Search results for: support vector machine

Authors: Boris Djartov, Sanaz Mostaghim

Abstract:

This paper presents a number-based dominance method. The main idea is how to fragment the many attributes of the problem into subsets suitable for the well-established concept of Pareto dominance. Although other similar methods can be found in the literature, they focus on comparing the solutions one objective at a time, while the focus of this method is to compare entire subsets of the objective vector. Given the nature of the method, it is computationally costlier than other methods and thus, it is geared more towards selecting an option from a finite set of alternatives, where each solution is defined by multiple objectives. The need for this method was motivated by dynamic alternate airport selection (DAAS). In DAAS, pilots, while en route to their destination, can find themselves in a situation where they need to select a new landing airport. In such a predicament, they need to consider multiple alternatives with many different characteristics, such as wind conditions, available landing distance, the fuel needed to reach it, etc. Hence, this method is primarily aimed at human decision-makers. Many methods within the field of multi-objective and many-objective decision-making rely on the decision maker to initially provide the algorithm with preference points and weight vectors; however, this method aims to omit this very difficult step, especially when the number of objectives is so large. The proposed method will be compared to Favour (1 − k)-Dom and L-dominance (LD) methods. The test will be conducted using well-established test problems from the literature, such as the DTLZ problems. The proposed method is expected to outperform the currently available methods in the literature and hopefully provide future decision-makers and pilots with support when dealing with many-objective optimization problems.

Keywords: multi-objective decision-making, many-objective decision-making, multi-objective optimization, many-objective optimization

Procedia PDF Downloads 86

Authors: Ibrahim Beldjilali, Adel Ghenaiet

Abstract:

The contra-rotating axial machine is a promising solution for several applications, where high pressure and efficiencies are needed. Also, they allow reducing the speed of rotation, the radial spacing and a better flexibility of use. However, this requires a better understanding of their operation, including the influence of second rotor on the overall aerodynamic performances. This work consisted of both experimental and numerical studies to characterize this counter-rotating fan, especially the analysis of the effects of the blades stagger angle and the inter-distance between the rotors. The experimental study served to validate the computational fluid dynamics model (CFD) used in the simulations. The numerical study permitted to cover a wider range of parameter and deeper investigation on flow structures details, including the effects of blade stagger angle and inter-distance, associated with the interaction between the rotors. As a result, there is a clear improvement in aerodynamic performance compared with a conventional machine.

Keywords: aerodynamic performance, axial fan, counter rotating rotors, CFD, experimental study

Procedia PDF Downloads 154

Authors: Shao Bo Cheng, Yong-Jin Han, Se Young Park, Seong-Bae Park

Abstract:

Consumer-to-Consumer (C2C) E-commerce has been growing at a very high speed in recent years. Since identical or nearly-same kinds of products compete one another by relying on keyword search in C2C E-commerce, some sellers describe their products with spam keywords that are popular but are not related to their products. Though such products get more chances to be retrieved and selected by consumers than those without spam keywords, the spam keywords mislead the consumers and waste their time. This problem has been reported in many commercial services like e-bay and taobao, but there have been little research to solve this problem. As a solution to this problem, this paper proposes a method to classify whether keywords of a product are spam or not. The proposed method assumes that a keyword for a given product is more reliable if the keyword is observed commonly in specifications of products which are the same or the same kind as the given product. This is because that a hierarchical category of a product in general determined precisely by a seller of the product and so is the specification of the product. Since higher layers of the hierarchical category represent more general kinds of products, a reliable degree is differently determined according to the layers. Hence, reliable degrees from different layers of a hierarchical category become features for keywords and they are used together with features only from specifications for classification of the keywords. Support Vector Machines are adopted as a basic classifier using the features, since it is powerful, and widely used in many classification tasks. In the experiments, the proposed method is evaluated with a golden standard dataset from Yi-han-wang, a Chinese C2C e-commerce, and is compared with a baseline method that does not consider the hierarchical category. The experimental results show that the proposed method outperforms the baseline in F1-measure, which proves that spam keywords are effectively identified by a hierarchical category in C2C e-commerce.

Keywords: spam keyword, e-commerce, keyword features, spam filtering

Procedia PDF Downloads 292

Authors: A. Kamel Abd Elaziz Mohamed, B. Sameh Kamal el Maraghi

Abstract:

Introduction: Adaptive support ventilation (ASV) is an improved closed-loop ventilation mode that provides both pressure-controlled ventilation and PSV according to the patient’s needs. Aim of the work: To compare the short-term effects of Adaptive support ventilation (ASV), with conventional Pressure support ventilation (PSV) in weaning of intubated COPD patients. Patients and methods: Fifty patients admitted in the intensive care with acute exacerbation of COPD and needing intubation were included in the study. All patients were initially ventilated with control/assist control mode, in a stepwise manner and were receiving standard medical therapy. Patients were randomized into two groups to receive either ASV or PSV. Results: Out of fifty patients included in the study forty one patients in both studied groups were weaned successfully according to their ABG data and weaning indices. APACHE II score showed no significant difference in both groups. There were statistically significant differences between the groups in term of, duration of mechanical ventilation, weaning hours and length of ICU stay being shorter in (group 1) weaned by ASV. Re-intubation and mortality rate were higher in (group 11) weaned by conventional PSV, however the differences were not significant. Conclusion: ASV can provide automated weaning and achieve shorter weaning time for COPD patients hence leading to reduction in the total duration of MV, length of stay, and hospital costs.

