Search results for: text classification

Authors: Ifeanyichukwu Valerie Oguafor

Abstract:

Women generally have been categorized and placed under the chain of business industry, sometimes highly regarded and other times merely. The social construction of womanhood does not in all sense support a woman going into business, let alone succeed in it because it is believed that it a man’s world. In a typical patriarchal setting, a woman is expected to know nothing more domestic roles. For some women, this is not the case as they have been able to break these barriers to excel in business amidst these social setting and stereotypes. This study examines media representation of Nigerians business women, using content analysis of TV interviews as media text, framing analysis as an approach in qualitative methodology, The study further aims to analyse media frames of two Nigerian business women: FolorunshoAlakija, a business woman in the petroleum industry with current net worth 1.1 billion U.S dollars, emerging as the richest black women in the world 2014. MosunmolaAbudu, a media magnate in Nigeria who launched the first Africa’s global black entertainment and lifestyle network in 2013. This study used six predefined frames: the business woman, the myth of business women, the non-traditional woman, women in leading roles, the family woman, the religious woman, and the philanthropist woman to analyse the representation of Nigerian business women in the media. The analysis of the aforementioned frames on TV interviews with these women reveals that the media perpetually reproduces existing gender stereotype and do not challenge patriarchy. Women face challenges in trying to succeed in business while trying to keep their homes stable. This study concludes that the media represent and reproduce gender stereotypes in spite of the expectation of empowering women. The media reduces these women’s success insignificant rather than a role model for women in society.

Keywords: representation of business women in the media, business women in Nigeria, framing in the media, patriarchy, women's subordination

Procedia PDF Downloads 146

Authors: Tzu-Hao Li, Yen-Ying Kung, Chang-Youh Tsai

Abstract:

Oral dryness is a common chief complaint among patients with Sjőgren syndrome (SS), which is a disorder currently known as autoantibodies production; however, to author’s best knowledge, there has been no satisfying pharmacy to relieve the associated symptoms. Hence the effectiveness of other non-pharmacological interventions such as acupuncture should be accessed. We conducted a meta-analysis of randomized clinical trials (RCTs) which evaluated the effectiveness of xerostomia in SS. PubMed, Embase, Cochrane Central Register of Controlled Trials (CENTRAL), Chongqing Weipu Database (CQVIP), China Academic Journals Full-text Database, AiritiLibrary, Chinese Electronic Periodicals Service (CEPS), China National Knowledge Infrastructure (CNKI) Database were searches through May 12, 2018 to select studies. Data for evaluation of subjective and objective xerostomia was extracted and was assessed with random-effects meta-analysis. After searching, a total of 541 references were yielded and five RCTs were included, covering 340 patients dry mouth resulted from SS, among whom 169 patients received acupuncture and 171 patients were control group. Acupuncture group was associated with higher subjective response rate (odds ratio 3.036, 95% confidence interval [CI] 1.828 – 5.042, P < 0.001) and increased salivary flow rate (weighted mean difference [WMD] 3.066, 95% CI 2.969 – 3.164, P < 0.001), as an objective marker. In addition, two studies examined IgG levels, which were lower in the acupuncture group (WMD -166.857, 95% CI -233.138 - -100.576, P < 0.001). Therefore, in the present meta-analysis, acupuncture improves both subjective and objective markers of dry mouth with autoantibodies reduction in patients with SS and is considered as an option of non-pharmacological treatment for SS.

Keywords: acupuncture, meta-analysis, Sjogren syndrome, xerostomia

Procedia PDF Downloads 107

Authors: Asna Anchalan, Anjana Bhagyanathan

Abstract:

Urban green space plays an important role in providing health (physical and mental well-being), economic, and environmental benefits for urban residents and neighborhoods. Ensuring equitable distribution of urban green space is vital to ensure equal access to these benefits. This study is developing a methodology for assessing spatial equity of urban green spaces in the Indian context. Through a systematic literature review, the research trends, parameters, data, and tools being used are identified. After 2020, the research in this domain is increasing rapidly, where COVID-19 acted as a catalyst. Indian documents use various terminologies, definitions, and classifications of urban green spaces. The terminology, definition, and classification for this study are done after reviewing several Indian documents, master plans, and research papers. Parameters identified for assessing spatial equity are availability, proximity, accessibility, and socio-economic disparity. Criteria for evaluating each parameter were identified from diverse research papers. There is a research gap identified as a comprehensive approach encompassing all four parameters. The outcome of this study led to the development of a methodology that addresses the gaps, providing a practical tool applicable across diverse Indian cities.

Keywords: urban green space, spatial equity, accessibility, proximity, methodology

Procedia PDF Downloads 36

Authors: Mostafa Dastori, Sirus Mohammadi

Abstract:

While plug-in electric vehicles (PEVs) potentially have the capability to fulfill the energy storage needs of the electric grid, the degradation on the battery during this operation makes it less preferable by the auto manufacturers and consumers. On the other hand, the on-board chargers can also supply energy storage system applications such as reactive power compensation, voltage regulation, and power factor correction without the need of engaging the battery with the grid and thereby preserving its lifetime. It presents the design motives of single-phase on-board chargers in detail and makes a classification of the chargers based on their future vehicle-to-grid usage. The pros and cons of each different ac–dc topology are discussed to shed light on their suit- ability for reactive power support. This paper also presents and analyzes the differences between charging-only operation and capacitive reactive power operation that results in increased demand from the dc-link capacitor (more charge/discharge cycles and in- creased second harmonic ripple current). Moreover, battery state of charge is spared from losses during reactive power operation, but converter output power must be limited below its rated power rating to have the same stress on the dc-link capacitor.

