Search results for: bug labels

Authors: Anshika Kankane, Dongshik Kang

Abstract:

Marine debris has a significant influence on coastal environments, damaging biodiversity, and causing loss and damage to marine and ocean sector. A functional cost-effective and automatic approach has been used to look up at this problem. Computer vision combined with a deep learning-based model is being proposed to identify and categorize marine debris of seven kinds on different beach locations of Japan. This research compares state-of-the-art deep learning models with a suggested model architecture that is utilized as a feature extractor for debris categorization. The model is being proposed to detect seven categories of litter using a manually constructed debris dataset, with the help of Mask R-CNN for instance segmentation and a shape matching network called HOGShape, which can then be cleaned on time by clean-up organizations using warning notifications of the system. The manually constructed dataset for this system is created by annotating the images taken by fixed KaKaXi camera using CVAT annotation tool with seven kinds of category labels. A pre-trained HOG feature extractor on LIBSVM is being used along with multiple templates matching on HOG maps of images and HOG maps of templates to improve the predicted masked images obtained via Mask R-CNN training. This system intends to timely alert the cleanup organizations with the warning notifications using live recorded beach debris data. The suggested network results in the improvement of misclassified debris masks of debris objects with different illuminations, shapes, viewpoints and litter with occlusions which have vague visibility.

Keywords: computer vision, debris, deep learning, fixed live camera images, histogram of gradients feature extractor, instance segmentation, manually annotated dataset, multiple template matching

Procedia PDF Downloads 107

Authors: Cristy Stagnar, Nina Hubig, Diana Ivankovic

Abstract:

The epigenome is a compelling candidate for mediating long-term responses to environmental effects modifying disease risk. The main goal of this research is to develop a machine learning-based DNA methylation score, which will be valuable in delineating the unique contribution of paternal epigenetic modifications to the germline impacting childhood health outcomes. It will also be a useful tool in validating self-reports of nonsmoking and in adjusting epigenome-wide DNA methylation association studies for this early-life exposure. Using secondary data from two population-based methylation profiling studies, our DNA methylation score is based on CpG DNA methylation measurements from cord blood gathered from children whose fathers smoked pre- and peri-conceptually. Each child’s mother and father fell into one of three class labels in the accompanying questionnaires -never smoker, former smoker, or current smoker. By applying different machine learning algorithms to the accessible resource for integrated epigenomic studies (ARIES) sub-study of the Avon longitudinal study of parents and children (ALSPAC) data set, which we used for training and testing of our model, the best-performing algorithm for classifying the father smoker and mother never smoker was selected based on Cohen’s κ. Error in the model was identified and optimized. The final DNA methylation score was further tested and validated in an independent data set. This resulted in a linear combination of methylation values of selected probes via a logistic link function that accurately classified each group and contributed the most towards classification. The result is a unique, robust DNA methylation score which combines information on DNA methylation and early life exposure of offspring to paternal smoking during pregnancy and which may be used to examine the paternal contribution to offspring health outcomes.

Keywords: epigenome, health outcomes, paternal preconception environmental exposures, supervised machine learning

Procedia PDF Downloads 186

Authors: Sabika Khalid, Endale Fantahun Tadesse

Abstract:

Unlike other professional sectors, a great deal of studies has addressed the overwhelming gender disparity phenomena in the early childhood education (ECE) workforce, which is acknowledged for the dominance of women over men teachers. The irony of ECE being a gendered working environment is not only observed in societies that are ruled by gender roles but also in Western countries that claim to margin the gender gap in several professions. The participation of male teachers in ECE across most countries ranged from 1% to 3% of the total preschool or kindergarten teachers. When it comes to a dynamic Chinese society tempered with a deep-rooted tradition and cultural ideology, the ECE has no less place for males, and males have a low place for ECE. According to the Ministry of Education of China (2020), there are over 5 million kindergarten teachers and staff members, while only 2.3% are accounted for male teachers. The traditional gender-based discourse asserts that giving care and guidance for young children related to nurturing ‘mothering’ labels the profession in ECE as women’s work derived from originated from their ‘naturality.’ Although a large volume of evidence sheds light on the cause for low male teachers, the perception of parents, female teachers working with male teachers, and the experience of male teachers working in ECE, less is known and understood before being a teacher. Hence, this study argues that the promotion of the involvement of male teachers in light of their masculinity identity asset in the children's learning environment is comprehended to understand the construction of male student teachers' (preservice) professional identity during early childhood teacher training that allows obtaining substantial evidence that provides a feasible and robust implication in the preparation of competent and professional male preschool teachers that understand, cherish, and bring harmony in Chinese ECE through professionalism socialization with the stakeholders. This study intended to reveal male ECE preservice teachers’ knowledge of their professional identity, i.e., how they perceive themselves as a teacher and what factors agents these perceptions towards their professional identity.

Keywords: male teachers, Early Childhood Education (ECE), self-identity, perception of stakeholders

Procedia PDF Downloads 41

Authors: S. Jabeen

Abstract:

Though Pakistan has a rich cultural history and a diverse population; its global image is tarnished with labels of Muslim ‘fundamentalism’ and ‘extremism.’ Cultural policy is a tool that can be used by the government of Pakistan to ameliorate this image, but instead, this fundamentalist reputation is reinforced in the 2005 draft of Pakistan’s cultural policy. With its stern focus on a homogenized cultural identity, this 2005 draft bases itself largely on forced participation from the largely Muslim public and leaves little or no benefits to them or cultural minorities in Pakistan. The effects of this homogenized ‘Muslim’ identity linger ten years later where the study and celebration of the cultural heritage of Pakistan in schools and educational festivals focus entirely on creating and maintaining a singular ‘Islamic’ cultural identity. The current lack of inclusion has many adverse effects that include the breeding of extremist mindsets through the usurpation of minority rights and lack of safe cultural public spaces. This paper argues that Pakistan can improve social inclusivity and boost its global image through cultural policy. The paper sets the grounds for research by surveying the effectiveness of different cultural policies across nations with differing socioeconomic status. Then, by sampling two public literary festivals in Pakistan as case studies, the National Youth Peace Festival hosted with a nationalistic agenda using public funds and the Lahore Literary Festival (LLF) that aims to boost the cultural literacy scene of Lahore using both private and public efforts, this paper looks at the success of the private, more inclusive LLF. A revision of cultural policy is suggested that combines public and private efforts to host cultural festivals for the sake of cultural celebration and human development, without a set nationalistic agenda. Consequently, this comparison which is grounded in the human capabilities approach, recommends revising the 2005 draft of the Cultural Policy to improve human capabilities in order to support cultural diversity and ultimately contribute to economic growth in Pakistan.

Keywords: cultural policy, festivals, human capabilities, Pakistan

Procedia PDF Downloads 139

Authors: Mehran Asadi, Afrand Agah

Abstract:

In data mining, partitioning is used as a fundamental tool for classification. With the help of partitioning, we study the structure of data, which allows us to envision decision rules, which can be applied to classification trees. In this research, we used online social network dataset and all of its attributes (e.g., Node features, labels, etc.) to determine what constitutes an above average chance of being a divergent node. We used the R statistical computing language to conduct the analyses in this report. The data were found on the UC Irvine Machine Learning Repository. This research introduces the basic concepts of classification in online social networks. In this work, we utilize overfitting and describe different approaches for evaluation and performance comparison of different classification methods. In classification, the main objective is to categorize different items and assign them into different groups based on their properties and similarities. In data mining, recursive partitioning is being utilized to probe the structure of a data set, which allow us to envision decision rules and apply them to classify data into several groups. Estimating densities is hard, especially in high dimensions, with limited data. Of course, we do not know the densities, but we could estimate them using classical techniques. First, we calculated the correlation matrix of the dataset to see if any predictors are highly correlated with one another. By calculating the correlation coefficients for the predictor variables, we see that density is strongly correlated with transitivity. We initialized a data frame to easily compare the quality of the result classification methods and utilized decision trees (with k-fold cross validation to prune the tree). The method performed on this dataset is decision trees. Decision tree is a non-parametric classification method, which uses a set of rules to predict that each observation belongs to the most commonly occurring class label of the training data. Our method aggregates many decision trees to create an optimized model that is not susceptible to overfitting. When using a decision tree, however, it is important to use cross-validation to prune the tree in order to narrow it down to the most important variables.