Keywords: COPD patients, ASV, PSV, mechanical ventilation (MV)

Procedia PDF Downloads 388

Authors: Chinlun Lai, Lunjyh Jiang

Abstract:

Due to the heavy burden and pressure of caring for infants, an integrated automatic baby watching system based on IoT smart sensing and deep learning machine vision techniques is proposed in this paper. By monitoring infant body conditions such as heartbeat, breathing, body temperature, sleeping posture, as well as the surrounding conditions such as dangerous/sharp objects, light, noise, humidity and temperature, the proposed system can analyze and predict the obvious/potential dangerous conditions according to observed data and then adopt suitable actions in real time to protect the infant from harm. Thus, reducing the burden of the caregiver and improving safety efficiency of the caring work. The experimental results show that the proposed system works successfully for the infant care work and thus can be implemented in various life fields practically.

Keywords: baby care system, Internet of Things, deep learning, machine vision

Procedia PDF Downloads 223

Authors: Anum Ali, Kashaf ad Dooja, Asif Saleem

Abstract:

The future smart cities trend will be towards Internet of Things (IoT); IoT creates dynamic connections in a ubiquitous manner. Smart cities offer ease and flexibility for daily life matters. By using small devices that are connected to cloud servers based on IoT, network traffic between these devices is growing exponentially, whose security is a concerned issue, since ratio of cyber attack may make the network traffic vulnerable. This paper discusses the latest machine learning approaches in related work further to tackle the increasing rate of cyber attacks, machine learning algorithm is applied to IoT-based network traffic data. The proposed algorithm train itself on data and identify different sections of devices interaction by using supervised learning which is considered as a classifier related to a specific IoT device class. The simulation results clearly identify the attacks and produce fewer false detections.

Keywords: IoT, traffic security, deep learning, classification

Procedia PDF Downloads 146

Authors: Alexandros Pournaras, Anastasia Papadopoulou, Serafim Kontos, Anastasios Karakostas

Abstract:

The air quality of modern cities is an important concern, as poor air quality contributes to human health and environmental issues. Reliable air quality forecasting has, thus, gained scientific and governmental attention as an essential tool that enables authorities to take proactive measures for public safety. In this study, the potential of Machine Learning (ML) models to forecast PM2.5 at local scale is investigated in the city of Thessaloniki, the second largest city in Greece, which has been struggling with the persistent issue of air pollution. ML models, with proven ability to address timeseries forecasting, are employed to predict the PM2.5 concentrations and the respective Air Quality Index 5-days ahead by learning from daily historical air quality and meteorological data from 2014 to 2016 and gathered from two stations with different land use characteristics in the urban fabric of Thessaloniki. The performance of the ML models on PM2.5 concentrations is evaluated with common statistical methods, such as R squared (r²) and Root Mean Squared Error (RMSE), utilizing a portion of the stations’ measurements as test set. A multi-categorical evaluation is utilized for the assessment of their performance on respective AQIs. Several conclusions were made from the experiments conducted. Experimenting on MLs’ configuration revealed a moderate effect of various parameters and training schemas on the model’s predictions. Their performance of all these models were found to produce satisfactory results on PM2.5 concentrations. In addition, their application on untrained stations showed that these models can perform well, indicating a generalized behavior. Moreover, their performance on AQI was even better, showing that the MLs can be used as predictors for AQI, which is the direct information provided to the general public.

Keywords: Air Quality, AQ Forecasting, AQI, Machine Learning, PM2.5

Procedia PDF Downloads 72

Authors: Steve Fish, Chris Lambert

Abstract:

Cumbria is a geo-political county in Northwest England within which the Lake District National Park, a UNESCO World Heritage site is located. Whilst the area has a formidable reputation for natural beauty and historic assets, the innovation ecosystem is described as ‘patchy’ for a number of reasons. The county is one of the largest in England by area and is sparsely populated. This paper describes the needs, development and delivery of an SME business-support programme funded by the European Regional Development Fund, Lancaster University and the University of Cumbria. The Cumbria Innovations Platform (CUSP) Project has been designed to respond to the nuanced needs of SMEs in this locale, whilst promoting the adoption of research and innovation. CUSP utilizes a funnel method to support rural businesses with access to university innovation intervention. CUSP has been built on a three-tier model: Communicate, Collaborate and Create. The paper describes this project in detail and presents results in terms of output indicators achieved, a beneficiary telephone survey and wider economic forecasts. From a pragmatic point-of-view, the paper provides experiences and reflections of those people who are delivering and evaluating knowledge exchange. The authors discuss some of the benefits, challenges and implications for both policy makers and practitioners. Finally, the paper aims to serve as an invitation to others who may consider adopting a similar method of university-industry collaboration in their own region.