Keywords: energy storage system, battery unit, cost, optimal sizing, plug-in electric vehicles (PEVs), smart grid

Procedia PDF Downloads 322

Authors: Aditya Karade, Sharada Falane, Dhananjay Deshmukh, Vijaykumar Mantri

Abstract:

Brain tumors pose a significant challenge in healthcare due to their complex nature and impact on patient outcomes. The application of deep learning (DL) algorithms in medical imaging have shown promise in accurate and efficient brain tumour detection. This paper explores the performance of various pre-trained DL models ResNet50, Xception, InceptionV3, EfficientNetB0, DenseNet121, NASNetMobile, VGG19, VGG16, and MobileNet on a brain tumour dataset sourced from Figshare. The dataset consists of MRI scans categorizing different types of brain tumours, including meningioma, pituitary, glioma, and no tumour. The study involves a comprehensive evaluation of these models’ accuracy and effectiveness in classifying brain tumour images. Data preprocessing, augmentation, and finetuning techniques are employed to optimize model performance. Among the evaluated deep learning models for brain tumour detection, ResNet50 emerges as the top performer with an accuracy of 98.86%. Following closely is Xception, exhibiting a strong accuracy of 97.33%. These models showcase robust capabilities in accurately classifying brain tumour images. On the other end of the spectrum, VGG16 trails with the lowest accuracy at 89.02%.

Keywords: brain tumour, MRI image, detecting and classifying tumour, pre-trained models, transfer learning, image segmentation, data augmentation

Procedia PDF Downloads 52

Authors: Judith Enriquez-Gibson

Abstract:

This paper meddles with the notion of phatic communion introduced 90 years ago by Malinowski, who was a Polish-born British anthropologist. It explores the phatic in Twitter within the contents of tweets related to moocs (massive online open courses) as a topic or trend. It is not about moocs though. It is about practices that could easily be hidden or neglected if we let big or massive topics take the lead or if we simply follow the computational or secret codes behind Twitter itself and third party software analytics. It draws from media and cultural studies. Though at first it appears data-driven as I submitted data collection and analytics into the hands of a third party software, Twitonomy, the aim is to follow how phatic communion might be practised in a social media site, such as Twitter. Lurking becomes its research method to analyse mooc-related tweets. A total of 3,000 tweets were collected on 11 October 2013 (UK timezone). The emphasis of lurking is to engage with Twitter as a system of connectivity. One interesting finding is that a click is in fact a phatic practice. A click breaks the silence. A click in one of the mooc website is actually a tweet. A tweet was posted on behalf of a user who simply chose to click without formulating the text and perhaps without knowing that it contains #mooc. Surely, this mechanism is not about reciprocity. To break the silence, users did not use words. They just clicked the ‘tweet button’ on a mooc website. A click performs and maintains connectivity – and Twitter as the medium in attendance in our everyday, available when needed to be of service. In conclusion, the phatic culture of breaking silence in Twitter does not have to submit to the power of code and analytics. It is a matter of human code.

Keywords: click, Twitter, phatic communion, social media data, mooc

Procedia PDF Downloads 397

Authors: Nuraisyah H. Zulkifley, Suriani Ismail, Rosliza Abdul Manaf, Poh Y. Lim

Abstract:

Taking care of a person with dementia (PWD) is one of the most problematic and challenging caregiving situations. Without proper support, caregiver would need to deal with the impact of caregiving that would lead to caregiver burden. One of the most common tools used to measure caregiver burden among caregivers of PWD is Zarit Burden Interview (ZBI). A systematic review has been conducted through searching Medline, Science Direct, Cochrane Library, Embase, PsycINFO, ProQuest, and Scopus databases to identify relevant articles that elaborate on intervention and outcomes on ZBI among informal caregiver of PWD. The articles were searched in October 2019 with no restriction on language or publication status. Inclusion criteria are randomized control trial (RCT) studies, participants were informal caregivers of PWD, ZBI measured as outcomes, and intervention group was compared with no intervention control or usual care control. Two authors reviewed and extracted the data from the full-text articles. From a total of 344 records, nine studies were selected and included in this narrative review, and eight studies were included in the meta-analysis. The types of interventions that were implemented to ease caregiver burden are psychoeducation, physical activity, psychosocial, and computer-based intervention. The meta-analysis showed that there is a significant difference in the mean score of ZBI (p = 0.006) in the intervention group compared to the control group after implementation of intervention. In conclusion, interventions such as psychoeducation, psychosocial, and physical activity can help to reduce the burden experiencing by the caregivers of PWD.

