QRS complex detecting was applied for analyzing ECG recordings
and five criteria for dangerous arrhythmia diagnosing are applied for a
protocol type of automatic arrhythmia diagnosing system. The
automatic detecting algorithm applied in this paper detected the
distribution of QRS complexes in ECG recordings and related
information, such as heart rate and RR interval. In this investigation,
twenty sampled ECG recordings of patients with different pathologic
conditions were collected for off-line analysis. A combinative
application of four digital filters for bettering ECG signals and
promoting detecting rate for QRS complex was proposed as
pre-processing. Both of hardware filters and digital filters were
applied to eliminate different types of noises mixed with ECG
recordings. Then, an automatic detecting algorithm of QRS complex
was applied for verifying the distribution of QRS complex. Finally,
the quantitative clinic criteria for diagnosing arrhythmia were
programmed in a practical application for automatic arrhythmia
diagnosing as a post-processor. The results of diagnoses by automatic
dangerous arrhythmia diagnosing were compared with the results of
off-line diagnoses by experienced clinic physicians. The results of
comparison showed the application of automatic dangerous
arrhythmia diagnosis performed a matching rate of 95% compared
with an experienced physician-s diagnoses.
Abstract: The complex shape of the human pelvic bone was
successfully imaged and modeled using finite element FE processing.
The bone was subjected to quasi-static and dynamic loading
conditions simulating the effect of both weight gain and impact.
Loads varying between 500 – 2500 N (~50 – 250 Kg of weight) was
used to simulate 3D quasi-static weight gain. Two different 3D
dynamic analyses, body free fall at two different heights (1 and 2 m)
and forced side impact at two different velocities (20 and 40 Km/hr)
were also studied. The computed resulted stresses were compared for
the four loading cases, where Von Misses stresses increases linearly
with the weight gain increase under quasi-static loading. For the
dynamic models, the Von Misses stress history behaviors were
studied for the affected area and effected load with respect to time.
The normalization Von Misses stresses with respect to the applied
load were used for comparing the free fall and the forced impact load
results. It was found that under the forced impact loading condition
an over lapping behavior was noticed, where as for the free fall the
normalized Von Misses stresses behavior was found to nonlinearly
different. This phenomenon was explained through the energy
dissipation concept. This study will help designers in different
specialization in defining the weakest spots for designing different
supporting systems.
Abstract: Cryo-electron microscopy (CEM) in combination with
single particle analysis (SPA) is a widely used technique for
elucidating structural details of macromolecular assemblies at closeto-
atomic resolutions. However, development of automated software
for SPA processing is still vital since thousands to millions of
individual particle images need to be processed. Here, we present our
workflow for automated particle picking. Our approach integrates
peak shape analysis to the classical correlation and an iterative
approach to separate macromolecules and background by
classification. This particle selection workflow furthermore provides
a robust means for SPA with little user interaction. Processing
simulated and experimental data assesses performance of the
presented tools.
Abstract: Artificial Immune System (AIS) is relatively naive paradigm for intelligent computations. The inspiration for AIS is derived from natural Immune System (IS). Classically it is believed that IS strives to discriminate between self and non-self. Most of the existing AIS research is based on this approach. Danger Theory (DT) argues this approach and proposes that IS fights against danger producing elements and tolerates others. We, the computational researchers, are not concerned with the arguments among immunologists but try to extract from it novel abstractions for intelligent computation. This paper aims to follow DT inspiration for intelligent data processing. The approach may introduce new avenue in intelligent processing. The data used is system calls data that is potentially significant in intrusion detection applications.
Abstract: The aim of the study was to determine how different
ripening processes (traditional vs. industrial) influenced the
proteolysis in traditional Serbian dry-fermented sausage Petrovská
klobása. The obtained results indicated more intensive pH decline
(0.7 units after 9 days) in industrially ripened products (I), what had a
positive impact on drying process and proteolytic changes in these
samples. Thus, moisture content in I sausages was lower at each
sampling time, amounting 24.7% at the end of production period
(90 days). Likewise, the process of proteolysis was more pronounced
in I samples, resulting in higher contents of non-protein nitrogen
(NPN) and free amino acids nitrogen (FAAN), as well as in faster
and more intensive degradation of myosin (≈220 kDa), actin (≈45
kDa) and other polypeptides during processing. Consequently, the
appearance and accumulation of several protein fragments were
registered.
