Search results for: hierarchical text classification models

Authors: Dionisio Andujar, Juan lópez-Correa, Hugo Moreno, Angela Ri

Abstract:

The increased number of weeds in tomato crops highly lower yields. Weed identification with the aim of machine learning is important to carry out site-specific control. The last advances in computer vision are a powerful tool to face the problem. The analysis of RGB (Red, Green, Blue) images through Artificial Neural Networks had been rapidly developed in the past few years, providing new methods for weed classification. The development of the algorithms for crop and weed species classification looks for a real-time classification system using Object Detection algorithms based on Convolutional Neural Networks. The site study was located in commercial corn fields. The classification system has been tested. The procedure can detect and classify weed seedlings in tomato fields. The input to the Neural Network was a set of 10,000 RGB images with a natural infestation of Cyperus rotundus l., Echinochloa crus galli L., Setaria italica L., Portulaca oeracea L., and Solanum nigrum L. The validation process was done with a random selection of RGB images containing the aforementioned species. The mean average precision (mAP) was established as the metric for object detection. The results showed agreements higher than 95 %. The system will provide the input for an online spraying system. Thus, this work plays an important role in Site Specific Weed Management by reducing herbicide use in a single step.

Keywords: deep learning, object detection, cnn, tomato, weeds

Procedia PDF Downloads 103

Authors: Cristina Felipeto, Catherine Bore, Eduardo Calil

Abstract:

This work aims to analyze and compare the punctuation marks (PM) in school texts of Brazilian and French students and the comments on these PM made spontaneously by the students during the ongoing text. Assuming textual genetics as an investigative field within a dialogical and enunciative approach, we defined a common methodological design in two 1st year classrooms (7 years old) of the primary school, one classroom in Brazil (Maceio) and the other one in France (Paris). Through a multimodal capture system of writing processes in real time and space (Ramos System), we recorded the collaborative writing proposal in dyads in each of the classrooms. This system preserves the classroom’s ecological characteristics and provides a video recording synchronized with dialogues, gestures and facial expressions of the students, the stroke of the pen’s ink on the sheet of paper and the movement of the teacher and students in the classroom. The multimodal register of the writing process allowed access to the text in progress and the comments made by the students on what was being written. In each proposed text production, teachers organized their students in dyads and requested that they should talk, combine and write a fictional narrative. We selected a Dyad of Brazilian students (BD) and another Dyad of French students (FD) and we have filmed 6 proposals for each of the dyads. The proposals were collected during the 2nd Term of 2013 (Brazil) and 2014 (France). In 6 texts written by the BD there were identified 39 PMs and 825 written words (on average, a PM every 23 words): Of these 39 PMs, 27 were highlighted orally and commented by either student. In the texts written by the FD there were identified 48 PMs and 258 written words (on average, 1 PM every 5 words): Of these 48 PM, 39 were commented by the French students. Unlike what the studies on punctuation acquisition point out, the PM that occurred the most were hyphens (BD) and commas (FD). Despite the significant difference between the types and quantities of PM in the written texts, the recognition of the need for writing PM in the text in progress and the comments have some common characteristics: i) the writing of the PM was not anticipated in relation to the text in progress, then they were added after the end of a sentence or after the finished text itself; ii) the need to add punctuation marks in the text came after one of the students had ‘remembered’ that a particular sign was needed; iii) most of the PM inscribed were not related to their linguistic functions, but the graphic-visual feature of the text; iv) the comments justify or explain the PM, indicating metalinguistic reflections made by the students. Our results indicate how the comments of the BD and FD express the dialogic and subjective nature of knowledge acquisition. Our study suggests that the initial learning of PM depends more on its graphic features and interactional conditions than on its linguistic functions.

Keywords: collaborative writing, erasure, graphic marks, learning, metalinguistic awareness, textual genesis

Procedia PDF Downloads 162

Authors: Yusuf Garba Baba

Abstract:

The construction industry and housing subsector are fraught with risks that have the potential of negatively impacting on the achievement of project objectives. The success or otherwise of most construction projects depends to large extent on how well these risks have been managed. The recent paradigm shift by the subsector to use of formal risk management approach in contrast to hitherto developed rules of thumb means that risks must not only be identified but also properly assessed and responded to in a systematic manner. The study focused on identifying risks associated with housing development projects and prioritisation assessment of the identified risks in order to provide basis for informed decision. The study used a three-step identification framework: review of literature for similar projects, expert consultation and questionnaire based survey to identify potential risk factors. Delphi survey method was employed in carrying out the relative prioritization assessment of the risks factors using computer-based Analytical Hierarchical Process (AHP) software. The results show that 19 out of the 50 risks significantly impact on housing development projects. The study concludes that although significant numbers of risk factors have been identified as having relevance and impacting to housing construction projects, economic risk group and, in particular, ‘changes in demand for houses’ is prioritised by most developers as posing a threat to the achievement of their housing development objectives. Unless these risks are carefully managed, their effects will continue to impede success in these projects. The study recommends the adoption and use of the combination of multi-technique identification framework and AHP prioritization assessment methodology as a suitable model for the assessment of risks in housing development projects.