Keywords: regional business support, rural business support, university-industry collaboration, collaborative R&D, SMEs, knowledge exchange

Procedia PDF Downloads 114

Authors: Min Chen, Rubi Gupta

Abstract:

Understanding and predicting stock market movements is a challenging problem. It is believed stock markets are partially driven by public sentiments, which leads to numerous research efforts to predict stock market trend using public sentiments expressed on social media such as Twitter but with limited success. Recently a microblogging website StockTwits is becoming increasingly popular for users to share their discussions and sentiments about stocks and financial market. In this project, we analyze the text content of StockTwits tweets and extract financial sentiment using text featurization and machine learning algorithms. StockTwits tweets are first pre-processed using techniques including stopword removal, special character removal, and case normalization to remove noise. Features are extracted from these preprocessed tweets through text featurization process using bags of words, N-gram models, TF-IDF (term frequency-inverse document frequency), and latent semantic analysis. Machine learning models are then trained to classify the tweets' sentiment as positive (bullish) or negative (bearish). The correlation between the aggregated daily sentiment and daily stock price movement is then investigated using Pearson’s correlation coefficient. Finally, the sentiment information is applied together with time series stock data to predict stock price movement. The experiments on five companies (Apple, Amazon, General Electric, Microsoft, and Target) in a duration of nine months demonstrate the effectiveness of our study in improving the prediction accuracy.

Keywords: machine learning, sentiment analysis, stock price prediction, tweet processing

Procedia PDF Downloads 148

Authors: Selim M. Khan, Dustin D. Pearson, Tryggve Rönnqvist, Markus E. Nielsen, Joshua M. Taron, Aaron A. Goodarzi

Abstract:

Accumulation of radioactive radon gas in indoor air poses a serious risk to human health by increasing the lifetime risk of lung cancer and is classified by IARC as a category one carcinogen. Radon exposure risks are a function of geologic, geographic, design, and human behavioural variables and can change over time. Using time series and deep machine learning modelling, we analyzed long-term radon test outcomes as a function of building metrics from 25,489 Canadian and 38,596 Swedish residential properties constructed between 1945 to 2020. While Canadian and Swedish properties built between 1970 and 1980 are comparable (96–103 Bq/m³), innate radon risks subsequently diverge, rising in Canada and falling in Sweden such that 21st Century Canadian houses show 467% greater average radon (131 Bq/m³) relative to Swedish equivalents (28 Bq/m³). These trends are consistent across housing types and regions within each country. The introduction of energy efficiency measures within Canadian and Swedish building codes coincided with opposing radon level trajectories in each nation. Deep machine learning modelling predicts that, without intervention, average Canadian residential radon levels will increase to 176 Bq/m³ by 2050, emphasizing the importance and urgency of future building code intervention to achieve systemic radon reduction in Canada.

Keywords: radon health risk, time-series, deep machine learning, lung cancer, Canada, Sweden

Procedia PDF Downloads 82

Authors: Jon Gunnar Bernburg

Abstract:

The present study addresses a topic that is fundamental to social movement theory, namely, the contingent link between movement support and movement participation. Usually, only a small fraction of those who agree with the cause of a social movement is mobilized into participating in it (a pattern sometimes referred to as 'the collective action problem'). However, historical moments sometimes emerge when many supporters become mobilized to participate in the movement, greatly enhancing the chance of movement success. By studying a case in point, this paper addresses the limited work on how support and participation are related at such critical moments. Specifically, the paper examines the association between supporting and participating in a huge 'pro-democracy' protest in Iceland in April 2016, in the wake of the global Panama Papers scandal. Organized via social media by only a handful of activists, but supported by a majority of Icelanders, the protest attracted about a fourth of the urban population, leading to a snap election and government change. Surveying Iceland’s urban population, this paper tests hypotheses about the processes mobilizing supporters to participate in the protest. The findings reveal how variables derived from the theories of biographical availability (males vs. females, working class vs. professionals), critical mass (expectations, prior protest success), and social embeddedness (close ties with protesters) moderate the association between protest support and participation. The study helps to account for one of the largest protests in Iceland’s history while contributing to the theory about how historical contexts shape the behavior of movement supporters.

Keywords: Iceland, crisis, protest support vs. participation, theories of mass mobilization

Procedia PDF Downloads 230

Authors: Saima Shafiq, Najma Iqbal Malik

Abstract:

This study was aimed to explore the relationship of perceived stigma, perception of burden and psychological distress among parents of intellectually disabled children. The study also aimed to explore the moderating role of perceived social support on all the variables of the study. The sample of the study comprised of (N = 250) parents of intellectually disabled children. The present study utilized the co-relational research design. It consists of two phases. Phase-I consisted of two steps which contained the translation of two scales that were used in the present study and tried out on the sample of parents (N = 70). The Affiliated Stigma Scale and Care Giver Burden Inventory were translated into Urdu for the present study. Phase-1 revealed that translated scaled entailed satisfactory psychometric properties. Phase -II of the study was carried out in order to test the hypothesis. Correlation, linear regression analysis, and t-test were computed for hypothesis testing. Hierarchical regression analysis was applied to study the moderating effect of perceived social support. Findings revealed that there was a positive relationship between perceived stigma and psychological distress, perception of burden and psychological distress. Linear regression analysis showed that perceived stigma and perception of burden were positive predictors of psychological distress. The study did not show the moderating role of perceived social support among variables of the present study. The major limitation of the study is the sample size and the major implication is awareness regarding problems of parents of intellectually disabled children.

