Search results for: state-space vectors

Authors: Maria C. Proença, Maria T. Rebelo, Maria J. Alves, Sofia Cunha

Abstract:

Vector-borne diseases are transmitted to humans by mosquitos, sandflies, bugs, ticks, and other vectors. Some are re-transmitted between vectors, if the infected human has a new contact when his levels of infection are high. The vector is infected for lifetime and can transmit infectious diseases not only between humans but also from animals to humans. Some vector borne diseases are very disabling and globally account for more than one million deaths worldwide. The mosquitoes from the complex Culex pipiens sl. are the most abundant in Portugal, and we dispose in this moment of a data set from the surveillance program that has been carried on since 2006 across the country. All mosquitos’ species are included, but the large coverage of Culex pipiens sl. and its importance for public health make this vector an interesting candidate to assess risk of disease amplification. This work focus on ports and airports identified as key areas of high density of vectors. Mosquitoes being ectothermic organisms, the main factor for vector survival and pathogen development is temperature. Minima and maxima local air temperatures for each area of interest are averaged by month from data gathered on a daily basis at the national network of meteorological stations, and interpolated in a geographic information system (GIS). The range of temperatures ideal for several pathogens are known and this work shows how to use it with the meteorological data in each port and airport facility, to focus an efficient implementation of countermeasures and reduce simultaneously risk transmission and mitigation costs. The results show an increased alert with decreasing latitude, which corresponds to higher minimum and maximum temperatures and a lower amplitude range of the daily temperature.

Keywords: human health, risk assessment, risk management, vector-borne diseases

Procedia PDF Downloads 370

Authors: Bowen Ding, Yihao Kuang

Abstract:

In recent years, with the development of large-scale pre-trained lan-guage models, building vector representations of text through deep neural network models has become a standard practice for natural language processing tasks. From the performance on downstream tasks, we can know that the text representation constructed by these models contains linguistic information, but its encoding mode and extent are unclear. In this work, a structural probe is proposed to detect whether the vector representation produced by a deep neural network is embedded with a syntax tree. The probe is trained with the deep metric learning method, so that the distance between word vectors in the metric space it defines encodes the distance of words on the syntax tree, and the norm of word vectors encodes the depth of words on the syntax tree. The experiment results on ELMo and BERT show that the syntax tree is encoded in their parameters and the word representations they produce.

Keywords: deep metric learning, syntax tree probing, natural language processing, word representations

Procedia PDF Downloads 32

Authors: Yuya Tanigami, Naoaki Yamanaka, Satoru Okamoto

Abstract:

Economic losses due to delays in traffic congestion regarding urban transportation networks have become a more serious social problem as traffic volume increases. Platooning has recently been attracting attention from many researchers to alleviate traffic jams, especially on the highway. On highways, platooning can have positive effects, such as reducing inter-vehicular distance and reducing air resistance. However, the impacts of platooning on urban roads have not been addressed in detail since traffic lights may break the platoons. In this study, we propose a platooning method using L2 norm and cosine similarity to form a platoon with highly similar routes. Also, we investigate the sorting method within a platoon according to each vehicle’s straightness. Our proposed sorting platoon method, which uses two lanes, eliminates Head of Line Blocking at the intersection and improves throughput at intersections. This paper proposes a cyber-physical system (CPS) approach to collaborative urban platoon control. We conduct simulations using the traffic simulator SUMO and the road network, which imitates Manhattan Island. Results from the SUMO confirmed that our method shortens the average travel time by 10-20%. This paper shows the validity of forming a platoon based on destination vectors and sorting vehicles within a platoon.

Keywords: CPS, platooning, connected car, vector correlation

Procedia PDF Downloads 51

Authors: Maria Teresa Signes Pont, Jose Juan Cortes Plana

Abstract:

Our proposal provides suitable modelling to the spread of plant pest and particularly to the propagation of Xylella fastidiosa in the almond trees. We compared the impact of temperature and humidity on the propagation of Xylella fastidiosa in various subspecies. Comparison between Balearic Islands and Alicante (Spain). Most sharpshooter and spittlebug species showed peaks in population density during the month of higher mean temperature and relative humidity (April-October), except for the splittlebug Clastoptera sp.1, whose adult population peaked from September-October (late summer and early autumn). The critical season is from when they hatch from the eggs until they are in the pre-reproductive season (January -April) to expand. We focused on winters in the egg state, which normally hatches in early March. The nymphs secrete a foam (mucilage) in which they live and that protects them from natural enemies of temperature changes and prevents dry as long as the humidity is above 75%. The interaction between the life cycles of vectors and vegetation influences the food preferences of vectors and is responsible for the general seasonal shift of the population from vegetation to trees and vice versa, In addition to the temperature maps, we have observed humidity as it affects the spread of the pest Xylella fastidiosa (Xf).

Keywords: xylella fastidiosa, almod tree, temperature, humidity, environmental model

Procedia PDF Downloads 138

Authors: Ganfeng Yu, Yuefeng Ma, Shanliang Yang

Abstract:

The word discovery is a key problem in text information retrieval technology. Methods in new word discovery tend to be closely related to words because they generally obtain new word results by analyzing words. With the popularity of social networks, individual netizens and online self-media have generated various network texts for the convenience of online life, including network words that are far from standard Chinese expression. How detect network words is one of the important goals in the field of text information retrieval today. In this paper, we integrate the word embedding model and clustering methods to propose a network word discovery framework based on sentence semantic similarity (S³-NWD) to detect network words effectively from the corpus. This framework constructs sentence semantic vectors through a distributed representation model, uses the similarity of sentence semantic vectors to determine the semantic relationship between sentences, and finally realizes network word discovery by the meaning of semantic replacement between sentences. The experiment verifies that the framework not only completes the rapid discovery of network words but also realizes the standard word meaning of the discovery of network words, which reflects the effectiveness of our work.

