Abstract: Recently, low-dose computed tomography (CT) has become highly desirable due to increasing attention to the potential risks of excessive radiation. For low-dose CT imaging, ensuring image quality while reducing radiation dose is a major challenge. To facilitate low-dose CT imaging, we propose an improved statistical iterative reconstruction scheme based on the Penalized Weighted Least Squares (PWLS) standard combined with total variation (TV) minimization and sparse dictionary learning (DL) to improve reconstruction performance. We call this method "PWLS-TV-DL". In order to evaluate the PWLS-TV-DL method, we performed experiments on digital phantoms and physical phantoms, respectively. The experimental results show that our method is in image quality and calculation. The efficiency is superior to other methods, which confirms the potential of its low-dose CT imaging.
Abstract: Computacional recognition of sign languages aims to
allow a greater social and digital inclusion of deaf people through
interpretation of their language by computer. This article presents
a model of recognition of two of global parameters from sign
languages; hand configurations and hand movements. Hand motion
is captured through an infrared technology and its joints are built
into a virtual three-dimensional space. A Multilayer Perceptron
Neural Network (MLP) was used to classify hand configurations and
Dynamic Time Warping (DWT) recognizes hand motion. Beyond
of the method of sign recognition, we provide a dataset of
hand configurations and motion capture built with help of fluent
professionals in sign languages. Despite this technology can be
used to translate any sign from any signs dictionary, Brazilian
Sign Language (Libras) was used as case study. Finally, the model
presented in this paper achieved a recognition rate of 80.4%.
Abstract: The problem of Entity relation discovery in structured
data, a well covered topic in literature, consists in searching within
unstructured sources (typically, text) in order to find connections
among entities. These can be a whole dictionary, or a specific
collection of named items. In many cases machine learning and/or
text mining techniques are used for this goal. These approaches
might be unfeasible in computationally challenging problems, such
as processing massive data streams. A faster approach consists in collecting the cooccurrences of any
two words (entities) in order to create a graph of relations - a
cooccurrence graph. Indeed each cooccurrence highlights some grade
of semantic correlation between the words because it is more common
to have related words close each other than having them in the
opposite sides of the text. Some authors have used sliding windows for such problem: they
count all the occurrences within a sliding windows running over the
whole text. In this paper we generalise such technique, coming up
to a Weighted-Distance Sliding Window, where each occurrence of
two named items within the window is accounted with a weight
depending on the distance between items: a closer distance implies
a stronger evidence of a relationship. We develop an experiment in
order to support this intuition, by applying this technique to a data
set consisting in the text of the Bible, split into verses.
Abstract: The massive development of online social networks
allows users to post and share their opinions on various topics.
With this huge volume of opinion, it is interesting to extract and
interpret these information for different domains, e.g., product and
service benchmarking, politic, system of recommendation. This is
why opinion detection is one of the most important research tasks.
It consists on differentiating between opinion data and factual data.
The difficulty of this task is to determine an approach which returns
opinionated document. Generally, there are two approaches used
for opinion detection i.e. Lexical based approaches and Machine
Learning based approaches. In Lexical based approaches, a dictionary
of sentimental words is used, words are associated with weights. The
opinion score of document is derived by the occurrence of words from
this dictionary. In Machine learning approaches, usually a classifier
is trained using a set of annotated document containing sentiment,
and features such as n-grams of words, part-of-speech tags, and
logical forms. Majority of these works are based on documents text
to determine opinion score but dont take into account if these texts
are really correct. Thus, it is interesting to exploit other information
to improve opinion detection. In our work, we will develop a new
way to consider the opinion score. We introduce the notion of
trust score. We determine opinionated documents but also if these
opinions are really trustable information in relation with topics. For
that we use lexical SentiWordNet to calculate opinion and trust
scores, we compute different features about users like (numbers of
their comments, numbers of their useful comments, Average useful
review). After that, we combine opinion score and trust score to
obtain a final score. We applied our method to detect trust opinions in
TRIPADVISOR collection. Our experimental results report that the
combination between opinion score and trust score improves opinion
detection.