Keywords: risk management, risk identification, risk analysis, analytic hierarchical process

Procedia PDF Downloads 118

Authors: M. Bodner, M. Scampicchio

Abstract:

Fourier Transform Infrared (FT-IR) spectroscopy coupled with chemometrics was used to distinguish between butter samples and non-butter samples. Further, quantification of the content of margarine in adulterated butter samples was investigated. Fingerprinting region (1400-800 cm^–1) was used to develop unsupervised pattern recognition (Principal Component Analysis, PCA), supervised modeling (Soft Independent Modelling by Class Analogy, SIMCA), classification (Partial Least Squares Discriminant Analysis, PLS-DA) and regression (Partial Least Squares Regression, PLS-R) models. PCA of the fingerprinting region shows a clustering of the two sample types. All samples were classified in their rightful class by SIMCA approach; however, nine adulterated samples (between 1% and 30% w/w of margarine) were classified as belonging both at the butter class and at the non-butter one. In the two-class PLS-DA model’s (R² = 0.73, RMSEP, Root Mean Square Error of Prediction = 0.26% w/w) sensitivity was 71.4% and Positive Predictive Value (PPV) 100%. Its threshold was calculated at 7% w/w of margarine in adulterated butter samples. Finally, PLS-R model (R² = 0.84, RMSEP = 16.54%) was developed. PLS-DA was a suitable classification tool and PLS-R a proper quantification approach. Results demonstrate that FT-IR spectroscopy combined with PLS-R can be used as a rapid, simple and safe method to identify pure butter samples from adulterated ones and to determine the grade of adulteration of margarine in butter samples.

Keywords: adulterated butter, margarine, PCA, PLS-DA, PLS-R, SIMCA

Procedia PDF Downloads 143

Authors: Pham Van Nha, Le Cam Binh

Abstract:

Particle swarm optimization (PSO) is a population-based stochastic optimization algorithm. PSO was inspired by the natural behavior of birds and fish in migration and foraging for food. PSO is considered as a multidisciplinary optimization model that can be applied in various optimization problems. PSO’s ideas are simple and easy to understand but PSO is only applied in simple model problems. We think that in order to expand the applicability of PSO in complex problems, PSO should be described more explicitly in the form of a mathematical model. In this paper, we represent PSO in a mathematical model and apply in the multivariate data classification. First, PSOs general mathematical model (MPSO) is analyzed as a universal optimization model. Then, Model of Optimal Centroids (MOC) is proposed for the multivariate data classification. Experiments were conducted on some benchmark data sets to prove the effectiveness of MOC compared with several proposed schemes.

Keywords: analysis of optimization, artificial intelligence based optimization, optimization for learning and data analysis, global optimization

Procedia PDF Downloads 208

Authors: Thirayu Jumsai Na Ayudhya

Abstract:

The attempt to understand about what architecture means to people as they go about their everyday life revealed that knowledge such as environmental psychology, environmental perception, environmental aesthetics, inadequately address the contextualized and holistic theoretical framework. In my previous research, it was found that people’s making senses of their everyday architecture can be addressed in terms of four super‐ordinate themes; (1) building in urban (text), (2) building in (text), (3) building in human (text), (4) and building in time (text). In this research, Bangkok CBD was selected as the focal urban context that the integrated style of architecture is noticeable. It is expected that in a unique urban context like Bangkok CBD unprecedented super-ordinate themes will be unveiled through the reflection of people’s everyday experiences. In this research, people’s architectural experience conducted in Bangkok CBD, Thailand, will be presented succinctly. The research addresses the question of how do people make sense of their everyday architecture/buildings especially in a unique urban context, Bangkok CBD, and identifies ways in which people make sense of their everyday architecture. Two key methodologies are adopted. First, Participant-Produced-Photograph (PPP) allows people to express their experiences of the everyday urban context freely without any interference or forced-data generating by researchers. Second, Interpretative Phenomenological Analysis (IPA) are also applied as main methodologies. With IPA methodology, a small pool of participants is considered giving the detailed level of analysis and its potential to produce a meaningful outcome.

Keywords: architectural experience, building appreciation, design psychology, environmental psychology, sense-making, the everyday experience, transactional theory

Procedia PDF Downloads 336

Authors: Vince Liégeois

Abstract:

Language of immediacy and distance: Within their discourse theory, Koch & Oesterreicher establish a distinction between a language of immediacy and a language of distance. The former refers to those discourses which are oriented more towards a spoken norm, whereas the latter entails discourses oriented towards a written norm, regardless of whether they are realised phonically or graphically. This means that an utterance can be realised phonically but oriented more towards the written language norm (e.g., a scientific presentation or eulogy) or realised graphically but oriented towards a spoken norm (e.g., a scribble or chat messages). Research desiderata: The methodological approach from Koch & Oesterreicher has often been criticised for not providing a corpus-linguistic methodology, which makes it difficult to work with quantitative data or address large text collections within this research paradigm. Consequently, the Koch & Oesterreicher approach has difficulties gaining ground in those research areas which rely more on corpus linguistic research models, like text linguistics and LSP-research. A combinatory approach: Accordingly, we want to establish a combinatory approach with corpus-based linguistic methodology. To this end, we propose to (i) include data about the context of an utterance (e.g., monologicity/dialogicity, familiarity with the speaker) – which were called “conditions of communication” in the original work of Koch & Oesterreicher – and (ii) correlate the linguistic phenomenon at the centre of the inquiry (e.g., evaluation markers) to a group of linguistic phenomena deemed typical for either distance- or immediacy-language. Based on these two parameters, linguistic phenomena and texts could then be mapped on an immediacy-distance continuum. Pilot study: To illustrate the benefits of this approach, we will conduct a pilot study on evaluation phenomena in French television weather reports, a form of domain-sensitive discourse which has often been cited as an example of a “text genre”. Within this text genre, we will look at so-called “evaluation markers,” e.g., fixed strings like bad weather, stifling hot, and “no luck today!”. These evaluation markers help to communicate the coming weather situation towards the lay audience but have not yet been studied within the Koch & Oesterreicher research paradigm. Accordingly, we want to figure out whether said evaluation markers are more typical for those weather reports which tend more towards immediacy or those which tend more towards distance. To this aim, we collected a corpus with different kinds of television weather reports,e.g., as part of the news broadcast, including dialogue. The evaluation markers themselves will be studied according to the explained methodology, by correlating them to (i) metadata about the context and (ii) linguistic phenomena characterising immediacy-language: repetition, deixis (personal, spatial, and temporal), a freer choice of tense and right- /left-dislocation. Results: Our results indicate that evaluation markers are more dominantly present in those weather reports inclining towards immediacy-language. Based on the methodology established above, we have gained more insight into the working of evaluation markers in the domain-sensitive text genre of (television) weather reports. For future research, it will be interesting to determine whether said evaluation markers are also typical for immediacy-language-oriented in other domain-sensitive discourses.