Keywords: online social networks, data mining, social cloud computing, interaction and collaboration

Procedia PDF Downloads 160

Authors: Hans Tjio, Wee Meng Seng

Abstract:

The interaction of contract and property has always been a concern in corporate and commercial law, where there are internal structures created that may not match the externally perceived image generated by the labels attached to those structures. We will focus, in particular, on the priority structures created by affirmative asset partitioning, which have increasingly come under challenge by those attempting to negotiate around them. The most prominent has been the AT1 bonds issued by Credit Suisse which were wiped out before its equity when the troubled bank was acquired by UBS. However, this should not have come as a surprise to those whose “bonds” had similarly been “redeemed” upon the occurrence of certain reference events in countries like Singapore, Hong Kong and Taiwan during their Minibond crisis linked to US sub-prime defaults. These were derivatives classified as debentures and sold as such. At the same time, we are again witnessing “liabilities” seemingly ranking higher up the balance sheet ladder, finding themselves lowered in events of default. We will examine the mechanisms holders of perpetual securities or preference shares have tried to use to protect themselves. This is happening against a backdrop that sees a rise in the strength of private credit and inter-creditor conflicts. The restructuring regime of the hybrid scheme in Singapore now, while adopting the absolute priority rule in Chapter 11 as the quid pro quo for creditor cramdown, does not apply to shareholders and so exempts them from cramdown. Complicating the picture further, shareholders are not exempted from cramdown in the Dutch scheme, but it adopts a relative priority rule. At the same time, the important UK Supreme Court decision in BTI 2014 LLC v Sequana [2022] UKSC 25 has held that directors’ duties to take account of creditor interests are activated only when a company is almost insolvent. All this has been complicated by digital assets created by businesses. Investors are quite happy to have them classified as property (like a thing) when it comes to their transferability, but then when the issuer defaults to have them seen as a claim on the business (as a choice in action), that puts them at the level of a creditor. But these hidden interests will not show themselves on an issuer’s balance sheet until it is too late to be considered and yet if accepted, may also prevent any meaningful restructuring.

Keywords: asset partitioning, creditor priority, restructuring, BTI v Sequana, digital assets

Procedia PDF Downloads 77

Authors: Filip Rusak, Yulia Arzhaeva, Dadong Wang

Abstract:

Machine learning based Computer-Aided Diagnosis (CAD) is gaining much popularity in medical imaging and diagnostic radiology. However, it requires a large amount of high quality and labeled training image datasets. The training images may come from different sources and be acquired from different radiography machines produced by different manufacturers, digital or digitized copies of film radiographs, with various sizes as well as different pixel intensity distributions. In this paper, a content-aware image augmentation method is presented to deal with these variations. The results of the proposed method have been validated graphically by plotting the removed and added seams of pixels on original images. Two different chest X-ray (CXR) datasets are used in the experiments. The CXRs in the datasets defer in size, some are digital CXRs while the others are digitized from analog CXR films. With the proposed content-aware augmentation method, the Seam Carving algorithm is employed to resize CXRs and the corresponding labels in the form of image masks, followed by histogram matching used to normalize the pixel intensities of digital radiography, based on the pixel intensity values of digitized radiographs. We implemented the algorithms, resized the well-known Montgomery dataset, to the size of the most frequently used Japanese Society of Radiological Technology (JSRT) dataset and normalized our digital CXRs for testing. This work resulted in the unified off-the-shelf CXR dataset composed of radiographs included in both, Montgomery and JSRT datasets. The experimental results show that even though the amount of augmentation is large, our algorithm can preserve the important information in lung fields, local structures, and global visual effect adequately. The proposed method can be used to augment training and testing image data sets so that the trained machine learning model can be used to process CXRs from various sources, and it can be potentially used broadly in any medical imaging applications.

Keywords: computer-aided diagnosis, image augmentation, lung segmentation, medical imaging, seam carving

Procedia PDF Downloads 224

Authors: Ademola A. Ladele, Peace I. Aburime

Abstract:

Fake and substandard agricultural inputs pose a serious stumbling block to farm productivity and subsequently improved livelihood. There is, therefore, a need to pave ways for sustainable agriculture and self-sufficiency in food production by proffering solutions to this challenge. Maize farmers' perception of sharp practices among agro-input dealers in Ibadan/Ibarapa agricultural zone in Oyo state was therefore investigated. A multi-stage random sampling technique was used to select registered maize farmers in the Ibadan/Ibarapa agricultural zone of the Oyo State Agricultural Development Programme (OYSADEP). A structured questionnaire was used to collect information on the perception of sharp practices and the effects of sharp practices. A total of seventy-five maize farmers were interviewed. A focus group discussion was organized to identify ways of curbing sharp practices to complement the survey. Data were analyzed using descriptive statistics, Chi-square, and Pearson Product Moment Correlation (PPMC). Forms of sharp practices indicated were sales of expired fertilizers, expired pesticides, expired herbicides, underweight fertilizers, adulterated fertilizers, adulterated herbicides, packs containing broken seeds, infested seeds, lack of truth in labeling/wrong labels, manipulation of measuring scales, and false declaration of hecterages covered by tractor operators. The majority had unfavorable perception of agro-input dealers on sharp practices. A significant relationship was observed between respondents’ level of education and their perception of sharp practices. There were no significant relationships between respondents’ sex, marital status and religion, and their perception of sharp practices. A significant correlation exists between the forms of sharp practices and the perceived effect on agricultural production. It is concluded that the perceived effect of sharp practices was critical and the endemic culture of sharp practices prevailed in agro-input in Ibadan/Ibarapa agricultural zone. A standard regulatory system that will certify and monitor the quality of inputs should be put in place.

Keywords: agricultural productivity, agro-input dealers, maize farmers, sharp practices

Procedia PDF Downloads 199

Authors: Silvia A. Magalhaes, Vasco P. De Freitas, Jose L. Alexandre

Abstract:

Most of the European literature concerning energy efficiency and thermal comfort of dwellings assumes permanent heating and focuses on energy-saving measures. European National regulations are designed for those permanent comfort conditions. On the other hand, very few studies focus on the effect of the improvement measures in comfort reduction, for free-floating conditions or intermittent heating, in fuel poverty vulnerable countries. In Portugal, only 21% of the household energy consumptions (and 10% of the cost) are spent in space heating, while, on average European bills, this value rises to 67%. The mild climate, but mainly fuel poverty and cultural background, justifies these low heating practices. This study proposes a “passive discomfort” index definition, considering free-floating temperatures or with intermittent heating profiles (more realistic conditions), putting the focus on comfort rather than energy consumption (which is low for these countries). The aim is to compare both energy (regarding the legal framework of national regulation) and comfort (considering realistic conditions of use) to identify some correlation. It was developed an experimental campaign of indoor thermal conditions in a 19th building located in Porto with several apartments. One dwelling was chosen as a case study to carry out a sensitivity analysis. The results are discussed comparing both theoretical energy consumption (energy rates from national regulation) and discomfort (new index defined), for different insulation thicknesses, orientations, and intermittent heating profiles. The results show that the different passive options (walls insulation and glazing options) have a small impact on winter discomfort, which is always high for low heating profiles. Moreover, it was shown that the insulation thickness on walls has no influence, and the minimum insulation thickness considered is enough to achieve the same impact on discomfort reduction. Plus, for these low heating profiles, other conditions are critical, as the orientation. Finally, there isn’t an unequivocal relation between the energy label and the discomfort index. These and other results are surprising when compared with the most usual approaches, which assume permanent heating.