Abstract: Sign Language (SL) is used by deaf and other people who cannot speak but can hear or have a problem with spoken languages due to some disability. It is a visual gesture language that makes use of either one hand or both hands, arms, face, body to convey meanings and thoughts. SL automation system is an effective way which provides an interface to communicate with normal people using a computer. In this paper, an avatar based dictionary has been proposed for text to Indian Sign Language (ISL) generation system. This research work will also depict a literature review on SL corpus available for various SL s over the years. For ISL generation system, a written form of SL is required and there are certain techniques available for writing the SL. The system uses Hamburg sign language Notation System (HamNoSys) and Signing Gesture Mark-up Language (SiGML) for ISL generation. It is developed in PHP using Web Graphics Library (WebGL) technology for 3D avatar animation. A multilingual ISL dictionary is developed using HamNoSys for both English and Hindi Language. This dictionary will be used as a database to associate signs with words or phrases of a spoken language. It provides an interface for admin panel to manage the dictionary, i.e., modification, addition, or deletion of a word. Through this interface, HamNoSys can be developed and stored in a database and these notations can be converted into its corresponding SiGML file manually. The system takes natural language input sentence in English and Hindi language and generate 3D sign animation using an avatar. SL generation systems have potential applications in many domains such as healthcare sector, media, educational institutes, commercial sectors, transportation services etc. This research work will help the researchers to understand various techniques used for writing SL and generation of Sign Language systems.
Abstract: Where human beings can easily learn and adopt pronunciation variations, machines need training before put into use. Also humans keep minimum vocabulary and their pronunciation variations are stored in front-end of their memory for ready reference, while machines keep the entire pronunciation dictionary for ready reference. Supervised methods are used for preparation of pronunciation dictionaries which take large amounts of manual effort, cost, time and are not suitable for real time use. This paper presents an unsupervised adaptation model for building agile and dynamic pronunciation dictionaries online. These methods mimic human approach in learning the new pronunciations in real time. A new algorithm for measuring sound distances called Dynamic Phone Warping is presented and tested. Performance of the system is measured using an adaptation model and the precision metrics is found to be better than 86 percent.
Abstract: A sparse representation speech denoising method based on adapted stopping residue error was presented in this paper. Firstly, the cross-correlation between the clean speech spectrum and the noise spectrum was analyzed, and an estimation method was proposed. In the denoising method, an over-complete dictionary of the clean speech power spectrum was learned with the K-singular value decomposition (K-SVD) algorithm. In the sparse representation stage, the stopping residue error was adaptively achieved according to the estimated cross-correlation and the adjusted noise spectrum, and the orthogonal matching pursuit (OMP) approach was applied to reconstruct the clean speech spectrum from the noisy speech. Finally, the clean speech was re-synthesised via the inverse Fourier transform with the reconstructed speech spectrum and the noisy speech phase. The experiment results show that the proposed method outperforms the conventional methods in terms of subjective and objective measure.
Abstract: In electromagnetic imaging, because of the diffraction limited system, the pixel values could change slowly near the edge of the image targets and they also change with the location in the same target. Using traditional digital image segmentation methods to segment electromagnetic gradient images could result in lots of errors because of this change in pixel values. To address this issue, this paper proposes a novel image segmentation and extraction algorithm based on Mean-Shift and dictionary learning. Firstly, the preliminary segmentation results from adaptive bandwidth Mean-Shift algorithm are expanded, merged and extracted. Then the overlap rate of the extracted image block is detected before determining a segmentation region with a single complete target. Last, the gradient edge of the extracted targets is recovered and reconstructed by using a dictionary-learning algorithm, while the final segmentation results are obtained which are very close to the gradient target in the original image. Both the experimental results and the simulated results show that the segmentation results are very accurate. The Dice coefficients are improved by 70% to 80% compared with the Mean-Shift only method.