Keywords: text information retrieval, natural language processing, new word discovery, information extraction

Procedia PDF Downloads 62

Authors: Chao He, Shunhua Zhou, Peijun Guo

Abstract:

The vast majority of existing underground railway lines consist of twin tunnels. In this paper, the dynamic interaction between two neighboring tunnels in a layered half-space is investigated by an analytical model. The two tunnels are modelled as cylindrical thin shells, while the soil in the form of a layered half-space with two cylindrical cavities is simulated by the elastic continuum theory. The transfer matrix method is first used to derive the relationship between the plane wave vectors in arbitrary layers and the source layer. Thereafter, the wave translation and transformation are introduced to determine the plane and cylindrical wave vectors in the source layer. The solution for the dynamic interaction between twin tunnels in a layered half-space is obtained by means of the compatibility of displacements and equilibrium of stresses on the two tunnel–soil interfaces. By coupling the proposed model with a fully track model, the train-induced vibrations from twin tunnels in a multi-layered half-space are investigated. The numerical results demonstrate that the existence of a neighboring tunnel has a significant effect on ground vibrations.

Keywords: underground railway, twin tunnels, wave translation and transformation, transfer matrix method

Procedia PDF Downloads 87

Authors: Bowen Ding, Yihao Kuang

Abstract:

In recent years, large-scale pre-trained language models have achieved state-of-the-art performance on a variety of natural language processing tasks. The word vectors produced by these language models can be viewed as dense encoded presentations of natural language that in text form. However, it is unknown how much linguistic information is encoded and how. In this paper, we construct several corresponding probing tasks for multiple linguistic information to clarify the encoding capabilities of different language models and performed a visual display. We firstly obtain word presentations in vector form from different language models, including BERT, ELMo, RoBERTa and GPT. Classifiers with a small scale of parameters and unsupervised tasks are then applied on these word vectors to discriminate their capability to encode corresponding linguistic information. The constructed probe tasks contain both semantic and syntactic aspects. The semantic aspect includes the ability of the model to understand semantic entities such as numbers, time, and characters, and the grammatical aspect includes the ability of the language model to understand grammatical structures such as dependency relationships and reference relationships. We also compare encoding capabilities of different layers in the same language model to infer how linguistic information is encoded in the model.

Keywords: language models, probing task, text presentation, linguistic information

Procedia PDF Downloads 69

Authors: Majid Habib Khan, Jinwei Zhao, Xinhong Hei, Liu Jiedong, Rana Shahzad Noor, Muhammad Imran

Abstract:

Deep learning is increasingly employed in image classification, yet the scarcity and high cost of labeled data for training remain a challenge. Limited samples often lead to overfitting due to biased sample distribution. This paper introduces a dynamic distribution calibration method for few-shot learning. Initially, base and new class samples undergo normalization to mitigate disparate feature magnitudes. A pre-trained model then extracts feature vectors from both classes. The method dynamically selects distribution characteristics from base classes (both adjacent and remote) in the embedding space, using a threshold value approach for new class samples. Given the propensity of similar classes to share feature distributions like mean and variance, this research assumes a Gaussian distribution for feature vectors. Subsequently, distributional features of new class samples are calibrated using a corrected hyperparameter, derived from the distribution features of both adjacent and distant base classes. This calibration augments the new class sample set. The technique demonstrates significant improvements, with up to 4% accuracy gains in few-shot classification challenges, as evidenced by tests on miniImagenet and CUB datasets.

Keywords: deep learning, computer vision, image classification, few-shot learning, threshold

Procedia PDF Downloads 31

Authors: Koon Weng Lau, Chee Dhang Chen, Abdul Aziz Azidah, Mohd Sofian-Azirun

Abstract:

Recently, Sarawak state of Malaysia encounter an outbreak of dengue fever. Aedes albopictus has incriminated as one of the important vectors of dengue transmission. Without an effective vaccine, approaches to control or prevent dengue will be a focus on the vectors. The control of Aedes mosquitoes is still dependent on the use of chemical insecticides and insecticide resistance represents a threat to the effectiveness of vector control. This study was conducted to determine the resistance status of 11 active ingredients representing four major insecticide classes: DDT, dieldrin, malathion, fenitrothion, bendiocarb, propoxur, etofenprox, deltamethrin, lambda-cyhalothrin, cyfluthrin, and permethrin. Standard WHO test procedures were conducted to determine the insecticide susceptibility. Aedes albopictus collected from Kapit (resistance ratio, RR = 1.04–3.02), Kuching (RR = 1.17–4.61), and Sibu (RR = 1.06–3.59) exhibited low resistance toward all insecticides except dieldrin. This study reveled that dieldrin is still effective against Ae. albopictus, followed by fenitrothion, cyfluthrin, and deltamethrin. In conclusion, Ae. albopictus in Sarawak exhibited different resistance levels toward various insecticides and alternative solutions should be implemented to prevent further deterioration of the condition.

Keywords: Aedes albopictus, dengue, insecticide resistance, Malaysia

Procedia PDF Downloads 325

Authors: Monika Soni, Chandra Bhattacharya, Siraj Ahmed Ahmed, Prafulla Dutta

Abstract:

Dengue is now a globally important arboviral disease. Extensive vector surveillance has already established A.aegypti as a primary vector, but A.albopictus is now accelerating the situation through gradual adaptation to human surroundings. Global destabilization and gradual climatic shift with rising in temperature have significantly expanded the geographic range of these species These versatile vectors also host Chikungunya, Zika, and yellow fever virus. Biggest challenge faced by endemic countries now is upsurge in co-infection reported with multiple serotypes and virus co-circulation. To foster vector control interventions and mitigate disease burden, there is surge for knowledge on vector susceptibility and viral tolerance in response to multiple infections. To address our understanding on transmission dynamics and reproductive fitness, both the vectors were exposed to single and dual combinations of all four dengue serotypes by artificial feeding and followed up to third generation. Artificial feeding observed significant difference in feeding rate for both the species where A.albopictus was poor artificial feeder (35-50%) compared to A.aegypti (95-97%) Robust sequential screening of viral antigen in mosquitoes was followed by Dengue NS1 ELISA, RT-PCR and Quantitative PCR. To observe viral dissemination in different mosquito tissues Indirect immunofluorescence assay was performed. Result showed that both the vectors were infected initially with all dengue(1-4)serotypes and its co-infection (D1 and D2, D1 and D3, D1 and D4, D2 and D4) combinations. In case of DENV-2 there was significant difference in the peak titer observed at 16th day post infection. But when exposed to dual infections A.aegypti supported all combinations of virus where A.albopictus only continued single infections in successive days. There was a significant negative effect on the fecundity and fertility of both the vectors compared to control (PANOVA < 0.001). In case of dengue 2 infected mosquito, fecundity in parent generation was significantly higher (PBonferroni < 0.001) for A.albopicus compare to A.aegypti but there was a complete loss of fecundity from second to third generation for A.albopictus. It was observed that A.aegypti becomes infected with multiple serotypes frequently even at low viral titres compared to A.albopictus. Possible reason for this could be the presence of wolbachia infection in A.albopictus or mosquito innate immune response, small RNA interference etc. Based on the observations it could be anticipated that transovarial transmission may not be an important phenomenon for clinical disease outcome, due to the absence of viral positivity by third generation. Also, Dengue NS1 ELISA can be used for preliminary viral detection in mosquitoes as more than 90% of the samples were found positive compared to RT-PCR and viral load estimation.

Keywords: co-infection, dengue, reproductive fitness, viral quantification

Procedia PDF Downloads 176

Authors: Samuel Matylewicz, K. W. Goossen

Abstract:

The deployment of white or cool (high albedo) roofing is a common energy savings recommendation for a variety of buildings all over the world. Here, the effect of a white roof on the energy savings of an ice rink facility in the northeastern US is determined by measuring the effect of solar irradiance on the consumption of the rink's ice refrigeration system. The consumption of the refrigeration system was logged over a year, along with multiple weather vectors, and a statistical model was applied. The experimental model indicates that the expected savings of replacing the existing grey roof with a white roof on the consumption of the refrigeration system is only 4.7 %. This overall result of the statistical model is confirmed with isolated instances of otherwise similar weather days, but cloudy vs. sunny, where there was no measurable difference in refrigeration consumption up to the noise in the local data, which was a few percent. This compares with a simple theoretical calculation that indicates 30% savings. The difference is attributed to a lack of convective cooling of the roof in the theoretical model. The best experimental model shows a relative effect of the weather vectors dry bulb temperature, solar irradiance, wind speed, and relative humidity on refrigeration consumption of 1, 0.026, 0.163, and -0.056, respectively. This result can have an impact on decisions to apply white roofing to refrigerated buildings in general.

Keywords: cool roofs, solar cooling load, refrigerated buildings, energy-efficient building envelopes

Procedia PDF Downloads 104

Authors: Kumaran Narayanan, Pei-Sheng Liew

Abstract:

This paper adapts the bacteriophage N15 protelomerase enzyme to assemble linear chromosomes as vectors for gene expression in human cells. Phage N15 has the unique ability to replicate as a linear plasmid with telomeres in E. coli during its prophage stage of life-cycle. The virus-encoded protelomerase enzyme cuts its circular genome and caps its ends to form hairpin telomeres, resulting in a linear human-chromosome-like structure in E. coli. In mammalian cells, however, no enzyme with TelN-like activities has been found. In this work, we show for the first-time transfer of the protelomerase from phage into human and mouse cells and demonstrate recapitulation of its activity in these hosts. The function of this enzyme is assayed by demonstrating cleavage of its target DNA, followed by detecting telomere formation based on its resistance to recBCD enzyme digestion. We show protelomerase expression persists for at least 60 days, which indicates limited silencing of its expression. Next, we show that an intact human β-globin gene delivered on this linear chromosome accurately retains its expression in the human cellular environment for at least 60 hours, demonstrating its stability and potential as a vector. These results demonstrate that the N15 protelomerse is able to function in mammalian cells to cut and heal DNA to create telomeres, which provides a new tool for creating novel structures by DNA resolution in these hosts.

Keywords: chromosome, beta-globin, DNA, gene expression, linear vector

Procedia PDF Downloads 163

Authors: Shohei Maruyama, Yasuo Matsuyama, Sachiyo Aburatani

Abstract:

The development of the method to annotate unknown gene functions is an important task in bioinformatics. One of the approaches for the annotation is The identification of the metabolic pathway that genes are involved in. Gene expression data have been utilized for the identification, since gene expression data reflect various intracellular phenomena. However, it has been difficult to estimate the gene function with high accuracy. It is considered that the low accuracy of the estimation is caused by the difficulty of accurately measuring a gene expression. Even though they are measured under the same condition, the gene expressions will vary usually. In this study, we proposed a feature extraction method focusing on the variability of gene expressions to estimate the genes' metabolic pathway accurately. First, we estimated the distribution of each gene expression from replicate data. Next, we calculated the similarity between all gene pairs by KL divergence, which is a method for calculating the similarity between distributions. Finally, we utilized the similarity vectors as feature vectors and trained the multiclass SVM for identifying the genes' metabolic pathway. To evaluate our developed method, we applied the method to budding yeast and trained the multiclass SVM for identifying the seven metabolic pathways. As a result, the accuracy that calculated by our developed method was higher than the one that calculated from the raw gene expression data. Thus, our developed method combined with KL divergence is useful for identifying the genes' metabolic pathway.

