AbstractPolysemy is a common phenomenon in the
biomedical domain. Ambiguous words directly influence
the accuracy of computer semantic analyses. Thus, word
sense disambiguation (WSD) is often conducted in
advance. Most current biomedical WSD methods rely on
manual selection of features for WSD. To identify latent
context features from a deep layer and reduce the negative
influence of manual selection of features in WSD, this
paper proposes the Convolutional...Polysemy is a common phenomenon in the
biomedical domain. Ambiguous words directly influence
the accuracy of computer semantic analyses. Thus, word
sense disambiguation (WSD) is often conducted in
advance. Most current biomedical WSD methods rely on
manual selection of features for WSD. To identify latent
context features from a deep layer and reduce the negative
influence of manual selection of features in WSD, this
paper proposes the Convolutional Neural Network (CNN)
method for biomedical WSD with enhanced text feature
modeling. First, this program automatically conducts
crawling of a large scale of relevant corpus from MEDLINE
for training and obtains relevant context feature vectors.
These feature vectors are subsequently adopted as input
data in CNN. Finally, the CNN classification method is
used for WSD. By testing 203 commonly used ambiguous
words from MSH-WSD corpus, the author finds that the
average accuracy of the proposed method is 94.65%,
which is a significant improvement relative to that of
previous methods. This result proves that CNN is an
efficient WSD method to be used in the biomedical
domain. Given that context feature representation and
WSD are important pre-works in extraction and retrieval
of biomedical information, WSD can reduce the negative
effect of ambiguous words on accuracy of such pre-works.Read MoreRead Less
AbstractThe questionable quality of the roads represents
the main factor of discomfort, being directly responsible
for the accidents, affecting car components,
but also the security of passengerscausing death and
serious injuries. According to statistics released by the
World Health Organization, road accidents, in underdeveloped
countries, tends to increase by 80 % in 2020
compared to 2000. In terms of road infrastructure,the lowand
middle-income countries are characterized by a...The questionable quality of the roads represents
the main factor of discomfort, being directly responsible
for the accidents, affecting car components,
but also the security of passengerscausing death and
serious injuries. According to statistics released by the
World Health Organization, road accidents, in underdeveloped
countries, tends to increase by 80 % in 2020
compared to 2000. In terms of road infrastructure,the lowand
middle-income countries are characterized by a higher
accident rate, reason for which the cars designers must
approach the suspension problem slightly different and
the parameters obtained by optimization algorithms should
be differentfrom the same model of car depending on
where they will be driven / sold.This paper presents the
optimization of a quarter-car model with two degree-offreedom
using evolutionary algorithms to determine the
optimal parameters for a vehicle suspension, in order to
improve ride comfort. The optimization problem consists
in minimizing the sprung mass acceleration and sprung
mass displacement subject to several constraints that
arise from kinematic considerations. The vehicle model
is considered to travel at a constant speed on a random
road profile generated according to the ISO 8608 standard.
The design variables to be optimized are the suspension
stiffness and damping coefficients. We analyzed
the algorithms in multiple scenarios so we can compare
their performance in terms of fast convergence and solution
diversity. The results showed that the optimization
algorithms find solutions in small number of iterations,
with slightly better performance obtained by Fast Pareto
Genetic Algorithm.Read MoreRead Less
AbstractAt present, many organizations try to gain
value from their exponential growth of data by implementing
new available technologies, processes and governance
mechanisms, such as big data and Cloud computing.
According to Gartner and Mackinsey predictions, big data
has been largely adopted in 2013. Effectively, nowadays
the challenge now is how to ensure an effective analysis
and management of large-scale data by minimizing all
the costs related to...At present, many organizations try to gain
value from their exponential growth of data by implementing
new available technologies, processes and governance
mechanisms, such as big data and Cloud computing.
According to Gartner and Mackinsey predictions, big data
has been largely adopted in 2013. Effectively, nowadays
the challenge now is how to ensure an effective analysis
and management of large-scale data by minimizing all
the costs related to accessing and processing those data.