Keywords: perceived stigma, perception of burden, psychological distress, perceived social support

Procedia PDF Downloads 209

Authors: Armando T. Zúñiga

Abstract:

As the number of English Language Learners (ELLs) in public schools continues to grow, so does the achievement gap between ELLs and other student populations. In an effort to support classroom teachers with effective instructional strategies for this student population, many districts have created instructional coaching positions specifically to support classroom teachers of ELLs—ELL Teachers on Special Assignment (ELL TOSAs). This study employed a gap analysis framework to the ELL TOSA professional support program in one California school district to examine knowledge, motivation, and organizational influences (KMO) on the ELL TOSAs’ goal of supporting classroom teachers of ELLs. Three themes emerged as a result of data analysis. First, there was evidence to illustrate the interaction between knowledge and the organization. Data from ELL TOSAs indicated an understanding of the role that collaboration plays in coaching and how to operationalize it in their support of teachers. Further, all of the ELL TOSAs indicated they have received professional development on effective strategies for instructional coaching. Additionally, a large percentage of the ELL TOSAs indicated a knowledge of modeling as an effective coaching practice. Accordingly, all of the ELL TOSAs indicated that they had knowledge of feedback as an effective coaching strategy. However, there was not sufficient evidence to support that they learned the latter two strategies through professional development. A second theme surfaced as there was evidence to illustrate an interaction between motivation and the organization. Some ELL TOSAs indicated that their sense of self-efficacy was affected by conflicting roles and expectations for the job. Most of the ELL TOSAs indicated that their sense of self-efficacy was affected by an increased workload brought about by fiscal decision making. Finally, there was evidence illustrating the interaction between the organization and motivation. The majority of the of ELL TOSAs indicated that there is confusion about how their roles are perceived, leaving the ELL TOSAs to feel that their actions did not contribute to instructional change. In conclusion, five research-based recommendations to support ELL TOSA goal attainment and considerations for future research on instructional coaches for classroom teachers of ELLs are provided.

Keywords: English language development, English language acquisition, language and leadership, language coaching, English language learners, second language acquisition

Procedia PDF Downloads 97

Authors: Jinhoa Lee

Abstract:

The relationships between environmental quality, energy use and economic output have created growing attention over the past decades among researchers and policy makers. Focusing on the empirical aspects of the role of CO2 emissions and energy use in affecting the economic output, this paper is an effort to fulfil the gap in a comprehensive case study at a country level using modern econometric techniques. To achieve the goal, this country-specific study examines the short-run and long-run relationships among energy consumption, carbon dioxide (CO2) emissions and gross domestic product (GDP) for Oman using time series analysis from the year 1980-2010. To investigate the relationships between the variables, this paper employs the Augmented Dickey Fuller (ADF) test for stationary, Johansen maximum likelihood method for co-integration and a Vector Error Correction Model (VECM) for both short- and long-run causality among the research variables for the sample. All the variables in this study show very strong significant effects on GDP in the country for the long term. The long-run equilibrium in the VECM suggests positive long-run causalities from CO2 emissions to GDP. Conversely, negative impacts of energy consumption on GDP are found to be significant in Oman during the period. In the short run, there exist negative unidirectional causalities among GDP, CO2 emissions and energy consumption running from GDP to CO2 emissions and from energy consumption to CO2 emissions. Overall, the results support arguments that there are relationships among environmental quality, energy use and economic output in Oman over of period 1980-2010.

Keywords: CO2 emissions, energy consumption, GDP, Oman, time series analysis

Procedia PDF Downloads 458

Authors: George Kurian, Hongmei Chi

Abstract:

Digital evidence plays a critical role in most legal investigations. In many cases, thumbnail databases show important information in that investigation. The probability of having digital evidence retrieved from a computer or smart device has increased, even though the previous user removed data and deleted apps on those devices. Due to the increase in digital forensics, the ability to store residual information from various thumbnail applications has improved. This paper will focus on investigating thumbnail information from Windows 10. Thumbnail images of interest in forensic investigations may be intact even when the original pictures have been deleted. It is our research goal to recover useful information from thumbnails. In this research project, we use various forensics tools to collect left thumbnail information from deleted videos or pictures. We examine and describe the various thumbnail sources in Windows and propose a methodology for thumbnail collection and analysis from laptops or desktops. A machine learning algorithm is adopted to help speed up content from thumbnail pictures.

Keywords: digital forensic, forensic tools, soundness, thumbnail, machine learning, OCR

Procedia PDF Downloads 124

Authors: Arun Prasad Jaganathan

Abstract:

In today's dynamic industrial world, traditional task allocation methods often fall short in adapting to evolving operational conditions. This paper introduces an AI-enabled task assistance and management system designed to overcome the limitations of conventional approaches. By using artificial intelligence (AI) and machine learning (ML), the system intelligently interprets user instructions, analyzes tasks, and allocates resources based on real-time data and environmental factors. Additionally, geolocation tracking enables proactive identification of potential delays, ensuring timely interventions. With its transparent reporting mechanisms, the system provides stakeholders with clear insights into task progress, fostering accountability and informed decision-making. The paper presents a comprehensive overview of the system architecture, algorithm, and implementation, highlighting its potential to revolutionize task management across diverse industries.

