Abstract: A state of the art Speaker Identification (SI) system
requires a robust feature extraction unit followed by a speaker
modeling scheme for generalized representation of these features.
Over the years, Mel-Frequency Cepstral Coefficients (MFCC)
modeled on the human auditory system has been used as a standard
acoustic feature set for speech related applications. On a recent
contribution by authors, it has been shown that the Inverted Mel-
Frequency Cepstral Coefficients (IMFCC) is useful feature set for
SI, which contains complementary information present in high
frequency region. This paper introduces the Gaussian shaped filter
(GF) while calculating MFCC and IMFCC in place of typical
triangular shaped bins. The objective is to introduce a higher
amount of correlation between subband outputs. The performances
of both MFCC & IMFCC improve with GF over conventional
triangular filter (TF) based implementation, individually as well as
in combination. With GMM as speaker modeling paradigm, the
performances of proposed GF based MFCC and IMFCC in
individual and fused mode have been verified in two standard
databases YOHO, (Microphone Speech) and POLYCOST
(Telephone Speech) each of which has more than 130 speakers.
Abstract: In this paper we intend to ascertain the state of the art on multifingered end-effectors, also known as robotic hands or dexterous robot hands, and propose an experimental setup for an innovative task based design approach, involving cutting edge technologies in motion capture. After an initial description of the capabilities and complexity of a human hand when grasping objects, in order to point out the importance of replicating it, we analyze the mechanical and kinematical structure of some important works carried out all around the world in the last three decades and also review the actuators and sensing technologies used. Finally we describe a new design philosophy proposing an experimental setup for the first stage using recent developments in human body motion capture systems that might lead to lighter and always more dexterous robotic hands.
Abstract: This paper shows a traceability framework for supply risk monitoring, beginning with the identification, analysis, and evaluation of the supply chain risk and focusing on the supply operations of the Health Care Institutions with oncology services in Bogota, Colombia. It includes a brief presentation of the state of the art of the Supply Chain Risk Management and traceability systems in logistics operations, and it concludes with the methodology to integrate the SCRM model with the traceability system.
Abstract: Describes the current situation of educational Robotics
"the State of the art" its concept, its evolution their niches of
opportunity, academic and business and the importance of education
and academic outreach. It shows that the development of high-tech
automated educational materials influence the teaching-learning
process and that communication between machines and humans is a
reality.
Abstract: During the last couple of years, the degree of dependence on IT systems has reached a dimension nobody imagined to be possible 10 years ago. The increased usage of mobile devices (e.g., smart phones), wireless sensor networks and embedded devices (Internet of Things) are only some examples of the dependency of modern societies on cyber space. At the same time, the complexity of IT applications, e.g., because of the increasing use of cloud computing, is rising continuously. Along with this, the threats to IT security have increased both quantitatively and qualitatively, as recent examples like STUXNET or the supposed cyber attack on Illinois water system are proofing impressively. Once isolated control systems are nowadays often publicly available - a fact that has never been intended by the developers. Threats to IT systems don’t care about areas of responsibility. Especially with regard to Cyber Warfare, IT threats are no longer limited to company or industry boundaries, administrative jurisdictions or state boundaries. One of the important countermeasures is increased cooperation among the participants especially in the field of Cyber Defence. Besides political and legal challenges, there are technical ones as well. A better, at least partially automated exchange of information is essential to (i) enable sophisticated situational awareness and to (ii) counter the attacker in a coordinated way. Therefore, this publication performs an evaluation of state of the art Intrusion Detection Message Exchange protocols in order to guarantee a secure information exchange between different entities.