Keywords: metabolic pathways, gene expression data, microarray, Kullback–Leibler divergence, KL divergence, support vector machines, SVM, machine learning

Procedia PDF Downloads 376

Authors: Matthew Baucum

Abstract:

With the increasing popularity of fMRI as an experimental method, psychology and neuroscience can greatly benefit from advanced techniques for summarizing and synthesizing large amounts of data from brain imaging studies. One promising avenue is automated meta-analyses, in which natural language processing methods are used to identify the brain regions consistently associated with certain semantic concepts (e.g. “social”, “reward’) across large corpora of studies. This study builds on this approach by demonstrating how, in fMRI meta-analyses, individual voxels can be treated as vectors in a semantic space and evaluated for their “proximity” to terms of interest. In this technique, a low-dimensional semantic space is built from brain imaging study texts, allowing words in each text to be represented as vectors (where words that frequently appear together are near each other in the semantic space). Consequently, each voxel in a brain mask can be represented as a normalized vector sum of all of the words in the studies that showed activation in that voxel. The entire brain mask can then be visualized in terms of each voxel’s proximity to a given term of interest (e.g., “vision”, “decision making”) or collection of terms (e.g., “theory of mind”, “social”, “agent”), as measured by the cosine similarity between the voxel’s vector and the term vector (or the average of multiple term vectors). Analysis can also proceed in the opposite direction, allowing word cloud visualizations of the nearest semantic neighbors for a given brain region. This approach allows for continuous, fine-grained metrics of voxel-term associations, and relies on state-of-the-art “open vocabulary” methods that go beyond mere word-counts. An analysis of over 11,000 neuroimaging studies from an existing meta-analytic fMRI database demonstrates that this technique can be used to recover known neural bases for multiple psychological functions, suggesting this method’s utility for efficient, high-level meta-analyses of localized brain function. While automated text analytic methods are no replacement for deliberate, manual meta-analyses, they seem to show promise for the efficient aggregation of large bodies of scientific knowledge, at least on a relatively general level.

Keywords: FMRI, machine learning, meta-analysis, text analysis

Procedia PDF Downloads 421

Authors: Hajar Hosseini Khorami

Abstract:

Porphyrins are organic, aromatic compounds found in heme, cytochrome, cobalamin, chlorophyll , and many other natural products with essential roles in biological processes that their cationic forms have been used as groups of favorable non-viral vectors recently. Cationic porphyrins are self-chromogenic reagents with a high capacity for modifications, great interaction with DNA and protection of DNA from nuclease during delivery of it into a cell with low toxicity. In order to have high efficient gene transfection into the cell while causing low toxicity, genetically manipulations of the non-viral vector, cationic porphyrin, would be useful. In this study newly modified cationic porphyrin derivative, 5, 10-dihexyl-15, 20bis (N-methyl-4-pyridyl) porphyrin was applied. Cytotoxicity of synthesized cationic porphyrin on Chinese Hamster Ovarian (CHO) cells was evaluated by using MTT assay. This cationic derivative is dose-dependent, with low cytotoxicity at the ranges from 100 μM to 0.01μM. It was uptake by cells at high concentration. Using direct non-viral gene transfection method and different concentration of cationic porphyrin were tested on transfection of CHO cells by applying derived transfection reagent with X-tremeGENE HP DNA as a positive control. However, no transfection observed by porphyrin derivative and the parameters tested except for positive control. Results of this study suggested that applying different protocol, and also trying other concentration of cationic porphyrins and DNA for forming a strong complex would increase the possibility of efficient gene transfection by using cationic porphyrins.

Keywords: cationic porphyrins, gene delivery, non-viral vectors, transfection reagents

Procedia PDF Downloads 170

Authors: Samina Jam Nazeer Ahmad, Samia Yasin, Ijaz Ahmad, Muhammad Tahir, Jam Nazeer Ahmad

Abstract:

Phytoplasmas are phloem-inhibited plant pathogenic bacteria that are transferred by insect vectors. Among biotic factors, Phytoplasma infection induces abnormality influencing the physiology as well as morphology of plants. In 16Sr-IX group phytoplasma-infected brassica compestris, flower abnormalities have been associated with changes in the expression of floral development genes. To determine whether methylation was involved in down-regulation of flower development, the process of DNA methylation and Demethylation was investigated as a possible mechanism for regulation of floral gene expression in phytoplasma infected Brassica transmitted by Orosious orientalis vector by using RT-PCR, MSRE-PCR, Southern blotting, Bisulfite Sequencing, etc. Transcriptional expression of methylated genes was found to be globally down-regulated in plants infected with phytoplasma, but not severely in those infested by insect vectors and variation in expression was found in genes involved in methylation. These results also showed that genes particularly orthologous to Arabidopsis APETALA3 involved in petal formation and flower development was down-regulated severely in phytoplasma-infected brassica and with the fact that phytoplasma and insect induce variation in developmental gene expression. The DNA methylation status of flower developmental gene in phytoplasma infected plants with 5-azacytidine restored gene expression strongly suggesting that DNA methylation was involved in down-regulation of floral development genes in phytoplasma infected brassica.

Keywords: genes expression, phytoplasma, DNA methylation, flower development

Procedia PDF Downloads 339

Authors: Rohit Gupta, Ravinder Agarwal

Abstract:

Surface electromyographic (sEMG) signal has the potential to identify the human activities and intention. This potential is further exploited to control the artificial limbs using the sEMG signal from residual limbs of amputees. The paper deals with the development of multichannel cost efficient sEMG signal interface for research application, along with evaluation of proposed class dependent statistical approach of the feature selection method. The sEMG signal acquisition interface was developed using ADS1298 of Texas Instruments, which is a front-end interface integrated circuit for ECG application. Further, the sEMG signal is recorded from two lower limb muscles for three locomotions namely: Plane Walk (PW), Stair Ascending (SA), Stair Descending (SD). A class dependent statistical approach is proposed for feature selection and also its performance is compared with 12 preexisting feature vectors. To make the study more extensive, performance of five different types of classifiers are compared. The outcome of the current piece of work proves the suitability of the proposed feature selection algorithm for locomotion recognition, as compared to other existing feature vectors. The SVM Classifier is found as the outperformed classifier among compared classifiers with an average recognition accuracy of 97.40%. Feature vector selection emerges as the most dominant factor affecting the classification performance as it holds 51.51% of the total variance in classification accuracy. The results demonstrate the potentials of the developed sEMG signal acquisition interface along with the proposed feature selection algorithm.

