Search results for: train platforming

Authors: Nizamuddin Zainuddin, Adam Mohd Saifudin, Ahmad Yusni Bahaudin, Mohd Hanizan Zalazilah, Roslan Jamaluddin

Abstract:

Students’ enhanced experience through simulation is a crucial factor that brings reality to the classroom. The enhanced experience is all about developing, enriching and applications of a generic process flow in the field of logistics and transportations. As educational technology has improved, the effective use of simulations has greatly increased to the point where simulations should be considered a valuable, mainstream pedagogical tool. Additionally, in this era of ongoing (some say never-ending) assessment, simulations offer a rich resource for objective measurement and comparisons. Simulation is not just another in the long line of passing fads (or short-term opportunities) in educational technology. It is rather a real key to helping our students understand the world. It is a way for students to acquire experience about how things and systems in the world behave and react, without actually touching them. In short, it is about interactive pretending. Simulation is all about representing the real world which includes grasping the complex issues and solving intricate problems. Therefore, it is crucial before stimulate the real process of inbound and outbound logistics and transportation a generic process flow shall be developed. The paper will be focusing on the validization of the process flow by looking at the inputs gains from the sample. The sampling of the study focuses on multi-national and local manufacturing companies, third party companies (3PL) and government agency, which are selected in Peninsular Malaysia. A simulation flow chart was proposed in the study that will be the generic flow in logistics and transportation. A qualitative approach was mainly conducted to gather data in the study. It was found out from the study that the systems used in the process of outbound and inbound are System Application Products (SAP) and Material Requirement Planning (MRP). Furthermore there were some companies using Enterprises Resources Planning (ERP) and Electronic Data Interchange (EDI) as part of the Suppliers Own Inventories (SOI) networking as a result of globalized business between one countries to another. Computerized documentations and transactions were all mandatory requirement by the Royal Custom and Excise Department. The generic process flow will be the basis of developing a simulation program that shall be used in the classroom with the objective of further enhanced the students’ learning experience. Thus it will contributes to the body of knowledge on the enrichment of the student’s employability and also shall be one of the way to train new workers in the logistics and transportation filed.

Keywords: enhancement, simulation, process flow, logistics, transportation

Procedia PDF Downloads 329

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 73

Authors: Federico Garrido, Mostafa El Hayani, Ahmed Shams

Abstract:

The exploration of the potential of artificial intelligence (AI) in architecture is still embryonic, however, its latent capacity to change design disciplines is significant. 'Synthetic Classism' is a research project that questions the underlying aspects of classically organized architecture not just in aesthetic terms but also from a geometrical and morphological point of view, intending to generate new architectural information using historical examples as source material. The main aim of this paper is to explore the uses of artificial intelligence and machine learning algorithms in architectural design while creating a coherent narrative to be contained within a design process. The purpose is twofold: on one hand, to develop and train machine learning algorithms to produce architectural information of small pavilions and on the other, to synthesize new information from previous architectural drawings. These algorithms intend to 'interpret' graphical information from each pavilion and then generate new information from it. The procedure, once these algorithms are trained, is the following: parting from a line profile, a synthetic 'front view' of a pavilion is generated, then using it as a source material, an isometric view is created from it, and finally, a top view is produced. Thanks to GAN algorithms, it is also possible to generate Front and Isometric views without any graphical input as well. The final intention of the research is to produce isometric views out of historical information, such as the pavilions from Sebastiano Serlio, James Gibbs, or John Soane. The idea is to create and interpret new information not just in terms of historical reconstruction but also to explore AI as a novel tool in the narrative of a creative design process. This research also challenges the idea of the role of algorithmic design associated with efficiency or fitness while embracing the possibility of a creative collaboration between artificial intelligence and a human designer. Hence the double feature of this research, both analytical and creative, first by synthesizing images based on a given dataset and then by generating new architectural information from historical references. We find that the possibility of creatively understand and manipulate historic (and synthetic) information will be a key feature in future innovative design processes. Finally, the main question that we propose is whether an AI could be used not just to create an original and innovative group of simple buildings but also to explore the possibility of fostering a novel architectural sensibility grounded on the specificities on the architectural dataset, either historic, human-made or synthetic.

Keywords: architecture, central pavilions, classicism, machine learning

Procedia PDF Downloads 140

Authors: Sylvie Sossou, Grégoire Gansou, Ildevert Egue

Abstract:

Introduction: The mission of the family and the school is to educate and train citizens of the city. But the family’s values , parental roles, respect for life collapse in their traditional African form. Indeed laxity with regard to divorce, liberal ideas about child rearing influence the emotional life of the latter. Several causes may contribute to the decline in academic performance. In order to seek a psychological solution to the issue, a study was conducted in 6 schools at the 9th district in Cotonou, cosmopolitan city of Benin. Objective: To evaluate the impact of single parenthood on the psycho child development. Materials and Methods: Questionnaires and interviews were used to gather verbal information. The questionnaires were administered to parents and children (schoolchildren 4, 5 and six form) from 7 to 12 years in lone parenthood. The interview was done with teachers and school leaders. We identified 209 cases of children living with a "single-parent" and 68 single parents. Results: Of the 209 children surveyed the results showed that 116 children are cut relational triangle in early childhood (before 3 years). The psychological effects showed that the separation has caused sadness for 52 children, anger 22, shame 17, crying at 31 children, fear for 14, the silence at 58 children. In front of complete family’s children, these children experience feelings of aggression in 11.48%; sadness in 30.64%; 5.26% the shame, the 6.69% tears; jealousy in 2.39% and 2.87% of indifference. The option to get married in 44.15% of children is a challenge to want to give a happy childhood for their offspring; 22.01% feel rejected, there is uncertainty for 11.48% of cases and 25.36% didn’t give answer. 49, 76% of children want to see their family together; 7.65% are against to avoid disputes and in many cases to save the mother of the father's physical abuse. 27.75% of the ex-partners decline responsibility in the care of the child. Furthermore family difficulties affecting the intellectual capacities of children: 37.32% of children see school difficulties related to family problems despite all the pressure single-parent to see his child succeed. Single parenthood affects inter-family relations: pressure 33.97%; nervousness 24.88%; overprotection 29.18%; backbiting 11.96%, are the lives of these families. Conclusion: At the end of the investigation, results showed that there is a causal relationship between psychological disorders, academic difficulties of children and quality of parental relationships. Other cases may exist, but the lack of resources meant that we have only limited at 6 schools. Early psychological treatment for these children is needed.

