Abstract: Both image steganography and image encryption have
advantages and disadvantages. Steganograhy allows us to hide a
desired image containing confidential information in a covered or
host image while image encryption is decomposing the desired image
to a non-readable, non-comprehended manner. The encryption
methods are usually much more robust than the steganographic ones.
However, they have a high visibility and would provoke the attackers
easily since it usually is obvious from an encrypted image that
something is hidden! The combination of steganography and
encryption will cover both of their weaknesses and therefore, it
increases the security. In this paper an image encryption method
based on sinc-convolution along with using an encryption key of 128
bit length is introduced. Then, the encrypted image is covered by a
host image using a modified version of JSteg steganography
algorithm. This method could be applied to almost all image formats
including TIF, BMP, GIF and JPEG. The experiment results show
that our method is able to hide a desired image with high security and
low visibility.
Abstract: The VoIP networks as alternative method to traditional PSTN system has been implemented in a wide variety of structures
with multiple protocols, codecs, software and hardware–based
distributions. The use of cryptographic techniques let the users to have a secure communication, but the calculate throughput as well as the QoS parameters are affected according to the used algorithm. This
paper analyzes the VoIP throughput and the QoS parameters with
different commercial encryption methods. The measurement–based
approach uses lab scenarios to simulate LAN and WAN
environments. Security mechanisms such as TLS, SIAX2, SRTP,
IPSEC and ZRTP are analyzed with μ-LAW and GSM codecs.
Abstract: Modeling the behavior of the dialogue management in
the design of a spoken dialogue system using statistical methodologies
is currently a growing research area. This paper presents a work
on developing an adaptive learning approach to optimize dialogue
strategy. At the core of our system is a method formalizing dialogue
management as a sequential decision making under uncertainty whose
underlying probabilistic structure has a Markov Chain. Researchers
have mostly focused on model-free algorithms for automating the
design of dialogue management using machine learning techniques
such as reinforcement learning. But in model-free algorithms there
exist a dilemma in engaging the type of exploration versus exploitation.
Hence we present a model-based online policy learning
algorithm using interconnected learning automata for optimizing
dialogue strategy. The proposed algorithm is capable of deriving
an optimal policy that prescribes what action should be taken in
various states of conversation so as to maximize the expected total
reward to attain the goal and incorporates good exploration and
exploitation in its updates to improve the naturalness of humancomputer
interaction. We test the proposed approach using the most
sophisticated evaluation framework PARADISE for accessing to the
railway information system.
Abstract: A procedural-animation-based approach which rapidly
synthesize the adaptive locomotion for quadruped characters that they
can walk or run in any directions on an uneven terrain within a
dynamic environment was proposed. We devise practical motion
models of the quadruped animals for adapting to a varied terrain in a
real-time manner. While synthesizing locomotion, we choose the
corresponding motion models by means of the footstep prediction of
the current state in the dynamic environment, adjust the key-frames of
the motion models relying on the terrain-s attributes, calculate the
collision-free legs- trajectories, and interpolate the key-frames
according to the legs- trajectories. Finally, we apply dynamic time
warping to each part of motion for seamlessly concatenating all desired
transition motions to complete the whole locomotion. We reduce the
time cost of producing the locomotion and takes virtual characters to
fit in with dynamic environments no matter when the environments are
changed by users.
Abstract: Recently many research has been conducted to
retrieve pertinent parameters and adequate models for automatic
music genre classification. In this paper, two measures based upon
information theory concepts are investigated for mapping the features
space to decision space. A Gaussian Mixture Model (GMM) is used
as a baseline and reference system. Various strategies are proposed
for training and testing sessions with matched or mismatched
conditions, long training and long testing, long training and short
testing. For all experiments, the file sections used for testing are
never been used during training. With matched conditions all
examined measures yield the best and similar scores (almost 100%).
With mismatched conditions, the proposed measures yield better
scores than the GMM baseline system, especially for the short testing
case. It is also observed that the average discrimination information
measure is most appropriate for music category classifications and on
the other hand the divergence measure is more suitable for music
subcategory classifications.
Abstract: This text studies glass bottle intelligent inspector
based machine vision instead of manual inspection. The system
structure is illustrated in detail in this paper. The text presents the
method based on watershed transform methods to segment the
possible defective regions and extract features of bottle wall by rules.
Then wavelet transform are used to exact features of bottle finish
from images. After extracting features, the fuzzy support vector
machine ensemble is putted forward as classifier. For ensuring that
the fuzzy support vector machines have good classification ability,
the GA based ensemble method is used to combining the several
fuzzy support vector machines. The experiments demonstrate that
using this inspector to inspect glass bottles, the accuracy rate may
reach above 97.5%.
