1,721,202 research outputs found
Computer vision-based vehicle recognition system using deep learning techniques / Tan Shi Hao
No full textVehicle recognition is essential for Intelligent Transportation System (ITS) in creating a comfortable commuting environment. It is the enabler for a diverse range of applications, including roadway maintenance, surveillance systems, electronic tolls, etc. With the aim of improving vehicle type and vehicle make and model recognition (VMMR) performance, the past studies are collated and a vehicle taxonomy that encompasses sensor-based and Computer Vision (CV)-based solutions is deliberated. Motivated to learn superior convolution filters, the first proposal employs Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) as filter learning techniques. The proposed network dubbed PCA-LDA-Convolutional Neural Network (CNN) also incorporates a parameter-free Channel-Based Attention Module (ChBAM) to tune the feature responses guided by the channel information saliency. The framework delivers 99.6% and 97.8% accuracies on datasets with 30 and 300 vehicle models, respectively. The robustness tests verify that PCA-LDA-CNN is steadfast against image distortions. Secondly, the past studies reveal that neglecting the degree of informativeness cripples the quality of representation learning. In this regard, a Spatial Attention Module (SAM), which is empowered by Multi-Head Self-Attention (MHSA), is proposed to scale the feature responses by exploiting spatial relevancy. The proposed ResNet50-SAM model records exceptional performance on Beijing Institute of Technology (BIT)- Vehicle, Stanford Cars and Web-Nature Comprehensive Cars (CompCarsWeb) datasets by reporting 98.2%, 84.5% and 96.0% accuracies, respectively. A qualitative inspection of the feature embeddings suggests high cohesivity within the group. Integrating SAM into other CNNs also leads to considerable improvements. Next, forgoing the low-level details and concentrating on high-level features is detrimental to VMMR. The Cross Granularity (CG) module, in contrast, integrates both information to render a balanced mix of local contextual information and global semantic details. The combination of ResNet50 and CG module attains 98.6%, 95.4%, 86.4% and 99.1% accuracies on CompCarsWeb, Stanford Cars, Car-FG3K and Surveillance-Nature Comprehensive Cars (CompCarsSV) datasets, respectively. The qualitative analysis further unveils its strong ability to locate the distinctive fine-grained vehicle details. The CG module is also highly compatible with various backbone CNNs. As the fourth proposal, the Coarse-to-Fine Context Aggregation (CFCA) module presents a parameter-efficient multi-scale feature learning paradigm. The cross-scale features are generated by first refining the scalespecific components independently and then fusing them in a nonlinear manner through convolution. The multi-scale feature maps produce 98.0%, 95.1%, 86.2%, 99.0%, and 96.9% accuracies on CompCarsWeb, Stanford Cars, Car-FG3K, CompCarsSV and Mohsin-VMMR datasets, respectively. Moreover, the neurons exhibit high feature responses on the discriminative vehicle parts, corresponding to the superior feature extraction ability of the CFCA module. The fifth proposal presents an Augmented- Granularity (AG) module that executes grouped focus convolution (GFConv) to compose multi-granularity features. With the spatial-to-channel transformation, the GFConv doubles the receptive field whilst mitigating information loss. When pairing the AG module with TResNet-L, the network claims 87.8%, 95.5%, 98.6% and 92.5% on Car- FG3K, Stanford Cars, CompCarsWeb and VMMRdb datasets, respectively. The dissection of the feature embeddings affirms the ability of the AG module to reduce the intraclass variance. The AG module also brings 2.7% accuracy improvements in average for 4 backbone CNNs
Comparative genome analysis and evolutionary study of human pathogenic Yersinia species / Tan Shi Yang
Full text linkYersinia is a Gram-negative bacterial genus that includes serious pathogens such as the
Yersinia pestis which causes plague, and Yersinia pseudotuberculosis and Yersinia
enterocolitica which cause gastrointestinal infections. The remaining species are
generally considered to be non-pathogenic to humans. While their virulence mechanisms
are well-characterized, the evolution of Yersinia pathogens are not well-understood. To
understand the evolution of Yersinia pathogens and Yersinia enterocolitica subspecies,
an exhaustive evolutionary and comparative genome studies on a total of 86 Yersinia
genomes using different bioinformatics approaches were performed. Based on
phylogenetic and the gene gain-and-loss analyses, Yersinia enterocolitica and Yersinia
pseudotuberculosis-Yersinia pestis were determined as belonging to different
phylogroups and have acquired different set of metabolism genes, suggesting that the
evolution of human pathogenic Yersinia species is most probably triggered by ecological
specialization. Besides, pairwise sequence comparisons showed that the ail virulence
gene of Yersinia enterocolitica had higher sequence identities to the ail gene family
(consists of both ail gene and homologs in the same family) of Yersinia