The huge commitment of hardware and processing
resources often needed when using big data, is one of
the limitations that must be taken into consideration.
Since the technology is permanently subject to advances
and development, the question for many businesses is
how they can benefit from big data using the power of
technique flexibility that Cloud computing can provide. In
this paper, we propose a decisional methodology based
on Fuzzy Analytic Hierarchy Process (FAHP) and
PROMETHEE (Preference Ranking Organization METHod
for Enrichment Evaluations) for comparing, ranking and
selecting the most suitable Cloud computing to
accommodate and access big data. Due to the varying
importance of the used criteria, we develop fuzzy AHP
software based on extent analysis method to assign the
importance weights to evaluation criteria, while the
PROMETHEE process exploits these weighted criteria
as input to evaluate and rank the decision alternatives.Read MoreRead Less
AbstractWith the rise of microblog, topic detection
in microblog posts has been a hotspot in natural language
processing and text mining. Different from regular text,
microblog post is a kind of short and idiomatic text.
Microblog post contains little information, which brings
great challenge for its topic detection. To address the
issue of topic detection in microblog, a new single pass
algorithm based on a double-vector model...With the rise of microblog, topic detection
in microblog posts has been a hotspot in natural language
processing and text mining. Different from regular text,
microblog post is a kind of short and idiomatic text.
Microblog post contains little information, which brings
great challenge for its topic detection. To address the
issue of topic detection in microblog, a new single pass
algorithm based on a double-vector model (DVM; Single
Pass_DM) is proposed. First, a support vector machine
(SVM) based algorithm is employed to filter irrelevant
posts, thereby improving the accuracy of the algorithm.
As for the representation model, on the basis of the
traditional vector space model, a DVM that includes event
and keyword vector is put forward. Subsequently,, a
combination of Jacoby ,cosine and semantic similarity
is used for similarity computation. Finally, some structural
characteristics of microblog posts are used to support
the topic detection problem. To validate the performance
of the proposed algorithm, experiments are conducted on
a real-world dataset. Experimental results show that,
comparing with three benchmark algorithms SinglePass,
Agglomerative Hierarchical Clustering (AHC) and Densitybased
Spatial Clustering ( DBSCAN), the performance of
SinglePass_DM has been improved greatly.Read MoreRead Less
AbstractIn the present study, a system is offered,
which can recommend news regarding the emotion of users
towards the previous news articles the user has searched
so far. This recommendation is in a way, which affects
the user's emotion positively. This study reveals that with
manipulating the recommendation list we can have a
positive impact on the emotion of users. For this purpose,
a news application for...In the present study, a system is offered,
which can recommend news regarding the emotion of users
towards the previous news articles the user has searched
so far. This recommendation is in a way, which affects
the user's emotion positively. This study reveals that with
manipulating the recommendation list we can have a
positive impact on the emotion of users. For this purpose,
a news application for android devices is developed, which
can inform users about daily news and recommend some
news to change their emotion toward a positive side. The
proposed system is checked in terms of its engine
performance and influence on their emotion. To evaluate
our system, two groups of people have been chosen which
one of them has used the proposed system and the other
one has used a simple news application. For a period of
more than a month, the emotional impact of the system
has been monitored. Investigations and analyses on the
users given feedbacks indicate the positive effect of the
proposed system on the emotion of users and the alteration
of their emotion towards a positive side is 11 times more
than a simple news application.Read MoreRead Less
AbstractContent distribution is a key technology to
achieve data sharing among mobile terminals in Mobile
Peer to Peer (MP2P) networks. Nevertheless, in the
dynamic/mobile environment, the poor computing ability
and storage capability of a single node make it difficult to
share the content among nodes. In order to enhance the
capability of the mobile terminals and improve the
efficiency of content distribution, a cloud-assisted
architecture to offload the...Content distribution is a key technology to
achieve data sharing among mobile terminals in Mobile
Peer to Peer (MP2P) networks. Nevertheless, in the
dynamic/mobile environment, the poor computing ability
and storage capability of a single node make it difficult to
share the content among nodes. In order to enhance the
capability of the mobile terminals and improve the
efficiency of content distribution, a cloud-assisted
architecture to offload the heavy computation load from
the mobile nodes to the cloud was put forward.