Keywords: corpus-based linguistics, evaluation markers, language of immediacy and distance, weather reports

Procedia PDF Downloads 219

Authors: Apostolos Kalatzis, Ashish Teotia, Vishnunarayan Girishan Prabhu, Laura Stanley

Abstract:

Emotions are functional behaviors influenced by thoughts, stimuli, and other factors that induce neurophysiological changes in the human body. Understanding and classifying emotions are challenging as individuals have varying perceptions of their environments. Therefore, it is crucial that there are publicly available databases and virtual reality (VR) based environments that have been scientifically validated for assessing emotional classification. This study utilized two commercially available VR applications (Guided Meditation VR™ and Richie’s Plank Experience™) to induce acute stress and calm state among participants. Subjective and objective measures were collected to create a validated multimodal dataset and classification scheme for affective state classification. Participants’ subjective measures included the use of the Self-Assessment Manikin, emotional cards and 9 point Visual Analogue Scale for perceived stress, collected using a Virtual Reality Assessment Tool developed by our team. Participants’ objective measures included Electrocardiogram and Respiration data that were collected from 25 participants (15 M, 10 F, Mean = 22.28  4.92). The features extracted from these data included heart rate variability components and respiration rate, both of which were used to train two machine learning models. Subjective responses validated the efficacy of the VR applications in eliciting the two desired affective states; for classifying the affective states, a logistic regression (LR) and a support vector machine (SVM) with a linear kernel algorithm were developed. The LR outperformed the SVM and achieved 93.8%, 96.2%, 93.8% leave one subject out cross-validation accuracy, precision and recall, respectively. The VR assessment tool and data collected in this study are publicly available for other researchers.

Keywords: affective computing, biosignals, machine learning, stress database

Procedia PDF Downloads 142

Authors: Isahakyan Heghine

Abstract:

Intertextuality, being in the centre of attention of both linguists and literary critics, is vividly expressed in the outstanding British novelist and philosopher J. Fowles' works. 'The Magus’ is a deep psychological and philosophical novel with vivid intertextual links with the Greek mythology and authors from different epochs. The aim of the paper is to show how intertextuality might serve as a dialogue between two authors (J. Fowles and J. Donne) disguised in the dialogue of two protagonists of the novel : Conchis and Nicholas. Contrastive viewpoints concerning man's isolation, loneliness are stated in the dialogue. Due to the conceptual analysis of the text it becomes possible both to decode the conceptual information of the text and find out its intertextual links.

Keywords: dialogue, conceptual analysis, isolation, intertextuality

Procedia PDF Downloads 329

Authors: Taghreed Alghamdi, Wendy Hall, David Millard

Abstract:

Massive Open Online Courses (MOOCs) have recently gained widespread interest in the academic world, starting a wide range of discussion of a number of issues. One of these issues, using MOOCs in teaching and learning in the higher education by integrating MOOCs’ contents with traditional face-to-face activities in blended learning format, is called blended MOOCs (bMOOCs) and is intended not to replace traditional learning but to enhance students learning. Most research on MOOCs has focused on students’ perception and institutional threats whereas there is a lack of published research on academics’ experiences and practices. Thus, the first aim of the study is to develop a classification of blended MOOCs models by conducting a systematic literature review, classifying 19 different case studies, and identifying the broad types of bMOOCs models namely: Supplementary Model and Integrated Model. Thus, the analyses phase will emphasize on these different types of bMOOCs models in terms of adopting MOOCs by lecturers. The second aim of the study is to improve the understanding of lecturers’ acceptance of bMOOCs by investigate the factors that influence academics’ acceptance of using MOOCs in traditional learning by distributing an online survey to lecturers who participate in MOOCs platforms. These factors can help institutions to encourage their lecturers to integrate MOOCs with their traditional courses in universities.