Keywords: dwellings in historical buildings, low-heating countries, mild climates, thermal comfort

Procedia PDF Downloads 151

Authors: Mateusz Wielopolski, Asia Guerreschi

Abstract:

Circular Economy, as the counterargument to the ‘make-take-dispose’ linear model, is an approach that includes a variety of schools of thought looking at environmental, economic, and social sustainability. This, in turn, leads to a variety of strategies and often confusion when it comes to choosing the right one to make a circular transition as effective as possible. Due to the close interplay of circular product design, business model and social responsibility, companies often struggle to develop strategies that comply with all three triple-bottom-line criteria. Hence, to transition to circularity effectively, product design approaches must become more inclusive. In a case study conducted with the University of Bayreuth and the ISPO, we correlated aspects of material choice in product design, labeling and technological innovation with customer preferences and education about specific material and technology features. The study revealed those attributes of the consumers’ environmental awareness that directly translate into an increase of purchase power - primarily connected with individual preferences regarding sports activity and technical knowledge. Based on this outcome, we constituted a product development approach that incorporates the consumers’ individual preferences towards sustainable product features as well as their awareness about materials and technology. It allows deploying targeted customer education campaigns to raise the willingness to pay for sustainability. Next, we implemented the customer preference and education analysis into a circularity assessment tool that takes into account inherent company assets as well as subjective parameters like customer awareness. The outcome is a detailed but not cumbersome scoring system, which provides guidance for material and technology choices for circular product design while considering business model and communication strategy to the attentive customers. By including customer knowledge and complying with corresponding labels, companies develop more effective circular design strategies, while simultaneously increasing customers’ trust and loyalty.

Keywords: circularity, sustainability, product design, material choice, education, awareness, willingness to pay

Procedia PDF Downloads 201

Authors: John Hardy

Abstract:

The early twenty-first century national security environment has been characterized by political coercion. Despite an abundance of political commentary on the various forms of non-state coercion leveraged against the state, there is a lack of literature which distinguishes between the mechanisms and the mediums of coercion. Frequently non-state movements seeking to coerce the state are labelled by their tactics, not their strategies. Terrorists, insurgencies and social movements are largely defined by the ways in which they seek to influence the state, rather than by their political aims. This study examines the strategies of coercion used by non-state actors against states. This approach includes terrorist groups, insurgencies, and social movements who seek to coerce state politics. Not all non-state actors seek political coercion, so not all examples of different group types are considered. This approach also excludes political coercion by states, focusing on the non-state actor as the primary unit of analysis. The study applies a general theory of political coercion, which is defined as attempts to change the policies or action of a polity against its will, to the strategies employed by terrorist groups, insurgencies, and social movements. This distinguishes non-state actors’ strategic objectives from their actions and motives, which are variables that are often used to differentiate between types of non-state actors and the labels commonly used to describe them. It also allows for a comparative analysis of theoretical perspectives from the disciplines of terrorism, insurgency and counterinsurgency, and social movements. The study finds that there is a significant degree of overlap in the way that different disciplines conceptualize the mechanism of political coercion by non-state actors. Studies of terrorism and counterterrorism focus more on the notions of cost tolerance and collective punishment, while studies of insurgency focus on a contest of legitimacy between actors, and social movement theory tend to link political objectives, social capital, and a mechanism of influence to leverage against the state. Each discipline has a particular vernacular for the mechanism of coercion, which is often linked to the means of coercion, but they converge on three core theoretical components of compelling a polity to change its policies or actions: exceeding resistance to change, using political or violent punishments, and withholding legitimacy or consent from a government.

Keywords: counter terrorism, homeland security, insurgency, political coercion, social movement theory, terrorism

Procedia PDF Downloads 177

Authors: Rhaetian Bern D. Azaula

Abstract:

The Philippines' indigenous population, estimated to be 10%-20%, is protected by the Indigenous Peoples Rights Act (IPRA), passed in 1997. However, due to their isolation and limited access to basic services such as health education or needs for health assistance, the law's implementation remains a challenge. As traditional medicine continues to play a significant role in society as the prevention and treatment of some illnesses, it is still customary and widely used to use plants in both traditional and modern ways; however, commercially prepared drugs are progressively advanced as time goes by. Therefore, the purpose of this quantitative study is to investigate the indigenous community at Barangay Magsikap General Nakar, Quezon, and analyze the factors that affect the respondent’s preferences in an indigenous community and reasons for patronizing traditional and commercially prepared medicines and proposes updated health education strategies and instructional materials. Slovin's formula was utilized to reduce the total population representation, followed by stratified sampling for proportional allocation of respondents. The study selects respondents (1) from an Indigenous Community in Barangay Magsikap, General Nakar, Quezon, (2) aged 60 and above, and (3) who are willing to participate. The researcher utilized a checklist-based questionnaire with a Tagalog version, and a Likert Scale was utilized to assess the respondent's choices on selected items. The researcher obtained informed consent from the indigenous community's regional and local office, the chieftain of the tribe, and the respondents, ensuring confidentiality in the collection and retrieval of data. The study revealed that respondents aged 60-69, males with no formal education, are unemployed and have no income source. They prefer traditional medicines due to their affordability, availability, and cultural practices but lack safe preparation, dosages, and contraindications of used medicines. Commercially prepared medications are acknowledged, but respondents are not fully aware of proper administration instructions and dosage labels. Recommendations include disseminating approved herbal medicines and ensuring proper preparation, indications, and contraindications.

Keywords: traditional medicine, commercially prepared medicine, indigenous community, elderly adult

Procedia PDF Downloads 73

Authors: Jamie E. Banker

Abstract:

For many families, pregnancy and the postpartum time are filled with both anticipation and change. For some pregnant or postpartum women, this time is marked by the onset of a mood or anxiety disorder. Experiencing a mood or anxiety disorders during this time of life differs from depression or anxiety at other times of life. Not only because of the physical changes occurring in the mother’s body but also the mental and physical preparation necessary to redefine family roles, responsibilities, and develop new identities in the life transition. The presence of a mood or anxiety disorder can influence the way in which a mother defines herself and can complicate her understanding of her abilities and competencies as a mother. The complexity of experiencing a mood or anxiety disorder in the midst of these changes necessitates specific treatment interventions to match both the symptomatology and psychological adjustments. This study explores the use of narrative family therapy techniques when treating a mother who is experiencing postpartum depression. Externalization is a common technique used in narrative family therapy and can help client’s separate their identity from the problems they are experiencing. This is crucial to a new mom who is in the middle of defining her identity during her transition to parenthood. The goal of this study is to examine how the use of externalization techniques help postpartum women separate their mood and anxiety symptoms from their identity as a mother. An exploratory case study design was conducted in a single setting, private practice therapy office, and explored how a narrative family therapy approach can be used to treat perinatal mood and anxiety disorders. The therapy sessions were audio recorded and transcribed. Constructivism and narrative theory are used as theoretical frameworks and data from the therapy sessions, and a follow-up survey was triangulated and analyzed. During the course of the treatment, the participant reports using the new externalizing labels for her symptoms. Within one month of treatment, the participant reports that she could stop herself from thinking the harmful thoughts faster, and within three months, the harmful thoughts went away. The main themes in this study were building courage and less self-blame. This case highlights the role narrative family therapy can play in the treatment of perinatal mood and anxiety disorders and the importance of separating a women’s mood from her identity as a mother. This conceptual framework was beneficial to the postpartum mother when treating perinatal mood and anxiety disorder symptoms.