Keywords: classifiers, feature selection, locomotion, sEMG

Procedia PDF Downloads 267

Authors: Xu Jiaqiao

Abstract:

Text sentiment analysis is an important branch of natural language processing. This technology is widely used in public opinion analysis and web surfing recommendations. At present, the mainstream sentiment analysis methods include three parts: sentiment analysis based on a sentiment dictionary, based on traditional machine learning, and based on deep learning. This paper mainly analyzes and compares the advantages and disadvantages of the SVM method of traditional machine learning and the Long Short-term Memory (LSTM) method of deep learning in the field of Chinese sentiment analysis, using Chinese comments on Sina Microblog as the data set. Firstly, this paper classifies and adds labels to the original comment dataset obtained by the web crawler, and then uses Jieba word segmentation to classify the original dataset and remove stop words. After that, this paper extracts text feature vectors and builds document word vectors to facilitate the training of the model. Finally, SVM and LSTM models are trained respectively. After accuracy calculation, it can be obtained that the accuracy of the LSTM model is 85.80%, while the accuracy of SVM is 91.07%. But at the same time, LSTM operation only needs 2.57 seconds, SVM model needs 6.06 seconds. Therefore, this paper concludes that: compared with the SVM model, the LSTM model is worse in accuracy but faster in processing speed.

Keywords: sentiment analysis, support vector machine, long short-term memory, Chinese microblog comments

Procedia PDF Downloads 61

Authors: H. G. C. P. Dinesh, G. Tharshini, M. P. B. Ekanayake, G. M. R. I. Godaliyadda

Abstract:

This paper presents a new spatial feature extraction method based on principle component analysis (PCA) and Fisher Discernment Analysis (FDA) for facial expression recognition. It not only extracts reliable features for classification, but also reduces the feature space dimensions of pattern samples. In this method, first each gray scale image is considered in its entirety as the measurement matrix. Then, principle components (PCs) of row vectors of this matrix and variance of these row vectors along PCs are estimated. Therefore, this method would ensure the preservation of spatial information of the facial image. Afterwards, by incorporating the spectral information of the eigen-filters derived from the PCs, a feature vector was constructed, for a given image. Finally, FDA was used to define a set of basis in a reduced dimension subspace such that the optimal clustering is achieved. The method of FDA defines an inter-class scatter matrix and intra-class scatter matrix to enhance the compactness of each cluster while maximizing the distance between cluster marginal points. In order to matching the test image with the training set, a cosine similarity based Bayesian classification was used. The proposed method was tested on the Cohn-Kanade database and JAFFE database. It was observed that the proposed method which incorporates spatial information to construct an optimal feature space outperforms the standard PCA and FDA based methods.

Keywords: facial expression recognition, principle component analysis (PCA), fisher discernment analysis (FDA), eigen-filter, cosine similarity, bayesian classifier, f-measure

Procedia PDF Downloads 401

Authors: Sandra Mitrovic, Gaurav Singh

Abstract:

In many industries, including telecommunications, churn prediction has been a topic of active research. A lot of attention has been drawn on devising the most informative features, and this area of research has gained even more focus with spread of (social) network analytics. The call detail records (CDRs) have been used to construct customer networks and extract potentially useful features. However, to the best of our knowledge, no studies including network features have yet proposed a generic way of representing network information. Instead, ad-hoc and dataset dependent solutions have been suggested. In this work, we build upon a recently presented method (node2vec) to obtain representations for nodes in observed network. The proposed approach is generic and applicable to any network and domain. Unlike node2vec, which assumes a static network, we consider a dynamic and time-evolving network. To account for this, we propose an approach that constructs the feature representation of each node by generating its node2vec representations at different timestamps, concatenating them and finally compressing using an auto-encoder-like method in order to retain reasonably long and informative feature vectors. We test the proposed method on churn prediction task in telco domain. To predict churners at timestamp ts+1, we construct training and testing datasets consisting of feature vectors from time intervals [t1, ts-1] and [t2, ts] respectively, and use traditional supervised classification models like SVM and Logistic Regression. Observed results show the effectiveness of proposed approach as compared to ad-hoc feature selection based approaches and static node2vec.

Keywords: churn prediction, dynamic networks, node2vec, auto-encoders

Procedia PDF Downloads 288

Authors: S. Teksin, S. Yayla

Abstract:

The aim of the present study was to investigate details of flow structure in downstream of a circular cylinder base mounted on a flat surface in a rectangular duct with the dimensions of 8000 x 1000 x 750 mm in deep water flow for the Reynolds number 2500, 5000 and 7500. A flexible strip was attached to behind the cylinder and compared the bare body. Also, it was analyzed that how boundary layer affects the structure of flow around the cylinder. Diameter of the cylinder was 60 mm and the length of the flexible splitter plate which had a certain modulus of elasticity was 150 mm (L/D=2.5). Time-averaged velocity vectors, vortex contours, streamwise and transverse velocity components were investigated via Particle Image Velocimetry (PIV). Velocity vectors and vortex contours were displayed through the sections in which boundary layer effect was not present. On the other hand, streamwise and transverse velocity components were monitored for both cases, i.e. with and without boundary layer effect. Experiment results showed that the vortex formation occured in a larger area for L/D=2.5 and the point where the vortex was maximum from the base of the cylinder was shifted. Streamwise and transverse velocity component contours were symmetrical with reference to the center of the cylinder for all cases. All Froud numbers based on the Reynolds numbers were quite smaller than 1. The flow characteristics of velocity component values of attached circular cylinder arrangement decreased approximately twenty five percent comparing to bare cylinder case.