Keywords: single-parent, psycho child, school, Cotonou

Procedia PDF Downloads 389

Authors: G. Natuhwera, M. Rabwoni, P. Ellis, A. Merriman

Abstract:

Aims: Health workers are likely to document patients’ care inaccurately, especially when using new and revised case tools, and this could negatively impact patient care. This study set out to; (1) assess nurses’ and clinicians’ documentation practices when using a new patients’ continuation case sheet (PCCS) and (2) explore nurses’ and clinicians’ experiences regarding documentation of patients’ information in the new PCCS. The purpose of introducing the PCCS was to improve continuity of care for patients attending clinics at which they were unlikely to see the same clinician or nurse consistently. Methods: This was a mixed methods study. The cross-sectional inquiry retrospectively reviewed 100 case notes of active patients on hospice and palliative care program. Data was collected using a structured questionnaire with constructs formulated from the new PCCS under study. The qualitative element was face-to-face audio-recorded, open-ended interviews with a purposive sample of one palliative care clinician, and four palliative care nurse specialists. Thematic analysis was used. Results: Missing patients’ biogeographic information was prevalent at 5-10%. Spiritual and psychosocial issues were not documented in 42.6%, and vital signs in 49.2%. Poorest documentation practices were observed in past medical history part of the PCCS at 40-63%. Four themes emerged from interviews with clinicians and nurses-; (1) what remains unclear and challenges, (2) comparing the past with the present, (3) experiential thoughts, and (4) transition and adapting to change. Conclusions: The PCCS seems to be a comprehensive and simple tool to be used to document patients’ information at subsequent visits. The comprehensiveness and utility of the PCCS does paper to be limited by the failure to train staff in its use prior to introducing. The authors find the PCCS comprehensive and suitable to capture patients’ information and recommend it can be adopted and used in other palliative and hospice care settings, if suitable introductory training accompanies its introduction. Otherwise, the reliability and validity of patients’ information collected by this PCCS can be significantly reduced if some sections therein are unclear to the clinicians/nurses. The study identified clinicians- and nurses-related pitfalls in documentation of patients’ care. Clinicians and nurses need to prioritize accurate and complete documentation of patient care in the PCCS for quality care provision. This study should be extended to other sites using similar tools to ensure representative and generalizable findings.

Keywords: documentation, information case sheet, palliative care, quality improvement

Procedia PDF Downloads 150

Authors: Friman Hen, Banner Ifaa, Shalom-Tuchin Bosmat, Einav Yulia

Abstract:

The action learning course is an academic course which involves academic learning and social activities. The courses deal with processes and social challenges, reveal different ideologies, and develop critical thinking and pragmatic ideas. Students receive course credits and a grade for being part of such courses. Participating students enroll in courses that involve action and activities to engage in the experiential learning process, thereby creating a dialogue and cross-fertilization between being taught in the classroom and experiencing the reality in the real world. A learning experience includes meeting with social organizations, institutions, and state authorities and carrying out practical work with diverse populations. Through experience, students strengthen their academic skills, formulate ethical attitudes toward reality, develop professional and civilian perspectives, and realize how they can influence their surrounding in the present and the hereafter. Under the guidance and supervision of Dr. Hen Friman, H.I.T. has built an innovative course that combines action and activities to increase the awareness and accessibility of the community in an experiential way. The end goal is to create Green Ambassadors—children with a high level of environmental awareness. This course is divided into two parts. The first part, focused on frontal teaching, delivers knowledge from extensive environmental fields to students. These areas include introduction to ecology, the process of electricity generation, air pollution, renewable energy, water economy, waste and recycling, and energy efficiency (first stage). In addition to the professional content in the environment field, students learn the method of effective and experiential teaching to younger learners (4 to 8 years old). With the attainment of knowledge, students are divided into operating groups. The second part of the course shows how the theory becomes practical and concrete. At this stage, students are asked to introduce to the first- and second-graders of ‘Revivim’ School in Holon a lesson of 90 minutes focused on presenting the issues and their importance during the course (second stage). This course is the beginning of a paradigm shift regarding energy usage in the modern society in Israel. The objective of the course is to expand worldwide and train the first and second-graders, and even pre-schoolers, in a wide scope to increase population awareness rate, both in Israel and all over the world, for a green future.

Keywords: air pollution, green ambassador, recycling, renewable energy

Procedia PDF Downloads 242

Authors: Tingwei Shu, Dong Zhou, Chengjun Guo

Abstract:

Semantic communication is an emerging form of communication that realize intelligent communication by extracting semantic information of data at the source and transmitting it, and recovering the data at the receiving end. It can effectively solve the problem of data transmission under the situation of large data volume, low SNR and restricted bandwidth. With the development of Deep Learning, semantic communication further matures and is gradually applied in the fields of the Internet of Things, Uumanned Air Vehicle cluster communication, remote sensing scenarios, etc. We propose an improved semantic communication system for the situation where the data volume is huge and the spectrum resources are limited during the transmission of remote sensing images. At the transmitting, we need to extract the semantic information of remote sensing images, but there are some problems. The traditional semantic communication system based on Convolutional Neural Network cannot take into account the global semantic information and local semantic information of the image, which results in less-than-ideal image recovery at the receiving end. Therefore, we adopt the improved vision-Transformer-based structure as the semantic encoder instead of the mainstream one using CNN to extract the image semantic features. In this paper, we first perform pre-processing operations on remote sensing images to improve the resolution of the images in order to obtain images with more semantic information. We use wavelet transform to decompose the image into high-frequency and low-frequency components, perform bilinear interpolation on the high-frequency components and bicubic interpolation on the low-frequency components, and finally perform wavelet inverse transform to obtain the preprocessed image. We adopt the improved Vision-Transformer structure as the semantic coder to extract and transmit the semantic information of remote sensing images. The Vision-Transformer structure can better train the huge data volume and extract better image semantic features, and adopt the multi-layer self-attention mechanism to better capture the correlation between semantic features and reduce redundant features. Secondly, to improve the coding efficiency, we reduce the quadratic complexity of the self-attentive mechanism itself to linear so as to improve the image data processing speed of the model. We conducted experimental simulations on the RSOD dataset and compared the designed system with a semantic communication system based on CNN and image coding methods such as BGP and JPEG to verify that the method can effectively alleviate the problem of excessive data volume and improve the performance of image data communication.

Keywords: semantic communication, transformer, wavelet transform, data processing

Procedia PDF Downloads 78

Authors: S. H. J. Liu

Abstract:

This paper aims to explore the role of peer Corrective Feedback (CF) in improving written productions by English-as-a- foreign-language (EFL) learners who work together via Wikispaces. It attempted to determine the effect of peer CF on form accuracy in English, such as grammar and lexis. Thirty-four EFL learners at the tertiary level were randomly assigned into the experimental (with peer feedback) or the control (without peer feedback) group; each group was subdivided into small groups of two or three. This resulted in six and seven small groups in the experimental and control groups, respectively. In the experimental group, each learner played a role as an assessor (providing feedback to others), as well as an assessee (receiving feedback from others). Each participant was asked to compose his/her written work and revise it based on the feedback. In the control group, on the other hand, learners neither provided nor received feedback but composed and revised their written work on their own. Data collected from learners’ compositions and post-task interviews were analyzed and reported in this study. Following the completeness of three writing tasks, 10 participants were selected and interviewed individually regarding their perception of collaborative learning in the Computer-Mediated Communication (CMC) environment. Language aspects to be analyzed included lexis (e.g., appropriate use of words), verb tenses (e.g., present and past simple), prepositions (e.g., in, on, and between), nouns, and articles (e.g., a/an). Feedback types consisted of CF, affective, suggestive, and didactic. Frequencies of feedback types and the accuracy of the language aspects were calculated. The results first suggested that accurate items were found more in the experimental group than in the control group. Such results entail that those who worked collaboratively outperformed those who worked non-collaboratively on the accuracy of linguistic aspects. Furthermore, the first type of CF (e.g., corrections directly related to linguistic errors) was found to be the most frequently employed type, whereas affective and didactic were the least used by the experimental group. The results further indicated that most participants perceived that peer CF was helpful in improving the language accuracy, and they demonstrated a favorable attitude toward working with others in the CMC environment. Moreover, some participants stated that when they provided feedback to their peers, they tended to pay attention to linguistic errors in their peers’ work but overlook their own errors (e.g., past simple tense) when writing. Finally, L2 or FL teachers or practitioners are encouraged to employ CMC technologies to train their students to give each other feedback in writing to improve the accuracy of the language and to motivate them to attend to the language system.