Keywords: externalizing techniques, narrative family therapy, perinatal mood and anxiety disorders, postpartum depression

Procedia PDF Downloads 275

Authors: Fatimah AlSaiari

Abstract:

In recent years, newspapers in the United Kingdom have been no longer just a means of sharing news about what happens in the world; they are also used to influence target readers by having them become more up-to-date, well-informed, entertained, exasperated, delighted, and infuriated. To achieve these objectives and maintain influence on public opinion, journalists use a particular language in which they can convey emotions and opinions, organize their discourse, and establish solidarity with their audience. This type of language has been widely analyzed under different labels, such as evaluation, appraisal, and stance. There is a considerable amount of linguistic and non-linguistic research devoted to analyzing this type of interpersonal language in journalistic discourse, and most of these studies were carried out to challenge the traditional assumptions of the objectivity and impartiality of news reporting. However, very little research has been undertaken on evaluative language in newspaper institutional editorials, and there is hardly any systematic or exhaustive analysis of this type of language in British tabloid and broadsheet newspapers. This study will attempt to provide new insights into the nature of authorial and non-authorial evaluation in leading articles in popular and quality British newspapers, along with their targets, sources, and discourse functions. The study will also attempt to develop a framework of evaluation that can be applied to evaluative lexical items in newspaper opinion texts. The framework is both theory-driven (i.e., it builds on and modifies previous frameworks of evaluation such as appraisal theory and parameter-based approach) and data-driven (i.e., it elicits the evaluative categories from the analysis of the corpus, which helps in the development of the current framework). To achieve this aim, a corpus of 140 leading articles were selected. The findings revealed that the tabloids tended to express their stance through explicitness, dramatization, frequent reference to social actors’ emotions and beliefs, and exaggeration in negativity, while the broadsheets preferred to express their stance through mitigation ambiguity and implicitness. conceptual themes and propositions were more preferable targets for expressing stance in the broadsheets while human behavior and characters were preferable targets for the tabloids.

Keywords: appraisal theory, evaluative language, British newspapers, broadsheets & tabloids, evaluative adjectives

Procedia PDF Downloads 294

Authors: Magdalena Igras, Joanna Grzybowska, Mariusz Ziółko

Abstract:

The study of emotions expressed in emergency phone call is presented, covering both statistical analysis of emotions configurations and an attempt to automatically classify emotions. An emergency call is a situation usually accompanied by intense, authentic emotions. They influence (and may inhibit) the communication between caller and responder. In order to support responders in their responsible and psychically exhaustive work, we studied when and in which combinations emotions appeared in calls. A corpus of 45 hours of conversations (about 3300 calls) from emergency call center was collected. Each recording was manually tagged with labels of emotions valence (positive, negative or neutral), type (sadness, tiredness, anxiety, surprise, stress, anger, fury, calm, relief, compassion, satisfaction, amusement, joy) and arousal (weak, typical, varying, high) on the basis of perceptual judgment of two annotators. As we concluded, basic emotions tend to appear in specific configurations depending on the overall situational context and attitude of speaker. After performing statistical analysis we distinguished four main types of emotional behavior of callers: worry/helplessness (sadness, tiredness, compassion), alarm (anxiety, intense stress), mistake or neutral request for information (calm, surprise, sometimes with amusement) and pretension/insisting (anger, fury). The frequency of profiles was respectively: 51%, 21%, 18% and 8% of recordings. A model of presenting the complex emotional profiles on the two-dimensional (tension-insecurity) plane was introduced. In the stage of acoustic analysis, a set of prosodic parameters, as well as Mel-Frequency Cepstral Coefficients (MFCC) were used. Using these parameters, complex emotional states were modeled with machine learning techniques including Gaussian mixture models, decision trees and discriminant analysis. Results of classification with several methods will be presented and compared with the state of the art results obtained for classification of basic emotions. Future work will include optimization of the algorithm to perform in real time in order to track changes of emotions during a conversation.

Keywords: acoustic analysis, complex emotions, emotion recognition, machine learning

Procedia PDF Downloads 399

Authors: Jonathan Gong

Abstract:

Purpose AI-driven solutions are at the forefront of many pathology and medical imaging methods. Using algorithms designed to better the experience of medical professionals within their respective fields, the efficiency and accuracy of diagnosis can improve. In particular, X-rays are a fast and relatively inexpensive test that can diagnose diseases. In recent years, X-rays have not been widely used to detect and diagnose COVID-19. The under use of Xrays is mainly due to the low diagnostic accuracy and confounding with pneumonia, another respiratory disease. However, research in this field has expressed a possibility that artificial neural networks can successfully diagnose COVID-19 with high accuracy. Models and Data The dataset used is the COVID-19 Radiography Database. This dataset includes images and masks of chest X-rays under the labels of COVID-19, normal, and pneumonia. The classification model developed uses an autoencoder and a pre-trained convolutional neural network (DenseNet201) to provide transfer learning to the model. The model then uses a deep neural network to finalize the feature extraction and predict the diagnosis for the input image. This model was trained on 4035 images and validated on 807 separate images from the ones used for training. The images used to train the classification model include an important feature: the pictures are cropped beforehand to eliminate distractions when training the model. The image segmentation model uses an improved U-Net architecture. This model is used to extract the lung mask from the chest X-ray image. The model is trained on 8577 images and validated on a validation split of 20%. These models are calculated using the external dataset for validation. The models’ accuracy, precision, recall, f1-score, IOU, and loss are calculated. Results The classification model achieved an accuracy of 97.65% and a loss of 0.1234 when differentiating COVID19-infected, pneumonia-infected, and normal lung X-rays. The segmentation model achieved an accuracy of 97.31% and an IOU of 0.928. Conclusion The models proposed can detect COVID-19, pneumonia, and normal lungs with high accuracy and derive the lung mask from a chest X-ray with similarly high accuracy. The hope is for these models to elevate the experience of medical professionals and provide insight into the future of the methods used.

