Search results for: train

Authors: Olivier Mills, Bernard McDonell, Laura A. S. MacDonald

Abstract:

The increasing availability and quality of internet access throughout the developing world provides an opportunity to utilize online spaces to disseminate water, sanitation and hygiene (WASH) knowledge to practitioners. Since 2001, CAWST has provided in-person education, training and consulting services to thousands of WASH practitioners all over the world, supporting them to start, troubleshoot, improve and expand their WASH projects. As CAWST continues to grow, the organization faces challenges in meeting demand from clients and in providing consistent, timely technical support. In 2012, CAWST began utilizing online spaces to expand its reach by developing a series of resources websites and webinars. CAWST has developed a WASH Education and Training resources website, a Biosand Filter (BSF) Knowledge Base, a Household Water Treatment and Safe Storage Knowledge Base, a mobile app for offline users, a live chat support tool, a WASH e-library, and a series of webinar-style online training sessions to complement its in-person capacity development services. In order to determine the preliminary outcomes of providing these online services, CAWST has monitored and analyzed registration to the online spaces, downloads of the educational materials, and webinar attendance; as well as conducted user surveys. The purpose of this analysis was to find out who was using the online spaces, where users came from, and how the resources were being used. CAWST’s WASH Resources website has served over 5,800 registered users from 3,000 organizations in 183 countries. Additionally, the BSF Knowledge Base has served over 1000 registered users from 68 countries, and over 540 people from 73 countries have attended CAWST’s online training sessions. This indicates that the online spaces are effectively reaching a large numbers of users, from a range of countries. A 2016 survey of the Biosand Filter Knowledge Base showed that approximately 61% of users are practitioners, and 39% are either researchers or students. Of the respondents, 46% reported using the BSF Knowledge Base to initiate a BSF project and 43% reported using the information to train BSF technicians. Finally, 61% indicated they would like even greater support from CAWST’s Technical Advisors going forward. The analysis has provided an encouraging indication that CAWST’s online spaces are contributing to its objective of engaging and supporting WASH practitioners to start, improve and expand their initiatives. CAWST has learned several lessons during the development of these online spaces, in particular related to the resources needed to create and maintain the spaces, and respond to the demand created. CAWST plans to continue expanding its online spaces, improving user experience of the sites, and involving new contributors and content types. Through the use of online spaces, CAWST has been able to increase its global reach and impact without significantly increasing its human resources by connecting WASH practitioners with the information they most need, in a practical and accessible manner. This paper presents on CAWST’s use of online spaces through the CAWST-developed platforms discussed above and the analysis of the use of these platforms.

Keywords: education and training, knowledge sharing, online resources, water and sanitation

Procedia PDF Downloads 240

Authors: C. Fortin, D. Tokmeninova, O. Ushakova

Abstract:

Among 500 Russian universities Skolkovo Institute of Science and Technology (Skoltech) is one of the youngest (established in 2011), quite small and vastly international, comprising 20 percent of international students and 70 percent of faculty with significant academic experience at top-100 universities (QS, THE). The institute has emerged from close collaboration with MIT and leading Russian universities. Skoltech is an entirely English speaking environment. Skoltech curriculum plans of ten Master programs are based on the CDIO learning outcomes model. However, despite the Institute’s unique focus on industrial innovations and startups, one of the main challenges has become an evident large proportion of nearly half of MSc graduates entering PhD programs at Skoltech or other universities rather than industry or entrepreneurship. In order to increase the share of students joining the industrial sector after graduation, Skoltech started implementing a number of unique practices with a focus on employers’ expectations incorporated into the curriculum redesign. In this sense, extended knowledge exchange with industrial partners via collaboration in learning activities, industrial projects and assessments became essential for students’ headway into industrial and entrepreneurship pathways. Current academic curriculum includes the following types of components based on extended knowledge exchange with industrial partners: innovation workshop, industrial immersion, special industrial tracks, MSc defenses. Innovation workshop is a 4 week full time diving into the Skoltech vibrant ecosystem designed to foster innovators, focuses on teamwork, group projects, and sparks entrepreneurial instincts from the very first days of study. From 2019 the number of mentors from industry and startups significantly increased to guide students across these sectors’ demands. Industrial immersion is an exclusive part of Skoltech curriculum where students after the first year of study spend 8 weeks in an industrial company carrying out an individual or team project and are guided jointly by both Skoltech and company supervisors. The aim of the industrial immersion is to familiarize students with relevant needs of Russian industry and to prepare graduates for job placement. During the immersion a company plays the role of a challenge provider for students. Skoltech has started a special industrial track comprising deep collaboration with IPG Photonics – a leading R&D company and manufacturer of high-performance fiber lasers and amplifiers for diverse applications. The track is aimed to train a new cohort of engineers and includes a variety of activities for students within the “Photonics” MSc program. It is expected to be a successful story and used as an example for similar initiatives with other Russian high-tech companies. One of the pathways of extended knowledge exchange with industrial partners is an active involvement of potential employers in MSc Defense Committees to review and assess MSc thesis projects and to participate in defense procedures. The paper will evaluate the effect and results of the above undertaken measures.

Keywords: Curriculum redesign, knowledge exchange model, learning outcomes framework, stakeholder engagement

Procedia PDF Downloads 51

Authors: Rodrigo Arnaldo Scarpel

Abstract:

Trend following is a widely accepted investment strategy that adopts a rule-based trading mechanism that rather than striving to predict market direction or on information gathering to decide when to buy and when to sell a stock. Thus, in trend following one must respond to market’s movements that has recently happen and what is currently happening, rather than on what will happen. Optimally, in trend following strategy, is to catch a bull market at its early stage, ride the trend, and liquidate the position at the first evidence of the subsequent bear market. For applying the trend following strategy one needs to find the trend and identify trade signals. In order to avoid false signals, i.e., identify fluctuations of short, mid and long terms and to separate noise from real changes in the trend, most academic works rely on moving averages and other technical analysis indicators, such as the moving average convergence divergence (MACD) and the relative strength index (RSI) to uncover intelligible stock trading rules following trend following strategy philosophy. Recently, some works has applied machine learning techniques for trade rules discovery. In those works, the process of rule construction is based on evolutionary learning which aims to adapt the rules to the current environment and searches for the global optimum rules in the search space. In this work, instead of focusing on the usage of machine learning techniques for creating trading rules, a time series trend classification employing a semi-supervised approach was used to early identify both the beginning and the end of upward and downward trends. Such classification model can be employed to identify trade signals and the decision-making procedure is that if an up-trend (down-trend) is identified, a buy (sell) signal is generated. Semi-supervised learning is used for model training when only part of the data is labeled and Semi-supervised classification aims to train a classifier from both the labeled and unlabeled data, such that it is better than the supervised classifier trained only on the labeled data. For illustrating the proposed approach, it was employed daily trade information, including the open, high, low and closing values and volume from January 1, 2000 to December 31, 2022, of the São Paulo Exchange Composite index (IBOVESPA). Through this time period it was visually identified consistent changes in price, upwards or downwards, for assigning labels and leaving the rest of the days (when there is not a consistent change in price) unlabeled. For training the classification model, a pseudo-label semi-supervised learning strategy was used employing different technical analysis indicators. In this learning strategy, the core is to use unlabeled data to generate a pseudo-label for supervised training. For evaluating the achieved results, it was considered the annualized return and excess return, the Sortino and the Sharpe indicators. Through the evaluated time period, the obtained results were very consistent and can be considered promising for generating the intended trading signals.