Keywords: peer corrective feedback, computer-mediated communication (CMC), second or foreign language (L2 or FL) learning, Wikispaces

Procedia PDF Downloads 245

Authors: Mallikarjun Vaddenkeri, Suresh Jange

Abstract:

This research study reports results of information behaviour by members of faculty and research scholars of various departments of social sciences working at universities with a sample of 300 and Members of Legislative Assembly and Council with 216 samples in Karnataka State, India. The results reveal that 29.3% and 20.3% of Social Scientists indicated medium and high level of awareness of primary sources - Primary Journals are found to be at scale level 5 and 9. The usage of primary journals by social scientists is found to be 28% at level 4, 24% of the respondent’s opined use of primary Conference Proceedings at level 5 as medium level of use. Similarly, the use of Secondary Information Sources at scale 8 and 9 particularly in case of Dictionaries (31.0% and 5.0%), Encyclopaedias (22.3% and 6.3%), Indexing Periodicals (7.0% and 15.3%) and Abstracting Periodicals (5.7% and 20.7%). For searching information from Journals Literature available in CD-ROM version, Keywords (43.7%) followed by Keywords with logical operators (39.7%) have been used for finding the required information. Statistical inference reveals rejection of null hypothesis `there is no association between designation of the respondents and awareness of primary information resources’. On the other hand, educational qualification possessed by Legislative members, more than half of them possess graduate degree as their academic qualification (57.4%) and just 16.7% of the respondents possess graduate degree while only 26.8% of the respondents possess degree in law and just 1.8% possess post-graduate degree in law. About 42.6% indicated the importance of information required to discharge their duties and responsibilities as a Policy Maker in the scale 8, as a Scholar (27.8%) on a scale 6, as a politician (64.8%) on a scale 10 and as a Councillor (51.9%) on a scale 8. The most preferred information agencies/sources very often contacted for obtaining useful information are by means of contacting the people of Karnataka State Legislative Library, listening Radio programmes, viewing Television programmes and reading the newspapers. The methods adopted for obtaining needed information quite often by means of sending their assistants to libraries to gather information (35.2%) and personally visiting the information source (64.8%). The null hypotheses `There is no association between Members of Legislature and Opinion on the usefulness of the resources of the Karnataka State Legislature Library’ is accepted using F ANOVA test. The studies conclude with a note revamp the existing library system in its structure and adopt latest technologies and educate and train social scientists and Legislators in using these resources in the interest of academic, government policies and decision making of the country.

Keywords: information use behaviour, government information, searching behaviour, policy makers

Procedia PDF Downloads 139

Authors: Huayuan Lu, Chunfang Yang, Ma Zhu, Baojun Qi, Yaqiong Qiao, Jiangqian Xu

Abstract:

Image geolocalization has great application prospects in fields such as autonomous driving and virtual/augmented reality. In practical application scenarios, the size of the image to be located is not fixed; it is impractical to train different networks for all possible sizes. When its size does not match the size of the input of the descriptor extraction model, existing image geolocalization methods usually directly scale or crop the image in some common ways. This will result in the loss of some information important to the geolocalization task, thus affecting the performance of the image geolocalization method. For example, excessive down-sampling can lead to blurred building contour, and inappropriate cropping can lead to the loss of key semantic elements, resulting in incorrect geolocation results. To address this problem, this paper designs a learnable image resizer and proposes an arbitrary-sized image geolocation method. (1) The designed learnable image resizer employs the self-attention mechanism to enhance the geometric features of the resized image. Firstly, it applies bilinear interpolation to the input image and its feature maps to obtain the initial resized image and the resized feature maps. Then, SKNet (selective kernel net) is used to approximate the best receptive field, thus keeping the geometric shapes as the original image. And SENet (squeeze and extraction net) is used to automatically select the feature maps with strong contour information, enhancing the geometric features. Finally, the enhanced geometric features are fused with the initial resized image, to obtain the final resized images. (2) The proposed image geolocalization method embeds the above image resizer as a fronting layer of the descriptor extraction network. It not only enables the network to be compatible with arbitrary-sized input images but also enhances the geometric features that are crucial to the image geolocalization task. Moreover, the triplet attention mechanism is added after the first convolutional layer of the backbone network to optimize the utilization of geometric elements extracted by the first convolutional layer. Finally, the local features extracted by the backbone network are aggregated to form image descriptors for image geolocalization. The proposed method was evaluated on several mainstream datasets, such as Pittsburgh30K, Tokyo24/7, and Places365. The results show that the proposed method has excellent size compatibility and compares favorably to recently mainstream geolocalization methods.

Keywords: image geolocalization, self-attention mechanism, image resizer, geometric feature

Procedia PDF Downloads 214

Authors: Pamela K. Coke, Heidi Frederiksen, Ann Sebald

Abstract:

Over the past three years, the researchers have been tracking a rise in the number of teacher education candidates leaving the field before completing their university’s educator preparation program. At their institution, this rise is most pronounced in English Education. The purpose of this qualitative research study is to understand English Education teacher candidates' expectations in becoming prepared educators at each phase of their four phase teacher education program at one institution of higher education in the United States. Research questions include: To what extent do we find differences in teacher candidates' expectations of their teacher training program and student teaching experiences based upon undergraduate and graduate programs? Why do (or do not) teacher candidates persist in their teacher training program and student teaching experiences? How do dispositions develop through the course of the teacher training program? What supports do teacher candidates self-identify as needing at each phase of the teacher training program? Based upon participant interviews at each phase of the teacher education program, the researchers, all teacher educators, examine the extent to which English Education students feel prepared to student teach, focusing on preparation, persistence, and dispositions. The Colorado State University Center for Educator Preparation (CEP) provides students with information about teaching dispositions, or desired professional behaviors, throughout their education program. CEP focuses these dispositions around nine categories: Professional Behaviors, Initiative and Dependability, Tact and Judgment, Ethical Behavior and Integrity, Collegiality and Responsiveness, Effective Communicator, Desire to Improve Own Performance, Culturally Responsive, and Commitment to the Profession. Currently, in the first phase of a four phase study, initial results indicate participants expect their greatest joys will be working with and learning from students. They anticipate their greatest challenges will involve discipline and confidence. They predict they will persist in their program because they believe the country needs well-prepared teachers and they have a commitment to their professional growth. None of the participants thus far could imagine why they would leave the program. With regard to strongest and weakest dispositions, results are mixed. Some participants see Tact and Judgment as their strongest disposition; others see it as their weakest. All participants stated mentoring is a necessary support at every phase of the teacher preparation process. This study informs the way teacher educators train and evaluate teacher candidates, and has implications for the frequency and types of feedback students receive from mentors and supervisors. This research contributes to existing work on teacher retention, candidate persistence, and dispositional development.