Abstract: Reverse engineering of full-genomic interaction networks based on compendia of expression data has been successfully applied for a number of model organisms. This study adapts these approaches for an important non-model organism: The major human fungal pathogen Candida albicans. During the infection process, the pathogen can adapt to a wide range of environmental niches and reversibly changes its growth form. Given the importance of these processes, it is important to know how they are regulated. This study presents a reverse engineering strategy able to infer fullgenomic interaction networks for C. albicans based on a linear regression, utilizing the sparseness criterion (LASSO). To overcome the limited amount of expression data and small number of known interactions, we utilize different prior-knowledge sources guiding the network inference to a knowledge driven solution. Since, no database of known interactions for C. albicans exists, we use a textmining system which utilizes full-text research papers to identify known regulatory interactions. By comparing with these known regulatory interactions, we find an optimal value for global modelling parameters weighting the influence of the sparseness criterion and the prior-knowledge. Furthermore, we show that soft integration of prior-knowledge additionally improves the performance. Finally, we compare the performance of our approach to state of the art network inference approaches.
Abstract: The design of technological procedures for
manufacturing certain products demands the definition and
optimization of technological process parameters. Their
determination depends on the model of the process itself and its
complexity. Certain processes do not have an adequate mathematical
model, thus they are modeled using heuristic methods. First part of
this paper presents a state of the art of using soft computing
techniques in manufacturing processes from the perspective of
applicability in modern CAx systems. Methods of artificial
intelligence which can be used for this purpose are analyzed. The
second part of this paper shows some of the developed models of
certain processes, as well as their applicability in the actual
calculation of parameters of some technological processes within the
design system from the viewpoint of productivity.
Abstract: In this paper, a new approach for quality assessment
tasks in lossy compressed digital video is proposed. The research
activity is based on the visual fixation data recorded by an eye
tracker. The method involved both a new paradigm for subjective
quality evaluation and the subsequent statistical analysis to match
subjective scores provided by the observer to the data obtained from
the eye tracker experiments. The study brings improvements to the
state of the art, as it solves some problems highlighted in literature.
The experiments prove that data obtained from an eye tracker can be
used to classify videos according to the level of impairment due to
compression. The paper presents the methodology, the experimental
results and their interpretation. Conclusions suggest that the eye
tracker can be useful in quality assessment, if data are collected and
analyzed in a proper way.
Abstract: Traffic Management and Information Systems, which rely on a system of sensors, aim to describe in real-time traffic in urban areas using a set of parameters and estimating them. Though the state of the art focuses on data analysis, little is done in the sense of prediction. In this paper, we describe a machine learning system for traffic flow management and control for a prediction of traffic flow problem. This new algorithm is obtained by combining Random Forests algorithm into Adaboost algorithm as a weak learner. We show that our algorithm performs relatively well on real data, and enables, according to the Traffic Flow Evaluation model, to estimate and predict whether there is congestion or not at a given time on road intersections.
Abstract: A state of the art Speaker Identification (SI) system requires a robust feature extraction unit followed by a speaker modeling scheme for generalized representation of these features. Over the years, Mel-Frequency Cepstral Coefficients (MFCC) modeled on the human auditory system has been used as a standard acoustic feature set for SI applications. However, due to the structure of its filter bank, it captures vocal tract characteristics more effectively in the lower frequency regions. This paper proposes a new set of features using a complementary filter bank structure which improves distinguishability of speaker specific cues present in the higher frequency zone. Unlike high level features that are difficult to extract, the proposed feature set involves little computational burden during the extraction process. When combined with MFCC via a parallel implementation of speaker models, the proposed feature set outperforms baseline MFCC significantly. This proposition is validated by experiments conducted on two different kinds of public databases namely YOHO (microphone speech) and POLYCOST (telephone speech) with Gaussian Mixture Models (GMM) as a Classifier for various model orders.
Abstract: This paper presents the development techniques
for a complete autonomous design model of an advanced train
control system and gives a new approach for the
implementation of multi-agents based system. This research
work proposes to develop a novel control system to enhance
the efficiency of the vehicles under constraints of various
conditions, and contributes in stability and controllability
issues, considering relevant safety and operational
requirements with command control communication and
various sensors to avoid accidents. The approach of speed
scheduling, management and control in local and distributed
environment is given to fulfill the dire needs of modern trend
and enhance the vehicles control systems in automation. These
techniques suggest the state of the art microelectronic
technology with accuracy and stability as forefront goals.