Keywords: acceptance, blended learning, blended MOOCs, higher education, lecturers, MOOCs, professors

Procedia PDF Downloads 131

Authors: Kritiyaporn Kunsook

Abstract:

Machine learning algorithms (MLAs) such us artificial neural networks (ANNs), decision tree, support vector machines (SVMs), Naïve Bayes, and ensemble classifier by voting are powerful data driven methods that are relatively less widely used in the mapping of technique of system, and thus have not been comparatively evaluated together thoroughly in this field. The performances of a series of MLAs, ANNs, decision tree, SVMs, Naïve Bayes, and ensemble classifier by voting in technique of hydroponic systems prospectively modeling are compared based on the accuracy of each model. Classification of hydroponic systems only covers the test samples from vegetables grown with Nutrient film technique (NFT) and Deep flow technique (DFT). The feature, which are the characteristics of vegetables compose harvesting height width, temperature, require light and color. The results indicate that the classification performance of the ANNs is 98%, decision tree is 98%, SVMs is 97.33%, Naïve Bayes is 96.67%, and ensemble classifier by voting is 98.96% algorithm respectively.

Keywords: artificial neural networks, decision tree, support vector machines, naïve Bayes, ensemble classifier by voting

Procedia PDF Downloads 372

Authors: Chia-Hau Liu, Tai-Yue Wang

Abstract:

Traditional multivariate control charts assume that measurement from manufacturing processes follows a multivariate normal distribution. However, this assumption may not hold or may be difficult to verify because not all the measurement from manufacturing processes are normal distributed in practice. This study develops a new multivariate control chart for monitoring the processes with non-normal data. We propose a mechanism based on integrating the one-class classification method and the adaptive technique. The adaptive technique is used to improve the sensitivity to small shift on one-class classification in statistical process control. In addition, this design provides an easy way to allocate the value of type I error so it is easier to be implemented. Finally, the simulation study and the real data from industry are used to demonstrate the effectiveness of the propose control charts.

Keywords: multivariate control chart, statistical process control, one-class classification method, non-normal data

Procedia PDF Downloads 422

Authors: Ekin Ozer

Abstract:

Assessment of structural reliability is essential for efficient use of civil infrastructure which is subjected hazardous events. Dynamic analysis of finite element models is a commonly used tool to simulate structural behavior and estimate its performance accordingly. However, theoretical models purely based on preliminary assumptions and design drawings may deviate from the actual behavior of the structure. This study proposes up-to-date reliability estimation procedures which engages actual bridge vibration data modifying finite element models for finite element model updating and performing reliability estimation, accordingly. The proposed method utilizes vibration response measurements of bridge structures to identify modal parameters, then uses these parameters to calibrate finite element models which are originally based on design drawings. The proposed method does not only show that reliability estimation based on updated models differs from the original models, but also infer that non-updated models may overestimate the structural capacity.

Keywords: earthquake engineering, engineering vibrations, reliability estimation, structural health monitoring

Procedia PDF Downloads 222

Authors: Taha SamadSoltani, Peyman Rezaei Hachesu, Marjan GhaziSaeedi, Maryam Zolnoori

Abstract:

Introduction: Data mining defined as a process to find patterns and relationships along data in the database to build predictive models. Application of data mining extended in vast sectors such as the healthcare services. Medical data mining aims to solve real-world problems in the diagnosis and treatment of diseases. This method applies various techniques and algorithms which have different accuracy and precision. The purpose of this study was to apply knowledge discovery and data mining techniques for the diagnosis of asthma based on patient symptoms and history. Method: Data mining includes several steps and decisions should be made by the user which starts by creation of an understanding of the scope and application of previous knowledge in this area and identifying KD process from the point of view of the stakeholders and finished by acting on discovered knowledge using knowledge conducting, integrating knowledge with other systems and knowledge documenting and reporting.in this study a stepwise methodology followed to achieve a logical outcome. Results: Sensitivity, Specifity and Accuracy of KNN, SVM, Naïve bayes, NN, Classification tree and CN2 algorithms and related similar studies was evaluated and ROC curves were plotted to show the performance of the system. Conclusion: The results show that we can accurately diagnose asthma, approximately ninety percent, based on the demographical and clinical data. The study also showed that the methods based on pattern discovery and data mining have a higher sensitivity compared to expert and knowledge-based systems. On the other hand, medical guidelines and evidence-based medicine should be base of diagnostics methods, therefore recommended to machine learning algorithms used in combination with knowledge-based algorithms.

Keywords: asthma, datamining, classification, machine learning

Procedia PDF Downloads 447

Authors: Carlos Roncero-Parra, Alfonso Parreño-Torres, Jorge Mateo Sotos, Alejandro L. Borja

Abstract:

In this research, different methods based on machine/deep learning algorithms are presented for the classification and diagnosis of patients with mental disorders such as alzheimer. For this purpose, the signals obtained from 32 unipolar electrodes identified by non-invasive EEG were examined, and their basic properties were obtained. More specifically, different well-known machine learning based classifiers have been used, i.e., support vector machine (SVM), Bayesian linear discriminant analysis (BLDA), decision tree (DT), Gaussian Naïve Bayes (GNB), K-nearest neighbor (KNN) and Convolutional Neural Network (CNN). A total of 668 patients from five different hospitals have been studied in the period from 2011 to 2021. The best accuracy is obtained was around 93 % in both ADM and ADA classifications. It can be concluded that such a classification will enable the training of algorithms that can be used to identify and classify different mental disorders with high accuracy.