Keywords: artificial intelligence, machine learning, task allocation, operational efficiency, resource optimization

Procedia PDF Downloads 50

Authors: Peter Balco, Miriam Filipova

Abstract:

The university education is generally concentrated on acquiring theoretical as well as professional knowledge. The right mix of these knowledges is key in creating innovative as well as inventive solutions. Despite the understanding of their importance by the professional community, these are promoted with problems and misunderstanding. The reason for the failure of many non-traditional, innovative approaches is the ignorance of Leadership in the process of their implementation, ie decision-making. In our paper, we focused on the role of Leadership in the educational process and how this knowledge can support decision-making, the selection of a suitable, optimal solution for practice.

Keywords: leadership, soft skills, innovation, invention, knowledge

Procedia PDF Downloads 181

Authors: Luke Taylor, Samantha J. Hall, Kenneth I. Cumming, Jakki Bardsley, Scott S. P. Wildman

Abstract:

Medway School of Pharmacy, as part of an Equality Diversity and Inclusivity (EDI) initiative run by the University of Kent, decided to take steps to try and negate disparities in numeracy competencies within students undertaking the Master of Pharmacy degree in order to combat a trend in pharmacy students’ numerical abilities upon entry. This included a research driven project 1) to identify if pharmacy students are aware of weaknesses in their numeracy capabilities, and 2) recognise where their numeracy skillset is lacking. In addition to gaining this student perspective, a number of actions have been implemented to support students in improving their numeracy competencies. Reflective and quantitative analysis has shown promising improvements for the final year cohort of 2014/15 when compared to previous years. The method of involving student feedback into the structure of numeracy teaching/support has proven to be extremely beneficial to both students and teaching staff alike. Students have felt empowered and in control of their own learning requirements, leading to increased engagement and attainment. School teaching staff have received quality data to help improve existing initiatives and to innovate further in the area of numeracy teaching. In light of the recognised improvements, further actions are currently being trialled in the area of numeracy support. This involves utilising Virtual Learning Environment platforms to provide individualised support as a supplement to the increased numeracy mentoring (staff and peer) provided to students. Mentors who provide group or one-to-one sessions are now given significant levels of training in dealing with situations that commonly arise from mentoring schemes. They are also provided with continued support throughout the life of their degree. Following results from this study, Medway School of Pharmacy hopes to drive increasing numeracy standards within Pharmacy (primarily through championing peer mentoring) as well as other healthcare professions including Midwifery and Nursing.

Keywords: attainment, ethnicity, numeracy, pharmacy, support

Procedia PDF Downloads 233

Authors: M. D. D. Chathurangi, M. G. K. Nayanathara, K. M. H. M. M. Gunapala, G. M. R. G. Dayananda, Kavinga Yapa Abeywardena, Deemantha Siriwardana

Abstract:

Due to the growing popularity of social media platforms at present, there are various concerns, mostly cyberbullying, spam, bot accounts, and the spread of incorrect information. To develop a risk score calculation system as a thorough method for deciphering and exposing unethical social media profiles, this research explores the most suitable algorithms to our best knowledge in detecting the mentioned concerns. Various multiple models, such as Naïve Bayes, CNN, KNN, Stochastic Gradient Descent, Gradient Boosting Classifier, etc., were examined, and the best results were taken into the development of the risk score system. For cyberbullying, the Logistic Regression algorithm achieved an accuracy of 84.9%, while the spam-detecting MLP model gained 98.02% accuracy. The bot accounts identifying the Random Forest algorithm obtained 91.06% accuracy, and 84% accuracy was acquired for fake news detection using SVM.

Keywords: cyberbullying, spam behavior, bot accounts, fake news, machine learning

Procedia PDF Downloads 31

Authors: Bharatendra Rai

Abstract:

Predictive data analysis and modeling involving machine learning techniques become challenging in presence of too many explanatory variables or features. Presence of too many features in machine learning is known to not only cause algorithms to slow down, but they can also lead to decrease in model prediction accuracy. This study involves housing dataset with 79 quantitative and qualitative features that describe various aspects people consider while buying a new house. Boruta algorithm that supports feature selection using a wrapper approach build around random forest is used in this study. This feature selection process leads to 49 confirmed features which are then used for developing predictive random forest models. The study also explores five different data partitioning ratios and their impact on model accuracy are captured using coefficient of determination (r-square) and root mean square error (rsme).

Keywords: housing data, feature selection, random forest, Boruta algorithm, root mean square error

Procedia PDF Downloads 316

Authors: Jacob Green, Cecilia Cabrera, Maximilian Jakobs, Andrea Dimitracopoulos, Mark van der Wilk, Ryan Greenhalgh

Abstract:

Predicting drug properties is key in drug discovery to enable de-risking of assets before expensive clinical trials and to find highly active compounds faster. Interest from the machine learning community has led to the release of a variety of benchmark datasets and proposed methods. However, it remains unclear for practitioners which method or approach is most suitable, as different papers benchmark on different datasets and methods, leading to varying conclusions that are not easily compared. Our large-scale empirical study links together numerous earlier works on different datasets and methods, thus offering a comprehensive overview of the existing property classes, datasets, and their interactions with different methods. We emphasise the importance of uncertainty quantification and the time and, therefore, cost of applying these methods in the drug development decision-making cycle. To the best of the author's knowledge, it has been observed that the optimal approach varies depending on the dataset and that engineered features with classical machine learning methods often outperform deep learning. Specifically, QSAR datasets are typically best analysed with classical methods such as Gaussian Processes, while ADMET datasets are sometimes better described by Trees or deep learning methods such as Graph Neural Networks or language models. Our work highlights that practitioners do not yet have a straightforward, black-box procedure to rely on and sets a precedent for creating practitioner-relevant benchmarks. Deep learning approaches must be proven on these benchmarks to become the practical method of choice in drug property prediction.