Keywords: English education, dispositions, persistence, teacher preparation

Procedia PDF Downloads 322

Authors: Foong Kiew Ooi, Aidi Naim Mohamad Samsani, Chee Keong Chen, Mohamed Saat Ismail

Abstract:

Introduction: Prolonged exercise in a hot and humid environment can result in glycogen depletion and associated with loss of body fluid. Carbohydrate contained in sports beverages is beneficial for improving sports performance and preventing dehydration. Carbohydrate contained in honey is believed can be served as an alternative form of carbohydrate for enhancing sports performance. Objective: To investigate the effectiveness of honey drink compared to sports drink as a recovery aid for running performance and physiological parameters in the heat. Method: Ten male recreational athletes (age: 22.2 ± 2.0 years, VO2max: 51.5 ± 3.7 ml.kg-1.min-1) participated in this randomized cross-over study. On each trial, participants were required to run for 1 hour in the glycogen depletion phase (Run-1), followed by a rehydration phase for 2 hours and subsequently a 20 minutes time trial performance (Run-2). During Run-1, subjects were required to run on the treadmill in the heat (31°C) with 70% relative humidity at 70 % of their VO2max. During rehydration phase, participants drank either honey drink or sports drink, or plain water with amount equivalent to 150% of body weight loss in dispersed interval (60 %, 50 % and 40 %) at 0 min, 30 min and 60 min respectively. Subsequently, time trial was performed by the participants in 20 minutes and the longest distance covered was recorded. Physiological parameters were analysed using two-way ANOVA with repeated measure and time trial performance was analysed using one-way ANOVA. Results: Result showed that Acacia honey elicited a better time trial performance with significantly longer distance compared to water trial (P<0.05). However, there was no significant difference between Acacia honey and sport drink trials (P > 0.05). Acacia honey and sports drink trials elicited 249 m (8.24 %) and 211 m (6.79 %) longer in distance compared to the water trial respectively. For physiological parameters, plasma glucose, plasma insulin and plasma free fatty acids in Acacia honey and sports drink trials were significantly higher compared to the water trial respectively during rehydration phase and time trial running performance phase. There were no significant differences in body weight changes, oxygen uptake, hematocrit, plasma volume changes and plasma cortisol in all the trials. Conclusion: Acacia honey elicited greatest beneficial effects on sports performance among the drinks, thus it has potential to be used for rehydration in athletes who train and compete in hot environment.

Keywords: honey drink, rehydration, sports performance, plasma glucose, plasma insulin, plasma cortisol

Procedia PDF Downloads 309

Authors: Antti Lanki, Justiina Halonen, Juuso Punnonen, Emmi Rantavuo

Abstract:

Marine oil spill response operation requires extensive vessel maneuvering and navigation skills. At-sea oil containment and recovery include both single vessel and multi-vessel operations. Towing long oil containment booms that are several hundreds of meters in length, is a challenge in itself. Boom deployment and towing in multi-vessel configurations is an added challenge that requires precise coordination and control of the vessels. Efficient communication, as a prerequisite for shared situational awareness, is needed in order to execute the response task effectively. To gain and maintain adequate maritime skills, practical training is needed. Field exercises are the most effective way of learning, but especially the related vessel operations are resource-intensive and costly. Field exercises may also be affected by environmental limitations such as high sea-state or other adverse weather conditions. In Finland, the seasonal ice-coverage also limits the training period to summer seasons only. In addition, environmental sensitiveness of the sea area restricts the use of real oil or other target substances. This paper examines, whether maritime simulator training can offer a complementary method to overcome the training challenges related to field exercises. The objective is to assess the efficiency and the learning impact of simulator training, and the specific skills that can be trained most effectively in simulators. This paper provides an overview of learning results from two oil spill response pilot courses, in which maritime navigational bridge simulators were used to train the oil spill response authorities. The simulators were equipped with an oil spill functionality module. The courses were targeted at coastal Fire and Rescue Services responsible for near shore oil spill response in Finland. The competence levels of the participants were surveyed before and after the course in order to measure potential shifts in competencies due to the simulator training. In addition to the quantitative analysis, the efficiency of the simulator training is evaluated qualitatively through feedback from the participants. The results indicate that simulator training is a valid and effective method for developing marine oil spill response competencies that complement traditional field exercises. Simulator training provides a safe environment for assessing various oil containment and recovery tactics. One of the main benefits of the simulator training was found to be the immediate feedback the spill modelling software provides on the oil spill behaviour as a reaction to response measures.

Keywords: maritime training, oil spill response, simulation, vessel manoeuvring

Procedia PDF Downloads 172

Authors: Laura Micheli, Majd Hijazi, Mahmoud Faytarouni

Abstract:

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

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

Procedia PDF Downloads 143

Authors: Sarah E. Nelson, Casey Weiner, Alexander Sigmon, Jun Hua, Haris I. Sair, Jose I. Suarez, Robert D. Stevens

Abstract:

Graph-theoretical information from structural connectomes indicated significant connectivity changes and improved acute prognostication in a Random Forest (RF) model in aneurysmal subarachnoid hemorrhage (aSAH), which can lead to significant morbidity and mortality and has traditionally been fraught by poor methods to predict outcome. This study’s hypothesis was that structural connectivity changes occur in canonical brain networks of acute aSAH patients, and that these changes are associated with functional outcome at six months. In a prospective cohort of patients admitted to a single institution for management of acute aSAH, patients underwent diffusion tensor imaging (DTI) as part of a multimodal MRI scan. A weighted undirected structural connectome was created of each patient’s images using Constant Solid Angle (CSA) tractography, with 176 regions of interest (ROIs) defined by the Johns Hopkins Eve atlas. ROIs were sorted into four networks: Default Mode Network, Executive Control Network, Salience Network, and Whole Brain. The resulting nodes and edges were characterized using graph-theoretic features, including Node Strength (NS), Betweenness Centrality (BC), Network Degree (ND), and Connectedness (C). Clinical (including demographics and World Federation of Neurologic Surgeons scale) and graph features were used separately and in combination to train RF and Logistic Regression classifiers to predict two outcomes: dichotomized modified Rankin Score (mRS) at discharge and at six months after discharge (favorable outcome mRS 0-2, unfavorable outcome mRS 3-6). A total of 56 aSAH patients underwent DTI a median (IQR) of 7 (IQR=8.5) days after admission. The best performing model (RF) combining clinical and DTI graph features had a mean Area Under the Receiver Operator Characteristic Curve (AUROC) of 0.88 ± 0.00 and Area Under the Precision Recall Curve (AUPRC) of 0.95 ± 0.00 over 500 trials. The combined model performed better than the clinical model alone (AUROC 0.81 ± 0.01, AUPRC 0.91 ± 0.00). The highest-ranked graph features for prediction were NS, BC, and ND. These results indicate reorganization of the connectome early after aSAH. The performance of clinical prognostic models was increased significantly by the inclusion of DTI-derived graph connectivity metrics. This methodology could significantly improve prognostication of aSAH.

Keywords: connectomics, diffusion tensor imaging, graph theory, machine learning, subarachnoid hemorrhage

Procedia PDF Downloads 189

Authors: A. Basu, A. A. Purohit, M. M. Vaidya, M. D. Kudale

Abstract:

Mumbai, being traditionally the epicenter of India's trade and commerce, the existing major ports such as Mumbai and Jawaharlal Nehru Ports (JN) situated in Thane estuary are also developing its waterfront facilities. Various developments over the passage of decades in this region have changed the tidal flux entering/leaving the estuary. The intake at Pir-Pau is facing the problem of shortage of water in view of advancement of shoreline, while jetty near Ulwe faces the problem of ship scheduling due to existence of shallower depths between JN Port and Ulwe Bunder. In order to solve these problems, it is inevitable to have information about tide levels over a long duration by field measurements. However, field measurement is a tedious and costly affair; application of artificial intelligence was used to predict water levels by training the network for the measured tide data for one lunar tidal cycle. The application of two layered feed forward Artificial Neural Network (ANN) with back-propagation training algorithms such as Gradient Descent (GD) and Levenberg-Marquardt (LM) was used to predict the yearly tide levels at waterfront structures namely at Ulwe Bunder and Pir-Pau. The tide data collected at Apollo Bunder, Ulwe, and Vashi for a period of lunar tidal cycle (2013) was used to train, validate and test the neural networks. These trained networks having high co-relation coefficients (R= 0.998) were used to predict the tide at Ulwe, and Vashi for its verification with the measured tide for the year 2000 & 2013. The results indicate that the predicted tide levels by ANN give reasonably accurate estimation of tide. Hence, the trained network is used to predict the yearly tide data (2015) for Ulwe. Subsequently, the yearly tide data (2015) at Pir-Pau was predicted by using the neural network which was trained with the help of measured tide data (2000) of Apollo and Pir-Pau. The analysis of measured data and study reveals that: The measured tidal data at Pir-Pau, Vashi and Ulwe indicate that there is maximum amplification of tide by about 10-20 cm with a phase lag of 10-20 minutes with reference to the tide at Apollo Bunder (Mumbai). LM training algorithm is faster than GD and with increase in number of neurons in hidden layer and the performance of the network increases. The predicted tide levels by ANN at Pir-Pau and Ulwe provides valuable information about the occurrence of high and low water levels to plan the operation of pumping at Pir-Pau and improve ship schedule at Ulwe.