Keywords: alzheimer, machine learning, deep learning, EEG

Procedia PDF Downloads 126

Authors: Reiner-Ace P. Mateo, Vince Paolo F. Obille

Abstract:

The traditional method of classifying the potential mineral resources requires a significant amount of time and money. In this paper, an alternative way to classify potential mineral resources with GIS application in Surigao del Sur. The three (3) analog map data inputs integrated to GIS are geologic map, topographic map, and land cover/vegetation map. The indicators used in the classification of potential nickel laterite integrated from the analog map data inputs are a geologic indicator, which is the presence of ultramafic rock from the geologic map; slope indicator and the presence of plateau edges from the topographic map; areas of forest land, grassland, and shrublands from the land cover/vegetation map. The potential mineral of the area was classified from low up to very high potential. The produced mineral potential classification map of Surigao del Sur has an estimated 4.63% low nickel laterite potential, 42.15% medium nickel laterite potential, 43.34% high nickel laterite potential, and 9.88% very high nickel laterite from its ultramafic terrains. For the validation of the produced map, it was compared with known occurrences of nickel laterite in the area using a nickel mining tenement map from the area with the application of remote sensing. Three (3) prominent nickel mining companies were delineated in the study area. The generated potential classification map of nickel-laterite in Surigao Del Sur may be of aid to the mining companies which are currently in the exploration phase in the study area. Also, the currently operating nickel mines in the study area can help to validate the reliability of the mineral classification map produced.

Keywords: mineral potential classification, nickel laterites, GIS, remote sensing, Surigao del Sur

Procedia PDF Downloads 123

Authors: Javad Khaligh, Aghileh Heydari, Ali Akbar Heydari

Abstract:

Mathematical epidemiological models for the spread of disease through a population are used to predict the prevalence of a disease or to study the impacts of treatment or prevention measures. Initial conditions for these models are measured from statistical data collected from a population since these initial conditions can never be exact, the presence of chaos in mathematical models has serious implications for the accuracy of the models as well as how epidemiologists interpret their findings. This paper confirms the chaotic behavior of a model for dengue fever and SI by investigating sensitive dependence, bifurcation, and 0-1 test under a variety of initial conditions.

Keywords: epidemiological models, SEIR disease model, bifurcation, chaotic behavior, 0-1 test

Procedia PDF Downloads 324

Authors: Jeremy Jenrette, Z. Y. C. Liu, Pranav Chimote, Edward Fox, Trevor Hastie, Francesco Ferretti

Abstract:

Suitable shark conservation depends on well-informed population assessments. Direct methods such as scientific surveys and fisheries monitoring are adequate for defining population statuses, but species-specific indices of abundance and distribution coming from these sources are rare for most shark species. We can rapidly fill these information gaps by boosting media-based remote monitoring efforts with machine learning and automation. We created a database of shark images by sourcing 24,546 images covering 219 species of sharks from the web application spark pulse and the social network Instagram. We used object detection to extract shark features and inflate this database to 53,345 images. We packaged object-detection and image classification models into a Shark Detector bundle. We developed the Shark Detector to recognize and classify sharks from videos and images using transfer learning and convolutional neural networks (CNNs). We applied these models to common data-generation approaches of sharks: boosting training datasets, processing baited remote camera footage and online videos, and data-mining Instagram. We examined the accuracy of each model and tested genus and species prediction correctness as a result of training data quantity. The Shark Detector located sharks in baited remote footage and YouTube videos with an average accuracy of 89\%, and classified located subjects to the species level with 69\% accuracy (n =\ eight species). The Shark Detector sorted heterogeneous datasets of images sourced from Instagram with 91\% accuracy and classified species with 70\% accuracy (n =\ 17 species). Data-mining Instagram can inflate training datasets and increase the Shark Detector’s accuracy as well as facilitate archiving of historical and novel shark observations. Base accuracy of genus prediction was 68\% across 25 genera. The average base accuracy of species prediction within each genus class was 85\%. The Shark Detector can classify 45 species. All data-generation methods were processed without manual interaction. As media-based remote monitoring strives to dominate methods for observing sharks in nature, we developed an open-source Shark Detector to facilitate common identification applications. Prediction accuracy of the software pipeline increases as more images are added to the training dataset. We provide public access to the software on our GitHub page.

Keywords: classification, data mining, Instagram, remote monitoring, sharks

Procedia PDF Downloads 121

Authors: Xu Jiaqiao

Abstract:

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

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

Procedia PDF Downloads 94

Authors: Hamda Ajmal, Karen Young, Ruth Melia, John Bogue, Mary O'Sullivan, Jim Duggan, Hannah Wood

Abstract:

The Covid-19 pandemic led to a range of public health mitigation strategies in order to suppress the SARS-CoV-2 virus. The drastic changes in everyday life due to lockdowns had the potential for a significant negative impact on public mental health, and a key public health goal is to now assess the evidence from available Irish datasets to provide useful insights on this issue. Text-50808 is an online text-based mental health support service, established in Ireland in 2020, and can provide a measure of revealed distress and mental health concerns across the population. The aim of this study is to explore statistical associations between public mental health in Ireland and the Covid-19 pandemic. Uniquely, this study combines two measures of emotional wellbeing in Ireland: (1) weekly text volume at Text-50808, and (2) emotional wellbeing indicators reported by respondents of the Amárach public opinion survey, carried out on behalf of the Department of Health, Ireland. For this analysis, a multivariate graphical exploratory data analysis (EDA) was performed on the Text-50808 dataset dated from 15th June 2020 to 30th June 2021. This was followed by time-series analysis of key mental health indicators including: (1) the percentage of daily/weekly texts at Text-50808 that mention Covid-19 related issues; (2) the weekly percentage of people experiencing anxiety, boredom, enjoyment, happiness, worry, fear and stress in Amárach survey; and Covid-19 related factors: (3) daily new Covid-19 case numbers; (4) daily stringency index capturing the effect of government non-pharmaceutical interventions (NPIs) in Ireland. The cross-correlation function was applied to measure the relationship between the different time series. EDA of the Text-50808 dataset reveals significant peaks in the volume of texts on days prior to level 3 lockdown and level 5 lockdown in October 2020, and full level 5 lockdown in December 2020. A significantly high positive correlation was observed between the percentage of texts at Text-50808 that reported Covid-19 related issues and the percentage of respondents experiencing anxiety, worry and boredom (at a lag of 1 week) in Amárach survey data. There is a significant negative correlation between percentage of texts with Covid-19 related issues and percentage of respondents experiencing happiness in Amárach survey. Daily percentage of texts at Text-50808 that reported Covid-19 related issues to have a weak positive correlation with daily new Covid-19 cases in Ireland at a lag of 10 days and with daily stringency index of NPIs in Ireland at a lag of 2 days. The sudden peaks in text volume at Text-50808 immediately prior to new restrictions in Ireland indicate an association between a rise in mental health concerns following the announcement of new restrictions. There is also a high correlation between emotional wellbeing variables in the Amárach dataset and the number of weekly texts at Text-50808, and this confirms that Text-50808 reflects overall public sentiment. This analysis confirms the benefits of the texting service as a community surveillance tool for mental health in the population. This initial EDA will be extended to use multivariate modeling to predict the effect of additional Covid-19 related factors on public mental health in Ireland.

Keywords: COVID-19 pandemic, data analysis, digital health, mental health, public health, digital health

Procedia PDF Downloads 143

Authors: T. Praveenkumar, Kulpreet Singh, Divy Bhanpuriya, M. Saimurugan

Abstract:

This study analysed the classification accuracy for gearbox faults using Machine Learning Techniques. Gearboxes are widely used for mechanical power transmission in rotating machines. Its rotating components such as bearings, gears, and shafts tend to wear due to prolonged usage, causing fluctuating vibrations. Increasing the dependability of mechanical components like a gearbox is hampered by their sealed design, which makes visual inspection difficult. One way of detecting impending failure is to detect a change in the vibration signature. The current study proposes various machine learning algorithms, with aid of these vibration signals for obtaining the fault classification accuracy of an automotive 4-Speed synchromesh gearbox. Experimental data in the form of vibration signals were acquired from a 4-Speed synchromesh gearbox using Data Acquisition System (DAQs). Statistical features were extracted from the acquired vibration signal under various operating conditions. Then the extracted features were given as input to the algorithms for fault classification. Supervised Machine Learning algorithms such as Support Vector Machines (SVM) and unsupervised algorithms such as Deep Feed Forward Neural Network (DFFNN), Deep Belief Networks (DBN) algorithms are used for fault classification. The fusion of DBN & DFFNN classifiers were architected to further enhance the classification accuracy and to reduce the computational complexity. The fault classification accuracy for each algorithm was thoroughly studied, tabulated, and graphically analysed for fused and individual algorithms. In conclusion, the fusion of DBN and DFFNN algorithm yielded the better classification accuracy and was selected for fault detection due to its faster computational processing and greater efficiency.

Keywords: deep belief networks, DBN, deep feed forward neural network, DFFNN, fault diagnosis, fusion of algorithm, vibration signal

Procedia PDF Downloads 113

Authors: Jaroslav Masek, Juraj Camaj, Eva Nedeliakova

Abstract:

The paper is focused on the operational model for transport the single wagon consignments on railway network by using two different models of train formation. The paper gives an overview of possibilities of improving the quality of transport services. Paper deals with two models used in problematic of train formatting - time continuously and time discrete. By applying these models in practice, the transport company can guarantee a higher quality of service and expect increasing of transport performance. The models are also applicable into others transport networks. The models supplement a theoretical problem of train formation by new ways of looking to affecting the organization of wagon flows.

Keywords: train formation, wagon flows, marshalling yard, railway technology

Procedia PDF Downloads 437

Authors: Kwangmin Joo

Abstract:

Automatic detection of lumbar vertebrae and classification method is proposed for evaluating the degree of disc narrowing. Prior to classification, deep learning based segmentation is applied to detect individual lumbar vertebra. M-net is applied to segment five lumbar vertebrae and fine-tuning segmentation is employed to improve the accuracy of segmentation. Using the features extracted from previous step, clustering technique, k-means clustering, is applied to estimate the degree of disc space narrowing under four grade scoring system. As preliminary study, techniques proposed in this research could help building an automatic scoring system to diagnose the severity of disc narrowing from X-ray images.

Keywords: Disc space narrowing, Degenerative disc disorders, Deep learning based segmentation, Clustering technique

Procedia PDF Downloads 125

Authors: Linghui Meng, James Atlas, Deborah Munro

Abstract:

There is an increasing demand for prosthetics capable of mimicking natural limb movements and hand gestures, but precise movement control of prosthetics using only electrode signals continues to be challenging. This study considers the implementation of machine learning as a means of improving accuracy and presents an initial investigation into hand gesture recognition using models based on electromyographic (EMG) signals. EMG signals, which capture muscle activity, are used as inputs to machine learning algorithms to improve prosthetic control accuracy, functionality and adaptivity. Using logistic regression, a machine learning classifier, this study evaluates the accuracy of classifying two hand gestures from the publicly available Ninapro dataset using two-time series feature extraction algorithms: Time Series Feature Extraction (TSFE) and Convolutional Neural Networks (CNNs). Trials were conducted using varying numbers of EMG channels from one to eight to determine the impact of channel quantity on classification accuracy. The results suggest that although both algorithms can successfully distinguish between hand gesture EMG signals, CNNs outperform TSFE in extracting useful information for both accuracy and computational efficiency. In addition, although more channels of EMG signals provide more useful information, they also require more complex and computationally intensive feature extractors and consequently do not perform as well as lower numbers of channels. The findings also underscore the potential of machine learning techniques in developing more effective and adaptive prosthetic control systems.