Keywords: activity (QSAR), ADMET, classical methods, drug property prediction, empirical study, machine learning

Procedia PDF Downloads 76

Authors: A. M. Byrne, E. Bonfiglio, C. Rigby, N. Edelstyn

Abstract:

Introduction: Neuromarketing employs numerous methodologies when investigating products and advertisement effectiveness. Electroencephalography (EEG), a non-invasive measure of electrical activity from the brain, is commonly used in neuromarketing. EEG data can be considered using time-frequency (TF) analysis, where changes in the frequency of brainwaves are calculated to infer participant’s mental states, or event-related potential (ERP) analysis, where changes in amplitude are observed in direct response to a stimulus. This presentation discusses the findings of a systematic review of EEG measures in neuromarketing. A systematic review summarises evidence on a research question, using explicit measures to identify, select, and critically appraise relevant research papers. Thissystematic review identifies which EEG measures are the most robust predictor of customer preference and purchase intention. Methods: Search terms identified174 papers that used EEG in combination with marketing-related stimuli. Publications were excluded if they were written in a language other than English or were not published as journal articles (e.g., book chapters). The review investigated which TF effect (e.g., theta-band power) and ERP component (e.g., N400) most consistently reflected preference and purchase intention. Machine-learning prediction was also investigated, along with the use of EEG combined with physiological measures such as eye-tracking. Results: Frontal alpha asymmetry was the most reliable TF signal, where an increase in activity over the left side of the frontal lobe indexed a positive response to marketing stimuli, while an increase in activity over the right side indexed a negative response. The late positive potential, a positive amplitude increase around 600 ms after stimulus presentation, was the most reliable ERP component, reflecting the conscious emotional evaluation of marketing stimuli. However, each measure showed mixed results when related to preference and purchase behaviour. Predictive accuracy was greatly improved through machine-learning algorithms such as deep neural networks, especially when combined with eye-tracking or facial expression analyses. Discussion: This systematic review provides a novel catalogue of the most effective use of each EEG measure commonly used in neuromarketing. Exciting findings to emerge are the identification of the frontal alpha asymmetry and late positive potential as markers of preferential responses to marketing stimuli. Predictive accuracy using machine-learning algorithms achieved predictive accuracies as high as 97%, and future research should therefore focus on machine-learning prediction when using EEG measures in neuromarketing.

Keywords: EEG, ERP, neuromarketing, machine-learning, systematic review, time-frequency

Procedia PDF Downloads 107

Authors: Lule Basha, Eralda Gjika

Abstract:

This study is focused on analyzing climate change in Albania and its potential effects on cereal yields. Initially, monthly temperature and rainfalls in Albania were studied for the period 1960-2021. Climacteric variables are important variables when trying to model cereal yield behavior, especially when significant changes in weather conditions are observed. For this purpose, in the second part of the study, linear and nonlinear models explaining cereal yield are constructed for the same period, 1960-2021. The multiple linear regression analysis and lasso regression method are applied to the data between cereal yield and each independent variable: average temperature, average rainfall, fertilizer consumption, arable land, land under cereal production, and nitrous oxide emissions. In our regression model, heteroscedasticity is not observed, data follow a normal distribution, and there is a low correlation between factors, so we do not have the problem of multicollinearity. Machine-learning methods, such as random forest, are used to predict cereal yield responses to climacteric and other variables. Random Forest showed high accuracy compared to the other statistical models in the prediction of cereal yield. We found that changes in average temperature negatively affect cereal yield. The coefficients of fertilizer consumption, arable land, and land under cereal production are positively affecting production. Our results show that the Random Forest method is an effective and versatile machine-learning method for cereal yield prediction compared to the other two methods.

Keywords: cereal yield, climate change, machine learning, multiple regression model, random forest

Procedia PDF Downloads 84

Authors: José A. Menezes, Giordano Cabral, Bruno T. Gomes

Abstract:

Choosing good features is an essential part of machine learning. Recent techniques aim to automate this process. For instance, feature learning intends to learn the transformation of raw data into a useful representation to machine learning tasks. In automatic audio classification tasks, this is interesting since the audio, usually complex information, needs to be transformed into a computationally convenient input to process. Another technique tries to generate features by searching a feature space. Genetic algorithms, for instance, have being used to generate audio features by combining or modifying them. We find this approach particularly interesting and, despite the undeniable advances of feature learning approaches, we wanted to take a step forward in the use of genetic algorithms to find audio features, combining them with more conventional methods, like PCA, and inserting search control mechanisms, such as constraints over a confusion matrix. This work presents the results obtained on particular audio classification problems.

