Search results for: genetic algorithms

Authors: Milca F. Coelho, K. Bousson, Kawser Ahmed

Abstract:

To accurately track an aerospace vehicle in a time-critical situation and in a highly nonlinear environment, is one of the strongest interests within the aerospace community. The tracking is achieved by estimating accurately the state of a moving target, which is composed of a set of variables that can provide a complete status of the system at a given time. One of the main ingredients for a good estimation performance is the use of efficient estimation algorithms. A well-known framework is the Kalman filtering methods, designed for prediction and estimation problems. The success of the Kalman Filter (KF) in engineering applications is mostly due to the Extended Kalman Filter (EKF), which is based on local linearization. Besides its popularity, the EKF presents several limitations. To address these limitations and as a possible solution to tracking problems, this paper proposes the use of the Ensemble Kalman Filter (EnKF). Although the EnKF is being extensively used in the context of weather forecasting and it is being recognized for producing accurate and computationally effective estimation on systems with a very high dimension, it is almost unknown by the tracking community. The EnKF was initially proposed as an attempt to improve the error covariance calculation, which on the classic Kalman Filter is difficult to implement. Also, in the EnKF method the prediction and analysis error covariances have ensemble representations. These ensembles have sizes which limit the number of degrees of freedom, in a way that the filter error covariance calculations are a lot more practical for modest ensemble sizes. In this paper, a realistic simulation of a radar tracking was performed, where the EnKF was applied and compared with the Extended Kalman Filter. The results suggested that the EnKF is a promising tool for tracking applications, offering more advantages in terms of performance.

Keywords: Kalman filter, nonlinear state estimation, optimal tracking, stochastic environment

Procedia PDF Downloads 112

Authors: Lydia Foucan, Laurent Larifla, Emmanuelle Durand, Christine Rambhojan, Veronique Dhennin, Jean-Marc Lacorte, Philippe Froguel, Amelie Bonnefond

Abstract:

In the population of Guadeloupe Island (472,124 inhabitants and 80% of subjects of African descent), overweight and obesity were estimated at 23% and 9% respectively among children. High prevalence of diabetes has been reported (~10%) in the adult population. Nevertheless, no study has investigated the contribution of gene mutations to childhood obesity in this population. We aimed to investigate rare genetic mutations in genes involved in monogenic obesity or diabetes in obese Afro-Caribbean children from Guadeloupe Island using next-generation sequencing. The present investigation included unrelated obese children, from a previous study on overweight conducted in Guadeloupe Island in 2013. We sequenced coding regions of 59 genes involved in monogenic obesity or diabetes. A total of 25 obese schoolchildren (with Z-score of body mass index [BMI]: 2.0 to 2.8) were screened for rare mutations (non-synonymous, splice-site, or insertion/deletion) in 59 genes. Mean age of the study population was 12.4 ± 1.1 years. Seventeen children (68%) had insulin-resistance (HOMA-IR > 3.16). A family history of obesity (mother or father) was observed in eight children and three of the accompanying parent presented with type 2 diabetes. None of the children had gonadotrophic abnormality or mental retardation. We detected five rare heterozygous mutations, in four genes involved in monogenic obesity, in five different obese children: MC4R p.Ile301Thr and SIM1 p.Val326Thrfs*43 mutations which were pathogenic; SIM1 p.Ser343Pro and SH2B1 p.Pro90His mutations which were likely pathogenic; and NTRK2 p.Leu140Phe that was of uncertain significance. In parallel, we identified seven carriers of mutation in ABCC8 or KCNJ11 (involved in monogenic diabetes), which were of uncertain significance (KCNJ11 p.Val13Met, KCNJ11 p.Val151Met, ABCC8 p.Lys1521Asn and ABCC8 p.Ala625Val). Rare pathogenic or likely pathogenic mutations, linked to severe obesity were detected in more than 15% of this Afro-Caribbean population at high risk of obesity and type 2 diabetes.

Keywords: childhood obesity, MC4R, monogenic obesity, SIM1

Procedia PDF Downloads 161

Authors: Ian Campbell, Gillian Mitchell, Paul James, Na Li, Ella Thompson

Abstract:

The genetic cause of the majority of multiple-case breast cancer families remains unresolved. Next generation sequencing has emerged as an efficient strategy for identifying predisposing mutations in individuals with inherited cancer. We are conducting whole exome sequence analysis of germ line DNA from multiple affected relatives from breast cancer families, with the aim of identifying rare protein truncating and non-synonymous variants that are likely to include novel cancer predisposing mutations. Data from more than 200 exomes show that on average each individual carries 30-50 protein truncating mutations and 300-400 rare non-synonymous variants. Heterogeneity among our exome data strongly suggest that numerous moderate penetrance genes remain to be discovered, with each gene individually accounting for only a small fraction of families (~0.5%). This scenario marks validation of candidate breast cancer predisposing genes in large case-control studies as the rate-limiting step in resolving the missing heritability of breast cancer. The aim of this study is to screen genes that are recurrently mutated among our exome data in a larger cohort of cases and controls to assess the prevalence of inactivating mutations that may be associated with breast cancer risk. We are using the Agilent HaloPlex Target Enrichment System to screen the coding regions of 168 genes in 1,000 BRCA1/2 mutation-negative familial breast cancer cases and 1,000 cancer-naive controls. To date, our interim analysis has identified 21 genes which carry an excess of truncating mutations in multiple breast cancer families versus controls. Established breast cancer susceptibility gene PALB2 is the most frequently mutated gene (13/998 cases versus 0/1009 controls), but other interesting candidates include NPSR1, GSN, POLD2, and TOX3. These and other genes are being validated in a second cohort of 1,000 cases and controls. Our experience demonstrates that beyond PALB2, the prevalence of mutations in the remaining breast cancer predisposition genes is likely to be very low making definitive validation exceptionally challenging.

Keywords: predisposition, familial, exome sequencing, breast cancer

Procedia PDF Downloads 467

Authors: Filimonova Alexanra

Abstract:

Inviscid incompressible fluid flows are considered. The object of the study is a vortex parquet – a structure consisting of distributed vortex spots of different directions, occupying the entire plane. The main attention is paid to the study of advection processes of passive particles in the corresponding velocity field. The dynamics of the vortex structures is considered in a rectangular region under the assumption that periodic boundary conditions are imposed on the stream function. Numerical algorithms are based on the solution of the initial-boundary value problem for nonstationary Euler equations in terms of vorticity and stream function. For this, the spectral-vortex meshless method is used. It is based on the approximation of the stream function by the Fourier series cut and the approximation of the vorticity field by the least-squares method from its values in marker particles. A vortex configuration, consisting of four vortex patches is investigated. Results of a numerical study of the dynamics and interaction of the structure are presented. The influence of the patch radius and the relative position of positively and negatively directed patches on the processes of interaction and mixing is studied. The obtained results correspond to the following possible scenarios: the initial configuration does not change over time; the initial configuration forms a new structure, which is maintained for longer times; the initial configuration returns to its initial state after a certain period of time. The processes of mass transfer of vorticity by liquid particles on a plane were calculated and analyzed. The results of a numerical analysis of the particles dynamics and trajectories on the entire plane and the field of local Lyapunov exponents are presented.