Keywords: dementia, informal caregiver, randomized control trial, Zarit burden interview

Procedia PDF Downloads 164

Authors: Mohammad Borhani, Afshin Danehkar

Abstract:

With the increase in population and the upward trend of energy demand, mankind has thought of using suppliers that guarantee a stable supply of energy, unlike fossil fuels, which, in addition to the widespread emission of greenhouse gases that one of the main factors in the destruction of the ozone layer and it will be finished in a short time in the not-so-distant future. In this regard, one of the sustainable ways of energy supply is the use of wind converters. That convert wind energy into electricity. For this reason, this research focused on wind turbines and their installation conditions. The main classification of wind turbines is based on the axis of rotation, which is divided into two groups: horizontal axis and vertical axis; each of these two types, with the advancement of technology in man-made environments such as cities, villages, airports, and other human environments can be installed and operated. The main difference between offshore and onshore wind turbines is their installation and foundation. Which are usually divided into five types; including of Monopile Wind Turbines, Jacket Wind Turbines, Tripile Wind Turbines, Gravity-Based Wind Turbines, and Floating Offshore Wind Turbines. For installation in a wind power plant requires an arrangement that produces electric power, the distance between the turbines is usually between 5 or 7 times the diameter of the rotor and if perpendicular to the wind direction be If they are 3 to 5 times the diameter of the rotor, they will be more efficient.

Keywords: wind farms, Savonius, Darrieus, offshore wind turbine, renewable energy

Procedia PDF Downloads 84

Authors: Sheena Christabel Pravin, M. Palanivelan

Abstract:

Speech disfluencies are common in spontaneous speech. The primary purpose of this study was to distinguish linguistic disfluencies from stuttering disfluencies in bilingual Tamil–English (TE) speaking children. The secondary purpose was to determine whether their disfluencies are mediated by native language dominance and/or on an early onset of developmental stuttering at childhood. A detailed study was carried out to identify the prosodic and acoustic features that uniquely represent the disfluent regions of speech. This paper focuses on statistical modeling of repetitions, prolongations, pauses and interjections in the speech corpus encompassing bilingual spontaneous utterances from school going children – English and Tamil. Two classifiers including Hidden Markov Models (HMM) and the Multilayer Perceptron (MLP), which is a class of feed-forward artificial neural network, were compared in the classification of disfluencies. The results of the classifiers document the patterns of disfluency in spontaneous speech samples of school-aged children to distinguish between Children Who Stutter (CWS) and Children with Language Impairment CLI). The ability of the models in classifying the disfluencies was measured in terms of F-measure, Recall, and Precision.

Keywords: bi-lingual, children who stutter, children with language impairment, hidden markov models, multi-layer perceptron, linguistic disfluencies, stuttering disfluencies

Procedia PDF Downloads 200

Authors: Saikiran Subbagari, Avinash Malladhi

Abstract:

Anti Money Laundering (AML) regulations are designed to prevent money laundering and terrorist financing activities worldwide. Financial institutions around the world are legally obligated to identify, assess and mitigate the risks associated with money laundering and report any suspicious transactions to governing authorities. With increasing volumes of data to analyze, financial institutions seek to automate their AML processes. In the rise of financial crimes, optical character recognition (OCR), in combination with machine learning (ML) algorithms, serves as a crucial tool for automating AML processes by extracting the data from documents and identifying suspicious transactions. In this paper, we examine the utilization of OCR for AML and delve into various OCR techniques employed in AML processes. These techniques encompass template-based, feature-based, neural network-based, natural language processing (NLP), hidden markov models (HMMs), conditional random fields (CRFs), binarizations, pattern matching and stroke width transform (SWT). We evaluate each technique, discussing their strengths and constraints. Also, we emphasize on how OCR can improve the accuracy of customer identity verification by comparing the extracted text with the office of foreign assets control (OFAC) watchlist. We will also discuss how OCR helps to overcome language barriers in AML compliance. We also address the implementation challenges that OCR-based AML systems may face and offer recommendations for financial institutions based on the data from previous research studies, which illustrate the effectiveness of OCR-based AML.

Keywords: anti-money laundering, compliance, financial crimes, fraud detection, machine learning, optical character recognition

Procedia PDF Downloads 124

Authors: C. W. Kan, Y. L. Lam

Abstract:

Cotton textile has large specific surfaces with good adhesion and water-storage properties which provide conditions for the growth and settlement of biological organisms. In addition, the soil, dust and solutes from sweat can also be the sources of nutrients for microorganisms [236]. Generally speaking, algae can grow on textiles under very moist conditions, providing nutrients for fungi and bacteria growth. Fungi cause multiple problems to textiles including discolouration, coloured stains and fibre damage. Bacteria can damage fibre and cause unpleasant odours with a slick and slimy feel. In addition, microbes can disrupt the manufacturing processes such as textile dyeing, printing and finishing operations through the reduction of viscosity, fermentation and mold formation. Therefore, a large demand exists for the anti-microbially finished textiles capable of avoiding or limiting microbial fibre degradation or bio fouling, bacterial incidence, odour generation and spreading or transfer of pathogens. In this review, the main strategy for cotton textile will be reviewed. In the beginning, the classification of bacteria and germs which are commonly found with cotton textiles will be introduced. The chemistry of antimicrobial finishing will be discussed. In addition, the types of antimicrobial treatment will be summarized. Finally, the application and evaluation of antimicrobial treatment on cotton textile will be discussed.