Keywords: artificial neural network, back-propagation, tide data, training algorithm

Procedia PDF Downloads 483

Authors: O. V. Jurieva, O. U. Jurieva, R. H. Yagudin, P. B. Chursin

Abstract:

In the recent scientific researches on the problems of public service the idea of the use of innovative technologies of management of personnel processes is accurately formulated. Authors made an attempt to analyze the changes in the public service organizations and to understand how the studied situation is interpreted by the government employees themselves. For this purpose the strategy of sociological research was carried out on the basis of application of questionnaire developed by M. Rokich and focus group research. For the research purposes it was necessary to get to microlevel in order to include daily activities of employees of an organization, their life experience and values in the focus of the analysis. Based on P. Bourdieu's methodology, authors investigated the established patterns of consciousness and behavior of officials (doxa) and also analyzed the tendencies of re-thinking (change) of the settled content of values (heterodoxy) by them. The distinctive feature of the conducted research is that the public servants who have different length of service in the public service took part in the research procedure. The obtained data helped to answer the following question: what are the specifics of doxs of the public servants who work in the public civil service more than 7-10 years and what perception of values of civil service have junior experts whose work experience doesn't exceed 3 years. Respondents were presented by two groups: (1) public servants of the level of main positions in the public civil service of the Republic of Tatarstan. (2) Public servants of the level of lower positions in the ministries and departments of the Republic of Tatarstan. For the study of doxa or of the existing values of public servants, the research with use of the questionnaire based on M. Rokich's system is conducted. Two types of values are emphasised: terminal and instrumental, which are united by us in the collective concept doxa. Doxa: the instrument of research of the established patterns of consciousness and behavior which can either resist to changes in the organization or, on the contrary, support their implementation. In the following stage an attempt to deepen our understanding of the essence and specifics of doxa of officials by means of the applied sociological research which is carried out by focus group method is made. Information obtained by authors during the research convinces that for the success of policy of changes in the organizations of public service it is necessary to develop special technologies of informing employees about the essence and inevitability of the developed innovations, to involve them in the process of changes, to train and to develop the younger generation of civil servants, seriously to perceive additional training and retraining of officials.

Keywords: innovative technologies, public service organizations, public servants

Procedia PDF Downloads 273

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 92

Authors: Olivia A. Wilson, Hannah E. Power, Murray Kendall

Abstract:

Sydney Harbour is an iconic location with a dense population and low-lying development. On the east coast of Australia, facing the Pacific Ocean, it is exposed to several tsunamigenic trenches. This paper presents a component of the most detailed assessment of the potential for earthquake-generated tsunami impact on Sydney Harbour to date. Models in this study use dynamic tides to account for tide-tsunami interaction. Sydney Harbour’s tidal range is 1.5 m, and the spring tides from January 2015 that are used in the modelling for this study are close to the full tidal range. The tsunami wave trains modelled include hypothetical tsunami generated from earthquakes of magnitude 7.5, 8.0, 8.5, and 9.0 M_W from the Puysegur and New Hebrides trenches as well as representations of the historical 1960 Chilean and 2011 Tohoku events. All wave trains are modelled for the peak wave to coincide with both a low tide and a high tide. A single wave train, representing a 9.0 M_W earthquake at the Puysegur trench, is modelled for peak waves to coincide with every hour across a 12-hour tidal phase. Using the hydrodynamic model ANUGA, results are compared according to the impact parameters of inundation area, depth variation and current speeds. Results show that both maximum inundation area and depth variation are tide dependent. Maximum inundation area increases when coincident with a higher tide, however, hazardous inundation is only observed for the larger waves modelled: NH90high and P90high. The maximum and minimum depths are deeper on higher tides and shallower on lower tides. The difference between maximum and minimum depths varies across different tidal phases although the differences are slight. Maximum current speeds are shown to be a significant hazard for Sydney Harbour; however, they do not show consistent patterns according to tide-tsunami phasing. The maximum current speed hazard is shown to be greater in specific locations such as Spit Bridge, a narrow channel with extensive marine infrastructure. The results presented for Sydney Harbour are novel, and the conclusions are consistent with previous modelling efforts in the greater area. It is shown that tide must be a consideration for both tsunami modelling and emergency management planning. Modelling with peak tsunami waves coinciding with a high tide would be a conservative approach; however, it must be considered that maximum current speeds may be higher on other tides.

Keywords: emergency management, sydney, tide-tsunami interaction, tsunami impact

Procedia PDF Downloads 240

Authors: Leonard Tiong, Sonit Singh, Kevin Ho Shon, Sarah Lewis

Abstract:

Investigation into the use of artificial intelligence in radiology continues to develop at a rapid rate. During the coronavirus pandemic, the combination of an exponential increase in chest x-rays and unpredictable staff shortages resulted in a huge strain on the department's workload. There is a World Health Organisation estimate that two-thirds of the global population does not have access to diagnostic radiology. Therefore, there could be demand for a program that could detect acute changes in imaging compatible with infection to assist with screening. We generated a conventional neural network and tested its efficacy in recognizing changes compatible with coronavirus infection. Following ethics approval, a deidentified set of 77 normal and 77 abnormal chest x-rays in patients with confirmed coronavirus infection were used to generate an algorithm that could train, validate and then test itself. DICOM and PNG image formats were selected due to their lossless file format. The model was trained with 100 images (50 positive, 50 negative), validated against 28 samples (14 positive, 14 negative), and tested against 26 samples (13 positive, 13 negative). The initial training of the model involved training a conventional neural network in what constituted a normal study and changes on the x-rays compatible with coronavirus infection. The weightings were then modified, and the model was executed again. The training samples were in batch sizes of 8 and underwent 25 epochs of training. The results trended towards an 85.71% true positive/true negative detection rate and an area under the curve trending towards 0.95, indicating approximately 95% accuracy in detecting changes on chest X-rays compatible with coronavirus infection. Study limitations include access to only a small dataset and no specificity in the diagnosis. Following a discussion with our programmer, there are areas where modifications in the weighting of the algorithm can be made in order to improve the detection rates. Given the high detection rate of the program, and the potential ease of implementation, this would be effective in assisting staff that is not trained in radiology in detecting otherwise subtle changes that might not be appreciated on imaging. Limitations include the lack of a differential diagnosis and application of the appropriate clinical history, although this may be less of a problem in day-to-day clinical practice. It is nonetheless our belief that implementing this program and widening its scope to detecting multiple pathologies such as lung masses will greatly assist both the radiology department and our colleagues in increasing workflow and detection rate.