Keywords: ideal fluid, meshless methods, vortex structures in liquids, vortex parquet.

Procedia PDF Downloads 43

Authors: Xianming Chen, Yu Lei, Meinan Wang

Abstract:

The dikaryotic basidiomycete fungus, Puccinia striiformis, causes stripe rust, one of the most important diseases of wheat and barley worldwide. The pathogen is largely reproduced asexually, and asexual recombination has been hypothesized to be one of the mechanisms for the pathogen variations. To test the hypothesis and understand the genetic process of asexual recombination, somatic recombinant isolates were obtained under controlled conditions by inoculating susceptible host plants with a mixture of equal quantity of urediniospores of isolates with different virulence patterns and selecting through a series of inoculation on host plants with different genes for resistance to one of the parental isolates. The potential recombinant isolates were phenotypically characterized by virulence testing on the set of 18 wheat lines used to differentiate races of the wheat stripe rust pathogen, P. striiformis f. sp. tritici (Pst), for the combinations of Pst isolates; or on both sets of the wheat differentials and 12 barley differentials for identifying races of the barley stripe rust pathogen, P. striiformis f. sp. hordei (Psh) for combinations of a Pst isolate and a Psh isolate. The progeny and parental isolates were also genotypically characterized with 51 simple sequence repeat and 90 single-nucleotide polymorphism markers. From nine combinations of parental isolates, 68 potential recombinant isolates were obtained, of which 33 (48.5%) had similar virulence patterns to one of the parental isolates, and 35 (51.5%) had virulence patterns distinct from either of the parental isolates. Of the 35 isolates of distinct virulence patterns, 11 were identified as races that had been previously detected from natural collections and 24 were identified as new races. The molecular marker data confirmed 66 of the 68 isolates as recombinants. The percentages of parental marker alleles ranged from 0.9% to 98.9% and were significantly different from equal proportions in the recombinant isolates. Except for a couple of combinations, the greater or less contribution was not specific to any particular parental isolates as the same parental isolates contributed more to some of the progeny isolates but less to the other progeny isolates in the same combination. The unequal contributions by parental isolates appear to be a general role in somatic recombination for the stripe rust fungus, which may be used to distinguish asexual recombination from sexual recombination in studying the evolutionary mechanisms of the highly variable fungal pathogen.

Keywords: molecular markers, Puccinia striiformis, somatic recombination, stripe rust

Procedia PDF Downloads 216

Authors: Qingsong Xiong, Cheng Yuan, Qingzhao Kong, Haibei Xiong

Abstract:

Deep-learning-driven approaches based on vibration responses have attracted larger attention in rapid structural condition assessment while obtaining sufficient measured training data with corresponding labels is relevantly costly and even inaccessible in practical engineering. This study proposes an integrated label propagation network for structural condition assessment, which is able to diffuse the labels from continuously-generating measurements by intact structure to those of missing labels of damage scenarios. The integrated network is embedded with damage-sensitive features extraction by deep autoencoder and pseudo-labels propagation by optimized fuzzy clustering, the architecture and mechanism which are elaborated. With a sophisticated network design and specified strategies for improving performance, the present network achieves to extends the superiority of self-supervised representation learning, unsupervised fuzzy clustering and supervised classification algorithms into an integration aiming at assessing damage conditions. Both numerical simulations and full-scale laboratory shaking table tests of a two-story building structure were conducted to validate its capability of detecting post-earthquake damage. The identifying accuracy of a present network was 0.95 in numerical validations and an average 0.86 in laboratory case studies, respectively. It should be noted that the whole training procedure of all involved models in the network stringently doesn’t rely upon any labeled data of damage scenarios but only several samples of intact structure, which indicates a significant superiority in model adaptability and feasible applicability in practice.

Keywords: autoencoder, condition assessment, fuzzy clustering, label propagation

Procedia PDF Downloads 75

Authors: Ngoc-Hieu Vu

Abstract:

Although dairy production in Vietnam is a relatively new agricultural activity, milk production increased remarkably in recent years. Smallholders are still the main drivers for this development, especially in the southern part of the country. However, information on the farming practices is very limited. Therefore, this study aimed to characterize husbandry practices, educational experiences, decision-making practices, constraints, income and expenses of smallholder dairy farms in Southern Vietnam. A total of 200 farms, located in the regions Ho Chi Minh (HCM, N=80 farms), Lam Dong (N=40 farms), Binh Duong (N=40 farms) and Long An (N=40 farms) were included. Between October 2013 and December 2014 farmers were interviewed twice. On average, farms owned 3.200m2, 2.000m2, and 193m2 of pasture, cropping and housing area, respectively. The number of total, milking and dry cows, heifers, and calves were 20.4, 11.6, 4.7, 3.3, and 2.9 head. The number of lactating dairy cows was higher (p<0.001) in HCM (15.5) and Lam Dong (14.7) than in Binh Duong (6.7) and Long An (10.7). Animals were mainly crossbred Holstein-Friesian (HF) cows with at least 75% HF origin (84%), whereas a higher (P<0.001) percentage of purebred HF was found in HCM and Lam Dong and crossbreds in Binh Duong and Long An. Animals were mainly raised in tie-stalls (94%) and machine-milked (80%). Farmers used their own replacement animals (76%), and both genetic and phenotypic information (67%) for selecting sires. Farmers were predominantly educated at primary school level (53%). Major constraints for dairy farming were the lack of capital (43%), diseases (17%), marketing (22%), lack of knowledge (8%) and feed (7%). Monthly profit per lactating cow was superior in Lam Dong (2,817 thousand VND) and HCM (2,798 thousand VND) compared to other regions in Long An (2,597 thousand VND), and Binh Duong (1,775 thousand VND). Regional differences may be mainly attributed to environmental factors, urbanization, and particularly governmental support and the availability of extension and financial institutions. Results from this study provide important information on farming practices of smallholders in Southern Vietnam that are useful in determining regions that need to be addressed by authorities in order to improve dairy production.