Keywords: antimicrobial, cotton, textile, review

Procedia PDF Downloads 350

Authors: Huang Yueh Chen, Sheng Ang Shen

Abstract:

Purpose: Sexual assault has always been a highly anticipated crime in Taiwan. People assume that the career of sexual offenders tends to be highly specialized. This study hopes to analyze the crime career and risk factors of offenders by means of another classification. Methods: A total of 145 sexual offenders were sentenced on the parole or expiration date from 2009 to 2011, through analysis of official existing documents such as ‘Re-infringement risk assessment report’ and ‘case assessment report’. Results: The section ‘Various Types of Crimes ‘ of criminal career is analyzed. The highest number of ‘ versatile sexual offender’ followed by ‘adult sexual offender’ is about 2.5, representing more than 1.5 kinds of non-sex crimes besides sexual crimes. Different specialized sexual offenders have had extensive experience in the ‘Sexual Assault Experiences in Children and School’, ‘Static 99 Levels’, ‘Pre-Commuted Substance Use’, ‘Excited Deviant Sexual Behavior’, ‘Various Types of Crimes,’ and ‘Sexual Crime in Forerunner’ , ‘Type of Index Crime’ and other projects to achieve significant differences. Conclusions: Resources continue to be devoted to specialized offenders, the character of first-time sexual offender depends on further research and makes the public aware of the different assumptions of diversified offenders from traditional professional offenses that reduce unnecessary panic in society.

Keywords: versatile sexual offender, specialized sexual offender, criminal career, risk factor

Procedia PDF Downloads 152

Authors: Medagedara Kaushalya Sewwandi Supun Gunarathne

Abstract:

This research explores the underlying motivations and consequences of individuals changing their sexual orientation as a response to sexual violence. The primary objective of the study is to unravel the psychological, emotional, and social factors that drive individuals, akin to Celie in Alice Walker’s ‘The Color Purple’, to contemplate and undergo changes in their sexual orientation following the trauma of sexual violence. Through an analytical and qualitative approach, the study employs in-depth textual and thematic analyses to scrutinize the complex interplay between sexual orientation and violence within the selected text. Through a close examination of Celie’s journey and experiences, the study reveals that her decision to switch sexual orientation arises from a desire for a more favorable and benevolent relationship driven by the absence of safety and refuge in her previous relationships. By establishing this bond between sexual orientation and violence, the research underscores how sexual violence can lead individuals to opt for a change in their sexual orientation. The findings highlight Celie’s transformation as a means to seek solace and security, thus concluding that sexual violence can prompt individuals to alter their sexual orientation. The ensuing discussion explores the implications of these findings, encompassing psychological, emotional, and social consequences, as well as the societal and cultural factors influencing the perception of sexual orientation. Additionally, it sheds light on the challenges and stigma faced by those who undergo such transformations. By comprehending the complex relationship between sexual violence and the decision to change sexual orientation, as exemplified by Celie in ‘The Color Purple’, a deeper understanding of the experiences of survivors who seek a safe haven through altering their sexual orientation can be attained.

Keywords: sexual violence, sexual orientation, refuge, transition

Procedia PDF Downloads 60

Authors: Xiang Yu, Chuntao Feng, Lu Yang, Meiyang Song, Wenhao Zhou

Abstract:

The existing two-dimensional micro-Doppler features extraction ignores the correlation information between the spatial and temporal dimension features. For the range-Doppler map, the time dimension is introduced, and a frequency modulation continuous wave (FMCW) radar human fall detection algorithm based on time-varying range-Doppler features is proposed. Firstly, the range-Doppler sequence maps are generated from the echo signals of the continuous motion of the human body collected by the radar. Then the three-dimensional data cube composed of multiple frames of range-Doppler maps is input into the three-dimensional Convolutional Neural Network (3D CNN). The spatial and temporal features of time-varying range-Doppler are extracted by the convolution layer and pool layer at the same time. Finally, the extracted spatial and temporal features are input into the fully connected layer for classification. The experimental results show that the proposed fall detection algorithm has a detection accuracy of 95.66%.

Keywords: FMCW radar, fall detection, 3D CNN, time-varying range-doppler features

Procedia PDF Downloads 105

Authors: B. U. Ibrahim, A. Okafor

Abstract:

Sixty-two (62) samples of Clarias anguillaris were collected from Tagwai Reservoir and used for the study. 29 male and 33 female samples were obtained for the study. Body measurement indicated that different sizes were collected for the study. Males, females and combined sexes had standard length and total length means of 26.56±4.99 and 31.13±6.43, 27.17±5.21 and 30.62±5.43, 26.88±5.08 and 30.86±5.88 cm, respectively. The weights of males, females and combined sexes have mean weights of 241.10±96.27, 225.75±78.66 and 232.93±86.95 gm, respectively. Eight items; fish, insects, plant materials, sand grains, crustaceans, algae, detritus and unidentified items were eaten as food by Clarias anguilarias in Tagwai Reservoir. Frequency of occurrence and numerical methods used in stomach contents analysis indicated that fish was the highest, followed by insect, while the lowest was the algae. Frequency of stomach fullness of Clarias anguillaris showed low percentage of empty stomachs or stomachs without food (21.00%) and high percentage of stomachs with food (79.00%), which showed high abundance of food and high feeding intensity during the period of study. Classification of fish based on feeding habits showed that Clarias anguillaris in this study is an omnivore because it consumed both plant and animal materials.

