Search results for: naive q-learning

Authors: Yanhua Zhao, Yu Gou, Shu Feng, Dongdong Li, Chuanmin Tao

Abstract:

The natural history of HBV infection could experience immune tolerant (IT), immune clearance (IC), HBeAg-negative inactive/quienscent carrier (ENQ), and HBeAg-negative hepatitis (ENH). As current biomarkers for discriminating these four phases have some weaknesses, additional serological indicators are needed. Hepatits B core-related antigen (HBcrAg) encoded with precore/core gene contains denatured HBeAg, HBV core antigen (HBcAg) and a 22KDa precore protein (p22cr), which was demonstrated to have a close association with natural history of hepatitis B infection, but no specific cutoff values and diagnostic parameters to evaluate the diagnostic efficacy. This study aimed to clarify the distribution of HBcrAg levels and evaluate its diagnostic performance during the natural history of infection from a Western Chinese perspective. 294 samples collected from treatment-naïve chronic hepatitis B (CHB) patients in different phases (IT=64; IC=72; ENQ=100, and ENH=58). We detected the HBcrAg values and analyzed the relationship between HBcrAg and HBV DNA. HBsAg and other clinical parameters were quantitatively tested. HBcrAg levels of four phases were 9.30 log U/mL, 8.80 log U/mL, 3.00 log U/mL, and 5.10 logU/mL, respectively (p < 0.0001). Receiver operating characteristic curve analysis demonstrated that the area under curves (AUCs) of HBcrAg and quantitative HBsAg at cutoff values of 9.25 log U/mL and 4.355 log IU/mL for distinguishing IT from IC phases were 0.704 and 0.694, with sensitivity 76.39% and 59.72%, specificity 53.13% and 79.69%, respectively. AUCs of HBcrAg and quantitative HBsAg at cutoff values of 4.15 log U/mlmL and 2.395 log IU/mlmL for discriminating between ENQ and ENH phases were 0.931 and 0.653, with sensitivity 87.93% and 84%, specificity 91.38% and 39%, respectively. Therefore, HBcrAg levels varied significantly among four natural phases of HBV infection. It had higher predictive performance than quantitative HBsAg for distinguishing between ENQ-patients and ENH-patients and similar performance with HBsAg for the discrimination between IT and IC phases, which indicated that HBcrAg could be a potential serological marker for CHB.

Keywords: chronic hepatitis B, hepatitis B core-related antigen, hepatitis B surface antigens, hepatitis B virus

Procedia PDF Downloads 382

Authors: Ermias A. Tegegn, Million Meshesha

Abstract:

Human Immunodeficiency Virus and Acquired Immunodeficiency Syndrome (HIV/AIDS) is a major cause of death for most African countries. Ethiopia is one of the seriously affected countries in sub Saharan Africa. Previously in Ethiopia, having HIV/AIDS was almost equivalent to a death sentence. With the introduction of Antiretroviral Therapy (ART), HIV/AIDS has become chronic, but manageable disease. The study focused on a data mining technique to predict future living status of HIV/AIDS patients at the time of drug regimen change when the patients become toxic to the currently taking ART drug combination. The data is taken from University of Gondar Hospital ART program database. Hybrid methodology is followed to explore the application of data mining on ART program dataset. Data cleaning, handling missing values and data transformation were used for preprocessing the data. WEKA 3.7.9 data mining tools, classification algorithms, and expertise are utilized as means to address the research problem. By using four different classification algorithms, (i.e., J48 Classifier, PART rule induction, Naïve Bayes and Neural network) and by adjusting their parameters thirty-two models were built on the pre-processed University of Gondar ART program dataset. The performances of the models were evaluated using the standard metrics of accuracy, precision, recall, and F-measure. The most effective model to predict the status of HIV patients with drug regimen substitution is pruned J48 decision tree with a classification accuracy of 98.01%. This study extracts interesting attributes such as Ever taking Cotrim, Ever taking TbRx, CD4 count, Age, Weight, and Gender so as to predict the status of drug regimen substitution. The outcome of this study can be used as an assistant tool for the clinician to help them make more appropriate drug regimen substitution. Future research directions are forwarded to come up with an applicable system in the area of the study.

Keywords: HIV drug regimen, data mining, hybrid methodology, predictive model

Procedia PDF Downloads 110

Authors: James Ladzekpo

Abstract:

Background: The urgent need to identify new pharmacological targets for diabetes treatment and prevention has been amplified by the disease's extensive impact on individuals and healthcare systems. A deeper insight into the biological underpinnings of diabetes is crucial for the creation of therapeutic strategies aimed at these biological processes. Current predictive models based on genetic variations fall short of accurately forecasting diabetes. Objectives: Our study aims to pinpoint key epigenetic factors that predispose individuals to diabetes. These factors will inform the development of an advanced predictive model that estimates diabetes risk from genetic profiles, utilizing state-of-the-art statistical and data mining methods. Methodology: We have implemented a recursive feature elimination with cross-validation using the support vector machine (SVM) approach for refined feature selection. Building on this, we developed six machine learning models, including logistic regression, k-Nearest Neighbors (k-NN), Naive Bayes, Random Forest, Gradient Boosting, and Multilayer Perceptron Neural Network, to evaluate their performance. Findings: The Gradient Boosting Classifier excelled, achieving a median recall of 92.17% and outstanding metrics such as area under the receiver operating characteristics curve (AUC) with a median of 68%, alongside median accuracy and precision scores of 76%. Through our machine learning analysis, we identified 31 genes significantly associated with diabetes traits, highlighting their potential as biomarkers and targets for diabetes management strategies. Conclusion: Particularly noteworthy were the Gradient Boosting Classifier and Multilayer Perceptron Neural Network, which demonstrated potential in diabetes outcome prediction. We recommend future investigations to incorporate larger cohorts and a wider array of predictive variables to enhance the models' predictive capabilities.

Keywords: diabetes, machine learning, prediction, biomarkers

Procedia PDF Downloads 15

Authors: Li-Fang CHou, Chun-Jung Tseng, Sung-Chun Tsai

Abstract:

Zhong-Yong represents unique values and cognitive beliefs of Chinese culture. Zhong-Yong thinking emphasizes (a) holistic thinking and perspective taking, (b) tolerance of contradictions, and (c) pursuance of a person’s interpersonal and inner harmony. With a unique way of naïve dialectical thinking based on Chinese culture, previous studies have found that people with higher Zhong-Yong thinking have more cognitive resources and resilience to make decision for dilemmas and cope stresses. Creativity is defined as the behavior to create novel and value products and viewed as the most important capital for individuals and enterprises. However, the relationship between Zhong-Yong thinking and creativity is still remaining to be unexplored. Three studies were conducted to explore the effects of Zhong-Yong thinking on creativity. In Study1, with 87 undergraduate students from a university in southern Taiwan as participants, we used questionnaire to measure Zhong-Yong thinking and processed creative task (unusual uses task) to get indicators of fluency and flexibility. After controlling background and openness to experience of Big five, the results showed that Zhong-Yong thinking had significant positive effects on fluency and flexibility. In Study 2, 97 undergraduate students were recruited to do Zhong-Yong thinking task and creative task. The result showed that, compared with control group, the participants had higher creative performance after being primed with Zhong-Yong thinking. In Study 3, we adopted questionnaire survey and took 397 employees from private enterprises in Taiwan as sample. Besides the main effects of Zhong-Yong thinking, the moderating effects on the relationship between leadership behavior and employee’s creative performance were also investigated. We found that (a) Zhong-Yong thinking was positively associated to creative performance; (b) Zhong-Yong thinking strengthened the positive effects of transformational and authoritative leadership on creative performance. Finally, the implications of theory/practice and limitations/future directions were also discussed.