Abstract: Linear convolutive filters are fast in calculation and in application, and thus, often used for real-time processing of continuous data streams. In the case of transient signals, a filter has not only to detect the presence of a specific waveform, but to estimate its arrival time as well. In this study, a measure is presented which indicates the performance of detectors in achieving both of these tasks simultaneously. Furthermore, a new sub-class of linear filters within the class of filters which minimize the quadratic response is proposed. The proposed filters are more flexible than the existing ones, like the adaptive matched filter or the minimum power distortionless response beamformer, and prove to be superior with respect to that measure in certain settings. Simulations of a real-time scenario confirm the advantage of these filters as well as the usefulness of the performance measure.
Abstract: The productivity of software development is one of the major concerns for project managers. Given the increasing complexity of the software being developed and the concomitant rise in the typical project size, the productivity has not consistently improved. By analyzing the latest release of ISBSG data repository with 4106 projects ever developed, we report on the factors found to significantly influence productivity, and present an original model for the estimation of productivity during project design. We further illustrate that software development productivity has experienced irregular variations between the years 1995 and 2005. Considering the factors significant to productivity, we found its variations are primarily caused by the variations of average team size for the development and the unbalanced use of the less productive development language 3GL.
Abstract: Word sense disambiguation is one of the most important open problems in natural language processing applications such as information retrieval and machine translation. Many approach strategies can be employed to resolve word ambiguity with a reasonable degree of accuracy. These strategies are: knowledgebased, corpus-based, and hybrid-based. This paper pays attention to the corpus-based strategy that employs an unsupervised learning method for disambiguation. We report our investigation of Latent Semantic Indexing (LSI), an information retrieval technique and unsupervised learning, to the task of Thai noun and verbal word sense disambiguation. The Latent Semantic Indexing has been shown to be efficient and effective for Information Retrieval. For the purposes of this research, we report experiments on two Thai polysemous words, namely /hua4/ and /kep1/ that are used as a representative of Thai nouns and verbs respectively. The results of these experiments demonstrate the effectiveness and indicate the potential of applying vector-based distributional information measures to semantic disambiguation.
Abstract: This paper presents a rule-based text- to- speech
(TTS) Synthesis System for Standard Malay, namely SMaTTS. The
proposed system using sinusoidal method and some pre- recorded
wave files in generating speech for the system. The use of phone
database significantly decreases the amount of computer memory
space used, thus making the system very light and embeddable. The
overall system was comprised of two phases the Natural Language
Processing (NLP) that consisted of the high-level processing of text
analysis, phonetic analysis, text normalization and morphophonemic
module. The module was designed specially for SM to overcome
few problems in defining the rules for SM orthography system before
it can be passed to the DSP module. The second phase is the Digital
Signal Processing (DSP) which operated on the low-level process of
the speech waveform generation. A developed an intelligible and
adequately natural sounding formant-based speech synthesis system
with a light and user-friendly Graphical User Interface (GUI) is
introduced. A Standard Malay Language (SM) phoneme set and an
inclusive set of phone database have been constructed carefully for
this phone-based speech synthesizer. By applying the generative
phonology, a comprehensive letter-to-sound (LTS) rules and a
pronunciation lexicon have been invented for SMaTTS. As for the
evaluation tests, a set of Diagnostic Rhyme Test (DRT) word list was
compiled and several experiments have been performed to evaluate
the quality of the synthesized speech by analyzing the Mean Opinion
Score (MOS) obtained. The overall performance of the system as
well as the room for improvements was thoroughly discussed.
Abstract: Traffic incident has bad effect on all parts of society
so controlling road networks with enough traffic devices could help
to decrease number of accidents, so using the best method for
optimum site selection of these devices could help to implement good
monitoring system. This paper has considered here important criteria
for optimum site selection of traffic camera based on aggregation
methods such as Bagging and Dempster-Shafer concepts. In the first
step, important criteria such as annual traffic flow, distance from
critical places such as parks that need more traffic controlling were
identified for selection of important road links for traffic camera
installation, Then classification methods such as Artificial neural
network and Decision tree algorithms were employed for
classification of road links based on their importance for camera
installation. Then for improving the result of classifiers aggregation
methods such as Bagging and Dempster-Shafer theories were used.
Abstract: A multimedia presentation system refers to the integration of a multimedia database with a presentation manager which has the functionality of content selection, organization and playout of multimedia presentations. It requires high performance of involved system components. Starting from multimedia information capture until the presentation delivery, high performance tools are required for accessing, manipulating, storing and retrieving these segments, for transferring and delivering them in a presentation terminal according to a playout order. The organization of presentations is a complex task in that the display order of presentation contents (in time and space) must be specified. A multimedia presentation contains audio, video, images and text media types. The critical decisions for presentation construction include what the contents are, how the contents are organized, and once the decision is made on the organization of the contents of the presentation, it must be conveyed to the end user in the correct organizational order and in a timely fashion. This paper introduces a framework for specification of multimedia presentations and describes the design of sample presentations using this framework from a multimedia database.