Keywords: dairy farms, milk yield, Southern Vietnam, socio-economics

Procedia PDF Downloads 430

Authors: Diwei Lin, Amanda Tan, Rajinder Singh-Rai

Abstract:

We present the first reported case of a concomitant Leydig cell tumor (LCT) and paratesticular leiomyoma in an adult male with a known history of bilateral cryptorchidism. An 80-year-old male presented with a 2-month history of a left testicular lump associated with mild discomfort and a gradual increase in size on a background of bilateral cryptorchidism requiring multiple orchidopexy procedures as a child. Ultrasound confirmed a lesion suspicious for malignancy and he proceeded to a left radical orchidectomy. Histopathological assessment of the left testis revealed a concomitant testicular LCT with malignant features and paratesticular leiomyoma. Leydig cell tumors (LCTs) are the most common pure testicular sex cord-stromal tumors, accounting for up to 3% of all testicular tumors. They can occur at almost any age, but are noted to have a bi-modal distribution, with a peak incidence at 6 to 10 and at 20 to 50 years of age. LCT’s are often hormonally active and can lead to feminizing or virilizing syndromes. LCT’s are usually regarded as benign but can rarely exhibit malignant traits. Paratesticular tumours are uncommon and their reported prevalence varies between 3% and 16%. They occur in a complex anatomical area which includes the contents of the spermatic cord, testicular tunics, epididymis and vestigial remnants. Up to 90% of paratesticular tumours are believed to originate from the spermatic cord, though it is often difficult to definitively ascertain the exact site of origin. Although any type of soft-tissue neoplasm can be found in the paratesticular region, the most common benign tumors reported are lipomas of the spermatic cord, adenomatoid tumours of the epididymis and leiomyomas of the testis. Genetic studies have identified potential mutations that could potentially cause LCTs, but there are no known associations between concomitant LCTs and paratesticular tumors. The presence of cryptorchidism in adults with both LCTs and paratesticular neoplasms individually has been previously reported and it appears intuitive that cryptorchidism is likely to be associated with the concomitant presentation in this case report. This report represents the first documented case in the literature of a unilateral concomitant LCT and paratesticular leiomyoma on a background of bilateral cryptorchidism.

Keywords: testicular cancer, leydig cell tumour, leiomyoma, paratesticular neoplasms

Procedia PDF Downloads 341

Authors: Rahul Paul, Kedar Nath Das

Abstract:

The paradigm of Reinforcement Learning (RL) has become prominent in training intelligent agents to make decisions in environments that are both dynamic and uncertain. The primary objective of RL is to optimize the policy of an agent in order to maximize the cumulative reward it receives throughout a given period. Nevertheless, the process of optimization presents notable difficulties as a result of the inherent trade-off between exploration and exploitation, the presence of extensive state-action spaces, and the intricate nature of the dynamics involved. Evolutionary Optimization Methods (EOMs) have garnered considerable attention as a supplementary approach to tackle these challenges, providing distinct capabilities for optimizing RL policies and value functions. The ongoing advancement of research in both RL and EOMs presents an opportunity for significant advancements in autonomous decision-making systems. The convergence of these two fields has the potential to have a transformative impact on various domains of artificial intelligence (AI) applications. This article highlights the considerable influence of EOMs in enhancing the capabilities of RL. Taking advantage of evolutionary principles enables RL algorithms to effectively traverse extensive action spaces and discover optimal solutions within intricate environments. Moreover, this paper emphasizes the practical implementations of EOMs in the field of RL, specifically in areas such as robotic control, autonomous systems, inventory problems, and multi-agent scenarios. The article highlights the utilization of EOMs in facilitating RL agents to effectively adapt, evolve, and uncover proficient strategies for complex tasks that may pose challenges for conventional RL approaches.

Keywords: machine learning, reinforcement learning, loss function, optimization techniques, evolutionary optimization methods

Procedia PDF Downloads 54

Authors: Keerti Kembhavi, M. R. Archana, V. Anjaneyappa

Abstract:

Most asphalt pavement condition evaluation use rating frameworks in which asphalt pavement distress is estimated by type, extent, and severity. Rating is carried out by the pavement condition rating (PCR), which is tedious and expensive. This paper presents the development of a low-cost technique for image pavement distress analysis that permits the identification of pothole and cracks. The paper explores the application of image processing tools for the detection of potholes and cracks. Longitudinal cracking and pothole are detected using Fuzzy-C- Means (FCM) and proceeded with the Spectral Theory algorithm. The framework comprises three phases, including image acquisition, processing, and extraction of features. A digital camera (Gopro) with the holder is used to capture pavement distress images on a moving vehicle. FCM classifier and Spectral Theory algorithms are used to compute features and classify the longitudinal cracking and pothole. The Matlab2016Ra Image preparing tool kit utilizes performance analysis to identify the viability of pavement distress on selected urban stretches of Bengaluru city, India. The outcomes of image evaluation with the utilization semi-computerized image handling framework represented the features of longitudinal crack and pothole with an accuracy of about 80%. Further, the detected images are validated with the actual dimensions, and it is seen that dimension variability is about 0.46. The linear regression model y=1.171x-0.155 is obtained using the existing and experimental / image processing area. The R2 correlation square obtained from the best fit line is 0.807, which is considered in the linear regression model to be ‘large positive linear association’.

Keywords: crack detection, pothole detection, spectral clustering, fuzzy-c-means

Procedia PDF Downloads 155

Authors: Irfan Ahmad Afip

Abstract:

This main research objective is to accurately identify the possibility for a Leptospirosis outbreak severity of a certain area based on its input features into a multivariate regression model. The research question is the possibility of an outbreak in a specific area being influenced by this feature, such as social demographics and hydrometeorological extremes. If the occurrence of an outbreak is being subjected to these features, then the epidemic severity for an area will be different depending on its environmental setting because the features will influence the possibility and severity of an outbreak. Specifically, this research objective was three-fold, namely: (a) to identify the relevant multivariate features and visualize the patterns data, (b) to develop a multivariate regression model based from the selected features and determine the possibility for Leptospirosis outbreak in an area, and (c) to compare the predictive ability of multivariate regression model and machine learning algorithms. Several secondary data features were collected locations in the state of Negeri Sembilan, Malaysia, based on the possibility it would be relevant to determine the outbreak severity in the area. The relevant features then will become an input in a multivariate regression model; a linear regression model is a simple and quick solution for creating prognostic capabilities. A multivariate regression model has proven more precise prognostic capabilities than univariate models. The expected outcome from this research is to establish a correlation between the features of social demographic and hydrometeorological with Leptospirosis bacteria; it will also become a contributor for understanding the underlying relationship between the pathogen and the ecosystem. The relationship established can be beneficial for the health department or urban planner to inspect and prepare for future outcomes in event detection and system health monitoring.