Keywords: artificial intelligence, COVID, neural network, machine learning

Procedia PDF Downloads 93

Authors: Kabuga Daniel

Abstract:

Road accidents resulting to deaths and injuries have become a new public health challenge especially in developing countries including Tanzania. Reports from Tanzania Traffic Police Force shows that last year 2016 accidents increased compare to previous year 2015, accident happened from 3710 up to 5219, accidents and safety data indicate that children are the most vulnerable to road crashes where 78 pupils died and 182 others were seriously injured in separate roads accident last year. A survey done by Amend indicates that Pupil mode of transport in Dar es salaam schools are by walk 87%, bus 9.21%, car 1.32%, motorcycle 0.88%, 3-wheeler 0.24%, train 0.14%, bicycle 0.10%, ferry 0.07%, and combined mode 0.44%. According to this study, majority of school children’s uses walking mode, most of school children’s agreed to continue using walking mode and request to have signs for traffic control during crossing road like STOP sign and CHILD CROSSING sign for safe crossing. Because children not only sit inside this buses (Daladala) but also they walk in a group to/from school, and few (33.2%) parents or adults are willing to supervise their children’s during working to school while 50% of parents agree to let their children walking alone to school if the public transport started from nearby street. The study used both qualitative and quantitative methods of research by conducting physical surveying on sample districts. The main objectives of this research are to carries out all factors affecting school children’s when they use public road, to promote and encourage the safe use of public road by all classes especially pupil or student through the circulation of advice, information and knowledge gain from research and to recommends future direction for the developments for road design or plan to vulnerable users. The research also critically analyze the problems causing death and injuries to school children’s in Dar es Salaam Region. This study determines the relationship between road traffic accidents and factors, such as socio-economic, status, and distance from school, number of sibling, behavioral problems, knowledge and attitudes of public and their parents towards road safety and parent educational study traffic. The study comes up with some of recommendations including Infrastructure Improvements like, safe footpaths, Safe crossings, Speed humps, Speed limits, Road signs. However, Planners and policymakers wishing to increase walking and cycling among children need to consider options that address distance constraints, the land use planners and transport professionals use better understanding of the various factors that affect children’s choices of school travel mode, results suggest that all school travel attributes should be considered during school location.

Keywords: accidents, childrens, school, Tanzania

Procedia PDF Downloads 243

Authors: Jared Beard, Ali Baheri

Abstract:

As autonomous systems become more prominent in society, ensuring their safe application becomes increasingly important. This is clearly demonstrated with autonomous cars traveling through a crowded city or robots traversing a warehouse with heavy equipment. Human environments can be complex, having high dimensional state and action spaces. This gives rise to two problems. One being that analytic solutions may not be possible. The other is that in simulation based approaches, searching the entirety of the problem space could be computationally intractable, ruling out formal methods. To overcome this, approximate solutions may seek to find failures or estimate their likelihood of occurrence. One such approach is adaptive stress testing (AST) which uses reinforcement learning to induce failures in the system. The premise of which is that a learned model can be used to help find new failure scenarios, making better use of simulations. In spite of these failures AST fails to find particularly sparse failures and can be inclined to find similar solutions to those found previously. To help overcome this, multi-fidelity learning can be used to alleviate this overuse of information. That is, information in lower fidelity can simulations can be used to build up samples less expensively, and more effectively cover the solution space to find a broader set of failures. Recent work in multi-fidelity learning has passed information bidirectionally using “knows what it knows” (KWIK) reinforcement learners to minimize the number of samples in high fidelity simulators (thereby reducing computation time and load). The contribution of this work, then, is development of the bidirectional multi-fidelity AST framework. Such an algorithm, uses multi-fidelity KWIK learners in an adversarial context to find failure modes. Thus far, a KWIK learner has been used to train an adversary in a grid world to prevent an agent from reaching its goal; thus demonstrating the utility of KWIK learners in an AST framework. The next step is implementation of the bidirectional multi-fidelity AST framework described. Testing will be conducted in a grid world containing an agent attempting to reach a goal position and adversary tasked with intercepting the agent as demonstrated previously. Fidelities will be modified by adjusting the size of a time-step, with higher-fidelity effectively allowing for more responsive closed loop feedback. Results will compare the single KWIK AST learner with the multi-fidelity algorithm with respect to number of samples, distinct failure modes found, and relative effect of learning after a number of trials.

Keywords: multi-fidelity reinforcement learning, multi-fidelity simulation, safety validation, falsification

Procedia PDF Downloads 157

Authors: Dewan Ahsan

Abstract:

Denmark is well ahead in generating electricity from renewable sources. The offshore wind sector is playing the pivotal role to achieve this target. Though there is a rapid growth of offshore wind sector in Denmark, still there is a dearth of synchronization in OHS (occupational health and safety) regulation and standards. Therefore, this paper attempts to ascertain: i) what are the major challenges of the company specific OHS standards? ii) why does the offshore wind industry need a standardized OHS management system? and iii) who can play the key role in this process? To achieve these objectives, this research applies the interview and survey techniques. This study has identified several key challenges in OHS management system which are; gaps in coordination and communication among the stakeholders, gaps in incident reporting systems, absence of a harmonized OHS standard and blame culture. Furthermore, this research has identified eleven key stakeholders who are actively involve with the offshore wind business in Denmark. As noticed, the relationships among these stakeholders are very complex specially between operators and sub-contractors. The respondent technicians are concerned with the compliance of various third-party OHS standards (e.g. ISO 31000, ISO 29400, Good practice guidelines by G+) which are applying by various offshore companies. On top of these standards, operators also impose their own OHS standards. From the technicians point of angle, many of these standards are not even specific for the offshore wind sector. So, it is a big challenge for the technicians and sub-contractors to comply with different company specific standards which also elevate the price of their services offer to the operators. For instance, when a sub-contractor is competing for a bidding, it must fulfill a number of OHS requirements (which demands many extra documantions) set by the individual operator and/the turbine supplier. According to sub-contractors’ point of view these extra works consume too much time to prepare the bidding documents and they also need to train their employees to pass the specific OHS certification courses to accomplish the demand for individual clients and individual project. The sub-contractors argued that in many cases these extra documentations and OHS certificates are inessential to ensure the quality service. So, a standardized OHS management procedure (which could be applicable for all the clients) can easily solve this problem. In conclusion, this study highlights that i) development of a harmonized OHS standard applicable for all the operators and turbine suppliers, ii) encouragement of technicians’ active participation in the OHS management, iii) development of a good safety leadership, and, iv) sharing of experiences among the stakeholders (specially operators-operators-sub contractors) are the most vital strategies to overcome the existing challenges and to achieve the goal of 'zero accident/harm' in the offshore wind industry.