Keywords: evolutionary learning, semi-supervised classification, time series data, trading signals generation

Procedia PDF Downloads 50

Authors: Shilpa Murthy, Hazlina Binti Abu Bakar, Juliet Mathew, Chandrashekhar Thummala Hlly Sreerama Reddy, Pathiyil Ravi Shankar

Abstract:

Simulation is defined as a technique that replaces or expands real experiences with guided experiences that interactively imitate real-world processes or systems. Simulation enables learners to train in a safe and non-threatening environment. For decades, simulation has been considered an integral part of clinical teaching and learning strategy in medical education. The several types of simulation used in medical education and the clinical environment can be applied to several models, including full-body mannequins, task trainers, standardized simulated patients, virtual or computer-generated simulation, or Hybrid simulation that can be used to facilitate learning. Simulation allows healthcare practitioners to acquire skills and experience while taking care of patient safety. The recent COVID pandemic has also led to an increase in simulation use, as there were limitations on medical student placements in hospitals and clinics. The learning is tailored according to the educational needs of students to make the learning experience more valuable. Simulation in the pre-clinical years has challenges with resource constraints, effective curricular integration, student engagement and motivation, and evidence of educational impact, to mention a few. As instructors, we may have more reliance on the use of simulation for pre-clinical students while the students’ confidence levels and perceived competence are to be evaluated. Our research question was whether the implementation of simulation-based learning positively influences preclinical medical students' confidence levels and perceived competence. This study was done to align the teaching activities with the student’s learning experience to introduce more low-fidelity simulation-based teaching sessions for pre-clinical years and to obtain students’ input into the curriculum development as part of inclusivity. The study was carried out at International Medical University, involving pre-clinical year (Medical) students who were started with low-fidelity simulation-based medical education from their first semester and were gradually introduced to medium fidelity, too. The Student Satisfaction and Self-Confidence in Learning Scale questionnaire from the National League of Nursing was employed to collect the responses. The internal consistency reliability for the survey items was tested with Cronbach’s alpha using an Excel file. IBM SPSS for Windows version 28.0 was used to analyze the data. Spearman’s rank correlation was used to analyze the correlation between students’ satisfaction and self-confidence in learning. The significance level was set at p value less than 0.05. The results from this study have prompted the researchers to undertake a larger-scale evaluation, which is currently underway. The current results show that 70% of students agreed that the teaching methods used in the simulation were helpful and effective. The sessions are dependent on the learning materials that are provided and how the facilitators engage the students and make the session more enjoyable. The feedback provided inputs on the following areas to focus on while designing simulations for pre-clinical students. There are quality learning materials, an interactive environment, motivating content, skills and knowledge of the facilitator, and effective feedback.

Keywords: low-fidelity simulation, pre-clinical simulation, students satisfaction, self-confidence

Procedia PDF Downloads 21

Authors: Yan Zhang

Abstract:

Predictive maintenance is a technique to predict when an in-service machine will fail so that maintenance can be planned in advance. Analytics-driven predictive maintenance is gaining increasing attention in many industries such as manufacturing, utilities, aerospace, etc., along with the emerging demand of Internet of Things (IoT) applications and the maturity of technologies that support Big Data storage and processing. This study aims to build an end-to-end analytics solution that includes both real-time machine condition monitoring and machine learning based predictive analytics capabilities. The goal is to showcase a general predictive maintenance solution architecture, which suggests how the data generated from field machines can be collected, transmitted, stored, and analyzed. We use a publicly available aircraft engine run-to-failure dataset to illustrate the streaming analytics component and the batch failure prediction component. We outline the contributions of this study from four aspects. First, we compare the predictive maintenance problems from the view of the traditional reliability centered maintenance field, and from the view of the IoT applications. When evolving to the IoT era, predictive maintenance has shifted its focus from ensuring reliable machine operations to improve production/maintenance efficiency via any maintenance related tasks. It covers a variety of topics, including but not limited to: failure prediction, fault forecasting, failure detection and diagnosis, and recommendation of maintenance actions after failure. Second, we review the state-of-art technologies that enable a machine/device to transmit data all the way through the Cloud for storage and advanced analytics. These technologies vary drastically mainly based on the power source and functionality of the devices. For example, a consumer machine such as an elevator uses completely different data transmission protocols comparing to the sensor units in an environmental sensor network. The former may transfer data into the Cloud via WiFi directly. The latter usually uses radio communication inherent the network, and the data is stored in a staging data node before it can be transmitted into the Cloud when necessary. Third, we illustrate show to formulate a machine learning problem to predict machine fault/failures. By showing a step-by-step process of data labeling, feature engineering, model construction and evaluation, we share following experiences: (1) what are the specific data quality issues that have crucial impact on predictive maintenance use cases; (2) how to train and evaluate a model when training data contains inter-dependent records. Four, we review the tools available to build such a data pipeline that digests the data and produce insights. We show the tools we use including data injection, streaming data processing, machine learning model training, and the tool that coordinates/schedules different jobs. In addition, we show the visualization tool that creates rich data visualizations for both real-time insights and prediction results. To conclude, there are two key takeaways from this study. (1) It summarizes the landscape and challenges of predictive maintenance applications. (2) It takes an example in aerospace with publicly available data to illustrate each component in the proposed data pipeline and showcases how the solution can be deployed as a live demo.