Keywords: geographical information system, hydrometeorological, leptospirosis, multivariate regression

Procedia PDF Downloads 86

Authors: Kayode A. Olaniyi, Adeola A. Ogunleye, Tola M. Osifeko

Abstract:

Electric Vehicles (EV) appear to be gaining increasing patronage as a feasible alternative to Internal Combustion Engine Vehicles (ICEVs) for having low emission and high operation efficiency. The EV energy storage systems are required to handle high energy and power density capacity constrained by limited space, operating temperature, weight and cost. The choice of strategies for energy storage evaluation, monitoring and control remains a challenging task. This paper presents review of various energy storage technologies and recent researches in battery evaluation techniques used in EV applications. It also underscores strategies for the hybrid energy storage management and control schemes for the improvement of EV stability and reliability. The study reveals that despite the advances recorded in battery technologies there is still no cell which possess both the optimum power and energy densities among other requirements, for EV application. However combination of two or more energy storages as hybrid and allowing the advantageous attributes from each device to be utilized is a promising solution. The review also reveals that State-of-Charge (SoC) is the most crucial method for battery estimation. The conventional method of SoC measurement is however questioned in the literature and adaptive algorithms that include all model of disturbances are being proposed. The review further suggests that heuristic-based approach is commonly adopted in the development of strategies for hybrid energy storage system management. The alternative approach which is optimization-based is found to be more accurate but is memory and computational intensive and as such not recommended in most real-time applications.

Keywords: battery state estimation, hybrid electric vehicle, hybrid energy storage, state of charge, state of health

Procedia PDF Downloads 200

Authors: Rachel Y. Zhang, Christopher K. Anderson

Abstract:

A critical aspect of revenue management is a firm’s ability to predict demand as a function of price. Historically hotels have used simple time series models (regression and/or pick-up based models) owing to the complexities of trying to build casual models of demands. Machine learning approaches are slowly attracting attention owing to their flexibility in modeling relationships. This study provides an overview of approaches to forecasting hospitality demand – focusing on the opportunities created by machine learning approaches, including K-Nearest-Neighbors, Support vector machine, Regression Tree, and Artificial Neural Network algorithms. The out-of-sample performances of above approaches to forecasting hotel demand are illustrated by using a proprietary sample of the market level (24 properties) transactional data for Las Vegas NV. Causal predictive models can be built and evaluated owing to the availability of market level (versus firm level) data. This research also compares and contrast model accuracy of firm-level models (i.e. predictive models for hotel A only using hotel A’s data) to models using market level data (prices, review scores, location, chain scale, etc… for all hotels within the market). The prospected models will be valuable for hotel revenue prediction given the basic characters of a hotel property or can be applied in performance evaluation for an existed hotel. The findings will unveil the features that play key roles in a hotel’s revenue performance, which would have considerable potential usefulness in both revenue prediction and evaluation.

Keywords: hotel revenue, k-nearest-neighbors, machine learning, neural network, prediction model, regression tree, support vector machine

Procedia PDF Downloads 108

Authors: Rolivhuwa Bishop Ramagoma1*, Lynn Cairncross1, , Saartjie Roux1

Abstract:

According to the world health organisation, colon cancer is among the most common cancers diagnosed in both men and women. Specifically, it is the second leading cause of cancer related deaths accounting for over 860 000 deaths worldwide in 2018. Currently, chemotherapy has become an essential component of most cancer treatments. Despite progress in cancer drug development over the previous years, traditional chemotherapeutic drugs still have low selectivity for targeting tumour tissues and are frequently constrained by dose-limiting toxicity. The creation of nanoscale delivery vehicles capable of directly directing treatment into cancer cells has recently caught the interest of researchers. Herein, the development of peptide-functionalized polyethylene glycol gold nanoparticles (Peptide-PEG-AuNPs) as a cellular probe and delivery agent is described, with the higher aim to develop a specific diagnostic prototype and assess their specificity not only against cell lines but primary human cells as well. Gold nanoparticles (AuNPs) were synthesized and stabilized through chemical conjugation. The synthesized AuNPs were characterized, stability in physiological solutions was assessed, their cytotoxicity against colon carcinoma and non-carcinoma skin fibroblasts was also studied. Furthermore, genetic effect through real-time polymerase chain reaction (RT-PCR), localization and uptake, peptide specificity were also determined. In this study, different peptide-AuNPs were found to have preferential toxicity at higher concentrations, as revealed by cell viability assays, however, all AuNPs presented immaculate stability for over 3 months following the method of synthesis. The final obtained peptide-PEG-AuNP conjugates showed good biocompatibility in the presence of high ionic solutions and biological media and good cellular uptake. Formulation of colon cancer specific targeting peptide was successful, additionally, the genes/pathways affected by the treatments were determined through RT-PCR. Primary cells study is still on going with promising results thus far.

Keywords: nanotechnology, cancer, diagnosis, therapeutics, gold nanoparticles.

Procedia PDF Downloads 56

Authors: Ahlem Bouziri, Chiraz Latiri, Eric Gaussier

Abstract:

The steady growth in the size of textual document collections is a key progress-driver for modern information retrieval techniques whose effectiveness and efficiency are constantly challenged. Given a user query, the number of retrieved documents can be overwhelmingly large, hampering their efficient exploitation by the user. In addition, retaining only relevant documents in a query answer is of paramount importance for an effective meeting of the user needs. In this situation, the query expansion technique offers an interesting solution for obtaining a complete answer while preserving the quality of retained documents. This mainly relies on an accurate choice of the added terms to an initial query. Interestingly enough, query expansion takes advantage of large text volumes by extracting statistical information about index terms co-occurrences and using it to make user queries better fit the real information needs. In this respect, a promising track consists in the application of data mining methods to extract dependencies between terms, namely a generic basis of association rules between terms. The key feature of our approach is a better trade off between the size of the mining result and the conveyed knowledge. Thus, face to the huge number of derived association rules and in order to select the optimal combination of query terms from the generic basis, we propose to model the problem as a classification problem and solve it using a supervised learning algorithm such as SVM or k-means. For this purpose, we first generate a training set using a genetic algorithm based approach that explores the association rules space in order to find an optimal set of expansion terms, improving the MAP of the search results. The experiments were performed on SDA 95 collection, a data collection for information retrieval. It was found that the results were better in both terms of MAP and NDCG. The main observation is that the hybridization of text mining techniques and query expansion in an intelligent way allows us to incorporate the good features of all of them. As this is a preliminary attempt in this direction, there is a large scope for enhancing the proposed method.