Keywords: feature generation, feature learning, genetic algorithm, music information retrieval

Procedia PDF Downloads 428

Authors: Y. Bablu Singh, B. S. Purkayashtha, Chungkham Yashawanta Singh

Abstract:

Morphological analysis forms the basic foundation in NLP applications including syntax parsing Machine Translation (MT), Information Retrieval (IR) and automatic indexing in all languages. It is the field of the linguistics; it can provide valuable information for computer based linguistics task such as lemmatization and studies of internal structure of the words. Computational Morphology is the application of morphological rules in the field of computational linguistics, and it is the emerging area in AI, which studies the structure of words, which are formed by combining smaller units of linguistics information, called morphemes: the building blocks of words. Morphological analysis provides about semantic and syntactic role in a sentence. It analyzes the Manipuri word forms and produces several grammatical information associated with the words. The Morphological Analyzer for Manipuri has been tested on 3500 Manipuri words in Shakti Standard format (SSF) using Meitei Mayek as source; thereby an accuracy of 80% has been obtained on a manual check.

Keywords: morphological analysis, machine translation, computational morphology, information retrieval, SSF

Procedia PDF Downloads 323

Authors: Simon Espigolé, Igor Shalyminov, Helen Hastie

Abstract:

Deep machine learning techniques including deep neural networks (DNN) have been used to model language and dialogue for conversational agents to perform tasks, such as giving technical support and also for general chit-chat. They have been shown to be capable of generating long, diverse and coherent sentences in end-to-end dialogue systems and natural language generation. However, these systems tend to imitate the training data and will only generate the concepts and language within the scope of what they have been trained on. This work explores how deep neural networks can be used in a task that would normally require human creativity, whereby the human would read the movie description and/or watch the movie and come up with a compelling, interesting movie title. This task differs from simple summarization in that the movie title may not necessarily be derivable from the content or semantics of the movie description. Here, we train a type of DNN called a sequence-to-sequence model (seq2seq) that takes as input a short textual movie description and some information on e.g. genre of the movie. It then learns to output a movie title. The idea is that the DNN will learn certain techniques and approaches that the human movie titler may deploy that may not be immediately obvious to the human-eye. To give an example of a generated movie title, for the movie synopsis: ‘A hitman concludes his legacy with one more job, only to discover he may be the one getting hit.’; the original, true title is ‘The Driver’ and the one generated by the model is ‘The Masquerade’. A human evaluation was conducted where the DNN output was compared to the true human-generated title, as well as a number of baselines, on three 5-point Likert scales: ‘creativity’, ‘naturalness’ and ‘suitability’. Subjects were also asked which of the two systems they preferred. The scores of the DNN model were comparable to the scores of the human-generated movie title, with means m=3.11, m=3.12, respectively. There is room for improvement in these models as they were rated significantly less ‘natural’ and ‘suitable’ when compared to the human title. In addition, the human-generated title was preferred overall 58% of the time when pitted against the DNN model. These results, however, are encouraging given the comparison with a highly-considered, well-crafted human-generated movie title. Movie titles go through a rigorous process of assessment by experts and focus groups, who have watched the movie. This process is in place due to the large amount of money at stake and the importance of creating an effective title that captures the audiences’ attention. Our work shows progress towards automating this process, which in turn may lead to a better understanding of creativity itself.

Keywords: creativity, deep machine learning, natural language generation, movies

Procedia PDF Downloads 324

Authors: Orit Shamir Balderman, Shamir Michal

Abstract:

Israel often deals with crisis situations, but most have been characterized as security crises (e.g., war). This is the first time that the Israel has dealt with a health and social emergency as part of a global crisis. The crisis began in January 2020 with the emergence of the novel coronavirus (Covid-19), which was defined as a pandemic (World Health Organization, 2020) and arrived in Israel in early March 2020. This study examined how single mothers by choice (SMBC) experience state anxiety (SA), social support, work–family conflict (WFC), and happiness. This group has not been studied in the context of crises in general or a global crisis. Using a snowball sample, 386 SMBCanswered an online questionnaire. The findings show a negative relationship between income and level of state anxiety. State anxiety was also negatively associated with social support, level of happiness, and WFC. Finally, a stepwise regression analysis indicated that happiness explained 34% of the variance in SA. We also found that most of the women did not turn to formal support agencies such as social workers, other Government Ministries, or municipal welfare. A positive and strong correlations was also found between SA and WFC. The findings of the study reinforce the understanding that although these women made a conscious and informed decision regarding the choice of their family cell, their situation is more complex in the absence of a spouse support. Therefore, this study, as other future studies in the field of SMBC, may contribute to the improvement of their social status and the understanding that they are a unique group. Although SMBC are a growing sector of society in the past few years, there are still special needs and special attention that is needed from the formal and informal supports systems. A comparative study of these two groups and in different countries would shed light on SA among mothers in general, regardless of their relationship status and location.Researchers should expand this study by comparing mothers in relationships and exploring how SMBC coped in other countries. In summary, the findings of the study contribute knowledge on three levels: (a) knowledge about SMBC in general and during crisis situations; (b) examination of social support using tools assessing receipt of assistance and support, some of which were developed for the present study; and (c) insights regarding counseling, accompaniment, and guidance of welfare mechanisms.