Keywords: stomach content, feeding habit, Clarias anguillaris, Tagwai Reservoir

Procedia PDF Downloads 578

Authors: Saulutė Juzelėnienė, Skirmantė Šarkauskienė

Abstract:

In this paper, it is aimed to analyse the multimodal representations of the concepts of LOVE and PASSION in Lithuanian graphic novel “Gertrūda”, by Gerda Jord. The research is based on the earlier findings by Forceville (2005), Eerden (2009) as well as insights made by Shihara and Matsunaka (2009) and Kövecses (2000). The domains of target and source of LOVE and PASSION metaphors in comics are expressed by verbal and non-verbal cues. The analysis of non-verbal cues adopts the concepts of rune and indexes. A pictorial rune is a graphic representation of an object that does not exist in reality in comics, such as lines, dashes, text "balloons", and pictorial index – a graphically represented object of reality, a real symptom expressing a certain emotion, such as a wide smile, furrowed eyebrows, etc. Indexes are often hyperbolized in comics. The research revealed that most frequent source domains are CLOSINESS/UNITY, NATURAL/ PHYSICAL FORCE, VALUABLE OBJECT, PRESSURE. The target is the emotion of LOVE/PASSION which belongs to a more abstract domain of psychological experience. In this kind of metaphor, the picture can be interpreted as representing the emotion of happiness. Data are taken from Lithuanian comic books and Internet sites, where comics have been presented. The data and the analysis we are providing in this article aims to reveal that there are pictorial metaphors that manifest conceptual metaphors that are also expressed verbally and that methodological framework constructed for the analysis in the papers by Forceville at all is applicable to other emotions and culture specific pictorial manifestations.

Keywords: multimodal metaphor, conceptual metaphor, comics, graphic novel, concept of love/passion

Procedia PDF Downloads 53

Authors: Gheida J. Shahrour, Martin J. Russell

Abstract:

The 3D body movement signals captured during human-human conversation include clues not only to the content of people’s communication but also to their culture and personality. This paper is concerned with automatic extraction of this information from body movement signals. For the purpose of this research, we collected a novel corpus from 27 subjects, arranged them into groups according to their culture. We arranged each group into pairs and each pair communicated with each other about different topics. A state-of-art recognition system is applied to the problems of person, culture, and topic recognition. We borrowed modeling, classification, and normalization techniques from speech recognition. We used Gaussian Mixture Modeling (GMM) as the main technique for building our three systems, obtaining 77.78%, 55.47%, and 39.06% from the person, culture, and topic recognition systems respectively. In addition, we combined the above GMM systems with Support Vector Machines (SVM) to obtain 85.42%, 62.50%, and 40.63% accuracy for person, culture, and topic recognition respectively. Although direct comparison among these three recognition systems is difficult, it seems that our person recognition system performs best for both GMM and GMM-SVM, suggesting that inter-subject differences (i.e. subject’s personality traits) are a major source of variation. When removing these traits from culture and topic recognition systems using the Nuisance Attribute Projection (NAP) and the Intersession Variability Compensation (ISVC) techniques, we obtained 73.44% and 46.09% accuracy from culture and topic recognition systems respectively.

Keywords: person recognition, topic recognition, culture recognition, 3D body movement signals, variability compensation

Procedia PDF Downloads 522

Authors: Andrey Matyukhin

Abstract:

Russian official statistics have been showing a steady decline in residential real estate prices for several consecutive years. Price risk in real estate markets is thus affecting various groups of economic agents, namely, individuals, construction companies and financial institutions. Potential use of property derivatives might help mitigate adverse consequences of negative price dynamics. Unless a sustainable price indicator is developed, settlement of such instruments imposes constraints on counterparties involved while imposing restrictions on real estate market development. The study addresses geographical and classification heterogeneity in real estate prices by means of variance analysis in various groups of real estate properties. In conclusion, we determine optimal sample structure of representative real estate assets with sufficient level of price homogeneity. The composite price indicator based on the sample would have a higher level of robustness and reliability and hence improving liquidity in the market for property derivatives through underlying standardization. Unlike the majority of existing real estate price indices, calculated on country-wide basis, the optimal indices for Russian market shall be constructed on the city-level.

Keywords: price homogeneity, property derivatives, real estate price index, real estate price risk

Procedia PDF Downloads 295

Authors: Shahad Nagoor, Lucy Hederman, Kevin Koidl, Annalina Caputo

Abstract:

Doctors’ notes reflect their impressions, attitudes, clinical sense, and opinions about patients’ conditions and progress, and other information that is essential for doctors’ daily clinical decisions. Despite their value, clinical notes are insufficiently researched within the language processing community. Automatically extracting information from unstructured text data is known to be a difficult task as opposed to dealing with structured information such as vital physiological signs, images, and laboratory results. The aim of this research is to investigate how Natural Language Processing (NLP) techniques and machine learning techniques applied to clinician notes can assist in doctors’ decision-making in Intensive Care Unit (ICU) for coronavirus disease 2019 (COVID-19) patients. The hypothesis is that clinical outcomes like survival or mortality can be useful in influencing the judgement of clinical sentiment in ICU clinical notes. This paper introduces two contributions: first, we introduce COVID_ICU_BERT, a fine-tuned version of clinical transformer models that can reliably predict clinical sentiment for notes of COVID patients in the ICU. We train the model on clinical notes for COVID-19 patients, a type of notes that were not previously seen by clinicalBERT, and Bio_Discharge_Summary_BERT. The model, which was based on clinicalBERT achieves higher predictive accuracy (Acc 93.33%, AUC 0.98, and precision 0.96 ). Second, we perform data augmentation using clinical contextual word embedding that is based on a pre-trained clinical model to balance the samples in each class in the data (survived vs. deceased patients). Data augmentation improves the accuracy of prediction slightly (Acc 96.67%, AUC 0.98, and precision 0.92 ).