Keywords: Zhong-Yong thinking, creativity and creative performance, unusual uses task, transformational leadership, authoritative leadership

Procedia PDF Downloads 539

Authors: Kemal Efe Eseller, Göktuğ Yazici

Abstract:

Laser-induced breakdown spectroscopy (LIBS) is a rapid optical atomic emission spectroscopy which is used for material identification and analysis with the advantages of in-situ analysis, elimination of intensive sample preparation, and micro-destructive properties for the material to be tested. LIBS delivers short pulses of laser beams onto the material in order to create plasma by excitation of the material to a certain threshold. The plasma characteristics, which consist of wavelength value and intensity amplitude, depends on the material and the experiment’s environment. In the present work, medicine samples’ spectrum profiles were obtained via LIBS. Medicine samples’ datasets include two different concentrations for both paracetamol based medicines, namely Aferin and Parafon. The spectrum data of the samples were preprocessed via filling outliers based on quartiles, smoothing spectra to eliminate noise and normalizing both wavelength and intensity axis. Statistical information was obtained and principal component analysis (PCA) was incorporated to both the preprocessed and raw datasets. The machine learning models were set based on two different train-test splits, which were 70% training – 30% test and 80% training – 20% test. Cross-validation was preferred to protect the models against overfitting; thus the sample amount is small. The machine learning results of preprocessed and raw datasets were subjected to comparison for both splits. This is the first time that all supervised machine learning classification algorithms; consisting of Decision Trees, Discriminant, naïve Bayes, Support Vector Machines (SVM), k-NN(k-Nearest Neighbor) Ensemble Learning and Neural Network algorithms; were incorporated to LIBS data of paracetamol based pharmaceutical samples, and their different concentrations on preprocessed and raw dataset in order to observe the effect of preprocessing.

Keywords: machine learning, laser-induced breakdown spectroscopy, medicines, principal component analysis, preprocessing

Procedia PDF Downloads 64

Authors: Tigabu Dagne Akal

Abstract:

While advances in computer and communications technology have made the network ubiquitous, they have also rendered networked systems vulnerable to malicious attacks devised from a distance. These attacks or intrusions start with attackers infiltrating a network through a vulnerable host and then launching further attacks on the local network or Intranet. Nowadays, system administrators and network professionals can attempt to prevent such attacks by developing intrusion detection tools and systems using data mining technology. In this study, the experiments were conducted following the Knowledge Discovery in Database Process Model. The Knowledge Discovery in Database Process Model starts from selection of the datasets. The dataset used in this study has been taken from Massachusetts Institute of Technology Lincoln Laboratory. After taking the data, it has been pre-processed. The major pre-processing activities include fill in missed values, remove outliers; resolve inconsistencies, integration of data that contains both labelled and unlabelled datasets, dimensionality reduction, size reduction and data transformation activity like discretization tasks were done for this study. A total of 21,533 intrusion records are used for training the models. For validating the performance of the selected model a separate 3,397 records are used as a testing set. For building a predictive model for intrusion detection J48 decision tree and the Naïve Bayes algorithms have been tested as a classification approach for both with and without feature selection approaches. The model that was created using 10-fold cross validation using the J48 decision tree algorithm with the default parameter values showed the best classification accuracy. The model has a prediction accuracy of 96.11% on the training datasets and 93.2% on the test dataset to classify the new instances as normal, DOS, U2R, R2L and probe classes. The findings of this study have shown that the data mining methods generates interesting rules that are crucial for intrusion detection and prevention in the networking industry. Future research directions are forwarded to come up an applicable system in the area of the study.

Keywords: intrusion detection, data mining, computer science, data mining

Procedia PDF Downloads 267

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 464

Authors: Chien-Wen Chen, Nguyen Duong Thuy Trang, Yu-Hsuan Chang

Abstract:

With the development of information technology, social networking sites are inseparable from life and have become an important way for people to communicate. Nonetheless, privacy issues are raised by the presence of personal information on social networking sites. However, users can benefit from using the functions of social networking sites, which also leads to users worrying about the leakage of personal information without corresponding privacy protection behaviors, which is called the privacy paradox. However, previous studies have questioned the viewpoint of the privacy paradox, believing that users are not so naive and that people with privacy concerns will conduct privacy management. Consequently, this study is based on the view of privacy calculation perspective to investigate the privacy behavior of users on social networking sites. Among them, social benefits and privacy concerns are taken as the expected benefits and costs in the viewpoint of privacy calculation. At the same time, this study also explores the antecedents, including positive feedback, self-presentation, privacy policy, and information sensitivity, and the consequence of privacy behavior of weighing benefits and costs, including self-disclosure and three privacy management strategies by interpersonal boundaries (Preventive, Censorship, and Corrective). The survey respondents' characteristics and prior use experience of social networking sites were analyzed. As a consequence, a survey of 596 social network users was conducted online to validate the research framework. The results show that social benefit has the greatest influence on privacy behavior. The most important external factors affecting privacy behavior are positive feedback, followed by the privacy policy and information sensitivity. In addition, the important findings of this study are that social benefits will positively affect privacy management. It shows that users can get satisfaction from interacting with others through social networking sites. They will not only disclose themselves but also manage their privacy on social networking sites after considering social benefits and privacy management on social networking sites, and it expands the adoption of the Privacy Calculus Perspective framework from prior research. Therefore, it is suggested that as the functions of social networking sites increase and the development of social networking sites, users' needs should be understood and updated in order to ensure the sustainable operation of social networking.

Keywords: privacy calculus perspective, self-disclosure, privacy management, social benefit, privacy concern

Procedia PDF Downloads 59

Authors: Lena Ernstgård, Aishwarya M. Dwivedi, Johan Lundström, Gunnar Johanson

Abstract:

A simple inexpensive olfactometer was constructed to enable valid measures of detection threshold of low concentrations of vapours of chemicals. The delivery system consists of seven syringe pumps, each connected to a Tedlar bag containing a predefined concentration of the test chemical in the air. The seven pumps are connected to a 8-way mixing valve which in turn connects to a birhinal nose piece. Chemical vapor of known concentration is generated by injection of an appropriate amount of the test chemical into a Tedlar bag with a known volume of clean air. Complete vaporization is assured by gentle heating of the bag from the outside with a heat flow. The six test concentrations are obtained by adding different volumes from the starting bag to six new Tedlar bags with known volumes of clean air. One bag contains clean air only. Thus, six different test concentrations and clean air can easily be tested in series by shifting the valve to new positions. Initial in-line measurement with a photoionization detector showed that the delivery system quickly responded to a shift in valve position. Thus 90% of the desired concentration was reached within 15 seconds. The concentrations in the bags are verified daily by gas chromatography. The stability of the system in terms of chemical concentration is monitored in real time by means of a photo-ionization detector. To determine lateralization thresholds, an additional pump supplying clean air is added to the delivery system in a way so that the nostrils can be separately and interchangeably be exposed to clean air and test chemical. Odor and lateralization thresholds were determined for three aldehydes; acrolein, crotonaldehyde, and hexanal in 20 healthy naïve individuals. Aldehydes generally have a strong odour, and the selected aldehydes are also considered to be irritating to mucous membranes. The median odor thresholds of the three aldehydes were 0.017, 0.0008, and 0.097 ppm, respectively. No lateralization threshold could be identified for acrolein, whereas the medians for crotonaldehyde and hexanal were 0.003 and 0.39 ppm, respectively. In conclusion, we constructed a simple, inexpensive olfactometer that allows for stable and easily measurable concentrations of vapors of the test chemical. Our test with aldehydes demonstrates that the system produces valid detection among volunteers in terms of odour and lateralization thresholds.

Keywords: irritation, odour delivery, olfactometer, smell

Procedia PDF Downloads 192

Authors: Ananya Gupta, Sangeeta Bhaskar

Abstract:

Mycobacterium indicus pranii (MIP) is a saprophytic mycobacterium. It is a predecessor of M. avium complex (MAC). Whole genome analysis and growth kinetics studies have placed MIP in between pathogenic and non-pathogenic species. It shares significant antigenic repertoire with M. tuberculosis and have unique immunomodulatory properties. MIP provides better protection than BCG against pulmonary tuberculosis in animal models. Immunization with MIP by aerosol route provides significantly higher protection as compared to immunization by subcutaneous (s.c.) route. However, mechanism behind differential protection has not been studied. In this study, using mice model we have evaluated and compared the M.tb specific immune response in lung compartments (airway lumen / lung interstitium) as well as spleen following MIP immunization via nasal (i.n.) and s.c. route. MIP i.n. vaccination resulted in increased seeding of memory T cells (CD4+ and CD8+ T-cells) in the airway lumen. Frequency of CD4+ T cells expressing Th1 migratory marker (CXCR3) and activation marker (CD69) were also high in airway lumen of MIP i.n. group. Significantly high ex vivo secretion of cytokines- IFN-, IL-12, IL-17 and TNF- from cells of airway luminal spaces provides evidence of antigen-specific lung immune response, besides generating systemic immunity comparable to MIP s.c. group. Analysis of T cell response on per cell basis revealed that antigen specific T-cells of MIP i.n. group were functionally superior as higher percentage of these cells simultaneously secreted IFN-gamma, IL-2 and TNF-alpha cytokines as compared to MIP s.c. group. T-cells secreting more than one of the cytokines simultaneously are believed to have robust effector response and crucial for protection, compared with single cytokine secreting T-cells. Adoptive transfer of airway luminal T-cells from MIP i.n. group into trachea of naive B6 mice revealed that MIP induced CD8 T-cells play crucial role in providing long term protection. Thus the study demonstrates that MIP intranasal vaccination induces M.tb specific memory T-cells in the airway lumen that results in an early and robust recall response against M.tb infection.