Furthermore, a Multi-Tree Structure of Internal Node
Disjoint (MTSIND) data transfer topology was proposed,
in which their internal nodes are disjoint, thus each node
can take part in the content delivery tasks. Finally, an
exclusive-OR (XOR) network coding method based on
vertex coloring problem was established to reduce the
number of transmissions and power consumption.
Simulation and numerical results were provided to support
the analyses and results. Results show that the content
distribution mechanism can reduce the total number of
the data packets and the energy consumption. The study
proves that the research of content distribution mechanism
on MP2P has a great significance on reducing the number
of data transmissions, lowering the power consumption
of terminals and increasing the resource utilization of mobiloe nodesRead MoreRead Less
AbstractDigital oilfields are highly complicated
information systems, and their size increases as the
enterprise scale expands. Cloud computing as a new
service model has been gradually extended from the
traditional IT industry to traditional industrial domains, but
research on and the application of the digital oilfield cloud
platform remain lacking. By introducing the reference frame
of the integrated platform of oil enterprises at home and
abroad, we adopt...Digital oilfields are highly complicated
information systems, and their size increases as the
enterprise scale expands. Cloud computing as a new
service model has been gradually extended from the
traditional IT industry to traditional industrial domains, but
research on and the application of the digital oilfield cloud
platform remain lacking. By introducing the reference frame
of the integrated platform of oil enterprises at home and
abroad, we adopt the design method of the integrated
architecture of enterprises and the metadata-based
object-oriented development model based on the design
concept of cloud computing to identify efficient and
inexpensive information platform solutions. Research is
conducted on a cloud data service management system
for digital oilfields. The overall structure of the cloud
platform for digital oilfields is divided into five layers of
infrastructure, data resources, functional services,
applications, and terminal access and into two support
subsystems, namely, cloud information specifications and
standards and cloud service management platform. The
cloud data service platform is generalized as an
architecture with "a center, three layers, two buses, and
two sub-functional systems." Results show that the cloud
data management system performs the four core functions
of model, data bus, data service bus, and data quality
control management. Furthermore, integrating cloud
computing into the transformation and upgrading of
traditional industries is feasible and applicable to other
related fields.Read MoreRead Less
AbstractWeb 3.0 and social bookmarking have
altered the traditional roles of the indexer and user.
Recently, web, allows users to create, organize, and
search for images and other information sources through
social tagging and other method activities. One of the
image social bookmarking is such as Flickr. This
research examines to increase the efficiency of image
search result by creating indexes. The assumption of the
experiment is a...Web 3.0 and social bookmarking have
altered the traditional roles of the indexer and user.
Recently, web, allows users to create, organize, and
search for images and other information sources through
social tagging and other method activities. One of the
image social bookmarking is such as Flickr. This
research examines to increase the efficiency of image
search result by creating indexes. The assumption of the
experiment is a combination of social tagging and other
factor such as image description that can improve web
performance. Therefore, three indexers were created and
were compared with the search results between a search
engine using the indexing method of "Description with Tag"
or DT indexer, "Posted Time With Tag" or PT indexer and
the "Tag only" or T indexer which is a native method. The
retrieval performance of this search engine is evaluated
using the mean values of Normalized Discount Cumulative
Gain (NDCG). The result illustrates that the search engine
with indexer using DT indexer provides better indexer using
the T indexer in all the ranks. This primary evaluation in
the experiments proves that the chosen heuristic indexer
can improve the efficiency of the web image searching
on social bookmarking websites.Read MoreRead Less