Keywords: partical image velocimetry, elastic plate, cylinder, flow structure

Procedia PDF Downloads 289

Authors: Xiaocong Liu, Huazhen Wang, Ting He, Xiaozheng Li, Weihan Zhang, Jian Chen

Abstract:

The utilization of electronic medical record (EMR) data to establish the disease diagnosis model has become an important research content of biomedical informatics. Deep learning can automatically extract features from the massive data, which brings about breakthroughs in the study of EMR data. The challenge is that deep learning lacks semantic knowledge, which leads to impracticability in medical science. This research proposes a method of incorporating lexical-semantic knowledge from abundant entities into a convolutional neural network (CNN) framework for pediatric disease diagnosis. Firstly, medical terms are vectorized into Lexical Semantic Vectors (LSV), which are concatenated with the embedded word vectors of word2vec to enrich the feature representation. Secondly, the semantic distribution of medical terms serves as Semantic Decision Guide (SDG) for the optimization of deep learning models. The study evaluate the performance of LSV-SDG-CNN model on four kinds of Chinese EMR datasets. Additionally, CNN, LSV-CNN, and SDG-CNN are designed as baseline models for comparison. The experimental results show that LSV-SDG-CNN model outperforms baseline models on four kinds of Chinese EMR datasets. The best configuration of the model yielded an F1 score of 86.20%. The results clearly demonstrate that CNN has been effectively guided and optimized by lexical-semantic knowledge, and LSV-SDG-CNN model improves the disease classification accuracy with a clear margin.

Keywords: convolutional neural network, electronic medical record, feature representation, lexical semantics, semantic decision

Procedia PDF Downloads 107

Authors: Z. Gharaee

Abstract:

Recognizing actions performed by others is important in our daily lives since it is necessary for communicating with others in a proper way. We perceive an action by observing the kinematics of motions involved in the performance. We use our experience and concepts to make a correct recognition of the actions. Although building the action concepts is a life-long process, which is repeated throughout life, we are very efficient in applying our learned concepts in analyzing motions and recognizing actions. Experiments on the subjects observing the actions performed by an actor show that an action is recognized after only about two hundred milliseconds of observation. In this study, hierarchical action recognition architecture is proposed by using growing grid layers. The first-layer growing grid receives the pre-processed data of consecutive 3D postures of joint positions and applies some heuristics during the growth phase to allocate areas of the map by inserting new neurons. As a result of training the first-layer growing grid, action pattern vectors are generated by connecting the elicited activations of the learned map. The ordered vector representation layer receives action pattern vectors to create time-invariant vectors of key elicited activations. Time-invariant vectors are sent to second-layer growing grid for categorization. This grid creates the clusters representing the actions. Finally, one-layer neural network developed by a delta rule labels the action categories in the last layer. System performance has been evaluated in an experiment with the publicly available MSR-Action3D dataset. There are actions performed by using different parts of human body: Hand Clap, Two Hands Wave, Side Boxing, Bend, Forward Kick, Side Kick, Jogging, Tennis Serve, Golf Swing, Pick Up and Throw. The growing grid architecture was trained by applying several random selections of generalization test data fed to the system during on average 100 epochs for each training of the first-layer growing grid and around 75 epochs for each training of the second-layer growing grid. The average generalization test accuracy is 92.6%. A comparison analysis between the performance of growing grid architecture and self-organizing map (SOM) architecture in terms of accuracy and learning speed show that the growing grid architecture is superior to the SOM architecture in action recognition task. The SOM architecture completes learning the same dataset of actions in around 150 epochs for each training of the first-layer SOM while it takes 1200 epochs for each training of the second-layer SOM and it achieves the average recognition accuracy of 90% for generalization test data. In summary, using the growing grid network preserves the fundamental features of SOMs, such as topographic organization of neurons, lateral interactions, the abilities of unsupervised learning and representing high dimensional input space in the lower dimensional maps. The architecture also benefits from an automatic size setting mechanism resulting in higher flexibility and robustness. Moreover, by utilizing growing grids the system automatically obtains a prior knowledge of input space during the growth phase and applies this information to expand the map by inserting new neurons wherever there is high representational demand.

Keywords: action recognition, growing grid, hierarchical architecture, neural networks, system performance

Procedia PDF Downloads 133

Authors: Armin Nabaei, M. Omair Ahmad, M. N. S. Swamy

Abstract:

Many facial expression and emotion recognition methods in the traditional approaches of using LDA, PCA, and EBGM have been proposed. In recent years deep learning models have provided a unique platform addressing by automatically extracting the features for the detection of facial expression and emotions. However, deep networks require large training datasets to extract automatic features effectively. In this work, we propose an efficient emotion detection algorithm using face images when only small datasets are available for training. We design a deep network whose feature extraction capability is enhanced by utilizing several parallel modules between the input and output of the network, each focusing on the extraction of different types of coarse features with fined grained details to break the symmetry of produced information. In fact, we leverage long range dependencies, which is one of the main drawback of CNNs. We develop this work by introducing a Dynamic Soft-Margin SoftMax.The conventional SoftMax suffers from reaching to gold labels very soon, which take the model to over-fitting. Because it’s not able to determine adequately discriminant feature vectors for some variant class labels. We reduced the risk of over-fitting by using a dynamic shape of input tensor instead of static in SoftMax layer with specifying a desired Soft- Margin. In fact, it acts as a controller to how hard the model should work to push dissimilar embedding vectors apart. For the proposed Categorical Loss, by the objective of compacting the same class labels and separating different class labels in the normalized log domain.We select penalty for those predictions with high divergence from ground-truth labels.So, we shorten correct feature vectors and enlarge false prediction tensors, it means we assign more weights for those classes with conjunction to each other (namely, “hard labels to learn”). By doing this work, we constrain the model to generate more discriminate feature vectors for variant class labels. Finally, for the proposed optimizer, our focus is on solving weak convergence of Adam optimizer for a non-convex problem. Our noteworthy optimizer is working by an alternative updating gradient procedure with an exponential weighted moving average function for faster convergence and exploiting a weight decay method to help drastically reducing the learning rate near optima to reach the dominant local minimum. We demonstrate the superiority of our proposed work by surpassing the first rank of three widely used Facial Expression Recognition datasets with 93.30% on FER-2013, and 16% improvement compare to the first rank after 10 years, reaching to 90.73% on RAF-DB, and 100% k-fold average accuracy for CK+ dataset, and shown to provide a top performance to that provided by other networks, which require much larger training datasets.