Keywords: EMG, machine learning, prosthetic control, electromyographic prosthetics, hand gesture classification, CNN, computational neural networks, TSFE, time series feature extraction, channel count, logistic regression, ninapro, classifiers

Procedia PDF Downloads 28

Authors: Emilio Galdeano-Gómez, Juan C. Pérez-Mesa, Laura Piedra-Muñoz, María C. García-Barranco, Jesús Hernández-Rubio

Abstract:

The situation in which firms engage in simultaneous cooperation and competition with each other is a phenomenon known as co-opetition. This scenario has received increasing attention in business economics and management analyses. In the domain of supply chain networks and for small and medium-sized enterprises, SMEs, these strategies are of greater relevance given the complex environment of globalization and competition in open markets. These firms face greater challenges regarding technology and access to specific resources due to their limited capabilities and limited market presence. Consequently, alliances and collaborations with both buyers and suppliers prove to be key elements in overcoming these constraints. However, rivalry and competition are also regarded as major factors in successful internationalization processes, as they are drivers for firms to attain a greater degree of specialization and to improve efficiency, for example enabling them to allocate scarce resources optimally and providing incentives for innovation and entrepreneurship. The present work aims to contribute to the literature on SMEs’ internationalization strategies. The sample is constituted by a panel data of marketing firms from the Andalusian food sector and a multivariate regression analysis is developed, measuring variables of co-opetition and international activity. The hierarchical regression equations method has been followed, thus resulting in three estimated models: the first one excluding the variables indicative of channel type, while the latter two include the international retailer chain and wholesaler variable. The findings show that the combination of several factors leads to a complex scenario of inter-organizational relationships of cooperation and competition. In supply chain management analyses, these relationships tend to be classified as either buyer-supplier (vertical level) or supplier-supplier relationships (horizontal level). Several buyers and suppliers tend to participate in supply chain networks, and in which the form of governance (hierarchical and non-hierarchical) influences cooperation and competition strategies. For instance, due to their market power and/or their closeness to the end consumer, some buyers (e.g. large retailers in food markets) can exert an influence on the selection and interaction of several of their intermediate suppliers, thus endowing certain networks in the supply chain with greater stability. This hierarchical influence may in turn allow these suppliers to develop their capabilities (e.g. specialization) to a greater extent. On the other hand, for those suppliers that are outside these networks, this environment of hierarchy, characterized by a “hub firm” or “channel master”, may provide an incentive for developing their co-opetition relationships. These results prove that the analyzed firms have experienced considerable growth in sales to new foreign markets, mainly in Europe, dealing with large retail chains and wholesalers as main buyers. This supply industry is predominantly made up of numerous SMEs, which has implied a certain disadvantage when dealing with the buyers, as negotiations have traditionally been held on an individual basis and in the face of high competition among suppliers. Over recent years, however, cooperation among these marketing firms has become more common, for example regarding R&D, promotion, scheduling of production and sales.

Keywords: co-petition networks, international supply chain, maketing agrifood firms, SMEs strategies

Procedia PDF Downloads 79

Authors: Alexiou Dimitra, Fragkaki Maria

Abstract:

The objective of the paper is the study of geographic, economic and educational variables and their contribution to determine the position of each member-state among the EU-28 countries based on the values of seven variables as given by Eurostat. The Data Analysis methods of Multiple Factorial Correspondence Analysis (MFCA) Principal Component Analysis and Factor Analysis have been used. The cross tabulation tables of data consist of the values of seven variables for the 28 countries for 2014. The data are manipulated using the CHIC Analysis V 1.1 software package. The results of this program using MFCA and Ascending Hierarchical Classification are given in arithmetic and graphical form. For comparison reasons with the same data the Factor procedure of Statistical package IBM SPSS 20 has been used. The numerical and graphical results presented with tables and graphs, demonstrate the agreement between the two methods. The most important result is the study of the relation between the 28 countries and the position of each country in groups or clouds, which are formed according to the values of the corresponding variables.

Keywords: Multiple Factorial Correspondence Analysis, Principal Component Analysis, Factor Analysis, E.U.-28 countries, Statistical package IBM SPSS 20, CHIC Analysis V 1.1 Software, Eurostat.eu Statistics

Procedia PDF Downloads 511

Authors: Taylor Kolody, Farkhund Iqbal, Rabia Batool, Benjamin Fung, Mohammed Hussaeni, Saiqa Aleem

Abstract:

The rising threat of climate change has led to an increase in public awareness and care about our collective and individual environmental impact. A key component of this impact is our use of cars and other polluting forms of transportation, but it is often difficult for an individual to know how severe this impact is. While there are applications that offer this feedback, they require manual entry of what transportation mode was used for a given trip, which can be burdensome. In order to alleviate this shortcoming, a data from the 2016 TRIPlab datasets has been used to train a variety of machine learning models to automatically recognize the mode of transportation. The accuracy of 89.6% is achieved using single deep neural network model with Gated Recurrent Unit (GRU) architecture applied directly to trip data points over 4 primary classes, namely walking, public transit, car, and bike. These results are comparable in accuracy to results achieved by others using ensemble methods and require far less computation when classifying new trips. The lack of trip context data, e.g., bus routes, bike paths, etc., and the need for only a single set of weights make this an appropriate methodology for applications hoping to reach a broad demographic and have responsive feedback.