Abstract: This paper presents an online method that learns the
corresponding points of an object from un-annotated grayscale images
containing instances of the object. In the first image being
processed, an ensemble of node points is automatically selected
which is matched in the subsequent images. A Bayesian posterior
distribution for the locations of the nodes in the images is formed.
The likelihood is formed from Gabor responses and the prior assumes
the mean shape of the node ensemble to be similar in a translation
and scale free space. An association model is applied for separating
the object nodes and background nodes. The posterior distribution is
sampled with Sequential Monte Carlo method. The matched object
nodes are inferred to be the corresponding points of the object
instances. The results show that our system matches the object nodes
as accurately as other methods that train the model with annotated
training images.
Abstract: Fuzzy Cognitive Maps (FCMs) is a causal graph, which shows the relations between essential components in complex systems. Experts who are familiar with the system components and their relations can generate a related FCM. There is a big gap when human experts cannot produce FCM or even there is no expert to produce the related FCM. Therefore, a new mechanism must be used to bridge this gap. In this paper, a novel learning method is proposed to construct causal graph based on historical data and by using metaheuristic such Tabu Search (TS). The efficiency of the proposed method is shown via comparison of its results of some numerical examples with those of some other methods.
Abstract: XML is becoming a de facto standard for online data exchange. Existing XML filtering techniques based on a publish/subscribe model are focused on the highly structured data marked up with XML tags. These techniques are efficient in filtering the documents of data-centric XML but are not effective in filtering the element contents of the document-centric XML. In this paper, we propose an extended XPath specification which includes a special matching character '%' used in the LIKE operation of SQL in order to solve the difficulty of writing some queries to adequately filter element contents using the previous XPath specification. We also present a novel technique for filtering a collection of document-centric XMLs, called Pfilter, which is able to exploit the extended XPath specification. We show several performance studies, efficiency and scalability using the multi-query processing time (MQPT).
Abstract: Robotic system is an important area in artificial intelligence that aims at developing the performance techniques of the robot and making it more efficient and more effective in choosing its correct behavior. In this paper the distributed learning classifier system is used for designing a simulated control system for robot to perform complex behaviors. A set of enhanced approaches that support default hierarchies formation is suggested and compared with each other in order to make the simulated robot more effective in mapping the input to the correct output behavior.
Abstract: Home is important for Chinese people. Because the
information regarding the house attributes and surrounding
environments is incomplete in most real estate agency, most house
buyers are difficult to consider the overall factors effectively and only
can search candidates by sorting-based approach. This study aims to
develop a decision support system for housing purchasing, in which
surrounding facilities of each house are quantified. Then, all
considered house factors and customer preferences are incorporated
into Simple Multi-Attribute Ranking Technique (SMART) to support
the housing evaluation. To evaluate the validity of proposed approach,
an empirical study was conducted from a real estate agency. Based on
the customer requirement and preferences, the proposed approach can
identify better candidate house with consider the overall house
attributes and surrounding facilities.
Abstract: This paper discusses an artificial mind model and its
applications. The mind model is based on some theories which assert
that emotion is an important function in human decision making. An
artificial mind model with emotion is built, and the model is applied to
action selection of autonomous agents. In three examples, the agents
interact with humans and their environments. The examples show the
proposed model effectively work in both virtual agents and real robots.
Abstract: Cellular automata have been used for design of cryptosystems. Recently some secret sharing schemes based on linear memory cellular automata have been introduced which are used for both text and image. In this paper, we illustrate that these secret sharing schemes are vulnerable to dishonest participants- collusion. We propose a cheating model for the secret sharing schemes based on linear memory cellular automata. For this purpose we present a novel uniform model for representation of all secret sharing schemes based on cellular automata. Participants can cheat by means of sending bogus shares or bogus transition rules. Cheaters can cooperate to corrupt a shared secret and compute a cheating value added to it. Honest participants are not aware of cheating and suppose the incorrect secret as the valid one. We prove that cheaters can recover valid secret by removing the cheating value form the corrupted secret. We provide methods of calculating the cheating value.
Abstract: Naive Bayes Nearest Neighbor (NBNN) and its variants, i,e., local NBNN and the NBNN kernels, are local feature-based classifiers that have achieved impressive performance in image classification. By exploiting instance-to-class (I2C) distances (instance means image/video in image/video classification), they avoid quantization errors of local image descriptors in the bag of words (BoW) model. However, the performances of NBNN, local NBNN and the NBNN kernels have not been validated on video analysis. In this paper, we introduce these three classifiers into human action recognition and conduct comprehensive experiments on the benchmark KTH and the realistic HMDB datasets. The results shows that those I2C based classifiers consistently outperform the SVM classifier with the BoW model.