Keywords: artificial intelligence, convolutional neural networks, deep learning, image processing, machine learning

Procedia PDF Downloads 131

Authors: Sareh Edalati, Nasrin Omidvar, Arezoo Haghighian Roudsari, Delaram Ghodsi, Azizollaah Zargaran

Abstract:

Background and aim: Improving consumer’s food choices and providing a healthy food environment by governments is one of the essential approaches to prevent non-communicable diseases and to fulfill the sustainable development goals (SDGs). The present study aimed to provide an analysis of the nutrition labeling policy as one of the main components of the healthy food environment to provide learning lessons for the country and other low and middle-income countries. Methods: Data were collected by reviewing documents and conducting semi-structured interviews with stakeholders. Respondents were selected through purposive and snowball sampling and continued until data saturation. MAXQDA software was used to manage data analysis. A deductive content analysis was used by applying the Kingdon multiple streams and the policy triangulation framework. Results: Iran is the first country in the Middle East and North Africa region, which has implemented nutrition traffic light labeling. The implementation process has gone through two phases: voluntary and mandatory. In the voluntary labeling, volunteer food manufacturers who chose to have the labels would receive an honorary logo and this helped to reduce the food-sector resistance gradually. After this phase, the traffic light labeling became mandatory. Despite these efforts, there has been poor involvement of media for public awareness and sensitization. Also, the inconsistency of nutrition traffic light colors which are based on food standard guidelines, lack of consistency between nutrition traffic light colors, the healthy/unhealthy nature of some food products such as olive oil and diet cola and the absence of a comprehensive evaluation plan were among the pitfalls and policy challenges identified. Conclusions: Strengthening the governance through improving collaboration within health and non-health sectors for implementation, more transparency of truthfulness of nutrition traffic labeling initiating with real ingredients, and applying international and local scientific evidence or any further revision of the program is recommended. Also, developing public awareness campaigns and revising school curriculums to improve students’ skills on nutrition label applications should be highly emphasized.

Keywords: nutrition labeling, policy analysis, food environment, Iran

Procedia PDF Downloads 193

Authors: Deepali Rastogi, Akanksha Rastogi

Abstract:

Comfort and safety are two essential factors in a newborn’s clothing. Natural dyes are considered safe for infant clothes because they are non-toxic and have medicinal properties. Natural dyes are sensitive to pH and may show changes in hue under different pH conditions. Infant garments face treatments different than adult clothing, for instance, exposure to infant’s saliva, milk, and urine. The present study was designed to study the suitability of natural dyes for infant clothes. Cotton fabric was dyed using fifteen natural dyes and two mordants, alum, and ferrous sulphate. The dyed samples were assessed for colour fastness to washing, rubbing, perspiration and light. In addition, fastness to milk, saliva, and urine was also tested. Simulated solutions of saliva and urine were prepared for the study. For milk, one of the commercial formulations for infants was taken and used as per the directions. A wide gamut of colours was obtained after dyeing the cotton with different natural dyes and mordants. The colour strength of all the dyed samples was determined in terms of K/S values. Most of the ferrous sulphate mordanted dyes gave higher K/S values than alum mordanted samples. The wash fastness of dyed cotton fabrics ranged from 3/4 -5. Perspiration fastness test for the samples was done in both acidic and alkaline mediums. The ratings ranged from 3-5, with most of the dyes falling in the range of 4-5. The rubbing fastness of the dyed samples was tested in dry and wet conditions. The results showed excellent rub fastness ranging between 4-5. Light fastness was found to be good to moderate. The main food for infants is milk, and this becomes one of the main agents to spot infants' garments. All dyes showed excellent fastness properties against milk with a grey scale rating of 4-5. Fastness against saliva is recommended by various eco-labels, standards, and organizations for fabrics of infants or babies. The fastness of most of the dyes was found to be satisfactory against saliva. Infant garments get frequently soiled with urine. Most of the natural dyes on cotton fabric had good to excellent fastness to simulated urine. The grey scale ratings ranged from 3/4 – 5. Thus, it can be concluded that most of the natural dyes can be successfully used for infant wear and accessories and are fast to various liquids to which infant wear are exposed. Therefore, we can surround little ones with beautiful hues from nature's garden and clothe them in natural fibres dyed with natural dyes.

Keywords: fastness properties, infant wear, mordants, natural dyes

Procedia PDF Downloads 143

Authors: O. Katz-Shufan, T. Simon-Tuval, L. Sabag, L. Granek, D. R. Shahar

Abstract:

Meals provided at catering systems are a common source of workers' nutrition and were found as contributing high amounts calories and fat. Thus, eating daily catering food can lead to overweight and chronic diseases. On the other hand, the institutional dining room may be an ideal environment for implementation of intervention programs that promote healthy eating. This may improve diners' lifestyle and reduce their prevalence of overweight, obesity and chronic diseases. The significance of this study is in developing an intervention program based on the diners’ dietary habits, preferences and their attitudes towards various intervention programs. In addition, a successful catering-based intervention program may have a significant effect simultaneously on a large group of diners, leading to improved nutrition, healthier lifestyle, and disease-prevention on a large scale. In order to develop the intervention program, we conducted a qualitative study. We interviewed 13 diners who eat regularly at catering systems, using a semi-structured interview. The interviews were recorded, transcribed and then analyzed by the thematic method, which identifies, analyzes and reports themes within the data. The interviews revealed several major themes, including expectation of diners to be provided with healthy food choices; their request for nutrition-expert involvement in planning the meals; the diners' feel that there is a conflict between sensory attractiveness of the food and its' nutritional quality. In the context of the catering-based intervention programs, the diners prefer scientific and clear messages focusing on labeling healthy dishes only, as opposed to the labeling of unhealthy dishes; they were interested in a nutritional education program to accompany the intervention program. Based on these findings, we have developed an intervention program that includes: changes in food served such as replacing several menu items and nutritional improvement of some of the recipes; as well as, environmental changes such as changing the location of some food items presented on the buffet, placing positive nutritional labels on healthy dishes and an ongoing healthy nutrition campaign, all accompanied by a nutrition education program. The intervention program is currently being tested for its impact on health outcomes and its cost-effectiveness.

Keywords: catering system, food services, intervention, nutrition policy, public health, qualitative research

Procedia PDF Downloads 196

Authors: Adel Edwar Waheeb Louka

Abstract:

Purpose AI-driven solutions are at the forefront of many pathology and medical imaging methods. Using algorithms designed to better the experience of medical professionals within their respective fields, the efficiency and accuracy of diagnosis can improve. In particular, X-rays are a fast and relatively inexpensive test that can diagnose diseases. In recent years, X-rays have not been widely used to detect and diagnose COVID-19. The under use of Xrays is mainly due to the low diagnostic accuracy and confounding with pneumonia, another respiratory disease. However, research in this field has expressed a possibility that artificial neural networks can successfully diagnose COVID-19 with high accuracy. Models and Data The dataset used is the COVID-19 Radiography Database. This dataset includes images and masks of chest X-rays under the labels of COVID-19, normal, and pneumonia. The classification model developed uses an autoencoder and a pre-trained convolutional neural network (DenseNet201) to provide transfer learning to the model. The model then uses a deep neural network to finalize the feature extraction and predict the diagnosis for the input image. This model was trained on 4035 images and validated on 807 separate images from the ones used for training. The images used to train the classification model include an important feature: the pictures are cropped beforehand to eliminate distractions when training the model. The image segmentation model uses an improved U-Net architecture. This model is used to extract the lung mask from the chest X-ray image. The model is trained on 8577 images and validated on a validation split of 20%. These models are calculated using the external dataset for validation. The models’ accuracy, precision, recall, f1-score, IOU, and loss are calculated. Results The classification model achieved an accuracy of 97.65% and a loss of 0.1234 when differentiating COVID19-infected, pneumonia-infected, and normal lung X-rays. The segmentation model achieved an accuracy of 97.31% and an IOU of 0.928. Conclusion The models proposed can detect COVID-19, pneumonia, and normal lungs with high accuracy and derive the lung mask from a chest X-ray with similarly high accuracy. The hope is for these models to elevate the experience of medical professionals and provide insight into the future of the methods used.