Abstract: Radio propagation from point-to-point is affected by
the physical channel in many ways. A signal arriving at a destination
travels through a number of different paths which are referred to as
multi-paths. Research in this area of wireless communications has
progressed well over the years with the research taking different
angles of focus. By this is meant that some researchers focus on
ways of reducing or eluding Multipath effects whilst others focus on
ways of mitigating the effects of Multipath through compensation
schemes. Baseband processing is seen as one field of signal
processing that is cardinal to the advancement of software defined
radio technology. This has led to wide research into the carrying out
certain algorithms at baseband. This paper considers compensating
for Multipath for Frequency Modulated signals. The compensation
process is carried out at Radio frequency (RF) and at Quadrature
baseband (QBB) and the results are compared. Simulations are
carried out using MatLab so as to show the benefits of working at
lower QBB frequencies than at RF.
Abstract: Question answering (QA) aims at retrieving precise information from a large collection of documents. Most of the Question Answering systems composed of three main modules: question processing, document processing and answer processing. Question processing module plays an important role in QA systems to reformulate questions. Moreover answer processing module is an emerging topic in QA systems, where these systems are often required to rank and validate candidate answers. These techniques aiming at finding short and precise answers are often based on the semantic relations and co-occurrence keywords. This paper discussed about a new model for question answering which improved two main modules, question processing and answer processing which both affect on the evaluation of the system operations. There are two important components which are the bases of the question processing. First component is question classification that specifies types of question and answer. Second one is reformulation which converts the user's question into an understandable question by QA system in a specific domain. The objective of an Answer Validation task is thus to judge the correctness of an answer returned by a QA system, according to the text snippet given to support it. For validating answers we apply candidate answer filtering, candidate answer ranking and also it has a final validation section by user voting. Also this paper described new architecture of question and answer processing modules with modeling, implementing and evaluating the system. The system differs from most question answering systems in its answer validation model. This module makes it more suitable to find exact answer. Results show that, from total 50 asked questions, evaluation of the model, show 92% improving the decision of the system.
Abstract: ''Cocktail party problem'' is well known as one of the human auditory abilities. We can recognize the specific sound that we want to listen by this ability even if a lot of undesirable sounds or noises are mixed. Blind source separation (BSS) based on independent component analysis (ICA) is one of the methods by which we can separate only a special signal from their mixed signals with simple hypothesis. In this paper, we propose an online approach for blind source separation using the sliding DFT and the time domain independent component analysis. The proposed method can reduce calculation complexity in comparison with conventional methods, and can be applied to parallel processing by using digital signal processors (DSPs) and so on. We evaluate this method and show its availability.
Abstract: In this study, a new criterion for determining the number of classes an image should be segmented is proposed. This criterion is based on discriminant analysis for measuring the separability among the segmented classes of pixels. Based on the new discriminant criterion, two algorithms for recursively segmenting the image into determined number of classes are proposed. The proposed methods can automatically and correctly segment objects with various illuminations into separated images for further processing. Experiments on the extraction of text strings from complex document images demonstrate the effectiveness of the proposed methods.1
Abstract: The existing image coding standards generally degrades at low bit-rates because of the underlying block based Discrete Cosine Transform scheme. Over the past decade, the success of wavelets in solving many different problems has contributed to its unprecedented popularity. Due to implementation constraints scalar wavelets do not posses all the properties such as orthogonality, short support, linear phase symmetry, and a high order of approximation through vanishing moments simultaneously, which are very much essential for signal processing. New class of wavelets called 'Multiwavelets' which posses more than one scaling function overcomes this problem. This paper presents a new image coding scheme based on non linear approximation of multiwavelet coefficients along with multistage vector quantization. The performance of the proposed scheme is compared with the results obtained from scalar wavelets.