Keywords: airway lumen, Mycobacterium indicus pranii, Th1 migratory markers, vaccination

Procedia PDF Downloads 158

Authors: Omar Khan, Shana Krstevska, Edwin George, Veronica Gorden, Fen Bao, Christina Caon, NP-C, Carla Santiago, Imad Zak, Navid Seraji-Bozorgzad

Abstract:

Objective: To quantify cellular injury in the substantia nigra (SN) in patients with Parkinson's disease (PD) and to examine the effect of rasagiline of tissue injury in the SN in patients with PD. Background: N-acetylaspartate (NAA) quantified with MRS is a reliable marker of neuronal metabolic function. Fractional anisotropy (FA) and mean diffusivity (MD) obtained with DTI, characterize tissue alignment and integrity. Rasagline, has been shown to exert anti-apototic effect. We applied these advanced MRI techniques to examine: (i) the effect of rasagiline on cellular injury and metabolism in patients with early PD, and (ii) longitudinal changes seen over time in PD. Methods: We conducted a prospective longitudinal study in patients with mild PD, naive to dopaminergic treatment. The imaging protocol included multi-voxel proton-MRS and DTI of the SN, acquired on a 3T scanner. Scans were performed at baseline and month 3, during which the patient was on no treatment. At that point, rasagiline 1 mg orally daily was initiated and MRI scans are were obtained at 6 and 12 months after starting rasagiline. The primary objective was to compare changes during the 3-month period of “no treatment” to the changes observed “on treatment” with rasagiline at month 12. Age-matched healthy controls were also imaged. Image analysis was performed blinded to treatment allocation and period. Results: 25 patients were enrolled in this study. Compared to the period of “no treatment”, there was significant increase in the NAA “on treatment” period (-3.04 % vs +10.95 %, p= 0.0006). Compared to the period of “no treatment”, there was significant increase in following 12 month in the FA “on treatment” (-4.8% vs +15.3%, p<0.0001). The MD increased during “no treatment” and decreased in “on treatment” (+2.8% vs -7.5%, p=0.0056). Further analysis and clinical correlation are ongoing. Conclusions: Advanced MRI techniques quantifying cellular injury in the SN in PD is a feasible approach to investigate dopaminergic neuronal injury and could be developed as an outcome in exploratory studies. Rasagiline appears to have a stabilizing effect on dopaminergic cell loss and metabolism in the SN in PD, that warrants further investigation in long-term studies.

Keywords: substantia nigra, Parkinson's disease, MRI, neuronal loss, biomarker

Procedia PDF Downloads 292

Authors: Libor Zachoval, Daire O Broin, Oisin Cawley

Abstract:

E-learning platforms, such as Blackboard have two major shortcomings: limited data capture as a result of the limitations of SCORM (Shareable Content Object Reference Model), and lack of incorporation of Artificial Intelligence (AI) and machine learning algorithms which could lead to better course adaptations. With the recent development of Experience Application Programming Interface (xAPI), a large amount of additional types of data can be captured and that opens a window of possibilities from which online education can benefit. In a corporate setting, where companies invest billions on the learning and development of their employees, some learner behaviours can be troublesome for they can hinder the knowledge development of a learner. Behaviours that hinder the knowledge development also raise ambiguity about learner’s knowledge mastery, specifically those related to gaming the system. Furthermore, a company receives little benefit from their investment if employees are passing courses without possessing the required knowledge and potential compliance risks may arise. Using xAPI and rules derived from a state-of-the-art review, we identified three learner behaviours, primarily related to guessing, in a corporate compliance course. The identified behaviours are: trying each option for a question, specifically for multiple-choice questions; selecting a single option for all the questions on the test; and continuously repeating tests upon failing as opposed to going over the learning material. These behaviours were detected on learners who repeated the test at least 4 times before passing the course. These findings suggest that gauging the mastery of a learner from multiple-choice questions test scores alone is a naive approach. Thus, next steps will consider the incorporation of additional data points, knowledge estimation models to model knowledge mastery of a learner more accurately, and analysis of the data for correlations between knowledge development and identified learner behaviours. Additional work could explore how learner behaviours could be utilised to make changes to a course. For example, course content may require modifications (certain sections of learning material may be shown to not be helpful to many learners to master the learning outcomes aimed at) or course design (such as the type and duration of feedback).

Keywords: artificial intelligence, corporate e-learning environment, knowledge maintenance, xAPI

Procedia PDF Downloads 87

Authors: Elcin Timur Cakmak, Ayse Oguzlar

Abstract:

This study presents the results of the tweets sent by Twitter users on social media about the Russia-Ukraine war by bigram and trigram methods. On February 24, 2022, Russian President Vladimir Putin declared a military operation against Ukraine, and all eyes were turned to this war. Many people living in Russia and Ukraine reacted to this war and protested and also expressed their deep concern about this war as they felt the safety of their families and their futures were at stake. Most people, especially those living in Russia and Ukraine, express their views on the war in different ways. The most popular way to do this is through social media. Many people prefer to convey their feelings using Twitter, one of the most frequently used social media tools. Since the beginning of the war, it is seen that there have been thousands of tweets about the war from many countries of the world on Twitter. These tweets accumulated in data sources are extracted using various codes for analysis through Twitter API and analysed by Python programming language. The aim of the study is to find the word sequences in these tweets by the n-gram method, which is known for its widespread use in computational linguistics and natural language processing. The tweet language used in the study is English. The data set consists of the data obtained from Twitter between February 24, 2022, and April 24, 2022. The tweets obtained from Twitter using the #ukraine, #russia, #war, #putin, #zelensky hashtags together were captured as raw data, and the remaining tweets were included in the analysis stage after they were cleaned through the preprocessing stage. In the data analysis part, the sentiments are found to present what people send as a message about the war on Twitter. Regarding this, negative messages make up the majority of all the tweets as a ratio of %63,6. Furthermore, the most frequently used bigram and trigram word groups are found. Regarding the results, the most frequently used word groups are “he, is”, “I, do”, “I, am” for bigrams. Also, the most frequently used word groups are “I, do, not”, “I, am, not”, “I, can, not” for trigrams. In the machine learning phase, the accuracy of classifications is measured by Classification and Regression Trees (CART) and Naïve Bayes (NB) algorithms. The algorithms are used separately for bigrams and trigrams. We gained the highest accuracy and F-measure values by the NB algorithm and the highest precision and recall values by the CART algorithm for bigrams. On the other hand, the highest values for accuracy, precision, and F-measure values are achieved by the CART algorithm, and the highest value for the recall is gained by NB for trigrams.

Keywords: classification algorithms, machine learning, sentiment analysis, Twitter

Procedia PDF Downloads 51

Authors: Michael Hast

Abstract:

Within their first year, infants can differentiate between objects based on their weight. By at least 5 years children hold consistent weight-related misconceptions about the physical world, such as that heavy things fall faster than lighter ones because of their weight. Such misconceptions are seen as a challenge for science education since they are often highly resistant to change through instruction. Understanding the time point of emergence of such ideas could, therefore, be crucial for early science pedagogy. The paper thus discusses two studies that jointly address the issue by examining young children’s search behaviour in hidden displacement tasks under consideration of relative object weight. In both studies, they were tested with a heavy or a light ball, and they either had information about one of the balls only or both. In Study 1, 88 toddlers aged 2 to 3½ years watched a ball being dropped into a curved tube and were then allowed to search for the ball in three locations – one straight beneath the tube entrance, one where the curved tube lead to, and one that corresponded to neither of the previous outcomes. Success and failure at the task were not impacted by weight of the balls alone in any particular way. However, from around 3 years onwards, relative lightness, gained through having tactile experience of both balls beforehand, enhanced search success. Conversely, relative heaviness increased search errors such that children increasingly searched in the location immediately beneath the tube entry – known as the gravity bias. In Study 2, 60 toddlers aged 2, 2½ and 3 years watched a ball roll down a ramp and behind a screen with four doors, with a barrier placed along the ramp after one of four doors. Toddlers were allowed to open the doors to find the ball. While search accuracy generally increased with age, relative weight did not play a role in 2-year-olds’ search behaviour. Relative lightness improved 2½-year-olds’ searches. At 3 years, both relative lightness and relative heaviness had a significant impact, with the former improving search accuracy and the latter reducing it. Taken together, both studies suggest that between 2 and 3 years of age, relative object weight is increasingly taken into consideration in navigating naïve physical concepts. In particular, it appears to contribute to the early emergence of misconceptions relating to object weight. This insight from developmental psychology research may have consequences for early science education and related pedagogy towards early conceptual change.