Keywords: artificial intelligence, convolutional neural networks, deeplearning, image processing, machine learningSarapin, intraarticular, chronic knee pain, osteoarthritisFNS, trauma, hip, neck femur fracture, minimally invasive surgery

Procedia PDF Downloads 74

Authors: Arindam Chaudhuri

Abstract:

Classification of data has been actively used for most effective and efficient means of conveying knowledge and information to users. The prima face has always been upon techniques for extracting useful knowledge from data such that returns are maximized. With emergence of huge datasets the existing classification techniques often fail to produce desirable results. The challenge lies in analyzing and understanding characteristics of massive data sets by retrieving useful geometric and statistical patterns. We propose a supervised parallel fuzzy rough support vector machine (PFRSVM) for data classification in cloud environment. The classification is performed by PFRSVM using hyperbolic tangent kernel. The fuzzy rough set model takes care of sensitiveness of noisy samples and handles impreciseness in training samples bringing robustness to results. The membership function is function of center and radius of each class in feature space and is represented with kernel. It plays an important role towards sampling the decision surface. The success of PFRSVM is governed by choosing appropriate parameter values. The training samples are either linear or nonlinear separable. The different input points make unique contributions to decision surface. The algorithm is parallelized with a view to reduce training times. The system is built on support vector machine library using Hadoop implementation of MapReduce. The algorithm is tested on large data sets to check its feasibility and convergence. The performance of classifier is also assessed in terms of number of support vectors. The challenges encountered towards implementing big data classification in machine learning frameworks are also discussed. The experiments are done on the cloud environment available at University of Technology and Management, India. The results are illustrated for Gaussian RBF and Bayesian kernels. The effect of variability in prediction and generalization of PFRSVM is examined with respect to values of parameter C. It effectively resolves outliers’ effects, imbalance and overlapping class problems, normalizes to unseen data and relaxes dependency between features and labels. The average classification accuracy for PFRSVM is better than other classifiers for both Gaussian RBF and Bayesian kernels. The experimental results on both synthetic and real data sets clearly demonstrate the superiority of the proposed technique.

Keywords: FRSVM, Hadoop, MapReduce, PFRSVM

Procedia PDF Downloads 491

Authors: Katarzyna Neffe-Skocinska, Marzena Tomaszewska, Beata Bilska, Dorota Zielinska, Monika Trzaskowska, Anna Lepecka, Danuta Kolozyn-Krajewska

Abstract:

The aim of the study was to assess Polish consumer behavior towards food waste, including knowledge of information on food labels. The survey was carried out using the CAPI (computer assisted personal interview) method, which involves interviewing the respondent using mobile devices. The research group was a representative sample for Poland due to demographic variables: gender, age, place of residence. A total of 1.115 respondents participated in the study (51.1% were women and 48.9% were men). The questionnaire included questions on five thematic aspects: 1. General knowledge and sources of information on the phenomenon of food waste; 2. Consumption of food after the date of minimum durability; 3. The meanings of the phrase 'best before ...'; 4. Indication of the difference between the meaning of the words 'best before ...' and 'use by'; 5. Indications products marked with the phrase 'best before ...'. It was found that every second surveyed Pole met with the topic of food waste (54.8%). Among the respondents, the most popular source of information related to the research topic was television (89.4%), radio (26%) and the Internet (24%). Over a third of respondents declared that they consume food after the date of minimum durability. Only every tenth (9.8%) respondent does not pay attention to the expiry date and type of consumed products (durable and perishable products). Correctly 39.8% of respondents answered the question: How do you understand the phrase 'best before ...'? In the opinion of 42.8% of respondents, the statements 'best before ...' and 'use by' mean the same thing, while 36% of them think differently. In addition, more than one-fifth of respondents could not respond to the questions. In the case of products of the indication information 'best before ...', more than 40% of the respondents chosen perishable products, e.g., yoghurts and durable, e.g., groats. A slightly lower percentage of indications was recorded for flour (35.1%), sausage (32.8%), canned corn (31.8%), and eggs (25.0%). Based on the assessment of the behavior of Polish consumers towards the phenomenon of food waste, it can be concluded that respondents have elementary knowledge of the study subject. Noteworthy is the good conduct of most respondents in terms of compliance with shelf life and dates of minimum durability of food products. The publication was financed on the basis of an agreement with the National Center for Research and Development No. Gospostrateg 1/385753/1/NCBR/2018 for the implementation and financing of the project under the strategic research and development program social and economic development of Poland in the conditions of globalizing markets – GOSPOSTRATEG - acronym PROM.

Keywords: food waste, shelf life, dates of durability, consumer knowledge and behavior

Procedia PDF Downloads 175

Authors: M. Kharrat, G. Moreau, Z. Aboura

Abstract:

The latest advances in the weaving industry, combined with increasingly sophisticated means of materials processing, have made it possible to produce complex 3D composite structures. Mainly used in aeronautics, composite materials with 3D architecture offer better mechanical properties than 2D reinforced composites. Nevertheless, these materials require a good understanding of their behavior. Because of the complexity of such materials, the damage mechanisms are multiple, and the scenario of their appearance and evolution depends on the nature of the exerted solicitations. The AE technique is a well-established tool for discriminating between the damage mechanisms. Suitable sensors are used during the mechanical test to monitor the structural health of the material. Relevant AE-features are then extracted from the recorded signals, followed by a data analysis using pattern recognition techniques. In order to better understand the damage scenarios of interlock composite materials, a multi-instrumentation was set-up in this work for tracking damage initiation and development, especially in the vicinity of the first significant damage, called macro-damage. The deployed instrumentation includes video-microscopy, Digital Image Correlation, Acoustic Emission (AE) and micro-tomography. In this study, a multi-variable AE data analysis approach was developed for the discrimination between the different signal classes representing the different emission sources during testing. An unsupervised classification technique was adopted to perform AE data clustering without a priori knowledge. The multi-instrumentation and the clustered data served to label the different signal families and to build a learning database. This latter is useful to construct a supervised classifier that can be used for automatic recognition of the AE signals. Several materials with different ingredients were tested under various solicitations in order to feed and enrich the learning database. The methodology presented in this work was useful to refine the damage threshold for the new generation materials. The damage mechanisms around this threshold were highlighted. The obtained signal classes were assigned to the different mechanisms. The isolation of a 'noise' class makes it possible to discriminate between the signals emitted by damages without resorting to spatial filtering or increasing the AE detection threshold. The approach was validated on different material configurations. For the same material and the same type of solicitation, the identified classes are reproducible and little disturbed. The supervised classifier constructed based on the learning database was able to predict the labels of the classified signals.