Abstract: This paper describes about the process of recognition and classification of brain images such as normal and abnormal based on PSO-SVM. Image Classification is becoming more important for medical diagnosis process. In medical area especially for diagnosis the abnormality of the patient is classified, which plays a great role for the doctors to diagnosis the patient according to the severeness of the diseases. In case of DICOM images it is very tough for optimal recognition and early detection of diseases. Our work focuses on recognition and classification of DICOM image based on collective approach of digital image processing. For optimal recognition and classification Particle Swarm Optimization (PSO), Genetic Algorithm (GA) and Support Vector Machine (SVM) are used. The collective approach by using PSO-SVM gives high approximation capability and much faster convergence.
Abstract: Image compression is one of the most important
applications Digital Image Processing. Advanced medical imaging
requires storage of large quantities of digitized clinical data. Due to
the constrained bandwidth and storage capacity, however, a medical
image must be compressed before transmission and storage. There
are two types of compression methods, lossless and lossy. In Lossless
compression method the original image is retrieved without any
distortion. In lossy compression method, the reconstructed images
contain some distortion. Direct Cosine Transform (DCT) and Fractal
Image Compression (FIC) are types of lossy compression methods.
This work shows that lossy compression methods can be chosen for
medical image compression without significant degradation of the
image quality. In this work DCT and Fractal Compression using
Partitioned Iterated Function Systems (PIFS) are applied on different
modalities of images like CT Scan, Ultrasound, Angiogram, X-ray
and mammogram. Approximately 20 images are considered in each
modality and the average values of compression ratio and Peak
Signal to Noise Ratio (PSNR) are computed and studied. The quality
of the reconstructed image is arrived by the PSNR values. Based on
the results it can be concluded that the DCT has higher PSNR values
and FIC has higher compression ratio. Hence in medical image
compression, DCT can be used wherever picture quality is preferred
and FIC is used wherever compression of images for storage and
transmission is the priority, without loosing picture quality
diagnostically.
Abstract: For about two decades scientists have been
developing techniques for enhancing the quality of medical images
using Fourier transform, DWT (Discrete wavelet transform),PDE
model etc., Gabor wavelet on hexagonal sampled grid of the images
is proposed in this work. This method has optimal approximation
theoretic performances, for a good quality image. The computational
cost is considerably low when compared to similar processing in the
rectangular domain. As X-ray images contain light scattered pixels,
instead of unique sigma, the parameter sigma of 0.5 to 3 is found to
satisfy most of the image interpolation requirements in terms of high
Peak Signal-to-Noise Ratio (PSNR) , lower Mean Squared Error
(MSE) and better image quality by adopting windowing technique.
Abstract: Embedding and extraction of a secret information as
well as the restoration of the original un-watermarked image is
highly desirable in sensitive applications like military, medical, and
law enforcement imaging. This paper presents a novel reversible
data-hiding method for digital images using integer to integer
wavelet transform and companding technique which can embed and
recover the secret information as well as can restore the image to its
pristine state. The novel method takes advantage of block based
watermarking and iterative optimization of threshold for companding
which avoids histogram pre and post-processing. Consequently, it
reduces the associated overhead usually required in most of the
reversible watermarking techniques. As a result, it keeps the
distortion small between the marked and the original images.
Experimental results show that the proposed method outperforms the
existing reversible data hiding schemes reported in the literature.
Abstract: Edge detection is usually the first step in medical
image processing. However, the difficulty increases when a
conventional kernel-based edge detector is applied to ultrasonic
images with a textural pattern and speckle noise. We designed an
adaptive diffusion filter to remove speckle noise while preserving the
initial edges detected by using a Sobel edge detector. We also propose
a genetic algorithm for edge selection to form complete boundaries of
the detected entities. We designed two fitness functions to evaluate
whether a criterion with a complex edge configuration can render a
better result than a simple criterion such as the strength of gradient.
The edges obtained by using a complex fitness function are thicker and
more fragmented than those obtained by using a simple fitness
function, suggesting that a complex edge selecting scheme is not
necessary for good edge detection in medical ultrasonic images;
instead, a proper noise-smoothing filter is the key.