Keywords: Internet of Things, machine learning, predictive maintenance, streaming data

Procedia PDF Downloads 358

Authors: J. S. M. Yang, G. E. T. Chua

Abstract:

Diploma in Optometry (OPT) course is a three-year program offered by Ngee Ann Polytechnic (NP) to train students to provide primary eye care. Students are equipped with foundational conceptual knowledge and practical skills in the first three semesters before clinical modules in fourth to six semesters. In the clinical modules, students typically have difficulties in integrating the acquired knowledge and skills from the past semesters to perform general eye examinations on public patients at NP Optometry Centre (NPOC). To help the students overcome the challenge, a web-based game Virtual Optometrist (VO) was developed to help students apply their skills and knowledge through scenario-based learning. It consisted of two interfaces, Optical Practice Counter (OPC) and Optometric Consultation Room (OCR), to provide two simulated settings for authentic learning experiences. In OPC, students would recommend and provide appropriate frame and lens selection based on virtual patient’s case history. In OCR, students would diagnose and manage virtual patients with common ocular conditions. Simulated scenarios provided real-world clinical situations that required contextual application of integrated knowledge from relevant modules. The stages in OPC and OCR are of increasing complexity to align to expected students’ clinical competency as they progress to more senior semesters. This prevented gameplay fatigue as VO was used over the semesters to achieve different learning outcomes. Numerous feedback opportunities were provided to students based on their decisions to allow individualized learning to take place. The game-based learning element in VO was achieved through the scoreboard and leader board to enhance students' motivation to perform. Scores were based on the speed and accuracy of students’ responses to the questions posed in the simulated scenarios, preparing the students to perform accurately and effectively under time pressure in a realistic optometric environment. Learning analytics was generated in VO’s backend office based on students’ responses, offering real-time data on distinctive and observable learners’ behavior to monitor students’ engagement and learning progress. The backend office allowed versatility to add, edit, and delete scenarios for different intended learning outcomes. Likert Scale was used to measure students’ learning experience with VO for OPT Year 2 and 3 students. The survey results highlighted the learning benefits of implementing VO in the different modules, such as enhancing recall and reinforcement of clinical knowledge for contextual application to develop higher-order thinking skills, increasing efficiency in clinical decision-making, facilitating learning through immediate feedback and second attempts, providing exposure to common and significant ocular conditions, and training effective communication skills. The results showed that VO has been useful in reinforcing optometry students’ learning and supporting the development of higher-order thinking, increasing efficiency in clinical decision-making, and allowing students to learn from their mistakes with immediate feedback and second attempts. VO also exposed the students to diverse ocular conditions through simulated real-world clinical scenarios, which may otherwise not be encountered in NPOC, and promoted effective communication skills.