Keywords: BERT fine-tuning, clinical sentiment, COVID-19, data augmentation

Procedia PDF Downloads 184

Authors: Khalida Douibi, Rodrigo Balp, Solène Le Bars

Abstract:

In the medical field, applications related to human experiments are frequently linked to reduced samples size, which makes the training of machine learning models quite sensitive and therefore not very robust nor generalizable. This is notably the case in Brain-Computer Interface (BCI) studies, where the sample size rarely exceeds 20 subjects or a few number of trials. To address this problem, several resampling approaches are often used during the data preparation phase, which is an overly critical step in a data science analysis process. One of the naive approaches that is usually applied by data scientists consists in the transformation of the entire database before the resampling phase. However, this can cause model’ s performance to be incorrectly estimated when making predictions on unseen data. In this paper, we explored the effect of data leakage observed during our BCI experiments for device control through the real-time classification of SSVEPs (Steady State Visually Evoked Potentials). We also studied potential ways to ensure optimal validation of the classifiers during the calibration phase to avoid overfitting. The results show that the scaling step is crucial for some algorithms, and it should be applied after the resampling phase to avoid data leackage and improve results.

Keywords: data leackage, data science, machine learning, SSVEP, BCI, overfitting

Procedia PDF Downloads 138

Authors: M. Macchiaroli, L. Dolores, V. Pellecchia

Abstract:

With the recent Resolution n. 580/2019/R/idr, the Italian Regulatory Authority for Energy, Networks, and Environment (ARERA) for the Urban Water Management has introduced, for water managements characterized by persistent critical issues regarding the planning and organization of the service and the implementation of the necessary interventions for the improvement of infrastructures and management quality, a new mechanism for determining tariffs: the regulatory scheme of Convergence. The aim of this regulatory scheme is the overcoming of the Water Service Divided in order to improve the stability of the local institutional structures, technical quality, contractual quality, as well as in order to guarantee transparency elements for Users of the Service. Convergence scheme presupposes the identification of the cost items to be considered in the tariff in parametric terms, distinguishing three possible cases according to the type of historical data available to the Manager. The study, in particular, focuses on operations that have neither data on tariff revenues nor data on operating costs. In this case, the Manager's Constraint on Revenues (VRG) is estimated on the basis of a reference benchmark and becomes the starting point for defining the structure of the tariff classes, in compliance with the TICSI provisions (Integrated Text for tariff classes, ARERA's Resolution n. 665/2017/R/idr). The proposed model implements the recent studies on optimization models for the definition of tariff classes in compliance with the constraints dictated by TICSI in the application of the Convergence mechanism, proposing itself as a support tool for the Managers and the local water regulatory Authority in the decision-making process.

Keywords: decision-making process, economic evaluation of projects, optimizing tools, urban water management, water tariff

Procedia PDF Downloads 102

Authors: Mohammad J. Rezai, Fereshteh Davarpanah

Abstract:

Producing a text in a language which is not one’s mother tongue can be a demanding task for language learners. Examining lexical errors committed by EFL learners is a challenging area of investigation which can shed light on the process of second language acquisition. Despite the considerable number of investigations into grammatical errors, few studies have tackled formal and semantic errors of lexis committed by EFL learners. The current study aimed at examining Persian learners’ formal and semantic errors of lexis in English. To this end, 60 students at three different proficiency levels were asked to write on 10 different topics in 10 separate sessions. Finally, 600 essays written by Persian EFL learners were collected, acting as the corpus of the study. An error taxonomy comprising formal and semantic errors was selected to analyze the corpus. The formal category covered misselection and misformation errors, while the semantic errors were classified into lexical, collocational and lexicogrammatical categories. Each category was further classified into subcategories depending on the identified errors. The results showed that there were 2583 errors in the corpus of 9600 words, among which, 2030 formal errors and 553 semantic errors were identified. The most frequent errors in the corpus included formal error commitment (78.6%), which were more prevalent at the advanced level (42.4%). The semantic errors (21.4%) were more frequent at the low intermediate level (40.5%). Among formal errors of lexis, the highest number of errors was devoted to misformation errors (98%), while misselection errors constituted 2% of the errors. Additionally, no significant differences were observed among the three semantic error subcategories, namely collocational, lexical choice and lexicogrammatical. The results of the study can shed light on the challenges faced by EFL learners in the second language acquisition process.