Keywords: acoustic emission, classifier, damage mechanisms, first damage threshold, interlock composite materials, pattern recognition

Procedia PDF Downloads 156

Authors: Mohsen Bahrami, Banafsheh Nikmehr, Yueqiang Song, Anuradha Koduru, Ayse K. Vuruskan, Hongkun Lu, Tamer M. Yalcinkaya

Abstract:

In recent years, we have witnessed an explosion of studies aimed at using a combination of artificial intelligence (AI) and time-lapse imaging data on embryos to improve IVF outcomes. However, despite promising results, no study has used a matched cohort of transferred embryos which only differ in pregnancy outcome, i.e., embryos from a single clinic which are similar in parameters, such as: morphokinetic condition, patient age, and overall clinic and lab performance. Here, we used time-lapse data on embryos with known pregnancy outcomes to see if the rich spatiotemporal information embedded in this data would allow the prediction of the pregnancy outcome regardless of such critical parameters. Methodology—We did a retrospective analysis of time-lapse data from our IVF clinic utilizing Embryoscope 100% of the time for embryo culture to blastocyst stage with known clinical outcomes, including live birth vs nonpregnant (embryos with spontaneous abortion outcomes were excluded). We used time-lapse data from 200 elective single transfer embryos randomly selected from January 2019 to June 2021. Our sample included 100 embryos in each group with no significant difference in patient age (P=0.9550) and morphokinetic scores (P=0.4032). Data from all patients were combined to make a 4th order tensor, and feature extraction were subsequently carried out by a tensor decomposition methodology. The features were then used in a machine learning classifier to classify the two groups. Major Findings—The performance of the model was evaluated using 100 random subsampling cross validation (train (80%) - test (20%)). The prediction accuracy, averaged across 100 permutations, exceeded 80%. We also did a random grouping analysis, in which labels (live birth, nonpregnant) were randomly assigned to embryos, which yielded 50% accuracy. Conclusion—The high accuracy in the main analysis and the low accuracy in random grouping analysis suggest a consistent spatiotemporal pattern which is associated with pregnancy outcomes, regardless of patient age and embryo morphokinetic condition, and beyond already known parameters, such as: early cleavage or early blastulation. Despite small samples size, this ongoing analysis is the first to show the potential of AI methods in capturing the complex morphokinetic changes embedded in embryo time-lapse data, which contribute to successful pregnancy outcomes, regardless of already known parameters. The results on a larger sample size with complementary analysis on prediction of other key outcomes, such as: euploidy and aneuploidy of embryos will be presented at the meeting.

Keywords: IVF, embryo, machine learning, time-lapse imaging data

Procedia PDF Downloads 93

Authors: Rafael do Amaral Teodoro, Leandro Augusto da Silva

Abstract:

Originated from graphite, graphene is a two-dimensional (2D) material that promises to revolutionize technology in many different areas, such as energy, telecommunications, civil construction, aviation, textile, and medicine. This is possible because its structure, formed by carbon bonds, provides desirable optical, thermal, and mechanical characteristics that are interesting to multiple areas of the market. Thus, several research and development centers are studying different manufacturing methods and material applications of graphene, which are often compromised by the scarcity of more agile and accurate methodologies to characterize the material – that is to determine its composition, shape, size, and the number of layers and crystals. To engage in this search, this study proposes a computational methodology that applies deep learning to identify graphene oxide crystals in order to characterize samples by crystal sizes. To achieve this, a fully convolutional neural network called U-net has been trained to segment SEM graphene oxide images. The segmentation generated by the U-net is fine-tuned with a standard deviation technique by classes, which allows crystals to be distinguished with different labels through an object delimitation algorithm. As a next step, the characteristics of the position, area, perimeter, and lateral measures of each detected crystal are extracted from the images. This information generates a database with the dimensions of the crystals that compose the samples. Finally, graphs are automatically created showing the frequency distributions by area size and perimeter of the crystals. This methodological process resulted in a high capacity of segmentation of graphene oxide crystals, presenting accuracy and F-score equal to 95% and 94%, respectively, over the test set. Such performance demonstrates a high generalization capacity of the method in crystal segmentation, since its performance considers significant changes in image extraction quality. The measurement of non-overlapping crystals presented an average error of 6% for the different measurement metrics, thus suggesting that the model provides a high-performance measurement for non-overlapping segmentations. For overlapping crystals, however, a limitation of the model was identified. To overcome this limitation, it is important to ensure that the samples to be analyzed are properly prepared. This will minimize crystal overlap in the SEM image acquisition and guarantee a lower error in the measurements without greater efforts for data handling. All in all, the method developed is a time optimizer with a high measurement value, considering that it is capable of measuring hundreds of graphene oxide crystals in seconds, saving weeks of manual work.

Keywords: characterization, graphene oxide, nanomaterials, U-net, deep learning

Procedia PDF Downloads 160

Authors: Anup Anand Deshmukh, Catherine Soladie, Renaud Seguier

Abstract:

Emotion plays a key role in many applications like healthcare, to gather patients’ emotional behavior. Unlike typical ASR (Automated Speech Recognition) problems which focus on 'what was said', it is equally important to understand 'how it was said.' There are certain emotions which are given more importance due to their effectiveness in understanding human feelings. In this paper, we propose an approach that models human stress from audio signals. The research challenge in speech emotion detection is finding the appropriate set of acoustic features corresponding to an emotion. Another difficulty lies in defining the very meaning of emotion and being able to categorize it in a precise manner. Supervised Machine Learning models, including state of the art Deep Learning classification methods, rely on the availability of clean and labelled data. One of the problems in affective computation is the limited amount of annotated data. The existing labelled emotions datasets are highly subjective to the perception of the annotator. We address the first issue of feature selection by exploiting the use of traditional MFCC (Mel-Frequency Cepstral Coefficients) features in Convolutional Neural Network. Our proposed Emo-CNN (Emotion-CNN) architecture treats speech representations in a manner similar to how CNN’s treat images in a vision problem. Our experiments show that Emo-CNN consistently and significantly outperforms the popular existing methods over multiple datasets. It achieves 90.2% categorical accuracy on the Emo-DB dataset. We claim that Emo-CNN is robust to speaker variations and environmental distortions. The proposed approach achieves 85.5% speaker-dependant categorical accuracy for SAVEE (Surrey Audio-Visual Expressed Emotion) dataset, beating the existing CNN based approach by 10.2%. To tackle the second problem of subjectivity in stress labels, we use Lovheim’s cube, which is a 3-dimensional projection of emotions. Monoamine neurotransmitters are a type of chemical messengers in the brain that transmits signals on perceiving emotions. The cube aims at explaining the relationship between these neurotransmitters and the positions of emotions in 3D space. The learnt emotion representations from the Emo-CNN are mapped to the cube using three component PCA (Principal Component Analysis) which is then used to model human stress. This proposed approach not only circumvents the need for labelled stress data but also complies with the psychological theory of emotions given by Lovheim’s cube. We believe that this work is the first step towards creating a connection between Artificial Intelligence and the chemistry of human emotions.

Keywords: deep learning, brain chemistry, emotion perception, Lovheim's cube

Procedia PDF Downloads 156

Authors: Caitlin Bailey, Marian Frattarola Saulino, Beth Steinberg

Abstract:

Today, virtually all programs offered to people with intellectual and developmental disabilities tout themselves as person-centered, community-based and inclusive, yet there is a vast range in type and quality of services that use these similar descriptors. The issue is exacerbated by the fields’ measurement practices around quality, inclusion, independent living, choice and person-centered outcomes. For instance, community inclusion for people with disabilities is often measured by the number of times person steps into his or her community. These measurement approaches set standards for quality too low so that agencies supporting group home residents to go bowling every week can report the same outcomes as an agency that supports one person to join a book club that includes people based on their literary interests rather than disability labels. Ultimately, lack of delineation in measurement contributes to the confusion between face value “quality” and true quality services and supports for many people with disabilities and their families. This exploratory study adopts alternative approaches to quality measurement including co-production methods and systems theoretical framework in order to identify the factors that 1) lead to high-quality supports and, 2) differentiate high-quality services. Project researchers have partnered with community practitioners who are all committed to providing quality services and supports but vary in the degree to which they are actually able to provide them. The study includes two parts; first, an online survey distributed to more than 500 agencies that have demonstrated commitment to providing high-quality services; and second, four in-depth case studies with agencies in three United States and Israel providing a variety of supports to children and adults with disabilities. Results from both the survey and in-depth case studies were thematically analyzed and coded. Results show that there are specific factors that differentiate service quality; however meaningful quality measurement practices also require that researchers explore the contextual factors that contribute to quality. These not only include direct services and interactions, but also characteristics of service users, their environments as well as organizations providing services, such as management and funding structures, culture and leadership. Findings from this study challenge researchers, policy makers and practitioners to examine existing quality service standards and measurements and to adopt alternate methodologies and solutions to differentiate and scale up evidence-based quality practices so that all people with disabilities have access to services that support them to live, work, and enjoy where and with whom they choose.