Abstract: The state of the art in instructional design for
computer-assisted learning has been strongly influenced by advances
in information technology, Internet and Web-based systems. The
emphasis of educational systems has shifted from training to
learning. The course delivered has also been changed from large
inflexible content to sequential small chunks of learning objects. The
concepts of learning objects together with the advanced technologies
of Web and communications support the reusability, interoperability,
and accessibility design criteria currently exploited by most learning
systems. These concepts enable just-in-time learning. We propose to
extend theses design criteria further to include the learnability
concept that will help adapting content to the needs of learners. The
learnability concept offers a better personalization leading to the
creation and delivery of course content more appropriate to
performance and interest of each learner. In this paper we present a
new framework of learning environments containing knowledge
discovery as a tool to automatically learn patterns of learning
behavior from learners' profiles and history.
Abstract: Named Entity Recognition (NER) aims to classify each word of a document into predefined target named entity classes and is now-a-days considered to be fundamental for many Natural Language Processing (NLP) tasks such as information retrieval, machine translation, information extraction, question answering systems and others. This paper reports about the development of a NER system for Bengali and Hindi using Support Vector Machine (SVM). Though this state of the art machine learning technique has been widely applied to NER in several well-studied languages, the use of this technique to Indian languages (ILs) is very new. The system makes use of the different contextual information of the words along with the variety of features that are helpful in predicting the four different named (NE) classes, such as Person name, Location name, Organization name and Miscellaneous name. We have used the annotated corpora of 122,467 tokens of Bengali and 502,974 tokens of Hindi tagged with the twelve different NE classes 1, defined as part of the IJCNLP-08 NER Shared Task for South and South East Asian Languages (SSEAL) 2. In addition, we have manually annotated 150K wordforms of the Bengali news corpus, developed from the web-archive of a leading Bengali newspaper. We have also developed an unsupervised algorithm in order to generate the lexical context patterns from a part of the unlabeled Bengali news corpus. Lexical patterns have been used as the features of SVM in order to improve the system performance. The NER system has been tested with the gold standard test sets of 35K, and 60K tokens for Bengali, and Hindi, respectively. Evaluation results have demonstrated the recall, precision, and f-score values of 88.61%, 80.12%, and 84.15%, respectively, for Bengali and 80.23%, 74.34%, and 77.17%, respectively, for Hindi. Results show the improvement in the f-score by 5.13% with the use of context patterns. Statistical analysis, ANOVA is also performed to compare the performance of the proposed NER system with that of the existing HMM based system for both the languages.
Abstract: Emotion in speech is an issue that has been attracting
the interest of the speech community for many years, both in the
context of speech synthesis as well as in automatic speech
recognition (ASR). In spite of the remarkable recent progress in
Large Vocabulary Recognition (LVR), it is still far behind the
ultimate goal of recognising free conversational speech uttered by
any speaker in any environment. Current experimental tests prove
that using state of the art large vocabulary recognition systems the
error rate increases substantially when applied to
spontaneous/emotional speech. This paper shows that recognition
rate for emotionally coloured speech can be improved by using a
language model based on increased representation of emotional
utterances.
Abstract: Instead of traditional (nominal) classification we investigate
the subject of ordinal classification or ranking. An enhanced
method based on an ensemble of Support Vector Machines (SVM-s)
is proposed. Each binary classifier is trained with specific weights
for each object in the training data set. Experiments on benchmark
datasets and synthetic data indicate that the performance of our
approach is comparable to state of the art kernel methods for
ordinal regression. The ensemble method, which is straightforward
to implement, provides a very good sensitivity-specificity trade-off
for the highest and lowest rank.