Keywords: conceptual development, early science education, intuitive physics, misconceptions, object weight

Procedia PDF Downloads 170

Authors: Gaelle Candel, David Naccache

Abstract:

t-SNE is an embedding method that the data science community has widely used. It helps two main tasks: to display results by coloring items according to the item class or feature value; and for forensic, giving a first overview of the dataset distribution. Two interesting characteristics of t-SNE are the structure preservation property and the answer to the crowding problem, where all neighbors in high dimensional space cannot be represented correctly in low dimensional space. t-SNE preserves the local neighborhood, and similar items are nicely spaced by adjusting to the local density. These two characteristics produce a meaningful representation, where the cluster area is proportional to its size in number, and relationships between clusters are materialized by closeness on the embedding. This algorithm is non-parametric. The transformation from a high to low dimensional space is described but not learned. Two initializations of the algorithm would lead to two different embeddings. In a forensic approach, analysts would like to compare two or more datasets using their embedding. A naive approach would be to embed all datasets together. However, this process is costly as the complexity of t-SNE is quadratic and would be infeasible for too many datasets. Another approach would be to learn a parametric model over an embedding built with a subset of data. While this approach is highly scalable, points could be mapped at the same exact position, making them indistinguishable. This type of model would be unable to adapt to new outliers nor concept drift. This paper presents a methodology to reuse an embedding to create a new one, where cluster positions are preserved. The optimization process minimizes two costs, one relative to the embedding shape and the second relative to the support embedding’ match. The embedding with the support process can be repeated more than once, with the newly obtained embedding. The successive embedding can be used to study the impact of one variable over the dataset distribution or monitor changes over time. This method has the same complexity as t-SNE per embedding, and memory requirements are only doubled. For a dataset of n elements sorted and split into k subsets, the total embedding complexity would be reduced from O(n²) to O(n²=k), and the memory requirement from n² to 2(n=k)², which enables computation on recent laptops. The method showed promising results on a real-world dataset, allowing to observe the birth, evolution, and death of clusters. The proposed approach facilitates identifying significant trends and changes, which empowers the monitoring high dimensional datasets’ dynamics.

Keywords: concept drift, data visualization, dimension reduction, embedding, monitoring, reusability, t-SNE, unsupervised learning

Procedia PDF Downloads 112

Authors: Sridhar A. Malkaram, Tamer E. Fandy

Abstract:

Purpose: 5-Azacytidine (5AC) and decitabine (DC) are DNA hypomethylating agents. We recently demonstrated that both drugs increase the enzymatic activity of the histone deacetylase enzyme SIRT6. Accordingly, we are comparing the changes H3K9 acetylation changes in the whole genome induced by both drugs using leukemia cells. Description of Methods & Materials: Mononuclear cells from the bone marrow of six de-identified naive acute myeloid leukemia (AML) patients were cultured with either 500 nM of DC or 5AC for 72 h followed by ChIP-Seq analysis using a ChIP-validated acetylated-H3K9 (H3K9ac) antibody. Chip-Seq libraries were prepared from treated and untreated cells using SMARTer ThruPLEX DNA- seq kit (Takara Bio, USA) according to the manufacturer’s instructions. Libraries were purified and size-selected with AMPure XP beads at 1:1 (v/v) ratio. All libraries were pooled prior to sequencing on an Illumina HiSeq 1500. The dual-indexed single-read Rapid Run was performed with 1x120 cycles at 5 pM final concentration of the library pool. Sequence reads with average Phred quality < 20, with length < 35bp, PCR duplicates, and those aligning to blacklisted regions of the genome were filtered out using Trim Galore v0.4.4 and cutadapt v1.18. Reads were aligned to the reference human genome (hg38) using Bowtie v2.3.4.1 in end-to-end alignment mode. H3K9ac enriched (peak) regions were identified using diffReps v1.55.4 software using input samples for background correction. The statistical significance of differential peak counts was assessed using a negative binomial test using all individuals as replicates. Data & Results: The data from the six patients showed significant (Padj<0.05) acetylation changes at 925 loci after 5AC treatment versus 182 loci after DC treatment. Both drugs induced H3K9 acetylation changes at different chromosomal regions, including promoters, coding exons, introns, and distal intergenic regions. Ten common genes showed H3K9 acetylation changes by both drugs. Approximately 84% of the genes showed an H3K9 acetylation decrease by 5AC versus 54% only by DC. Figures 1 and 2 show the heatmaps for the top 100 genes and the 99 genes showing H3K9 acetylation decrease after 5AC treatment and DC treatment, respectively. Conclusion: Despite the similarity in hypomethylating activity and chemical structure, the effect of both drugs on H3K9 acetylation change was significantly different. More changes in H3K9 acetylation were observed after 5 AC treatments compared to DC. The impact of these changes on gene expression and the clinical efficacy of these drugs requires further investigation.

Keywords: DNA methylation, leukemia, decitabine, 5-Azacytidine, epigenetics

Procedia PDF Downloads 117

Authors: Katie E. Jennings

Abstract:

The interactions between family dynamics and environmental factors with mental health vulnerability in individuals are well known and are a theme for on-going research and debate. The impact upon mental health issues and forensic issues on family dynamics, experience, and emotional wellbeing cannot be over-Emphasised. For forensic patients with diagnosed mental disorders, these relationships and environments may have also been functionally linked to the development and maintenance of those disorders; with significant adverse childhood experiences being a common feature of many Patient’s histories. Mental health hospitals remove the patient from their home environments and provide treatment outside of these relationships and often outside of the home area. There is, therefore, a major focus on Services ensuring that patients are able to build and maintain relationships with family and friends, requiring services to involve families in Patients' care and treatment wherever possible. There are standards set by Government and clinical bodies that require absolute demonstration of the inclusion of family and friends in all aspects of the care and treatment of forensic patients. For some patients and family members, this push to take on a “role” in care can be unhelpful, extremely stressful, and has constant implications for the potential delicate reparation of relationships. Based on work undertaken for over 20 years in forensic mental health settings, this paper explores the positive psychology approach to a dimensional model to family inclusion in mental health care that learns from family court work and allows for the maintenance of relationships to be at both proximal and Distil levels; to prevent the replication of abuse, decrease the need for falsehoods and assist the recovery of all. The model is based on allowing families to choose to not be involved or be involved in different ways if this is seen to be more helpful. It also allows patients to choose the level of potential involvement that they would find helpful, and for this to be reviewed at a timeframe agreed by all parties, rather than when the next survey is due or the patient has a significant care meeting. This paper is significant as there is a lack of research to support services to use a positive psychology approach to work in this area, the assumption that being asked to be involved must be positive for all seems naïve at best for this patient group. Work relating to the psychology of family can significantly contribute to the development of knowledge in this area. The development of a dimensional model will support choice within families and assist in the development of more honest and open relationships.