Keywords: computer vision, facial expression recognition, machine learning, algorithms, depp learning, neural networks

Procedia PDF Downloads 51

Authors: Isaac K. E. Ampomah, Seong-Bae Park, Sang-Jo Lee

Abstract:

Over the past decade, there have been promising developments in Natural Language Processing (NLP) with several investigations of approaches focusing on Recognizing Textual Entailment (RTE). These models include models based on lexical similarities, models based on formal reasoning, and most recently deep neural models. In this paper, we present a sentence encoding model that exploits the sentence-to-sentence relation information for RTE. In terms of sentence modeling, Convolutional neural network (CNN) and recurrent neural networks (RNNs) adopt different approaches. RNNs are known to be well suited for sequence modeling, whilst CNN is suited for the extraction of n-gram features through the filters and can learn ranges of relations via the pooling mechanism. We combine the strength of RNN and CNN as stated above to present a unified model for the RTE task. Our model basically combines relation vectors computed from the phrasal representation of each sentence and final encoded sentence representations. Firstly, we pass each sentence through a convolutional layer to extract a sequence of higher-level phrase representation for each sentence from which the first relation vector is computed. Secondly, the phrasal representation of each sentence from the convolutional layer is fed into a Bidirectional Long Short Term Memory (Bi-LSTM) to obtain the final sentence representations from which a second relation vector is computed. The relations vectors are combined and then used in then used in the same fashion as attention mechanism over the Bi-LSTM outputs to yield the final sentence representations for the classification. Experiment on the Stanford Natural Language Inference (SNLI) corpus suggests that this is a promising technique for RTE.

Keywords: deep neural models, natural language inference, recognizing textual entailment (RTE), sentence-to-sentence relation

Procedia PDF Downloads 323

Authors: Def Primal, Sasanty Kusumaningtyas, Ermita I. Ibrahim

Abstract:

Purpose: The main objective of this study is to determine the pes planus plantaris (flat foot) condition can contribute to the disturbance of postural stability in basketball athletes in static and dynamic activities. Methods: This cross-sectional quantitative analytical retrospective study on 47 subjects of basketball student-athletes identified the foot arch index by extensive footprint area and AMTI (Advanced Mechanical Technology Inc.) Force flat-form (force plate) determined their postural stability. Subjects were conducted in three activities (static, dynamic vertical jump, and dynamic loading response) for ground reaction force (GRF) resultant vectors towards the vertical plane of body mass (W). Results Analytical results obtained that 80.9% of subjects had pes planus plantaris. It shows no significant differences in pes planus plantaris incidence in both sexes subject (p>0.005); however, there are differences in athlete’s exercise period aspect. Athlete students who have practiced strictly for more than four years’ experience over 50% of pes planus plantaris; furthermore, a long period of exercise was believed to stimulate pes planus. The average value of GRF vectors of pes planus plantaris subjects on three different basketball movements shows a significant correlation to postural stability. Conclusions Pes planus plantaris affected almost basketball athletes regarding the length and intensity of exercise performed. The condition significantly contributes to postural stability disturbance on a static condition, dynamic vertical jump, and dynamic vertical jump loading response.

Keywords: pes planus plantaris, flatfoot, ground reaction force, static and dynamic stability

Procedia PDF Downloads 115

Authors: Tekle Olbamo, Tegegn Tesfaye, Dikaso Unbushe, Belete Jorga

Abstract:

Bovine trypanosomosis is a haemoprotozoan parasitic disease, mostly transmitted by the tsetse fly (Glossina species) and poses significant losses to the livestock industry in pastoral and agro-pastoral areas. Therefore, the current study was aimed to determine the prevalence of bovine trypanosomosis and its vectorial density in some selected tsetse suppression and non-tsetse suppression areas of South Omo Zonefrom December 2018- November 2019. Dark phase contrast buffy coat, hematocrit techniques, and thin blood smear method were used for determination of prevalence and packed cell volume of trypanosomosis infection, respectively. For entomological investigation, 96 NGU traps were deployed (64 traps in tsetse suppression areas, 32 traps in tsetse non-suppression areas) in vector breeding areas. The overall prevalence of bovine trypanosomosis was 11.05% (142/1284), and overall seasonal prevalence of disease was 14.33% (92/642) and 7.78% (50/642) for dry and wet seasons, respectively. There was a statistically significant difference (P <0.05) in disease prevalence between the two seasons. Trypanosomacongolensewas the dominant parasite species; 80% and 71.64%, followed by Trypanosomavivax. Overall mean packed cell volume indicated parasitaemic animals (23.57±3.13) had significantly lower PCV than aparasitaemic animals (27.80±4.95), and animals examined during dry season (26.22±4.37) had lower mean PCV than animals examined during wet season with the significant association. Entomological study result revealed a total of 2.64 F/T/D and 2.03 F/T/D respectively from tsetse suppression areas and tsetse non-suppression areas during dry season and 0.42 F/T/D and 0.56 F/T/D during the wet season. Glossinapallidipes was the only cyclical vectors collected and identified from current study areas along with numerous mechanical vectors of genus Tabanus, Stomoxys, and Haematopota. Therefore integrated and safe control and prevention effort should be engaged to uphold cattle production and productivity in the area.