Abstract: Mixing in the hyperspectral imaging occurs due to the low spatial resolutions of the used cameras. The existing pure materials “endmembers” in the scene share the spectra pixels with different amounts called “abundances”. Unmixing of the data cube is an important task to know the present endmembers in the cube for the analysis of these images. Unsupervised unmixing is done with no information about the given data cube. Sparsity is one of the recent approaches used in the source recovery or unmixing techniques. The l1-norm optimization problem “basis pursuit” could be used as a sparsity-based approach to solve this unmixing problem where the endmembers is assumed to be sparse in an appropriate domain known as dictionary. This optimization problem is solved using proximal method “iterative thresholding”. The l1-norm basis pursuit optimization problem as a sparsity-based unmixing technique was used to unmix real and synthetic hyperspectral data cubes.
Abstract: Often a Grade 12 certificate is perceived as a passport to tertiary education and the minimum requirement to enter the world of work. In spite of its importance, many students do not make this milestone in South Africa. It is important to find out why so many students still fail in spite of transformation in the education system in the post-apartheid era. Given the complexity of education and its context, this study adopted a case study design to examine one historically underperforming high school in Bushbuckridge, Mpumalanga Province, South Africa in 2013. The aim was to gain a understanding of the inner and outer school contextual factors associated with the high failure rate among Grade 12 students. Government documents and reports were consulted to identify factors in the district and the village surrounding the school and a student survey was conducted to identify school, home and student factors. The randomly-sampled half of the population of Grade 12 students (53) participated in the survey and quantitative data are analyzed using descriptive statistical methods. The findings showed that a host of factors is at play. The school is located in a village within a municipality which has been one of the poorest three municipalities in South Africa and the lowest Grade 12 pass rate in the Mpumalanga province. Moreover, over half of the families of the students are single parents, 43% are unemployed and the majority has a low level of education. In addition, most families (83%) do not have basic study materials such as a dictionary, books, tables, and chairs. A significant number of students (70%) are over-aged (+19 years old); close to half of them (49%) are grade repeaters. The school itself lacks essential resources, namely computers, science laboratories, library, and enough furniture and textbooks. Moreover, teaching and learning are negatively affected by the teachers’ occasional absenteeism, inadequate lesson preparation, and poor communication skills. Overall, the continuous low performance of students in this school mirrors the vicious circle of multiple negative conditions present within and outside of the school. The complexity of factors associated with the underperformance of Grade 12 students in this school calls for a multi-dimensional intervention from government and stakeholders. One important intervention should be the placement of over-aged students and grade-repeaters in suitable educational institutions for the benefit of other students.
Abstract: In this paper, a data-driven dictionary approach is proposed for the automatic detection and classification of cardiovascular abnormalities. Electrocardiography (ECG) signal is represented by the trained complete dictionaries that contain prototypes or atoms to avoid the limitations of pre-defined dictionaries. The data-driven trained dictionaries simply take the ECG signal as input rather than extracting features to study the set of parameters that yield the most descriptive dictionary. The approach inherently learns the complicated morphological changes in ECG waveform, which is then used to improve the classification. The classification performance was evaluated with ECG data under two different preprocessing environments. In the first category, QT-database is baseline drift corrected with notch filter and it filters the 60 Hz power line noise. In the second category, the data are further filtered using fast moving average smoother. The experimental results on QT database confirm that our proposed algorithm shows a classification accuracy of 92%.