Keywords: family dynamics, forensic, mental disorder, positive psychology

Procedia PDF Downloads 122

Authors: Laura Micheli, Majd Hijazi, Mahmoud Faytarouni

Abstract:

The damage reported by oil and gas industrial facilities revealed the utmost vulnerability of steel liquid storage tanks to seismic events. The failure of steel storage tanks may yield devastating and long-lasting consequences on built and natural environments, including the release of hazardous substances, uncontrolled fires, and soil contamination with hazardous materials. It is, therefore, fundamental to reliably predict the damage that steel liquid storage tanks will likely experience under future seismic hazard events. The seismic performance of steel liquid storage tanks is usually assessed using vulnerability curves obtained from the numerical simulation of a tank under different hazard scenarios. However, the computational demand of high-fidelity numerical simulation models, such as finite element models, makes the vulnerability assessment of liquid storage tanks time-consuming and often impractical. As a solution, this paper presents a surrogate model-based strategy for predicting seismic-induced damage in steel liquid storage tanks. In the proposed strategy, the surrogate model is leveraged to reduce the computational demand of time-consuming numerical simulations. To create the data set for training the surrogate model, field damage data from past earthquakes reconnaissance surveys and reports are collected. Features representative of steel liquid storage tank characteristics (e.g., diameter, height, liquid level, yielding stress) and seismic excitation parameters (e.g., peak ground acceleration, magnitude) are extracted from the field damage data. The collected data are then utilized to train a surrogate model that maps the relationship between tank characteristics, seismic hazard parameters, and seismic-induced damage via a data-driven surrogate model. Different types of surrogate algorithms, including naïve Bayes, k-nearest neighbors, decision tree, and random forest, are investigated, and results in terms of accuracy are reported. The model that yields the most accurate predictions is employed to predict future damage as a function of tank characteristics and seismic hazard intensity level. Results show that the proposed approach can be used to estimate the extent of damage in steel liquid storage tanks, where the use of data-driven surrogates represents a viable alternative to computationally expensive numerical simulation models.

Keywords: damage prediction , data-driven model, seismic performance, steel liquid storage tanks, surrogate model

Procedia PDF Downloads 121

Authors: Edoardo Schinco

Abstract:

Studying the Marxist intellectual tradition, it is possible to verify that there were numerous cases of philosophical regression, in which the important achievements of detailed studies have been replaced by naïve ideas and previous misunderstandings: one of most important example of this tendency is related to the question of ideology. According to a common Enlightenment approach, the ideology is essentially not a reality, i.e., a factor capable of having an effect on the reality itself; in other words, the ideology is a mere error without specific historical meaning, which is only due to ignorance or inability of subjects to understand the truth. From this point of view, the consequent and immediate practice against every form of ideology are the rational dialogue, the reasoning based on common sense, in order to dispel the obscurity of ignorance through the light of pure reason. The limits of this philosophical orientation are however both theoretical and practical: on the one hand, the Enlightenment criticism of ideology is not an historicistic thought, since it cannot grasp the inner connection that ties an historical context and its peculiar ideology together; moreover, on the other hand, when the Enlightenment approach fails to release people from their illusions (e.g., when the ideology persists, despite the explanation of its illusoriness), it usually becomes a racist or elitarian thought. Unlike this first conception of ideology, Gramsci attempts to recover Marx’s original thought and to valorize its dialectical methodology with respect to the reality of ideology. As Marx suggests, the ideology – in negative meaning – is surely an error, a misleading knowledge, which aims to defense the current state of things and to conceal social, political or moral contradictions; but, that is precisely why the ideological error is not casual: every ideology mediately roots in a particular material context, from which it takes its reason being. Gramsci avoids, however, any mechanistic interpretation of Marx and, for this reason; he underlines the dialectic relation that exists between material base and ideological superstructure; in this way, a specific ideology is not only a passive product of base but also an active factor that reacts on the base itself and modifies it. Therefore, there is a considerable revaluation of ideology’s role in maintenance of status quo and the consequent thematization of both ideology as objective force, active in history, and ideology as cultural hegemony of ruling class on subordinate groups. Among the Marxists, the French philosopher Louis Althusser also gives his contribution to this crucial question; as follower of Gramsci’s thought, he develops the idea of ideology as an objective force through the notions of Repressive State Apparatus (RSA) and Ideological State Apparatuses (ISA). In addition to this, his philosophy is characterized by the presence of structuralist elements, which must be studied, since they deeply change the theoretical foundation of his Marxist thought.

Keywords: Althusser, enlightenment, Gramsci, ideology

Procedia PDF Downloads 168

Authors: Susan C. Graham

Abstract:

Islands have a long established allure for travellers the world over. From earliest accounts of human history, travellers were drawn by the sense of islandness embodied by these destinations. The concept of islandness describes the essence of what makes islands unique relative to non-islands and extends beyond geographic interpretations by attempting to capture the specific sense of self-exhibited by islanders in relation to their connection to place. The themes most strongly associated with islandness include a) a strong connection to water as both the life blood and a physical barrier, b) a unique culture and robust arts community that is deeply linked to both the island and islanders, c) an appreciation of and for nature, d) a rich sense of history and tradition connected to the place, e) a sense of community and belonging that arose through shared triumphs and struggles, and f) a profound awareness of independence, separateness, and uniqueness derived from both physical and social experience. The island brand, like all brands, is a marketing tactic designed to succinctly express a specific value proposition in simplistic ways which might include a brand symbol, logo, slogan, or representation meant to distinguish one brand from another. If a value proposition is the identification of attributes that separate one brand from another by highlighting the brand’s uniqueness, then presumably island brands may, at least in part, emphasize islandness as part of the destination brand. Yet it may in naïve to expect all islands to brand themselves using similar themes when islands can differ so substantially in terms of population, geography, political climate, economy, culture, and history. Of particular interest is the increased focus on tourism among 'cold-water' islands. This paper will examine the incorporation of themes related to islandness in tourism branding among cold-water, warm-water, and temperate-water islands. The tourism logos of 83 islands were collected and assessed for the use of themes related to islandness, namely water, arts and culture, nature, history and tradition, community and belongingness, and independence, separateness, and uniqueness. The ratings for each theme related to islandness for each of the 83 island destinations were then analyzed to identify if differences exist between cold-water, warm-water, and temperate-water islands. A general consensus of what constitutes 'cold-water' destinations is lacking, therefore a water temperature of 15C was adopted using the guidelines from the National Center for Cold Water Safety. Among these 83 islands, the average high and average low water temperatures of 196 specific locations, including the capital, northern, and southern most points of each island, was recorded to determine if the location was a cold-water (average high and low below 15C), warm-water (average high and low above 15C), or temperate-water (average high above 15C and low below 15C) location.

Keywords: branding, cold-water, islands, tourism

Procedia PDF Downloads 191

Authors: Lakshmidevi Sreeramareddy, Komalpreet Kaur, Nane Pothier

Abstract:

Graphical-based passwords have existed for decades. Their major advantage is that they are easier to remember than an alphanumeric password. However, their disadvantage (especially recognition-based passwords) is the smaller password space, making them more vulnerable to brute force attacks. Graphical passwords are also highly susceptible to the shoulder-surfing effect. The gesture-based password method that we developed is a grid-free, template-free method. In this study, we evaluated the gesture-based passwords for usability and vulnerability. The results of the study are significant. We developed a gesture-based password application for data collection. Two modes of data collection were used: Creation mode and Replication mode. In creation mode (Session 1), users were asked to create six different passwords and reenter each password five times. In replication mode, users saw a password image created by some other user for a fixed duration of time. Three different duration timers, such as 5 seconds (Session 2), 10 seconds (Session 3), and 15 seconds (Session 4), were used to mimic the shoulder-surfing attack. After the timer expired, the password image was removed, and users were asked to replicate the password. There were 74, 57, 50, and 44 users participated in Session 1, Session 2, Session 3, and Session 4 respectfully. In this study, the machine learning algorithms have been applied to determine whether the person is a genuine user or an imposter based on the password entered. Five different machine learning algorithms were deployed to compare the performance in user authentication: namely, Decision Trees, Linear Discriminant Analysis, Naive Bayes Classifier, Support Vector Machines (SVMs) with Gaussian Radial Basis Kernel function, and K-Nearest Neighbor. Gesture-based password features vary from one entry to the next. It is difficult to distinguish between a creator and an intruder for authentication. For each password entered by the user, four features were extracted: password score, password length, password speed, and password size. All four features were normalized before being fed to a classifier. Three different classifiers were trained using data from all four sessions. Classifiers A, B, and C were trained and tested using data from the password creation session and the password replication with a timer of 5 seconds, 10 seconds, and 15 seconds, respectively. The classification accuracies for Classifier A using five ML algorithms are 72.5%, 71.3%, 71.9%, 74.4%, and 72.9%, respectively. The classification accuracies for Classifier B using five ML algorithms are 69.7%, 67.9%, 70.2%, 73.8%, and 71.2%, respectively. The classification accuracies for Classifier C using five ML algorithms are 68.1%, 64.9%, 68.4%, 71.5%, and 69.8%, respectively. SVMs with Gaussian Radial Basis Kernel outperform other ML algorithms for gesture-based password authentication. Results confirm that the shorter the duration of the shoulder-surfing attack, the higher the authentication accuracy. In conclusion, behavioral features extracted from the gesture-based passwords lead to less vulnerable user authentication.