Keywords: supervised leaning, classification, query expansion, association rules

Procedia PDF Downloads 302

Authors: Nadia Naseem, Farwa Batool, Nasir Mehmood, AbdulHannan Nagi

Abstract:

Background: The incidence and mortality of breast cancer vary significantly in geographically distinct populations. In Pakistan, breast cancer has shown an increase in incidence in young females and is characterized by more aggressive behavior. The tumor suppressor TP53 gene is a crucial genetic factor that plays a significant role in breast carcinogenesis. This study investigated the TP53 mutations in molecular subtypes of both nodes negative and positive breast cancer in young Pakistani patients. Material and Methods: p53, Estrogen Receptor (ER), Progesterone Receptor (PR), Her-2 neu and Ki 67 expressions were analyzed immunohistochemically in a series of 75 node negative (A) and 75 node positive (B) young (aged: 19-40 years) breast cancer patients diagnosed between 2014 to 2017 at two leading hospitals of Punjab, Pakistan. Tumor tissue specimens and peripheral blood samples were examined for TP53 mutations by direct sequencing of the gene (exons 4-9). The relation of TP53 mutations to these markers and clinicopathological data was investigated. Results: Mean age of the patients was 32.4 + 9.1 SD. Invasive breast carcinoma was the most frequent histological variant (A=92%, B=94.6%). Grade 3 carcinoma was the commonest grade (A=72%, B=81.3%). Triple negative cases (ER-, PR-, Her-2) formed most of the molecular subtypes (A=44%, B=50.6%). A total of 17.2% (A: 6.6%, B: 10.6%) patients showed TP53 mutations. Mutations were significantly more frequent in triple negative cases (A: 74.8%, B: 62.2%) compared to HER2-positive patients (P < 0.0001). In the multivariate analysis of the whole patient group, the independent prognosticator were triple negative cases (P=0.021), TP53 overexpression by IHC (P=0.001) and advanced-stage disease (P=0.007). No statistically significant correlation between TP53 mutations and clinicopathological parameters was found (P < 0.05). Conclusions: It is concluded that TP53 mutations are infrequently present in breast carcinoma of young Pakistani population and there was no significant correlation between p53 mutation and early onset disease. Immunohistochemically detected TP53 expression in our resource-constrained to set up can be beneficial in predicting mutations at the younger age in our population.

Keywords: immunohistochemistry (IHC), invasive breast carcinoma (IBC), Pakistan, TP53

Procedia PDF Downloads 133

Authors: Mpho Mokoatle, Darlington Mapiye, James Mashiyane, Stephanie Muller, Gciniwe Dlamini

Abstract:

Great advances in high-throughput sequencing technologies have resulted in availability of huge amounts of sequencing data in public and private repositories, enabling a holistic understanding of complex biological phenomena. Sequence data are used for a wide range of applications such as gene annotations, expression studies, personalized treatment and precision medicine. However, this rapid growth in sequence data poses a great challenge which calls for novel data processing and analytic methods, as well as huge computing resources. In this work, a machine and statistical learning approach for DNA sequence classification based on $k$-mer representation of sequence data is proposed. The approach is tested using whole genome sequences of Mycobacterium tuberculosis (MTB) isolates to (i) reduce the size of genomic sequence data, (ii) identify an optimum size of k-mers and utilize it to build classification models, (iii) predict the phenotype from whole genome sequence data of a given bacterial isolate, and (iv) demonstrate computing challenges associated with the analysis of whole genome sequence data in producing interpretable and explainable insights. The classification models were trained on 104 whole genome sequences of MTB isoloates. Cluster analysis showed that k-mers maybe used to discriminate phenotypes and the discrimination becomes more concise as the size of k-mers increase. The best performing classification model had a k-mer size of 10 (longest k-mer) an accuracy, recall, precision, specificity, and Matthews Correlation coeffient of 72.0%, 80.5%, 80.5%, 63.6%, and 0.4 respectively. This study provides a comprehensive approach for resampling whole genome sequencing data, objectively selecting a k-mer size, and performing classification for phenotype prediction. The analysis also highlights the importance of increasing the k-mer size to produce more biological explainable results, which brings to the fore the interplay that exists amongst accuracy, computing resources and explainability of classification results. However, the analysis provides a new way to elucidate genetic information from genomic data, and identify phenotype relationships which are important especially in explaining complex biological mechanisms.

Keywords: AWD-LSTM, bootstrapping, k-mers, next generation sequencing

Procedia PDF Downloads 137

Authors: Darlington Mapiye, Mpho Mokoatle, James Mashiyane, Stephanie Muller, Gciniwe Dlamini

Abstract:

Great advances in high-throughput sequencing technologies have resulted in availability of huge amounts of sequencing data in public and private repositories, enabling a holistic understanding of complex biological phenomena. Sequence data are used for a wide range of applications such as gene annotations, expression studies, personalized treatment and precision medicine. However, this rapid growth in sequence data poses a great challenge which calls for novel data processing and analytic methods, as well as huge computing resources. In this work, a machine and statistical learning approach for DNA sequence classification based on k-mer representation of sequence data is proposed. The approach is tested using whole genome sequences of Mycobacterium tuberculosis (MTB) isolates to (i) reduce the size of genomic sequence data, (ii) identify an optimum size of k-mers and utilize it to build classification models, (iii) predict the phenotype from whole genome sequence data of a given bacterial isolate, and (iv) demonstrate computing challenges associated with the analysis of whole genome sequence data in producing interpretable and explainable insights. The classification models were trained on 104 whole genome sequences of MTB isoloates. Cluster analysis showed that k-mers maybe used to discriminate phenotypes and the discrimination becomes more concise as the size of k-mers increase. The best performing classification model had a k-mer size of 10 (longest k-mer) an accuracy, recall, precision, specificity, and Matthews Correlation coeffient of 72.0 %, 80.5 %, 80.5 %, 63.6 %, and 0.4 respectively. This study provides a comprehensive approach for resampling whole genome sequencing data, objectively selecting a k-mer size, and performing classification for phenotype prediction. The analysis also highlights the importance of increasing the k-mer size to produce more biological explainable results, which brings to the fore the interplay that exists amongst accuracy, computing resources and explainability of classification results. However, the analysis provides a new way to elucidate genetic information from genomic data, and identify phenotype relationships which are important especially in explaining complex biological mechanisms

Keywords: AWD-LSTM, bootstrapping, k-mers, next generation sequencing

Procedia PDF Downloads 126

Authors: Thomas Schalow

Abstract:

It is commonly recognized that our present curriculum is not preparing students to function in the 21st century. This is particularly true in regard to communication needs across cultures - both human and non-human. In this paper, a comprehensive theory of communication-based on communication with non-human cultures and intelligences is presented to meet the following three imminent contingencies: communicating with sentient biological intelligences, communicating with extraterrestrial intelligences, and communicating with artificial super-intelligences. The paper begins with the argument that we need to become much more serious about communicating with the non-human, intelligent life forms that already exists around us here on Earth. We need to broaden our definition of communication and reach out to other sentient life forms in order to provide humanity with a better perspective of its place within our ecosystem. The paper next examines the science and philosophy behind CETI (communication with extraterrestrial intelligences) and how it could prove useful even in the absence of contact with alien life. However, CETI’s assumptions and methodology need to be revised in accordance with the communication theory being proposed in this paper if we are truly serious about finding and communicating with life beyond Earth. The final theme explored in this paper is communication with non-biological super-intelligences. Humanity has never been truly compelled to converse with other species, and our failure to seriously consider such intercourse has left us largely unprepared to deal with communication in a future that will be mediated and controlled by computer algorithms. Fortunately, our experience dealing with other cultures can provide us with a framework for this communication. The basic concepts behind intercultural communication can be applied to the three types of communication envisioned in this paper if we are willing to recognize that we are in fact dealing with other cultures when we interact with other species, alien life, and artificial super-intelligence. The ideas considered in this paper will require a new mindset for humanity, but a new disposition will yield substantial gains. A curriculum that is truly ready for the 21st century needs to be aligned with this new theory of communication.