Keywords: co-production, inclusion, independent living, quality measurement, quality supports

Procedia PDF Downloads 400

Authors: Anat Peleg, Hadar Dancig-Rosenberg

Abstract:

This interdisciplinary study, to our knowledge the first in this field, is located on the intersection of victimology-law and society-and media literature, and it corresponds both with feminist writing and with cyber literature which explores the techno-social sphere. It depicts the multifaceted dimensions of shaming in the eyes of the survivors through the following research questions: What are the motivations of sexual-assault survivors to publicize the assailants' identity or to refrain from this practice? Is shaming on Facebook perceived by sexual–assault victims as a substitute for the CJS or as a new form of social activism? What positive and negative consequences do survivors experience as a result of shaming their assailants online? The study draws on in-depth semi-structured interviews which we have conducted between 2016-2018 with 20 sexual-assaults survivors who exposed themselves on Facebook. They were sexually attacked in various forms: six participants reported that they had been raped when they were minors; eight women reported that they had been raped as adults; three reported that they had been victims of an indecent act and three reported that they had been harassed either in their workplace or in the public sphere. Most of our interviewees (12) reported to the police and were involved in criminal procedures. More than half of the survivors (11) disclosed the identity of their attackers online. The vocabularies of motives that have emerged from the thematic analysis of the interviews with the survivors consist of both social and personal motivations for using the practice of shaming online. Some survivors maintain that the use of shaming derives from the decline in the public trust in the criminal justice system. It reflects demand for accountability and justice and serves also as a practice of warning other potential victims of the assailants. Other survivors assert that shaming people in a position of privilege is meant to fulfill the public right to know who these privileged men really are. However, these aforementioned moral and practical justifications of the practice of shaming are often mitigated by fear from the attackers' physical or legal actions in response to their allegations. Some interviewees who are feminist activists argue that the practice of shaming perpetuates the social ancient tendency to define women by labels linking them to the men who attacked them, instead of being defined by their own life complexities. The variety of motivations to adopt or resent the practice of shaming by sexual assault victims presented in our study appear to refute the prevailing intuitive stereotype that shaming is an irrational act of revenge, and denote its rationality. The role of social media as an arena for seeking informal justice raises questions about the new power relations created between victims, assailants, the community and the State, outside the formal criminal justice system. At the same time, the survivors' narratives also uncover the risks and pitfalls embedded within the online sphere for sexual assault survivors.

Keywords: criminal justice, gender, Facebook, sexual-assaults

Procedia PDF Downloads 113

Authors: Dembel Bonta Gebeyehu

Abstract:

In the study area, the impacts of deforestation for environmental degradation and livelihood of farmers manifest in different faces. They are more vulnerable as they depend on rain-fed agriculture and immediate natural forests. On the other hand, after planting seedling, waste disposal and management system of the plastic cover is poorly practiced and administered in the country in general and in the study area in particular. If this situation continues, the plastic waste would also accentuate land degradation. Besides, there is the absence of empirical studies conducted comprehensively on the research under study the case. The results of the study could suffice to inform any intervention schemes or to contribute to the existing knowledge on these issues. The study employed a qualitative approach based on intensive fieldwork data collected via various tools namely open-ended interviews, focus group discussion, key-informant interview and non-participant observation. The collected data was duly transcribed and latter categorized into different labels based on pre-determined themes to make further analysis. The major causes of deforestation were the expansion of agricultural land, poor administration, population growth, and the absence of conservation methods. The farmers are vulnerable to soil erosion and soil infertility culminating in low agricultural production; loss of grazing land and decline of livestock production; climate change; and deterioration of social capital. Their adaptation and coping strategies include natural conservation measures, diversification of income sources, safety-net program, and migration. Due to participatory natural resource conservation measures, soil erosion has been decreased and protected, indigenous woodlands started to regenerate. These brought farmers’ attitudinal change. The existing forestation program has many flaws. Especially, after planting seedlings, there is no mechanism for the plastic waste disposal and management. It was also found out organizational challenges among the mandated offices In the studied area, deforestation is aggravated by a number of factors, which made the farmers vulnerable. The current forestation programs are not well-planned, implemented, and coordinated. Sustainable and efficient seedling plastic cover collection and reuse methods should be devised. This is possible through creating awareness, organizing micro and small enterprises to reuse, and generate income from the collected plastic etc.

Keywords: land-cover and land-dynamics, vulnerability, adaptation strategy, mitigation strategies, sustainable plastic waste management

Procedia PDF Downloads 389

Authors: In-Tsang Lin, Chiching Wei

Abstract:

Reading order is an important task in many digitization scenarios involving the preservation of the logical structure of a document. From the paper survey, it finds that the state-of-the-art algorithm could not fulfill to get the accurate reading order in the portable document format (PDF) files with rich formats, diverse layout arrangement. In recent years, most of the studies on the analysis of reading order have targeted the specific problem of associating layout components with logical labels, while less attention has been paid to the problem of extracting relationships the problem of detecting the reading order relationship between logical components, such as cross-references. Over 3 years of development, the company Foxit has demonstrated the layout recognition (LR) engine in revision 20601 to eager for the accuracy of the reading order. The bounding box of each paragraph can be obtained correctly by the Foxit LR engine, but the result of reading-order is not always correct for single-column, and two-column layout format due to the table issue, formula issue, and multiple mini separated bounding box and footer issue. Thus, the algorithm is developed to improve the accuracy of the reading order based on the Foxit LR structure. In this paper, a creative observation method (Here called the MESH method) is provided here to open a new chance in the research of the reading-order field. Here two important parameters are introduced, one parameter is the number of the bounding box on the right side of the present bounding box (NRight), and another parameter is the number of the bounding box under the present bounding box (Nunder). And the normalized x-value (x/the whole width), the normalized y-value (y/the whole height) of each bounding box, the x-, and y- position of each bounding box were also put into consideration. Initial experimental results of single column layout format demonstrate a 19.33% absolute improvement in accuracy of the reading-order over 7 PDF files (total 150 pages) using our proposed method based on the LR structure over the baseline method using the LR structure in 20601 revision, which its accuracy of the reading-order is 72%. And for two-column layout format, the preliminary results demonstrate a 44.44% absolute improvement in accuracy of the reading-order over 2 PDF files (total 18 pages) using our proposed method based on the LR structure over the baseline method using the LR structure in 20601 revision, which its accuracy of the reading-order is 0%. Until now, the footer issue and a part of multiple mini separated bounding box issue can be solved by using the MESH method. However, there are still three issues that cannot be solved, such as the table issue, formula issue, and the random multiple mini separated bounding boxes. But the detection of the table position and the recognition of the table structure are out of the scope in this paper, and there is needed another research. In the future, the tasks are chosen- how to detect the table position in the page and to extract the content of the table.

Keywords: document processing, reading order, observation method, layout recognition

Procedia PDF Downloads 181