Keywords: authentication, gesture-based passwords, machine learning algorithms, shoulder-surfing attacks, usability

Procedia PDF Downloads 76

Authors: Claire Tranter, Coral Dando

Abstract:

Gathering information from others is a fundamental goal for those concerned with investigating crime, and protecting national and international security. Persuading an individual to move from an opposing to converging viewpoint, and an understanding on the cognitive style behind this change can serve to increase understanding of traditional face-to-face interactions, as well as synthetic environments (SEs) often used for communication across varying geographical locations. SEs are growing in usage, and with this increase comes an increase in crime being undertaken online. Communication technologies can allow people to mask their real identities, supporting anonymous communication which can raise significant challenges for investigators when monitoring and managing these conversations inside SEs. To date, the psychological literature concerning how to maximise information-gain in SEs for real-world interviewing purposes is sparse, and as such this aspect of social cognition is not well understood. Here, we introduce an overview of a novel programme of PhD research which seeks to enhance understanding of cross-cultural and cross-gender communication in SEs for maximising information gain. Utilising a dyadic jury paradigm, participants interacted with a confederate who attempted to persuade them to the opposing verdict across three distinct environments: face-to-face, instant messaging, and a novel virtual reality environment utilising avatars. Participants discussed a criminal scenario, acting as a two-person (male; female) jury. Persuasion was manipulated by the confederate claiming an opposing viewpoint (guilty v. not guilty) to the naïve participants from the outset. Pre and post discussion data, and observational digital recordings (voice and video) of participant’ discussion performance was collected. Information regarding cognitive style was also collected to ascertain participants need for cognitive closure and biases towards jumping to conclusions. Findings revealed that individuals communicating via an avatar in a virtual reality environment reacted in a similar way, and thus equally persuasive, when compared to individuals communicating face-to-face. Anonymous instant messaging however created a resistance to persuasion in participants, with males showing a significant decline in persuasive outcomes compared to face to face. The findings reveal new insights particularly regarding the interplay of persuasion on gender and modality, with anonymous instant messaging enhancing resistance to persuasion attempts. This study illuminates how varying SE can support new theoretical and applied understandings of how judgments are formed and modified in response to advocacy.

Keywords: applied cognition, persuasion, social media, virtual reality

Procedia PDF Downloads 122

Authors: F. O’Dowd, G. Murphy, M. Roche, E. Shudell, F. Keane, M. O’Kane

Abstract:

Intoduction: Apremilast (Otezla®) is an oral phosphodiesterase-4 (PDE4) inhibitor indicated for treatment of adult patients with moderate to severe plaque psoriasis who have contraindications to have failed or intolerant of standard systemic therapy and/or phototherapy; and adult patients with active psoriatic arthritis. Apremilast influences intracellular regulation of inflammatory mediators. Two randomized, placebo-controlled trials evaluating apremilast in 1426 patients with moderate to severe plague psoriasis (ESTEEM 1 and 2) demonstrated that the commonest adverse reactions (AE’s) leading to discontinuation were nausea (1.6%), diarrhoea (1.0%), and headaches (0.8%). The overall proportion of subjects discontinuing due to adverse reactions was 6.1%. At week 16 these trials demonstrated significant more apremilast-treated patients (33.1%) achieved the primary end point PASI-75 than placebo (5.3%). We began prescribing apremilast in July 2015. Aim: To evaluate efficacy and tolerability of apremilast in an Irish teaching hospital psoriasis population. Methods: A proforma documenting clinical evaluation parameters, prior treatment experience and AE’s; was completed prospectively on all patients commenced on apremilast since July 2015 – July 2017. Data was collected at week 0,6,12,24,36 and week 52 with 20/71 patients having passed week 52. Efficacy was assessed using Psoriasis Area and Severity Index (PASI) and Dermatology Life Quality Index (DLQI). AE’s documented included GI effects, infections, changes in weight and mood. Retrospective chart review and telephone review was utilised for missing data. Results: A total of 71 adult subjects (38 male, 33 female; age range 23-57), with moderate to severe psoriasis, were evaluated. Prior treatment: 37/71 (52%) were systemic/biologic/phototherapy naïve; 14/71 (20%) has prior phototherapy alone;20/71 (28%) had previous systemic/biologic exposure; 12/71 (17%) had both psoriasis and psoriatic arthritis. PASI responses: mean baseline PASI was 10.1 and DLQI was 15.Week 6: N=71, n=15 (21%) achieved PASI 75. Week 12: N= 48, n=6 (13%) achieved a PASI 100%; n=16 (34.5%) achieved a PASI 75. Week 24: N=40, n=10 (25%) achieved a PASI 100; n=15 (37.5%) achieved a PASI 75. Week 52: N= 20, n=4 (20%) achieved a PASI 100; n= 16 (80%) achieved a PASI 75. (N= number of pts having passed the time point indicated, n= number of pts (out of N) achieving PASI or DLQI responses at that time). DLQI responses: week 24: N= 40, n=30 (75%) achieved a DLQI score of 0; n=5 (12.5%) achieved a DLQI score of 1; n=1 (2.5%) achieved a DLQI score of 10 (due to lack of efficacy). Adverse Events: The proportion of patients that discontinued treatment due to AE’s was n=7 (9.8%). One patient experienced nausea alleviated by dose reduction; another developed significant dysgeusia for certain foods, both continued therapy. Two patients lost 2-3 kg. Conclusion: Initial Irish patient experience of Apremilast appears comparable to that observed in trials with good efficacy and tolerability.

Keywords: Apremilast, introduction, Ireland, clinical audit

Procedia PDF Downloads 123

Authors: W. Staiano, S. Marcora

Abstract:

Introduction: It has been proposed that acute negative effect of mental fatigue (MF) could potentially become a training stimulus for the brain (Brain endurance training (BET)) to adapt and improve its ability to attenuate MF states during sport competitions. Purpose: The aim of this study was to test the efficacy of 6 weeks of BET on cognitive and cycling tests in a group of well-trained subjects. We hypothesised that combination of BET and standard physical training (SPT) would increase cognitive capacity and cycling performance by reducing rating of perceived exertion (RPE) and increase resilience to fatigue more than SPT alone. Methods: In a randomized controlled trial design, 26 well trained participants, after a familiarization session, cycled to exhaustion (TTE) at 80% peak power output (PPO) and, after 90 min rest, at 65% PPO, before and after random allocation to a 6 week BET or active placebo control. Cognitive performance was measured using 30 min of STROOP coloured task performed before cycling performance. During the training, BET group performed a series of cognitive tasks for a total of 30 sessions (5 sessions per week) with duration increasing from 30 to 60 min per session. Placebo engaged in a breathing relaxation training. Both groups were monitored for physical training and were naïve to the purpose of the study. Physiological and perceptual parameters of heart rate, lactate (LA) and RPE were recorded during cycling performances, while subjective workload (NASA TLX scale) was measured during the training. Results: Group (BET vs. Placebo) x Test (Pre-test vs. Post-test) mixed model ANOVA’s revealed significant interaction for performance at 80% PPO (p = .038) or 65% PPO (p = .011). In both tests, groups improved their TTE performance; however, BET group improved significantly more compared to placebo. No significant differences were found for heart rate during the TTE cycling tests. LA did not change significantly at rest in both groups. However, at completion of 65% TTE, it was significantly higher (p = 0.043) in the placebo condition compared to BET. RPE measured at ISO-time in BET was significantly lower (80% PPO, p = 0.041; 65% PPO p= 0.021) compared to placebo. Cognitive results in the STROOP task showed that reaction time in both groups decreased at post-test. However, BET decreased significantly (p = 0.01) more compared to placebo despite no differences accuracy. During training sessions, participants in the BET showed, through NASA TLX questionnaires, constantly significantly higher (p < 0.01) mental demand rates compared to placebo. No significant differences were found for physical demand. Conclusion: The results of this study provide evidences that combining BET and SPT seems to be more effective than SPT alone in increasing cognitive and cycling performance in well trained endurance participants. The cognitive overload produced during the 6-week training of BET can induce a reduction in perception of effort at a specific power, and thus improving cycling performance. Moreover, it provides evidence that including neurocognitive interventions will benefit athletes by increasing their mental resilience, without affecting their physical training load and routine.