Abstract: Speaker recognition is performed in high Additive White Gaussian Noise (AWGN) environments using principals of Computational Auditory Scene Analysis (CASA). CASA methods often classify sounds from images in the time-frequency (T-F) plane using spectrograms or cochleargrams as the image. In this paper atomic decomposition implemented by matching pursuit performs a transform from time series speech signals to the T-F plane. The atomic decomposition creates a sparsely populated T-F vector in “weight space” where each populated T-F position contains an amplitude weight. The weight space vector along with the atomic dictionary represents a denoised, compressed version of the original signal. The arraignment or of the atomic indices in the T-F vector are used for classification. Unsupervised feature learning implemented by a sparse autoencoder learns a single dictionary of basis features from a collection of envelope samples from all speakers. The approach is demonstrated using pairs of speakers from the TIMIT data set. Pairs of speakers are selected randomly from a single district. Each speak has 10 sentences. Two are used for training and 8 for testing. Atomic index probabilities are created for each training sentence and also for each test sentence. Classification is performed by finding the lowest Euclidean distance between then probabilities from the training sentences and the test sentences. Training is done at a 30dB Signal-to-Noise Ratio (SNR). Testing is performed at SNR’s of 0 dB, 5 dB, 10 dB and 30dB. The algorithm has a baseline classification accuracy of ~93% averaged over 10 pairs of speakers from the TIMIT data set. The baseline accuracy is attributable to short sequences of training and test data as well as the overall simplicity of the classification algorithm. The accuracy is not affected by AWGN and produces ~93% accuracy at 0dB SNR.
Abstract: The Romanian multilingual dictionaries – also named polyglot, plurilingual or polylingual dictionaries, have known a slow yet constant development starting with the end of the 17th century, when the first such work is attested, to the present time, when we witness a considerable increase of the number of polyglot dictionaries, especially the terminological ones. This paper aims at analyzing the context in which the first Romanian multilingual dictionaries were issued, as well as and the organization and structure particularities of the first lexicographic works of this type. The irretrievable loss of some of these works as well as the partial conservation of others renders the attempt to retrace the beginnings of Romanian lexicography extremely difficult. The research methodology is part of a descriptive and analytical approach based on two types of sources, subject to contrastive analysis: the notes made by the initiators of lexicographic projects and the testimonies of their contemporaries, respectively, along with the specialized studies regarding the history of the old Romanian lexicography. The analysis of the contents has indicated that these dictionaries lacked a scientific apparatus in the true sense of the phrase, failed to obey unitary organizational criteria, being limited, most of the times, to mere inventories of words, where the Romanian term was assigned its correspondent in other languages. Motivated by practical reasons, the first multilingual dictionaries were aimed at the clerics their purpose being to ensure the translators’ fidelity towards the original religious texts, regarded as sacred.
Abstract: The most important elements of a novel are the characters, events and background. The background represents the time, place and situation that character appears, and conveys event and atmosphere more realistically. If readers have the proper knowledge about background of novels, it may be helpful for understanding the atmosphere of a novel and choosing a novel that readers want to read. In this paper, we are targeting Korean historical novels because spatio-temporal background especially performs an important role in historical novels among the genre of Korean novels. To the best of our knowledge, we could not find previous study that was aimed at Korean novels. In this paper, we build a Korean historical national dictionary. Our dictionary has historical places and temple names of kings over many generations as well as currently existing spatial words or temporal words in Korean history. We also present a method for recognizing spatio-temporal background based on patterns of phrasal words in Korean sentences. Our rules utilize postposition for spatial background recognition and temple names for temporal background recognition. The knowledge of the recognized background can help readers to understand the flow of events and atmosphere, and can use to visualize the elements of novels.
Abstract: In VLSI, testing plays an important role. Major
problem in testing are test data volume and test power. The important
solution to reduce test data volume and test time is test data
compression. The Proposed technique combines the bit maskdictionary
and 2n pattern run length-coding method and provides a
substantial improvement in the compression efficiency without
introducing any additional decompression penalty. This method has
been implemented using Mat lab and HDL Language to reduce test
data volume and memory requirements. This method is applied on
various benchmark test sets and compared the results with other
existing methods. The proposed technique can achieve a compression
ratio up to 86%.