Keywords: artificial intelligence, CETI, communication, language

Procedia PDF Downloads 335

Authors: Shivankar Agrawal, Sunil Kumar Deshmukh, Colin Barrow, Alok Adholeya

Abstract:

A variety of genetic and environmental factors cause various cosmetics and dermatological problems. There are already claimed drugs available in market for treating these problems. However, the challenge remains in finding more potent, environmental friendly, causing minimal side effects and economical cosmeceuticals. This leads to an increased demand for natural cosmeceutical products in the last few decades. Plant derived ingredients are limited because plants either contain toxic metabolites, grow too slow or seasonal harvesting is a problem. To identify new bioactive cosmetics ingredients of marine microbial bioresource, we screened 35 marine fungi isolated from marine samples collected from Andaman Island and west coast of India. Fungal crude extracts were investigated for their antityrosinase, antioxidant and antibacterial activities for the purpose of identifying anti-aging, skin-whitening and anti-acne biomolecule with the potential in cosmetics. In the tyrosinase inhibition and 2, 2-Diphenyl-1-picrylhydrazyl (DPPH) free radical scavenging assays, two fungal extracts, including “P2”, Talaromyces stipitatus and “D4”, Aspergillus terreus showed high inhibitory activity at 1mg/mL for tyrosinase inhibition and 0.5mg/mL for DPPH scavenging. The in vitro antimicrobial activity was investigated by the agar well diffusion method. In the tyrosinase inhibition assay, 8 extracts showed significant antibacterial activity against bacteria causing skin and wound infection in humans. In the course of systematic screening program for bioactive marine fungi, strain “D5” was found to be most potent strain with MIC value of 1mg/mL, which was morphologically identified as Simplicillium lamellicola. The effects of the most active crude extracts against their susceptible test microorganisms were also investigated by SEM analysis. Further investigations will focus on purification and characterization major active components responsible for these activities.

Keywords: antioxidant, antimicrobial activity, tyrosinase, cosmeceuticals, marine fungi

Procedia PDF Downloads 257

Authors: Vaishali Sharma

Abstract:

The research is an attempt to hunt a scientific and objective method to transform Ajmer's traditional walled city into a living cultural heritage space, exploring urban management methods to elevate local economy and social space in relation to specific cultural-based initiatives. Ajmer is among the oldest and religiously diverse settlements in Rajasthan, that has seen superimposed developments through the eras. With numerous agencies operating towards the development of the town core of Ajmer, it becomes essential to structure development changes in tune with the transformations and the existing heritage. The study was radio-controlled by the subsequent analysis question: What is the way to overcome the genetic social and economic stress inside the communities and revive public life? In order to create necessary interventions at the neighbourhood level, fifteen neighbourhoods were identified. Each of those was analyzed relatively on three major dimensions: Heritage, Social and Local Economy. Each dimension was further broken down into multiple sub-aspects for an overall and exhaustive understanding. The average median values of the responses were used to develop a color-coded matrix to represent the scores in an exceedingly structured quantified manner, moreover, linking it to the spatial structure. Respondent perceptions on numerous dimensions were additionally recorded, so that the proposals are inclusive in nature. The goals are targeted at Ajmer's traditional walled towns, which will make it easier for the community to regulate the rapid transformations and commercialization occurring within the space. The study recommends the necessity for accrued support in methods and policies from the non-public sector, businesses as well as local stakeholders. An expansion, revitalization and maintenance of the major business and heritage corridors, for an increased local and visitor experience, can produce an impetus for promotion of the intangible heritage, to spur the local economic processes, conservation of heritage precincts and upward development.

Keywords: cultural heritage, economic revitalization, neighbourhoods in walled cities, social space, tangible and intangible heritage

Procedia PDF Downloads 127

Authors: Ying Han, Yuanxiang Chen, Yongtao Huang, Jia Fu, Kaile Li, Shangjing Lin, Jianguo Yu

Abstract:

In long-haul and high-speed optical transmission system, the orthogonal frequency division multiplexing (OFDM) signal suffers various linear and non-linear impairments. In recent years, researchers have proposed compensation schemes for specific impairment, and the effects are remarkable. However, different impairment compensation algorithms have caused an increase in transmission delay. With the widespread application of deep neural networks (DNN) in communication, multi-impairment compensation based on DNN will be a promising scheme. In this paper, we propose and apply DNN to compensate multi-impairment of 16-QAM coherent optical OFDM signal, thereby improving the performance of the transmission system. The trained DNN models are applied in the offline digital signal processing (DSP) module of the transmission system. The models can optimize the constellation mapping signals at the transmitter and compensate multi-impairment of the OFDM decoded signal at the receiver. Furthermore, the models reduce the peak to average power ratio (PAPR) of the transmitted OFDM signal and the bit error rate (BER) of the received signal. We verify the effectiveness of the proposed scheme for 16-QAM Coherent Optical OFDM signal and demonstrate and analyze transmission performance in different transmission scenarios. The experimental results show that the PAPR and BER of the transmission system are significantly reduced after using the trained DNN. It shows that the DNN with specific loss function and network structure can optimize the transmitted signal and learn the channel feature and compensate for multi-impairment in fiber transmission effectively.