Keywords: cognitive training, perception of effort, endurance performance, neuro-performance

Procedia PDF Downloads 86

Authors: Burak Oksuzoglu, Savas Yildirim, Ferhat Kutlu

Abstract:

Opinion mining (OM) is one of the natural language processing (NLP) problems to determine the polarity of opinions, mostly represented on a positive-neutral-negative axis. The data for OM is usually collected from various social media platforms. In an era where social media has considerable control over companies’ futures, it’s worth understanding social media and taking actions accordingly. OM comes to the fore here as the scale of the discussion about companies increases, and it becomes unfeasible to gauge opinion on individual levels. Thus, the companies opt to automize this process by applying machine learning (ML) approaches to their data. For the last two decades, OM or sentiment analysis (SA) has been mainly performed by applying ML classification algorithms such as support vector machines (SVM) and Naïve Bayes to a bag of n-gram representations of textual data. With the advent of deep learning and its apparent success in NLP, traditional methods have become obsolete. Transfer learning paradigm that has been commonly used in computer vision (CV) problems started to shape NLP approaches and language models (LM) lately. This gave a sudden rise to the usage of the pretrained language model (PTM), which contains language representations that are obtained by training it on the large datasets using self-supervised learning objectives. The PTMs are further fine-tuned by a specialized downstream task dataset to produce efficient models for various NLP tasks such as OM, NER (Named-Entity Recognition), Question Answering (QA), and so forth. In this study, the traditional and modern NLP approaches have been evaluated for OM by using a sizable corpus belonging to a large private company containing about 76,000 comments in Turkish: SVM with a bag of n-grams, and two chosen pre-trained models, multilingual universal sentence encoder (MUSE) and bidirectional encoder representations from transformers (BERT). The MUSE model is a multilingual model that supports 16 languages, including Turkish, and it is based on convolutional neural networks. The BERT is a monolingual model in our case and transformers-based neural networks. It uses a masked language model and next sentence prediction tasks that allow the bidirectional training of the transformers. During the training phase of the architecture, pre-processing operations such as morphological parsing, stemming, and spelling correction was not used since the experiments showed that their contribution to the model performance was found insignificant even though Turkish is a highly agglutinative and inflective language. The results show that usage of deep learning methods with pre-trained models and fine-tuning achieve about 11% improvement over SVM for OM. The BERT model achieved around 94% prediction accuracy while the MUSE model achieved around 88% and SVM did around 83%. The MUSE multilingual model shows better results than SVM, but it still performs worse than the monolingual BERT model.

Keywords: BERT, MUSE, opinion mining, pretrained language model, SVM, Turkish

Procedia PDF Downloads 112

Authors: Angela O. Ugwu, Sunday Ocheni

Abstract:

Background: Cancer-associated thrombosis (CAT) is a cause of morbidity and mortality among cancer patients. Several risk factors for developing venous thromboembolism (VTE) also coexist with cancer patients, such as chemotherapy and immobilization, thus contributing to the higher risk of VTE in cancer patients when compared to non-cancer patients. This study aimed to determine if there is any correlation between levels of some inflammatory cytokines/haematological parameters and Khorana scores of newly diagnosed chemotherapy naïve ambulatory cancer patients (CNACP). Methods: This was a cross-sectional analytical study carried out from June 2021 to May 2022. Eligible newly diagnosed cancer patients 18 years and above (case group) were enrolled consecutively from the adult Oncology Clinics of the University of Nigeria Teaching Hospital, Ituku/Ozalla (UNTH). The control group was blood donors at UNTH Ituku/Ozalla, Enugu blood bank, and healthy members of the Medical and Dental Consultants Association of Nigeria (MDCAN), UNTH Chapter. Blood samples collected from the participants were assayed for IL-6, TNF-Alpha, and haematological parameters such as haemoglobin, white blood cell count (WBC), and platelet count. Data were entered into an Excel worksheet and were then analyzed using Statistical Package for Social Sciences (SPSS) computer software version 21.0 for windows. A P value of < 0.05 was considered statistically significant. Results: A total of 200 participants (100 cases and 100 controls) were included in the study. The overall mean age of the participants was 47.42 ±15.1 (range 20-76). The sociodemographic characteristics of the two groups, including age, sex, educational level, body mass index (BMI), and occupation, were similar (P > 0.05). Following One Way ANOVA, there were significant differences between the mean levels of interleukin-6 (IL-6) (p = 0.036) and tumor necrotic factor-α (TNF-α) (p = 0.001) in the three Khorana score groups of the case group. Pearson’s correlation analysis showed a significant positive correlation between the Khorana scores and IL-6 (r=0.28, p = 0.031), TNF-α (r= 0.254, p= 0.011), and PLR (r= 0.240, p=0.016). The mean serum levels of IL-6 were significantly higher in CNACP than in the healthy controls [8.98 (8-12) pg/ml vs. 8.43 (2-10) pg/ml, P=0.0005]. There were also significant differences in the mean levels of the haemoglobin (Hb) level (P < 0.001)); white blood cell (WBC) count ((P < 0.001), and platelet (PL) count (P = 0.005) between the two groups of participants. Conclusion: There is a significant positive correlation between the serum levels of IL-6, TNF-α, and PLR and the Khorana scores of CNACP. The mean serum levels of IL-6, TNF-α, PLR, WBC, and PL count were significantly higher in CNACP than in the healthy controls. Ambulatory cancer patients with high-risk Khorana scores may benefit from anti-inflammatory drugs because of the positive correlation with inflammatory cytokines. Recommendations: Ambulatory cancer patients with 2 Khorana scores may benefit from thromboprophylaxis since they have higher Khorana scores. A multicenter study with a heterogeneous population and larger sample size is recommended in the future to further elucidate the relationship between IL-6, TNF-α, PLR, and the Khorana scores among cancer patients in the Nigerian population.

Keywords: thromboprophylaxis, cancer, Khorana scores, inflammatory cytokines, haematological parameters

Procedia PDF Downloads 52

Authors: Dmitriy Babenko, Sergey Yegorov, Ilya Korshukov, Aidana Sultanbekova, Valentina Barkhanskaya, Tatiana Bashirova, Yerzhan Zhunusov, Yevgeniya Li, Viktoriya Parakhina, Svetlana Kolesnichenko, Yeldar Baiken, Aruzhan Pralieva, Zhibek Zhumadilova, Matthew S. Miller, Gonzalo H. Hortelano, Anar Turmuhambetova, Antonella E. Chesca, Irina Kadyrova

Abstract:

Introduction: The rapidly evolving COVID-19 pandemic, along with the re-emergence of pathogens causing acute respiratory infections (ARI), has necessitated the development of novel diagnostic tools to differentiate various causes of ARI. MALDI-MS, due to its wide usage and affordability, has been proposed as a potential instrument for diagnosing SARS-CoV-2 versus non-SARS-CoV-2 ARI. The aim of this study was to investigate the potential of MALDI-MS in conjunction with a machine learning model to accurately distinguish between symptomatic infections caused by SARS-CoV-2 and non-SARS-CoV-2 during both the early and later phases of the pandemic. Furthermore, this study aimed to analyze mass spectrometry (MS) data obtained from nasal swabs of healthy individuals. Methods: We gathered mass spectra from 252 samples, comprising 108 SARS-CoV-2-positive samples obtained in 2020 (Covid 2020), 7 SARS-CoV- 2-positive samples obtained in 2023 (Covid 2023), 71 samples from symptomatic individuals without SARS-CoV-2 (Control non-Covid ARVI), and 66 samples from healthy individuals (Control healthy). All the samples were subjected to RT-PCR testing. For data analysis, we employed the caret R package to train and test seven machine-learning algorithms: C5.0, KNN, NB, RF, SVM-L, SVM-R, and XGBoost. We conducted a training process using a five-fold (outer) nested repeated (five times) ten-fold (inner) cross-validation with a randomized stratified splitting approach. Results: In this study, we utilized the Covid 2020 dataset as a case group and the non-Covid ARVI dataset as a control group to train and test various machine learning (ML) models. Among these models, XGBoost and SVM-R demonstrated the highest performance, with accuracy values of 0.97 [0.93, 0.97] and 0.95 [0.95; 0.97], specificity values of 0.86 [0.71; 0.93] and 0.86 [0.79; 0.87], and sensitivity values of 0.984 [0.984; 1.000] and 1.000 [0.968; 1.000], respectively. When examining the Covid 2023 dataset, the Naive Bayes model achieved the highest classification accuracy of 43%, while XGBoost and SVM-R achieved accuracies of 14%. For the healthy control dataset, the accuracy of the models ranged from 0.27 [0.24; 0.32] for k-nearest neighbors to 0.44 [0.41; 0.45] for the Support Vector Machine with a radial basis function kernel. Conclusion: Therefore, ML models trained on MALDI MS of nasopharyngeal swabs obtained from patients with Covid during the initial phase of the pandemic, as well as symptomatic non-Covid individuals, showed excellent classification performance, which aligns with the results of previous studies. However, when applied to swabs from healthy individuals and a limited sample of patients with Covid in the late phase of the pandemic, ML models exhibited lower classification accuracy.