pseudotuberculosis-Yersinia pestis compared to its own ail homolog, suggesting that the
ail gene might have been duplicated in the latter species and then transferred laterally to
Yersinia enterocolitica. Taken all together, it is proposed that the evolution of Yersinia
is not in parallel, but rather accompanied by the gene gain-and-loss, gene duplication and
lateral gene transfer. This contradicts finding of previous study that suggested the human
pathogenic Yersinia species might have evolved in parallel to acquire the same virulence
determinants. On the other hand, phylogenetic tree and gene gain-and-loss analyses in this study showed
that Yersinia enterocolitica strains could be demarcated into three distinct phylogroups,with each of them acquiring different sets of putative metabolism genes. This postulates
that ecological specialization might have triggered subspeciations in Yersinia
enterocolitica species and lead to the emergence of highly pathogenic, low pathogenic
and non-pathogenic subspecies, instead of two subspecies as previously reported. Data
gathered in this study also suggest that the lateral gene transfer between subspecies in
Yersinia enterocolitica might not be extensive as the gene content-based phylogenetic
tree highly resembled supermatrix tree. Further virulence gene analyses showed that the
ail gene was pseudogenized in the non-pathogenic subspecies, probably causing the loss
of pYV virulence plasmid and pathogenicity in this subspecies.
To facilitate the ongoing and future research of Yersinia, YersiniaBase, a robust and userfriendly
Yersinia resource and comparative analysis platform for analysing Yersinia
genomic data was developed. The AJAX-based real-time searching system was
implemented to smooth the process of searching genomic data in large databases.
YersiniaBase also has in-house developed tools: (1) Pairwise Genome Comparison tool
for comparing two user-selected genomes; (2) Pathogenomics Profiling Tool for
comparative virulence gene analysis of Yersinia genomes; (3) YersiniaTree for
constructing phylogenetic tree of Yersinia. Successful applications of these useful tools
was demonstrated in this study.
Overall, this study provides better insights in elucidating the evolution of human
pathogenic Yersinia and subspeciation in Yersinia enterocolitica. Lastly, the
YersiniaBase will offer invaluable Yersinia genomic resource and analysis platform for
the analysis of Yersinia in the future
Character network analysis of two science fiction Series – stargate and Star Trek / Melody Tan Shi Ai
Full text linkThis work undertakes a social network analysis of two science fiction franchise, Stargate and Star Trek. These two franchise consist of several television series and movies. Social network analysis is used to explore the social network of characters, derived from the transcripts. The stories conveyed are in the form of the interactions of characters, which can be represented as “character networks”. The character networks are formed by extracting the social interactions or connectivity of the characters. That is, the co-occurrences of the characters from a specific scene demarcates the presence of a connection irrespective of exchange of spoken dialogue. These networks are then used to characterise the overall structure and topology of each franchise. The character networks of both franchise have similar structure and topology to that found in previous work on scientific collaborations, literature, mythology and comics networks. The character networks exhibit the small-world effect and is disassortative, but no significant support for power-law distribution was found. Furthermore, since the progression of a story depends to a large extent on the interaction between each of its characters, the underlying network structure relates something about the complexity of the storyline. The complexity is assessed using techniques from spectral graph theory. The episode networks are found to be structured either as (1) closed networks, (2) those containing bottlenecks, (3) a mixture of the first two structures, or (4) those containing two or more connected components. Lastly, the characters’ role in the narrative was found to be supported by the characters’ centrality and centralisation measures
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Dispelling the Myths Behind First-author Citation Counts
Full text linkWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
koamabayili/VECTRON-author-checklist: VECTRON author checklist
No full textWe have done our best to complete the author checklist relating to the use of animals in the hut study. Note that the objective for the hut study was to evaluate the IRS treatment applications for residual efficacy against Anopheles mosquitoes, including the local An. coluzzii mosquito population. Cows were only used to attract mosquitoes into the huts and no tests were carried out directly on the cows. The author checklist is intended for use with studies where experiments are carried out on animals, which is why we have had such difficulty in completing this for the hut study, as many of the questions do not relate to how the cows were used
- …