Keywords: coherent optical OFDM, deep neural network, multi-impairment compensation, optical transmission

Procedia PDF Downloads 111

Authors: Hossein Rassi, Marjan Moradi Fard, Masoud Houshmand

Abstract:

Background: Cervical cancer is multistep disease that is thought to result from an interaction between genetic background and environmental factors. Human papillomavirus (HPV) infection is the leading risk factor for cervical intraepithelial neoplasia(CIN)and cervical cancer. In other hand, some of p53 and miRNA polymorphism may plays an important role in carcinogenesis. This study attempts to clarify the relation of p53 genotypes and miR-146a rs2910164 polymorphism in cervical lesions. Method: Forty two archival samples with cervical lesion retired from Khatam hospital and 40 sample from healthy persons used as control group. A simple and rapid method was used to detect the simultaneous amplification of the HPV consensus L1 region and HPV-16,-18, -11, -31, 33 and -35 along with the b-globin gene as an internal control. We use Multiplex PCR for detection of P53 and miR-146a rs2910164 genotypes in our lab. Finally, data analysis was performed using the 7 version of the Epi Info(TM) 2012 software and test chi-square(x2) for trend. Results: Cervix lesions were collected from 42 patients with Squamous metaplasia, cervical intraepithelial neoplasia, and cervical carcinoma. Successful DNA extraction was assessed by PCR amplification of b-actin gene (99bp). According to the results, p53 GG genotype and miR-146a rs2910164 CC genotype was significantly associated with increased risk of cervical lesions in the study population. In this study, we detected 13 HPV 18 from 42 cervical cancer. Conclusion: The connection between several SNP polymorphism and human virus papilloma in rare researches were seen. The reason of these differences in researches' findings can result in different kinds of races and geographic situations and also differences in life grooves in every region. The present study provided preliminary evidence that a p53 GG genotype and miR-146a rs2910164 CC genotype may effect cervical cancer risk in the study population, interacting synergistically with HPV 18 genotype. Our results demonstrate that the testing of p53 codon 72 polymorphism genotypes and miR-146a rs2910164 polymorphism genotypes in combination with HPV18 can serve as major risk factors in the early identification of cervical cancers. Furthermore, the results indicate the possibility of primary prevention of cervical cancer by vaccination against HPV18 in Iran.

Keywords: cervical cancer, p53, miR-146a, rs2910164, polymorphism

Procedia PDF Downloads 448

Authors: Idris M. Olatunde, Kareem B.

Abstract:

In manufacturing systems, especially job shops, service performance is a key factor that determines customer satisfaction. Service performance depends not only on the quality of the output but on the delivery lead times as well. Besides product quality enhancement, delivery lead time must be minimized for optimal patronage. Quoting accurate due dates is sine quo non for job shop operational survival in a global competitive environment. Quoting accurate due dates in job shops has been a herculean task that nearly defiled solutions from many methods employed due to complex jobs routing nature of the system. This class of NP-hard problems possessed no rigid algorithms that can give an optimal solution. Jobshop operational problem is more complex in developing nations due to some peculiar factors. Operational complexity in job shops emanated from political instability, poor economy, technological know-how, and the non-promising socio-political environment. The mentioned exogenous factors were hardly considered in the previous studies on scheduling problem related to due date determination in job shops. This study has filled the gap created in the past studies by developing a dynamic model that incorporated the exogenous factors for accurate determination of due dates for varying jobs complexity. Real data from six job shops selected from the different part of Nigeria, were used to test the efficacy of the model, and the outcomes were analyzed statistically. The results of the analyzes showed that the model is more promising in determining accurate due dates than the traditional models deployed by many job shops in terms of patronage and lead times minimization.

Keywords: due dates prediction, improved performance, customer satisfaction, dynamic model, exogenous factors, job shops

Procedia PDF Downloads 387

Authors: P. Valsalal, S. Thangalakshmi

Abstract:

There is a widespread changeover in the electrical power industry universally from old-style monopolistic outline towards a horizontally distributed competitive structure to come across the demand of rising consumption. When the transmission lines of derestricted system are incapable to oblige the entire service needs, the lines are overloaded or congested. The governor between customer and power producer is nominated as Independent System Operator (ISO) to lessen the congestion without obstructing transmission line restrictions. Among the existing approaches for congestion management, the frequently used approaches are reorganizing the generation and load curbing. There is a boundary for reorganizing the generators, and further loads may not be supplemented with the prevailing resources unless more private power producers are added in the system by considerably raising the cost. Hence, congestion is relaxed by appropriate Flexible AC Transmission Systems (FACTS) devices which boost the existing transfer capacity of transmission lines. The FACTs device, namely, Unified Power Flow Controller (UPFC) is preferred, and the correct placement of UPFC is more vital and should be positioned in the highly congested line. Hence, the weak line is identified by using power flow performance index with the new objective function with proposed hybrid Fish – Bee algorithm. Further, the location of UPFC at appropriate line reduces the branch loading and minimizes the voltage deviation. The power transfer capacity of lines is determined with and without UPFC in the identified congested line of IEEE 30 bus structure and the simulated results are compared with prevailing algorithms. It is observed that the transfer capacity of existing line is increased with the presented algorithm and thus alleviating the congestion.

Keywords: available line transfer capability, congestion management, FACTS device, Hybrid Fish-Bee Algorithm, ISO, UPFC

Procedia PDF Downloads 356

Authors: Hossein Rassi, Marjan Moradi fard, Masoud Houshmand

Abstract:

Background: Cervical cancer is multistep disease that is thought to result from an interaction between genetic background and environmental factors. Human Papillomavirus (HPV) infection is the leading risk factor for Cervical Intraepithelial Neoplasia (CIN) and cervical cancer. In other hand, some of p53 and miRNA polymorphism may plays an important role in carcinogenesis. This study attempts to clarify the relation of p53 genotypes and miR-146a rs2910164 polymorphism in cervical lesions. Method: Forty two archival samples with cervical lesion retired from Khatam hospital and 40 sample from healthy persons used as control group. A simple and rapid method was used to detect the simultaneous amplification of the HPV consensus L1 region and HPV-16,-18, -11, -31, 33, and -35 along with the b-globin gene as an internal control. We use Multiplex PCR for detection of P53 and miR-146a rs2910164 genotypes in our lab. Finally, data analysis was performed using the 7 version of the Epi Info(TM) 2012 software and test chi-square(x2) for trend. Results: Cervix lesions were collected from 42 patients with Squamous metaplasia, cervical intraepithelial neoplasia, and cervical carcinoma. Successful DNA extraction was assessed by PCR amplification of b-actin gene (99 bp). According to the results, p53 GG genotype and miR-146a rs2910164 CC genotype was significantly associated with increased risk of cervical lesions in the study population. In this study, we detected 13 HPV 18 from 42 cervical cancer. Conclusion: The connection between several SNP polymorphism and human virus papilloma in rare researches were seen. The reason of these differences in researches' findings can result in different kinds of races and geographic situations and also differences in life grooves in every region. The present study provided preliminary evidence that a p53 GG genotype and miR-146a rs2910164 CC genotype may effect cervical cancer risk in the study population, interacting synergistically with HPV 18 genotype. Our results demonstrate that the testing of p53 codon 72 polymorphism genotypes and miR-146a rs2910164 polymorphism genotypes in combination with HPV18 can serve as major risk factors in the early identification of cervical cancers. Furthermore, the results indicate the possibility of primary prevention of cervical cancer by vaccination against HPV18 in Iran.