Keywords: SARS-CoV-2, MALDI-TOF MS, ML models, nasopharyngeal swabs, classification

Procedia PDF Downloads 72

Authors: Sara Rejeb, Catherine Duveau, Tabea Rebafka

Abstract:

To monitor the production process of turbofan aircraft engines, multiple measurements of various geometrical parameters are systematically recorded on manufactured parts. Engine parts are subject to extremely high standards as they can impact the performance of the engine. Therefore, it is essential to analyze these databases to better understand the influence of the different parameters on the engine's performance. Self-organizing maps are unsupervised neural networks which achieve two tasks simultaneously: they visualize high-dimensional data by projection onto a 2-dimensional map and provide clustering of the data. This technique has become very popular for data exploration since it provides easily interpretable results and a meaningful global view of the data. As such, self-organizing maps are usually applied to aircraft engine condition monitoring. As databases in this field are huge and complex, they naturally contain multiple missing entries for various reasons. The classical Kohonen algorithm to compute self-organizing maps is conceived for complete data only. A naive approach to deal with partially observed data consists in deleting items or variables with missing entries. However, this requires a sufficient number of complete individuals to be fairly representative of the population; otherwise, deletion leads to a considerable loss of information. Moreover, deletion can also induce bias in the analysis results. Alternatively, one can first apply a common imputation method to create a complete dataset and then apply the Kohonen algorithm. However, the choice of the imputation method may have a strong impact on the resulting self-organizing map. Our approach is to address simultaneously the two problems of computing a self-organizing map and imputing missing values, as these tasks are not independent. In this work, we propose an extension of self-organizing maps for partially observed data, referred to as missSOM. First, we introduce a criterion to be optimized, that aims at defining simultaneously the best self-organizing map and the best imputations for the missing entries. As such, missSOM is also an imputation method for missing values. To minimize the criterion, we propose an iterative algorithm that alternates the learning of a self-organizing map and the imputation of missing values. Moreover, we develop an accelerated version of the algorithm by entwining the iterations of the Kohonen algorithm with the updates of the imputed values. This method is efficiently implemented in R and will soon be released on CRAN. Compared to the standard Kohonen algorithm, it does not come with any additional cost in terms of computing time. Numerical experiments illustrate that missSOM performs well in terms of both clustering and imputation compared to the state of the art. In particular, it turns out that missSOM is robust to the missingness mechanism, which is in contrast to many imputation methods that are appropriate for only a single mechanism. This is an important property of missSOM as, in practice, the missingness mechanism is often unknown. An application to measurements on one type of part is also provided and shows the practical interest of missSOM.

Keywords: imputation method of missing data, partially observed data, robustness to missingness mechanism, self-organizing maps

Procedia PDF Downloads 125

Authors: Vivek Mahadev, Manoj Kumar, Neelu Mathur, Brahm Dutt Pandey

Abstract:

Perimeter guarding and protection of critical installations require prompt intrusion detection and assessment to take effective countermeasures. Currently, visual and electronic surveillance are the primary methods used for perimeter guarding. These methods can be costly and complicated, requiring careful planning according to the location and terrain. Moreover, these methods often struggle to detect stealthy and camouflaged insurgents. The object of the present work is to devise a surveillance technique using seismic sensors that overcomes the limitations of existing systems. The aim is to improve intrusion detection, assessment, and characterization by utilizing seismic sensors. Most of the similar systems have only two types of intrusion detection capability viz., human or vehicle. In our work we could even categorize further to identify types of intrusion activity such as walking, running, group walking, fence jumping, tunnel digging and vehicular movements. A virtual fence of 60 meters at GCNEP, Bahadurgarh, Haryana, India, was created by installing four underground geophones at a distance of 15 meters each. The signals received from these geophones are then processed to find unique seismic signatures called features. Various feature optimization and selection methodologies, such as LightGBM, Boruta, Random Forest, Logistics, Recursive Feature Elimination, Chi-2 and Pearson Ratio were used to identify the best features for training the machine learning models. The trained models were developed using algorithms such as supervised support vector machine (SVM) classifier, kNN, Decision Tree, Logistic Regression, Naïve Bayes, and Artificial Neural Networks. These models were then used to predict the category of events, employing weighted ensemble voting to analyze and combine their results. The models were trained with 1940 training events and results were evaluated with 831 test events. It was observed that using the weighted ensemble voting increased the efficiency of predictions. In this study we successfully developed and deployed the virtual fence using geophones. Since these sensors are passive, do not radiate any energy and are installed underground, it is impossible for intruders to locate and nullify them. Their flexibility, quick and easy installation, low costs, hidden deployment and unattended surveillance make such systems especially suitable for critical installations and remote facilities with difficult terrain. This work demonstrates the potential of utilizing seismic sensors for creating better perimeter guarding and protection systems using multiple machine learning models in weighted ensemble voting. In this study the virtual fence achieved an intruder detection efficiency of over 97%.

Keywords: geophone, seismic perimeter surveillance, machine learning, weighted ensemble method

Procedia PDF Downloads 37

Authors: Z. Xu

Abstract:

Immersive virtual reality (VR) has gained momentum in humanitarian communication due to its utopian promises of co-presence, immediacy, and transcendence. These potential benefits have led the United Nations (UN) to tirelessly produce and distribute VR series to evoke global empathy and encourage policymakers, philanthropic business tycoons and citizens around the world to actually do something (i.e. give a donation). However, it is unclear whether or not VR can cultivate cosmopolitans with a sense of social responsibility towards the geographically, socially/culturally and morally mediated misfortune of faraway others. Drawing upon existing works on the mediation of distant suffering, this article constructs an analytical framework to articulate the issue. Applying this framework on a case study of five of the UN’s VR pieces, the article identifies three paradoxes that exist between cyber-utopian and cyber-dystopian narratives. In the “paradox of distance”, VR relies on the notions of “presence” and “storyliving” to implicitly link audiences spatially and temporally to distant suffering, creating global connectivity and reducing perceived distances between audiences and others; yet it also enables audiences to fully occupy the point of view of distant sufferers (creating too close/absolute proximity), which may cause them to feel naive self-righteousness or narcissism with their pleasures and desire, thereby destroying the “proper distance”. In the “paradox of agency”, VR simulates a superficially “real” encounter for visual intimacy, thereby establishing an “audiences–beneficiary” relationship in humanitarian communication; yet in this case the mediated hyperreality is not an authentic reality, and its simulation does not fill the gap between reality and the virtual world. In the “paradox of the hierarchies of human life”, VR enables an audience to experience virtually fundamental “freedom”, epitomizing an attitude of cultural relativism that informs a great deal of contemporary multiculturalism, providing vast possibilities for a more egalitarian representation of distant sufferers; yet it also takes the spectator’s personally empathic feelings as the focus of intervention, rather than structural inequality and political exclusion (an economic and political power relations of viewing). Thus, the audience can potentially remain trapped within the minefield of hegemonic humanitarianism. This study is significant in two respects. First, it advances the turn of digitalization in studies of media and morality in the polymedia milieu; it is motivated by the necessary call for a move beyond traditional technological environments to arrive at a more novel understanding of the asymmetry of power between the safety of spectators and the vulnerability of mediated sufferers. Second, it not only reminds humanitarian journalists and NGOs that they should not rely entirely on the richer news experience or powerful response-ability enabled by VR to gain a “moral bond” with distant sufferers, but also argues that when fully-fledged VR technology is developed, it can serve as a kind of alchemy and should not be underestimated merely as a “bugaboo” of an alarmist philosophical and fictional dystopia.

Keywords: audience, cosmopolitan, distant suffering, virtual reality, humanitarian communication

Procedia PDF Downloads 107