Keywords: classification, gated recurrent unit, recurrent neural network, transportation

Procedia PDF Downloads 137

Authors: Diana Codat

Abstract:

Tweets' analysis is part of text mining. Each document is a written text. It's possible to apply the usual text search techniques, in particular by switching to the bag-of-words representation. But the tweets induce peculiarities. Some may enrich the analysis. Thus, their length is calibrated (at least as far as public messages are concerned), special characters make it possible to identify authors (@) and themes (#), the tweet and retweet mechanisms make it possible to follow the diffusion of the information. Conversely, other characteristics may disrupt the analyzes. Because space is limited, authors often use abbreviations, emoticons to express feelings, and they do not pay much attention to spelling. All this creates noise that can complicate the task. The tweets carry a lot of potentially interesting information. Their exploitation is one of the main axes of the analysis of the social networks. We show how to access Twitter-related messages. We will initiate a study of the properties of the tweets, and we will follow up on the exploitation of the content of the messages. We will work under R with the package 'twitteR'. The study of tweets is a strong focus of analysis of social networks because Twitter has become an important vector of communication. This example shows that it is easy to initiate an analysis from data extracted directly online. The data preparation phase is of great importance.

Keywords: data mining, language R, social networks, Twitter

Procedia PDF Downloads 184

Authors: Spoorthi Sripad

Abstract:

Remote sensing is a powerful tool for acquiring information about the Earth's surface without direct contact, relying on the interaction of electromagnetic radiation with various materials and features. This paper explores the fundamental principle of "Interaction with Earth's Surface" in remote sensing, shedding light on the intricate processes that occur when electromagnetic waves encounter different surfaces. The absorption, reflection, and transmission of radiation generate distinct spectral signatures, allowing for the identification and classification of surface materials. The paper delves into the significance of the visible, infrared, and thermal infrared regions of the electromagnetic spectrum, highlighting how their unique interactions contribute to a wealth of applications, from land cover classification to environmental monitoring. The discussion encompasses the types of sensors and platforms used to capture these interactions, including multispectral and hyperspectral imaging systems. By examining real-world applications, such as land cover classification and environmental monitoring, the paper underscores the critical role of understanding the interaction with the Earth's surface for accurate and meaningful interpretation of remote sensing data.

Keywords: remote sensing, earth's surface interaction, electromagnetic radiation, spectral signatures, land cover classification, archeology and cultural heritage preservation

Procedia PDF Downloads 59

Authors: Roza Dzierzak, Waldemar Wojcik, Piotr Kacejko

Abstract:

Analysis of the texture of medical images consists of determining the parameters and characteristics of the examined tissue. The main goal is to assign the analyzed area to one of two basic groups: as a healthy tissue or a tissue with pathological changes. The CT images of the thoracic lumbar spine from 15 healthy patients and 15 with confirmed osteoporosis were used for the analysis. As a result, 120 samples with dimensions of 50x50 pixels were obtained. The set of features has been obtained based on the histogram, gradient, run-length matrix, co-occurrence matrix, autoregressive model, and Haar wavelet. As a result of the image analysis, 290 descriptors of textural features were obtained. The dimension of the space of features was reduced by the use of three selection methods: Fisher coefficient (FC), mutual information (MI), minimization of the classification error probability and average correlation coefficients between the chosen features minimization of classification error probability (POE) and average correlation coefficients (ACC). Each of them returned ten features occupying the initial place in the ranking devised according to its own coefficient. As a result of the Fisher coefficient and mutual information selections, the same features arranged in a different order were obtained. In both rankings, the 50% percentile (Perc.50%) was found in the first place. The next selected features come from the co-occurrence matrix. The sets of features selected in the selection process were evaluated using six classification tree methods. These were: decision stump (DS), Hoeffding tree (HT), logistic model trees (LMT), random forest (RF), random tree (RT) and reduced error pruning tree (REPT). In order to assess the accuracy of classifiers, the following parameters were used: overall classification accuracy (ACC), true positive rate (TPR, classification sensitivity), true negative rate (TNR, classification specificity), positive predictive value (PPV) and negative predictive value (NPV). Taking into account the classification results, it should be stated that the best results were obtained for the Hoeffding tree and logistic model trees classifiers, using the set of features selected by the POE + ACC method. In the case of the Hoeffding tree classifier, the highest values of three parameters were obtained: ACC = 90%, TPR = 93.3% and PPV = 93.3%. Additionally, the values of the other two parameters, i.e., TNR = 86.7% and NPV = 86.6% were close to the maximum values obtained for the LMT classifier. In the case of logistic model trees classifier, the same ACC value was obtained ACC=90% and the highest values for TNR=88.3% and NPV= 88.3%. The values of the other two parameters remained at a level close to the highest TPR = 91.7% and PPV = 91.6%. The results obtained in the experiment show that the use of classification trees is an effective method of classification of texture features. This allows identifying the conditions of the spongy tissue for healthy cases and those with the porosis.

Keywords: classification, feature selection, texture analysis, tree algorithms

Procedia PDF Downloads 177