Keywords: green energy, offshore, safety, Denmark

Procedia PDF Downloads 214

Authors: Szymon Rutkowski, Tomasz Korbak

Abstract:

We present a reinforcement-learning-based method of training neural machine translation models without parallel corpora. The standard encoder-decoder approach to machine translation suffers from two problems we aim to address. First, it needs parallel corpora, which are scarce, especially for low-resource languages. Second, it lacks psychological plausibility of learning procedure: learning a foreign language is about learning to communicate useful information, not merely learning to transduce from one language’s 'encoding' to another. We instead pose the problem of learning to translate as learning a policy in a communication game between two agents: the translator and the classifier. The classifier is trained beforehand on a natural language inference task (determining the entailment relation between a premise and a hypothesis) in the target language. The translator produces a sequence of actions that correspond to generating translations of both the hypothesis and premise, which are then passed to the classifier. The translator is rewarded for classifier’s performance on determining entailment between sentences translated by the translator to disciple’s native language. Translator’s performance thus reflects its ability to communicate useful information to the classifier. In effect, we train a machine translation model without the need for parallel corpora altogether. While similar reinforcement learning formulations for zero-shot translation were proposed before, there is a number of improvements we introduce. While prior research aimed at grounding the translation task in the physical world by evaluating agents on an image captioning task, we found that using a linguistic task is more sample-efficient. Natural language inference (also known as recognizing textual entailment) captures semantic properties of sentence pairs that are poorly correlated with semantic similarity, thus enforcing basic understanding of the role played by compositionality. It has been shown that models trained recognizing textual entailment produce high-quality general-purpose sentence embeddings transferrable to other tasks. We use stanford natural language inference (SNLI) dataset as well as its analogous datasets for French (XNLI) and Polish (CDSCorpus). Textual entailment corpora can be obtained relatively easily for any language, which makes our approach more extensible to low-resource languages than traditional approaches based on parallel corpora. We evaluated a number of reinforcement learning algorithms (including policy gradients and actor-critic) to solve the problem of translator’s policy optimization and found that our attempts yield some promising improvements over previous approaches to reinforcement-learning based zero-shot machine translation.

Keywords: agent-based language learning, low-resource translation, natural language inference, neural machine translation, reinforcement learning

Procedia PDF Downloads 128

Authors: Malcolm Richardson, Gabriele Richardson

Abstract:

This paper illustrates how historical problems can be studied successfully using GIS even in cases in which data, in the modern sense, is fragmentary. The overall problem under investigation is how early (1300-1500) English schools of Common Law moved from apprenticeship training in random individual London inns run in part by clerks of the royal chancery to become what is widely called 'the Third University of England,' a recognized system of independent but connected legal inns. This paper focuses on the preparatory legal inns, called the Inns of Chancery, rather than the senior (and still existing) Inns of Court. The immediate problem studied in this paper is how the junior legal inns were organized, staffed, and located from 1292 to about 1500, and what maps tell us about the role of the chancery clerks as managers of legal inns. The authors first uncovered the names of all chancery clerks of the period, most of them unrecorded in histories, from archival sources in the National Archives, Kew. Then they matched the names with London property leases. Using ArcGIS, the legal inns and their owners were plotted on a series of maps covering the period 1292 to 1500. The results show a distinct pattern of ownership of the legal inns and suggest a narrative that would help explain why the Inns of Chancery became serious centers of learning during the fifteenth century. In brief, lower-ranking chancery clerks, always looking for sources of income, discovered by 1370 that legal inns could be a source of income. Since chancery clerks were intimately involved with writs and other legal forms, and since the chancery itself had a long-standing training system, these clerks opened their own legal inns to train fledgling lawyers, estate managers, and scriveners. The maps clearly show growth patterns of ownership by the chancery clerks for both legal inns and other London properties in the areas of Holborn and The Strand between 1450 and 1417. However, the maps also show that a royal ordinance of 1417 forbidding chancery clerks to live with lawyers, law students, and other non-chancery personnel had an immediate effect, and properties in that area of London leased by chancery clerks simply stop after 1417. The long-term importance of the patterns shown in the maps is that while the presence of chancery clerks in the legal inns likely created a more coherent education system, their removal forced the legal profession, suddenly without a hostelry managerial class, to professionalize the inns and legal education themselves. Given the number and social status of members of the legal inns, the effect on English education was to free legal education from the limits of chancery clerk education (the clerks were not practicing common lawyers) and to enable it to become broader in theory and practice, in fact, a kind of 'finishing school' for the governing (if not noble) class.

Keywords: GIS, law, London, education

Procedia PDF Downloads 174

Authors: James Rigor Camacho, Wansu Lim

Abstract:

Over the last few years, the development of new wearable and processing technologies has accelerated in order to harness physiological data such as electroencephalograms (EEGs) for EEG-based applications. EEG has been demonstrated to be a source of emotion recognition signals with the highest classification accuracy among physiological signals. However, when emotion recognition systems are used for real-time classification, the training unit is frequently left to run offline or in the cloud rather than working locally on the edge. That strategy has hampered research, and the full potential of using an edge AI device has yet to be realized. Edge AI devices are computers with high performance that can process complex algorithms. It is capable of collecting, processing, and storing data on its own. It can also analyze and apply complicated algorithms like localization, detection, and recognition on a real-time application, making it a powerful embedded device. The NVIDIA Jetson series, specifically the Jetson Nano device, was used in the implementation. The cEEGrid, which is integrated to the open-source brain computer-interface platform (OpenBCI), is used to collect EEG signals. An EEG-based real-time emotion recognition system on Edge AI is proposed in this paper. To perform graphical spectrogram categorization of EEG signals and to predict emotional states based on input data properties, machine learning-based classifiers were used. Until the emotional state was identified, the EEG signals were analyzed using the K-Nearest Neighbor (KNN) technique, which is a supervised learning system. In EEG signal processing, after each EEG signal has been received in real-time and translated from time to frequency domain, the Fast Fourier Transform (FFT) technique is utilized to observe the frequency bands in each EEG signal. To appropriately show the variance of each EEG frequency band, power density, standard deviation, and mean are calculated and employed. The next stage is to identify the features that have been chosen to predict emotion in EEG data using the K-Nearest Neighbors (KNN) technique. Arousal and valence datasets are used to train the parameters defined by the KNN technique.Because classification and recognition of specific classes, as well as emotion prediction, are conducted both online and locally on the edge, the KNN technique increased the performance of the emotion recognition system on the NVIDIA Jetson Nano. Finally, this implementation aims to bridge the research gap on cost-effective and efficient real-time emotion recognition using a resource constrained hardware device, like the NVIDIA Jetson Nano. On the cutting edge of AI, EEG-based emotion identification can be employed in applications that can rapidly expand the research and implementation industry's use.

Keywords: edge AI device, EEG, emotion recognition system, supervised learning algorithm, sensors

Procedia PDF Downloads 105

Authors: Neha Pranav Kolhe, Harithapriya Vijaye, Arushi Kamle

Abstract:

The economic growth engines are urban regions. As the economy expands, so does the need for peace and quiet, and noise pollution is one of the important social and environmental issue. Health and wellbeing are at risk from environmental noise pollution. Because of urbanisation, population growth, and the consequent rise in the usage of increasingly potent, diverse, and highly mobile sources of noise, it is now more severe and pervasive than ever before, and it will only become worse. Additionally, it will expand as long as there is an increase in air, train, and highway traffic, which continue to be the main contributors of noise pollution. The current study will be conducted in two zones of class I city of central India (population range: 1 million–4 million). Total 56 measuring points were chosen to assess noise pollution. The first objective evaluates the noise pollution in various urban habitats determined as formal and informal settlement. It identifies the comparison of noise pollution within the settlements using T- Test analysis. The second objective assess the noise pollution in silent zones (as stated in Central Pollution Control Board) in a hierarchical way. It also assesses the noise pollution in the settlements and compares with prescribed permissible limits using class I sound level equipment. As appropriate indices, equivalent noise level on the (A) frequency weighting network, minimum sound pressure level and maximum sound pressure level were computed. The survey is conducted for a period of 1 week. Arc GIS is used to plot and map the temporal and spatial variability in urban settings. It is discovered that noise levels at most stations, particularly at heavily trafficked crossroads and subway stations, were significantly different and higher than acceptable limits and squares. The study highlights the vulnerable areas that should be considered while city planning. The study demands area level planning while preparing a development plan. It also demands attention to noise pollution from the perspective of residential and silent zones. The city planning in urban areas neglects the noise pollution assessment at city level. This contributes to that, irrespective of noise pollution guidelines, the ground reality is far away from its applicability. The result produces incompatible land use on a neighbourhood scale with respect to noise pollution. The study's final results will be useful to policymakers, architects and administrators in developing countries. This will be useful for noise pollution in urban habitat governance by efficient decision making and policy formulation to increase the profitability of these systems.