Keywords: bovine trypanosomiasis, South Omo, tsetse fly density, epidemiological study

Procedia PDF Downloads 133

Authors: O. Delage, H. Bencherif, T. Portafaix, A. Bourdier

Abstract:

The main purpose of time series analysis is to learn about the dynamics behind some time ordered measurement data. Two approaches are used in the literature to get a better knowledge of the dynamics contained in observation data sequences. The first of these approaches concerns time series decomposition, which is an important analysis step allowing patterns and behaviors to be extracted as components providing insight into the mechanisms producing the time series. As in many cases, time series are short, noisy, and non-stationary. To provide components which are physically meaningful, methods such as Empirical Mode Decomposition (EMD), Empirical Wavelet Transform (EWT) or, more recently, Empirical Adaptive Wavelet Decomposition (EAWD) have been proposed. The second approach is to reconstruct the dynamics underlying the time series as a trajectory in state space by mapping a time series into a set of Rᵐ lag vectors by using the method of delays (MOD). Takens has proved that the trajectory obtained with the MOD technic is equivalent to the trajectory representing the dynamics behind the original time series. This work introduces the singular spectrum decomposition (SSD), which is a new adaptive method for decomposing non-linear and non-stationary time series in narrow-banded components. This method takes its origin from singular spectrum analysis (SSA), a nonparametric spectral estimation method used for the analysis and prediction of time series. As the first step of SSD is to constitute a trajectory matrix by embedding a one-dimensional time series into a set of lagged vectors, SSD can also be seen as a reconstruction method like MOD. We will first give a brief overview of the existing decomposition methods (EMD-EWT-EAWD). The SSD method will then be described in detail and applied to experimental time series of observations resulting from total columns of ozone measurements. The results obtained will be compared with those provided by the previously mentioned decomposition methods. We will also compare the reconstruction qualities of the observed dynamics obtained from the SSD and MOD methods.

Keywords: time series analysis, adaptive time series decomposition, wavelet, phase space reconstruction, singular spectrum analysis

Procedia PDF Downloads 79

Authors: J. Lamilla-Monje, C. Solano-Puerto, L. Franco-Lara

Abstract:

Trees play an essential role in cities due to their ability to provide multiple ecosystem goods and services. Bogota trees are threatened by factors such as pests, pathogens, contamination, among others. Among the pathogens, phytoplasmas are a potential risk for urban trees, generating symptoms that affect the ecosystem services that these trees provide in Bogota, an example of this is the affectation of Q. humboldtii by phytoplasmas, these bacteria are transmitted for insects of the order Hemiptera, this is why the objective of this work was to know if the climatic variables (humidity, precipitation, and temperature) and environmental variables (PM10 and PM2.5) could be related to the distribution of the Oak Quercus entomofauna and specifically with the phytoplasma vector insects in Bogota. For this study, the sampling points were distributed in areas of the city with contrasting variables in two types of locations: parks and streets. A total of 68 trees were sampled in which the associated insects were collected using two methodologies: jameo and agitation traps. The results show that insects of the order Hemiptera were the most abundant, including a total of 1682 individuals represented by 29 morphotypes, within this order individuals from eight families were collected (Aphidae, Aradidae, Berytidae, Cicadellidae, Issidae, Membracidae, Miridae, and Psyllidae), finding as possible vectors the families Cicadellidae, Membracidae, and Psyllidae with 959, 8 and 14 individuals respectively. Within the Cicadellidae family, 21 morphotypes were found, being reported as vectors in the literature: Amplicephalus, Exitianus atratus, Haldorus sp., Xestocephalus desertorum, Idiocerinae sp., Scaphytopius sp., the Membracidae family was represented by two morphotypes and the Psyllidae by one. Results that suggest that there is no correlation between climatic and environmental variables with the diversity of insects associated with oak. Knowing the vector insects of phytoplasmas in oak trees will complete the pathosystem and generate effective vector control.

Keywords: vector insects, diversity, phytoplasmas, Cicadellidae

Procedia PDF Downloads 124

Authors: Vikas Kumar, Kailash Chandra, Kaomud Tyagi

Abstract:

The insect order Thysanoptera includes small insects commonly called thrips. As insect vectors, only thrips are capable of Tospoviruses transmission (genus Tospovirus, family Bunyaviridae) affecting various crops. Currently, fifteen species of subfamily Thripinae (Thripidae) have been reported as vectors for tospoviruses. Frankliniella schultzei, which is reported as act as a vector for at least five tospovirses, have been suspected to be a species complex with more than one species. It is one of the historical unresolved issues where, two species namely, F. schultzei Trybom and F. sulphurea Schmutz were erected from South Africa and Srilanaka respectively. These two species were considered to be valid until 1968 when sulphurea was treated as colour morph (pale form) and synonymised under schultzei (dark form) However, these two have been considered as valid species by some of the thrips workers. Parallel studies have indicated that brown form of schultzei is a vector for tospoviruses while yellow form is a non-vector. However, recent studies have shown that yellow populations have also been documented as vectors. In view of all these facts, it is highly important to have a clear understanding whether these colour forms represent true species or merely different populations with different vector carrying capacities and whether there is some hidden diversity in 'Frankliniella schultzei species complex'. In this study, we aim to study the 'Frankliniella schultzei species complex' with molecular spectacles with DNA data from India and Australia and Africa. A total of fifty-five specimens was collected from diverse locations in India and Australia. We generated molecular data using partial fragments of mitochondrial cytochrome c oxidase I gene (mtCOI) and 28S rRNA gene. For COI dataset, there were seventy-four sequences, out of which data on fifty-five was generated in the current study and others were retrieved from NCBI. All the four different tree construction methods: neighbor-joining, maximum parsimony, maximum likelihood and Bayesian analysis, yielded the same tree topology and produced five cryptic species with high genetic divergence. For, rDNA, there were forty-five sequences, out of which data on thirty-nine was generated in the current study and others were retrieved from NCBI. The four tree building methods yielded four cryptic species with high bootstrap support value/posterior probability. Here we could not retrieve one cryptic species from South Africa as we could not generate data on rDNA from South Africa and sequence for rDNA from African region were not available in the database. The results of multiple species delimitation methods (barcode index numbers, automatic barcode gap discovery, general mixed Yule-coalescent, and Poisson-tree-processes) also supported the phylogenetic data and produced 5 and 4 Molecular Operational Taxonomic Units (MOTUs) for mtCOI and 28S dataset respectively. These results of our study indicate the likelihood that F. sulphurea may be a valid species, however, more morphological and molecular data is required on specimens from type localities of these two species and comparison with type specimens.

Keywords: DNA barcoding, species complex, thrips, species delimitation

Procedia PDF Downloads 105