Keywords: single mothers by choice, state anxiety, social support, happiness, work–family conflict

Procedia PDF Downloads 81

Authors: Saeed Yazdani, Sima Mohamadi Amidabadi, Amir Mohamadi Nejsd, Farahnaz Nekoofar

Abstract:

As a result of uncertainty and doubts about the quantity of agricultural products, greater significance has been attached to risk management in the agricultural sector. Normally, farmers seek to minimize risks, and crop diversity has always been a means to reduce risk. The study at hand seeks to explore the long-term impact of crop diversity on income risk reduction. The timeframe of the study is 1998 to 2018. Initially, the Herfindahl index was used to estimate crop diversity in different periods, and next, the Hodrick-Prescott filter was applied to estimate income risk both in nominal and real terms. Finally, using the vector error correction model (VECM), the long-term impact of crop diversity on two modes of risk for the farmer's income has been estimated. Given the long-term pattern’s results, it is evident that in the long run, crop diversity can reduce income fluctuations in two nominal and real terms. Moreover, results showed that in case the fluctuation shock affects the agricultural income in the short run, to balance out the shock in nominal and real terms, 4 and 3 cycles are needed, respectively. In other words, in each cycle, 25% and 33% of the shock impact can be removed, respectively. Thus, as the results of the error correction coefficient showed, policies need to be put in place to prevent income shocks. In case of a shock, they need to be balanced out in a four-year period, taking inflation into account, and in a three-year period irrespective of the inflation, and reparative policies such as insurance services should be developed.

Keywords: risk, long-term model, Herfindahl index, time series model, vector error correction model

Procedia PDF Downloads 11

Authors: Mary Ann L. Halliday, Zoengpari Gohain

Abstract:

The stigma associated with HIV-AIDS negatively affect mental health and ability to effectively manage the disease. While the number of People living with HIV/AIDS (PLHIV) has been increasing day by day in Mizoram (a small north-eastern state in India), research on HIV/AIDS stigma has so far been limited. Despite the potential significance of Internalized HIV Stigma (IHS) in the lives of PLHIV, there has been very limited research in this area. It was therefore, felt necessary to explore the internalized HIV stigma, mental health, coping and perceived social support of PLHIV in Aizawl District, Mizoram. The present study was designed with the objectives to determine the degree of IHS, to study the relationship between the socio-demographic characteristics and level of IHS, to highlight the mental health status, coping strategies and perceived social support of PLHIV and to elucidate the relationship between these psychosocial variables. In order to achieve the objectives of the study, six hypotheses were formulated and statistical analyses conducted accordingly. The sample consisted of 300 PLWHA from Aizawl District, 150 males and 150 females, of the age group 20 to 70 years. Two- way classification of “Gender” (male and female) and three-way classification of “Level of IHS” (High IHS, Moderate IHS, Low IHS) on the dependent variables was employed, to elucidate the relationship between Internalized HIV Stigma, mental health, coping and perceived social support of PLHIV. The overall analysis revealed moderate level of IHS (67.3%) among PLHIV in Aizawl District, with a small proportion of subjects reporting high level of IHS. IHS was found to be significantly different on the basis of disclosure status, with the disclosure status of PLHIV accounting for 9% variability in IHS.  Results also revealed more or less good mental health among the participants, which was assessed by minimal depression (50.3%) and minimal anxiety (45%), with females with high IHS scoring significantly higher in both depression and anxiety (p<.01). Examination of the coping strategies of PLHIV found that the most frequently used coping styles were Acceptance (91%), Religion (84.3%), Planning (74.7%), Active Coping (66%) and Emotional Support (52.7%). High perception of perceived social support (48%) was found in the present study. Correlation analysis revealed significant positive relationships between IHS and depression as well as anxiety (p<.01), thus revealing that IHS negatively affects the mental health of PLHIV. Results however revealed that this effect may be lessened by the use of various coping strategies by PLHIV as well as their perception of social support.

Keywords: Aizawl, anxiety, depression, internalized HIV stigma, HIV/AIDS, mental health, mizoram, perceived social support

Procedia PDF Downloads 255

Authors: Radoslav Židek, Veronika Šidlová, Radovan Kasarda, Birgit Fuerst-Waltl

Abstract:

Machine learning represents a set of topics dealing with the creation and evaluation of algorithms that facilitate pattern recognition, classification, and prediction, based on models derived from existing data. The data can present identification patterns which are used to classify into groups. The result of the analysis is the pattern which can be used for identification of data set without the need to obtain input data used for creation of this pattern. An important requirement in this process is careful data preparation validation of model used and its suitable interpretation. For breeders, it is important to know the origin of animals from the point of the genetic diversity. In case of missing pedigree information, other methods can be used for traceability of animal´s origin. Genetic diversity written in genetic data is holding relatively useful information to identify animals originated from individual countries. We can conclude that the application of data mining for molecular genetic data using supervised learning is an appropriate tool for hypothesis testing and identifying an individual.

Keywords: genetic data, Pinzgau cattle, supervised learning, machine learning

Procedia PDF Downloads 542