Abstract: A simple adaptive voice activity detector (VAD) is
implemented using Gabor and gammatone atomic decomposition of
speech for high Gaussian noise environments. Matching pursuit is
used for atomic decomposition, and is shown to achieve optimal
speech detection capability at high data compression rates for low
signal to noise ratios. The most active dictionary elements found by
matching pursuit are used for the signal reconstruction so that the
algorithm adapts to the individual speakers dominant time-frequency
characteristics. Speech has a high peak to average ratio enabling
matching pursuit greedy heuristic of highest inner products to isolate
high energy speech components in high noise environments. Gabor
and gammatone atoms are both investigated with identical
logarithmically spaced center frequencies, and similar bandwidths.
The algorithm performs equally well for both Gabor and gammatone
atoms with no significant statistical differences. The algorithm
achieves 70% accuracy at a 0 dB SNR, 90% accuracy at a 5 dB SNR
and 98% accuracy at a 20dB SNR using 30d B SNR as a reference
for voice activity.
Abstract: Organizational tendencies towards computer-based
information processing have been observed noticeably in the
third-world countries. Many enterprises are taking major initiatives
towards computerized working environment because of massive
benefits of computer-based information processing. However,
designing and developing information resource management software
for small and mid-size enterprises under budget costs and strict
deadline is always challenging for software engineers. Therefore, we
introduced an approach to design mid-size enterprise software by
using the Waterfall model, which is one of the SDLC (Software
Development Life Cycles), in a cost effective way. To fulfill research
objectives, in this study, we developed mid-sized enterprise software
named “BSK Management System” that assists enterprise software
clients with information resource management and perform complex
organizational tasks. Waterfall model phases have been applied to
ensure that all functions, user requirements, strategic goals, and
objectives are met. In addition, Rich Picture, Structured English, and
Data Dictionary have been implemented and investigated properly in
engineering manner. Furthermore, an assessment survey with 20
participants has been conducted to investigate the usability and
performance of the proposed software. The survey results indicated
that our system featured simple interfaces, easy operation and
maintenance, quick processing, and reliable and accurate transactions.
Abstract: Information Security is the most describing problem in present times. To cop up with the security of the information, the passwords were introduced. The alphanumeric passwords are the most popular authentication method and still used up to now. However, text based passwords suffer from various drawbacks such as they are easy to crack through dictionary attacks, brute force attacks, keylogger, social engineering etc. Graphical Password is a good replacement for text password. Psychological studies say that human can remember pictures better than text. So this is the fact that graphical passwords are easy to remember. But at the same time due to this reason most of the graphical passwords are prone to shoulder surfing. In this paper, we have suggested a shoulder-surfing resistant graphical password authentication method. The system is a combination of recognition and pure recall based techniques. Proposed scheme can be useful for smart hand held devices (like smart phones i.e. PDAs, iPod, iPhone, etc) which are more handy and convenient to use than traditional desktop computer systems.
Abstract: Reformulating the user query is a technique that aims to improve the performance of an Information Retrieval System (IRS) in terms of precision and recall. This paper tries to evaluate the technique of query reformulation guided by an external resource for Arabic texts. To do this, various precision and recall measures were conducted and two corpora with different external resources like Arabic WordNet (AWN) and the Arabic Dictionary (thesaurus) of Meaning (ADM) were used. Examination of the obtained results will allow us to measure the real contribution of this reformulation technique in improving the IRS performance.
Abstract: Three-party password authenticated key exchange (3PAKE) protocols are widely deployed on lots of remote user authentication system due to its simplicity and convenience of maintaining a human-memorable password at client side to achieve secure
communication within a hostile network. Recently, an improvement of 3PAKE protocol by processing a built-in data attached to other party for identity authentication to individual data was proposed by some researchers. However, this paper points out that the improved 3PAKE protocol is still vulnerable to undetectable on-line dictionary attack and off-line dictionary attack.