Keywords: noise pollution, formal settlements, informal settlements, built environment, silent zone, residential area

Procedia PDF Downloads 118

Authors: M. Maier, I. Dedigama, J. Majasan, Y. Wu, Q. Meyer, L. Castanheira, G. Hinds, P. R. Shearing, D. J. L. Brett

Abstract:

Increasing the efficiency of electrolyser technology is commonly seen as one of the main challenges on the way to the Hydrogen Economy. There is a significant lack of understanding of the different states of operation of polymer electrolyte membrane water electrolysers (PEMWE) and how these influence the overall efficiency. This in particular means the two-phase flow through the membrane, gas diffusion layers (GDL) and flow channels. In order to increase the efficiency of PEMWE and facilitate their spread as commercial hydrogen production technology, new analytic approaches have to be found. Acoustic emission (AE) offers the possibility to analyse the processes within a PEMWE in a non-destructive, fast and cheap in-situ way. This work describes the generation and analysis of AE data coming from a PEM water electrolyser, for, to the best of our knowledge, the first time in literature. Different experiments are carried out. Each experiment is designed so that only specific physical processes occur and AE solely related to one process can be measured. Therefore, a range of experimental conditions is used to induce different flow regimes within flow channels and GDL. The resulting AE data is first separated into different events, which are defined by exceeding the noise threshold. Each acoustic event consists of a number of consequent peaks and ends when the wave diminishes under the noise threshold. For all these acoustic events the following key attributes are extracted: maximum peak amplitude, duration, number of peaks, peaks before the maximum, average intensity of a peak and time till the maximum is reached. Each event is then expressed as a vector containing the normalized values for all criteria. Principal Component Analysis is performed on the resulting data, which orders the criteria by the eigenvalues of their covariance matrix. This can be used as an easy way of determining which criteria convey the most information on the acoustic data. In the following, the data is ordered in the two- or three-dimensional space formed by the most relevant criteria axes. By finding spaces in the two- or three-dimensional space only occupied by acoustic events originating from one of the three experiments it is possible to relate physical processes to certain acoustic patterns. Due to the complex nature of the AE data modern machine learning techniques are needed to recognize these patterns in-situ. Using the AE data produced before allows to train a self-learning algorithm and develop an analytical tool to diagnose different operational states in a PEMWE. Combining this technique with the measurement of polarization curves and electrochemical impedance spectroscopy allows for in-situ optimization and recognition of suboptimal states of operation.

Keywords: acoustic emission, gas diffusion layers, in-situ diagnosis, PEM water electrolyser

Procedia PDF Downloads 155

Authors: Matias Hargreaves, Martin Del Valle, Diego Rodriguez, Riveros Jose Luis

Abstract:

Trough years, all kind of social development projects have tried to solve social problems such as hunger, poverty, malnutrition, food insecurity, among others, with poor success. Both private and state initiatives have invested resources in several countries and communities. Nevertheless, most of these initiatives are scientific or external developers-centered, with a lack of local participation. This compromises the sustainability of any intervention and also leads to a poor empowerment of local community. The participatory approach aims to rescue and enhance the local knowledge since it recognizes that this kind of problems are better known by native actors. The objective of the study was to describe the role played by the community empowerment on food security improvement in the NGO “O Viveiro” (15°43'37.77"S; 32°46'27.53"E) and Barrio Broma village (15°43'58.78"S; 32°46'7.27"E) in Chitima, Mozambique. A center for training in goat livestock and orchard was build. A community orchard was co-constructed between foreign technicians and local actors. The prototype was installed in February, 2016 by the technician team and local community with 16 m2 as a nursery garden. Two orchard workshops were conducted in order to design a sustainable productive model which mixes both local and technological approaches. Two goat meat workshops were conducted in order to describe local methods and train the community to conduce their own techniques with high sanitary and productive standards. Technician team stayed in Mozambique until May, 2016. The quorum for the orchard workshops was 20 and 14 persons respectively, which represents 100% and 70%of the total requested quorum (20). For the goat meat workshops were 4 and 5 persons, which representa80% and 100% of the total requested quorum (5). Until August, 2016, the orchard is 3.219 m2 and it grows several vegetables as beans, chili pepper, garlic, onion, tomatoes, lettuce, sweet potato, yuca potato, cabbage, eggplant, papaya trees, mango, and cassava. The process of increasing in size and diversification of vegetables grown was led entirely by the local community. In connection with this, the local community started to harvest and began to sell the vegetable products at the local market. At the meat goat workshops, local participants rescued a local knowledge by describing and practicing a traditional way to process goat meat by drying it outdoors and then doing a smoked treatment. This information might contribute to describe the level of empowerment of this community, and thus give evidence of acceptance of foreign intervention for improving their own proceedings and traditions.

Keywords: children malnutrition, food security, Local community, participatory approach

Procedia PDF Downloads 275

Authors: Hossein Havaeji, Tony Wong, Thien-My Dao

Abstract:

1. Research Problems and Research Objectives: Blockchain Technology-enabled Supply Chain System (BT-enabled SCS) is the system using BT to drive SCS transparency, security, durability, and process integrity as SCS data is not always visible, available, or trusted. The costs of operating BT in the SCS are a common problem in several organizations. The costs must be estimated as they can impact existing cost control strategies. To account for system and deployment costs, it is necessary to overcome the following hurdle. The problem is that the costs of developing and running a BT in SCS are not yet clear in most cases. Many industries aiming to use BT have special attention to the importance of BT installation cost which has a direct impact on the total costs of SCS. Predicting BT installation cost in SCS may help managers decide whether BT is to be an economic advantage. The purpose of the research is to identify some main BT installation cost components in SCS needed for deeper cost analysis. We then identify and categorize the main groups of cost components in more detail to utilize them in the prediction process. The second objective is to determine the suitable Supervised Learning technique in order to predict the costs of developing and running BT in SCS in a particular case study. The last aim is to investigate how the running BT cost can be involved in the total cost of SCS. 2. Work Performed: Applied successfully in various fields, Supervised Learning is a method to set the data frame, treat the data, and train/practice the method sort. It is a learning model directed to make predictions of an outcome measurement based on a set of unforeseen input data. The following steps must be conducted to search for the objectives of our subject. The first step is to make a literature review to identify the different cost components of BT installation in SCS. Based on the literature review, we should choose some Supervised Learning methods which are suitable for BT installation cost prediction in SCS. According to the literature review, some Supervised Learning algorithms which provide us with a powerful tool to classify BT installation components and predict BT installation cost are the Support Vector Regression (SVR) algorithm, Back Propagation (BP) neural network, and Artificial Neural Network (ANN). Choosing a case study to feed data into the models comes into the third step. Finally, we will propose the best predictive performance to find the minimum BT installation costs in SCS. 3. Expected Results and Conclusion: This study tends to propose a cost prediction of BT installation in SCS with the help of Supervised Learning algorithms. At first attempt, we will select a case study in the field of BT-enabled SCS, and then use some Supervised Learning algorithms to predict BT installation cost in SCS. We continue to find the best predictive performance for developing and running BT in SCS. Finally, the paper will be presented at the conference.

Keywords: blockchain technology, blockchain technology-enabled supply chain system, installation cost, supervised learning

Procedia PDF Downloads 122