Keywords: cervical cancer, miR-146a rs2910164 polymorphism, p53 polymorphism, intraepithelial, neoplasia, HPV

Procedia PDF Downloads 379

Authors: Bahareh Golchin, Nooshin Riahi

Abstract:

One of the most significant issues as attended a lot in recent years is that of recognizing the sentiments and emotions in social media texts. The analysis of sentiments and emotions is intended to recognize the conceptual information such as the opinions, feelings, attitudes and emotions of people towards the products, services, organizations, people, topics, events and features in the written text. These indicate the greatness of the problem space. In the real world, businesses and organizations are always looking for tools to gather ideas, emotions, and directions of people about their products, services, or events related to their own. This article uses the Twitter social network, one of the most popular social networks with about 420 million active users, to extract data. Using this social network, users can share their information and opinions about personal issues, policies, products, events, etc. It can be used with appropriate classification of emotional states due to the availability of its data. In this study, supervised learning and deep neural network algorithms are used to classify the emotional states of Twitter users. The use of deep learning methods to increase the learning capacity of the model is an advantage due to the large amount of available data. Tweets collected on various topics are classified into four classes using a combination of two Bidirectional Long Short Term Memory network and a Convolutional network. The results obtained from this study with an average accuracy of 93%, show good results extracted from the proposed framework and improved accuracy compared to previous work.

Keywords: emotion classification, sentiment analysis, social networks, deep neural networks

Procedia PDF Downloads 114

Authors: Ayman K. El Essawy, Amal M. Hosny, Hala M. Abu Shady

Abstract:

The rapid detection of TB and drug resistance, both optimizes treatment and improves outcomes. In the current study, respiratory specimens were collected from 155 patients. Conventional susceptibility testing and MIC determination were performed for rifampicin (RIF) and isoniazid (INH). Genotype MTBDRplus assay, which is a molecular genetic assay based on the DNA-STRIP technology and specific gene sequencing with primers for rpoB, KatG, and mab-inhA genes were used to detect mutations associated with resistance to rifampicin and isoniazid. In comparison to other categories, most of rifampicin resistant (61.5%) and isoniazid resistant isolates (47.1%) were from patients relapsed in treatment. The genotypic profile (using Genotype MTBDRplus assay) of multi-drug resistant (MDR) isolates showed missing of katG wild type 1 (WT1) band and appearance of mutation band katG MUT2. For isoniazid mono-resistant isolates, 80% showed katG MUT1, 20% showed katG MUT1, and inhA MUT1, 20% showed only inhA MUT1. Accordingly, 100% of isoniazid resistant strains were detected by this assay. Out of 17 resistant strains, 16 had mutation bands for katG distinguished high resistance to isoniazid. The assay could clearly detect rifampicin resistance among 66.7% of MDR isolates that showed mutation band rpoB MUT3 while 33.3% of them were considered as unknown. One mono-resistant rifampicin isolate did not show rifampicin mutation bands by Genotype MTBDRplus assay, but it showed an unexpected mutation in Codon 531 of rpoB by DNA sequence analysis. Rifampicin resistance in this strain could be associated with a mutation in codon 531 of rpoB (based on molecular sequencing), and Genotype MTBDRplus assay could not detect the associated mutation. If the results of Genotype MTBDRplus assay and sequencing were combined, this strain shows hetero-resistance pattern. Gene sequencing of eight selected isolates, previously tested by Genotype MTBDRplus assay, could detect resistance mutations mainly in codon 315 (katG gene), position -15 in inhA promotes gene for isoniazid resistance and codon 531 (rpoB gene) for rifampicin resistance. Genotyping techniques allow distinguishing between recurrent cases of reinfection or reactivation and supports epidemiological studies.

Keywords: M. tuberculosis, rpoB, KatG, inhA, genotype MTBDRplus

Procedia PDF Downloads 126

Authors: Z. Abdollahi Biron, P. Pisu

Abstract:

Connected vehicles are one of the promising technologies for future Intelligent Transportation Systems (ITS). A connected vehicle system is essentially a set of vehicles communicating through a network to exchange their information with each other and the infrastructure. Although this interconnection of the vehicles can be potentially beneficial in creating an efficient, sustainable, and green transportation system, a set of safety and reliability challenges come out with this technology. The first challenge arises from the information loss due to unreliable communication network which affects the control/management system of the individual vehicles and the overall system. Such scenario may lead to degraded or even unsafe operation which could be potentially catastrophic. Secondly, faulty sensors and actuators can affect the individual vehicle’s safe operation and in turn will create a potentially unsafe node in the vehicular network. Further, sending that faulty sensor information to other vehicles and failure in actuators may significantly affect the safe operation of the overall vehicular network. Therefore, it is of utmost importance to take these issues into consideration while designing the control/management algorithms of the individual vehicles as a part of connected vehicle system. In this paper, we consider a connected vehicle system under Co-operative Adaptive Cruise Control (CACC) and propose a fault diagnosis scheme that deals with these aforementioned challenges. Specifically, the conventional CACC algorithm is modified by adding a Kalman filter-based estimation algorithm to suppress the effect of lost information under unreliable network. Further, a sliding mode observer-based algorithm is used to improve the sensor reliability under faults. The effectiveness of the overall diagnostic scheme is verified via simulation studies.

Keywords: fault diagnostics, communication network, connected vehicles, packet drop out, platoon

Procedia PDF Downloads 215

Authors: Luanna B. Prevost, Kelli Carter, Margaurete Romero, Kirsti Martinez

Abstract:

Writing is an essential scientific practice, yet, in several countries, the increasing university science class-size limits the use of written assessments. Written assessments allow students to demonstrate their learning in their own words and permit the faculty to evaluate students’ understanding. However, the time and resources required to grade written assessments prohibit their use in large-enrollment science courses. This study examined the use of machine learning algorithms to automatically analyze student writing and provide timely feedback to the faculty about students' writing in biology. Written responses to questions about matter and energy transformation were collected from large-enrollment undergraduate introductory biology classrooms. Responses were analyzed using the LightSide text mining and classification software. Cohen’s Kappa was used to measure agreement between the LightSide models and human raters. Predictive models achieved agreement with human coding of 0.7 Cohen’s Kappa or greater. Models captured that when writing about matter-energy transformation at the ecosystem level, students focused on primarily on the concepts of heat loss, recycling of matter, and conservation of matter and energy. Models were also produced to capture writing about processes such as decomposition and biochemical cycling. The models created in this study can be used to provide automatic feedback about students understanding of these concepts to biology faculty who desire to use formative written assessments in larger enrollment biology classes, but do not have the time or personnel for manual grading.

Keywords: machine learning, written assessment, biology education, text mining

Procedia PDF Downloads 250