Keywords: collocational errors, lexical errors, Persian EFL learners, semantic errors

Procedia PDF Downloads 126

Authors: Yoonjung An, Yongtae Park

Abstract:

Knowledge flows are a critical source of faster technological progress and stouter economic growth. Knowledge flows have been accelerated dramatically with the establishment of a patent system in which each patent is required by law to disclose sufficient technical information for the invention to be recreated. Patent analysis, thus, has been widely used to help investigate technological knowledge flows. However, the existing research is limited in terms of both subject and approach. Particularly, in most of the previous studies, business method (BM) patents were not covered although they are important drivers of knowledge flows as other patents. In addition, these studies usually focus on the static analysis of knowledge flows. Some use approaches that incorporate the time dimension, yet they still fail to trace a true dynamic process of knowledge flows. Therefore, we investigate dynamic patterns of knowledge flows driven by BM patents using a Hidden Markov Model (HMM). An HMM is a popular statistical tool for modeling a wide range of time series data, with no general theoretical limit in regard to statistical pattern classification. Accordingly, it enables characterizing knowledge patterns that may differ by patent, sector, country and so on. We run the model in sets of backward citations and forward citations to compare the patterns of knowledge utilization and knowledge dissemination.

Keywords: business method patents, dynamic pattern, Hidden-Markov Model, knowledge flow

Procedia PDF Downloads 316

Authors: Catarina Grande, Barbara Mota

Abstract:

The main goal of the present study was to understand the impact of childhood cancer on the quality of life of survivors and the extent to which oncologic disease affects the functionality and participation of survivors at the present time, compared to the time of diagnosis. Six survivors of pediatric cancer participated in the study. Participants were interviewed using a semi-structured interview, adapted from two instruments present in the literature - QALY and QLACS - and piloted through a previous study. This study is based on a qualitative approach using content analysis, allowing the identification of categories and subcategories. Subsequently, the correspondence between the units of meaning and the codes in the International Classification of Functioning, Disability, and Health for Children and Young, which contributed to a more detailed analysis of the impact on the quality of life of survivors in relation to the domains under study. The results showed significant changes between the moment of diagnosis and the present moment, concretely at the microsystem of the survivor. Regarding functionality and participation, the results show that the functions of the body are the most affected domain, emphasizing the emotional component that currently has a greater impact on the quality of life of survivors. The present study allowed identifying a set of codes for the development of a CIF-CJ core set for pediatric cancer survivors. He also indicated the need for future studies to validate and deepen these issues.

Keywords: cancer, participation, quality of life, survivor

Procedia PDF Downloads 222

Authors: Abdelrahman Mohamed Abdelrahman

Abstract:

Canopic jars are one of the vessels of funerary nature used by the ancient Egyptian in mummification process that were used to save the viscera of the mummified body after being extracted from the body and treated. Canopic jars are made of several types of materials like Limestone, Alabaster, and Pottery. The studied canopic jar dates back to Late period, located in the Grand Egyptian Museum (GEM), Giza, Egypt. This jar carved from limestone with carved hieroglyphic inscriptions, and it filled and closed by mortar from inside. Some aspects of damage appeared in the jar, such as dust, dirts, classification, wide crack, weakness of limestone. In this study, we used documentation and investigation modern techniques to document and examine the jar. 3D scanning and X-ray Radiography imaging used in applied study. X-ray imaging showed that the mortar was placed at a time when the jar contained probably viscera where the mortar appeared that not reach up to the base of the inner jar. Through the three-dimensional photography, the jar was documented, and we have 3D model of the jar, and now we have the ability through the computer to see any part of the jar in all its details. After that, conservation procedures have been applied with high accuracy to conserve the jar, including mechanical, wet, and chemical cleaning, filling wide crack in the body of the jar using mortar consisting of calcium carbonate powder mixing with primal E330 S, and consolidation, so the limestone became strong after using paraloid B72 2% concentrate as a consolidate material.

Keywords: vessel, limestone, canopic jar, mortar, 3D scanning, X-ray radiography

Procedia PDF Downloads 60

Authors: Travis Morris

Abstract:

The purpose of this study is to measure the intersection of environmental security entities in terrorist propaganda. To the best of author’s knowledge, this is the first study of its kind to examine this intersection within terrorist propaganda. Rosoka, natural language processing software and frame analysis are used to advance our understanding of how environmental frames function as emotive triggers. Violent jihadi demagogues use frames to suggest violent and non-violent solutions to their grievances. Emotive triggers are framed in a way to leverage individual and collective attitudes in psychological warfare. A comparative research design is used because of the differences and similarities that exist between two variants of violent jihadi propaganda that target western audiences. Analysis is based on salience and network text analysis, which generates violent jihadi semantic networks. Findings indicate that environmental frames are used as emotive triggers across both data sets, but also as tactical and information data points. A significant finding is that certain core environmental emotive triggers like “water,” “soil,” and “trees” are significantly salient at the aggregate level across both data sets. All environmental entities can be classified into two categories, symbolic and literal. Importantly, this research illustrates how demagogues use environmental emotive triggers in cyber space from a subcultural perspective to mobilize target audiences to their ideology and praxis. Understanding the anatomy of propaganda construction is necessary in order to generate effective counter narratives in information operations. This research advances an additional method to inform practitioners and policy makers of how environmental security and propaganda intersect.

Keywords: propaganda analysis, emotive triggers environmental security, frames

Procedia PDF Downloads 123

Authors: Levente Varga, Dávid Deritei, Mária Ercsey-Ravasz, Răzvan Florian, Zsolt I. Lázár, István Papp, Ferenc Járai-Szabó

Abstract:

One of the major shortcomings of widely used scientometric indicators is that different disciplines cannot be compared with each other. The issue of cross-disciplinary normalization has been long discussed, but even the classification of publications into scientific domains poses problems. Structural properties of citation networks offer new possibilities, however, the large size and constant growth of these networks asks for precaution. Here we present a new tool that in order to perform cross-field normalization of scientometric indicators of individual publications relays on the structural properties of citation networks. Due to the large size of the networks, a systematic procedure for identifying scientific domains based on a local community detection algorithm is proposed. The algorithm is tested with different benchmark and real-world networks. Then, by the use of this algorithm, the mechanism of the scientometric indicator normalization process is shown for a few indicators like the citation number, P-index and a local version of the PageRank indicator. The fat-tail trend of the article indicator distribution enables us to successfully perform the indicator normalization process.

Keywords: citation networks, cross-field normalization, local cluster detection, scientometric indicators

Procedia PDF Downloads 184

Authors: Bandar Alahmadi, Manohar Mareboyana, Lethia Jackson

Abstract:

Today, there are many applications that are using computer vision models, such as face recognition, image classification, and object detection. The accuracy of these models is very important for the performance of these applications. One challenge that facing the computer vision models is the adversarial examples attack. In computer vision, the adversarial example is an image that is intentionally designed to cause the machine learning model to misclassify it. One of very well-known method that is used to attack the Convolution Neural Network (CNN) is Fast Gradient Sign Method (FGSM). The goal of this method is to find the perturbation that can fool the CNN using the gradient of the cost function of CNN. In this paper, we introduce a novel model that can attack Regional-Convolution Neural Network (R-CNN) that use FGSM. We first extract the regions that are detected by R-CNN, and then we resize these regions into the size of regular images. Then, we find the best perturbation of the regions that can fool CNN using FGSM. Next, we add the resulted perturbation to the attacked region to get a new region image that looks similar to the original image to human eyes. Finally, we placed the regions back to the original image and test the R-CNN with the attacked images. Our model could drop the accuracy of the R-CNN when we tested with Pascal VOC 2012 dataset.

Keywords: adversarial examples, attack, computer vision, image processing

Procedia PDF Downloads 173

Authors: Glavan Claudiu

Abstract:

My paper focuses on the cultural semiotic interpretation of the Romanian costume from Banat region, from the perspective of Lotman’s semiotic theory of culture. Using Lotman’s system we will analyse the level of language, text and semiosphere within the unity of Banat’s traditional costume. In order to establish a common language and to communicate, the forms and chromatic compositions were expressed through symbols, which carried semantic meanings with an obvious significant semantic load. The symbols, used in this region, receive a strong specific ethnical mark in its representation, in its compositional and chromatic complexity, in accordance with the values and conceptions of life for the people living here. Thus the signs become a unifying force of this ethnic community. Associated with the signs, were the fabrics used in manufacturing the costumes and the careful selections of colours. For example, softer fabrics like silk associated with red vivid colours were used for young woman sending the message they ready to be married. The unity of these elements created the important message that you were sending to your community. The unity of the symbol, fabrics and choice of colours used on the costume carried out an important message like: marital status, social position, or even the village you belonged to. Using Lotman’s perspective on cultural semiotics we will read and analyse the symbolism of the traditional Romanian art from Banat. We will discover meaning in the codified existence of ancient solar symbols, symbols regarding fertility, religious symbols and very few heraldic symbols. Visual communication makes obvious the importance of semiotic value that the traditional costume is carrying from our ancestors.

Keywords: traditional costume, semiotics, Lotman’s theory of culture, traditional culture, signs and symbols

Procedia PDF Downloads 125

Authors: C. Caçador, M. J. Reis Lima, J. Oliveira, M. J. Veiga, M. Teixeira Veríssimo, F. Ramos, M. C. Castilho, E. Teixeira-Lemos

Abstract:

In the present study we evaluated the nutritional status of 214 institutionalized elderly residents of both genders, aged 65 years and older of 11 care homes located in the district of Viseu (center of Portugal). The evaluation was based on anthropometric measurements and the Mini Nutritional Assessment (MNA) score. The mean age of the subjects was 82.3 ± 6.1 years-old. Most of the elderly residents were female (72.0%). The majority had 4 years of formal education (51.9%) and was widowed (74.3%) or married (14.0%). Men presented a mean age of 81.2±8.5 years-old, weight 69.3±14.5 kg and BMI 25.33±6.5 kg/m2. In women, the mean age was 84.5±8.2 years-old, weight 61.2±14.7 kg and BMI 27.43±5.6 kg/m2. The evaluation of the nutritional status using the MNA score showed that 24.0% of the residents show a risk of undernutrition and 76.0% of them were well nourished. There was a high prevalence of obese (24.8%) and overweight residents (33.2%) according to the BMI. 7.5% were considered underweight. We also found that according to their waist circumference measurements 88.3% of the residents were at risk for cardiovascular disease (CVD) and 64.0% of them presented very high risk for CVD (WC≥88 cm for women and WC ≥102 cm for men). The present study revealed the coexistence of a dual form of malnutrition (undernourished and overweight) among the institutionalized Portuguese concomitantly with an excess of abdominal adiposity. The high prevalence of residents at high risk for CVD should not be overlooked. Given the vulnerability of the group of institutionalized elderly, our study highlights the importance of the classification of nutritional status based on both instruments: the BMI and the MNA.

Keywords: nutritional satus, MNA, BMI, elderly

Procedia PDF Downloads 306