Keywords: authentic learning, game-based learning, scenario-based learning, simulated clinical scenarios

Procedia PDF Downloads 86

Authors: A. Kourou, A. Ioakeimidou, E. Pelli, M. Panoutsopoulou, V. Abramea

Abstract:

Worldwide there is a growing recognition that education is a critical component of any disaster impacts reduction effort and a great challenge too. Given this challenge, a broad range of awareness raising projects at all levels are implemented and are continuously evaluated by Earthquake Planning and Protection Organization (EPPO). This paper presents an overview of EPPO educational initiative (seminars, lectures, workshops, campaigns and educational material) and its evaluation results. The abovementioned initiative is focused to aware the public, train teachers and civil protection staff, inform students and educate people with disabilities on subjects related to earthquake reduction issues. The better understating of how human activity can link to disaster and what can be done at the individual, family or workplace level to contribute to seismic reduction are the main issues of EPPO projects. Survey results revealed that a high percentage of teachers (included the ones of special schools) from all over the country have taken the appropriate preparedness measures at schools. On the other hand, the implementation of earthquake preparedness measures at various workplaces (kindergartens, banks, utilities etc.) has still significant room for improvement. Results show that the employees in banks and public utilities have substantially higher rates in preventive and preparedness actions in their workplaces than workers in kindergartens and other workplaces. One of the EPPO educational priorities is to enhance earthquake preparedness of people with disabilities. Booklets, posters and applications have been created with the financial support of the Council of Europe, addressed to people who have mobility impairments, learning difficulties or cognitive disability (ή intellectual disabilities). Part of the educational material was developed using the «easy-to-read» method and Makaton language program with the collaboration of experts on special needs education and teams of people with cognitive disability. Furthermore, earthquake safety seminars and earthquake drills have been implemented in order to develop children’s, parents’ and teachers abilities and skills on earthquake impacts reduction. To enhance the abovementioned efforts, EPPO is a partner at prevention and preparedness projects supported by EU Civil Protection Financial Instrument. One of them is E-PreS’ project (Monitoring and Evaluation of Natural Hazard Preparedness at School Environment). The main objectives of E-PreS project are: 1) to create smart tools which define, simulate and evaluate drills procedure at schools, centers of vocational training of people with disabilities or other workplaces, and 2) to involve students or adults with disabilities in the E-PreS system evacuation procedure in case of earthquake, flood, or volcanic occurrence. Two other EU projects (RACCE educational kit and EVANDE educational platform) are also with the aim of contributing to raising awareness among people with disabilities, students, teachers, volunteers etc. It is worth mentioning that even though in Greece many efforts have been done till now to build awareness towards earthquakes and establish preparedness status for prospective earthquakes, there are still actions to be taken.

Keywords: earthquake, emergency plans, E-PreS project, people with disabilities, special needs education

Procedia PDF Downloads 237

Authors: Julien G. Chenet, Mario A. Hernandez, U. Leonardo Rodriguez

Abstract:

The tropical areas are places where there is scarcity of access to potable water and where renewable energies need further development. They also display high undernourishment levels, even though they are one of the resources-richest areas in the world. In these areas, it is common to count on great extension of soils, high solar radiation and raw water from rain, groundwater, surface water or even saltwater. Even though resources are available, access to them is limited, and the low-density habitat makes central solutions expensive and investments not worthy. In response to this lack of investment, rural inhabitants use fossil fuels and timber as an energy source and import agrochemical for soils fertilization, which increase GHG emissions. The OASIS project brings an answer to this situation. It supplies renewable energy, potable water and organic food. The first step is the determination of the needs of the communities in terms of energy, water quantity and quality, food requirements and soil characteristics. Second step is the determination of the available resources, such as solar energy, raw water and organic residues on site. The pilot OASIS project is located in the Vichada department, Colombia, and ensures the sustainable use of natural resources to meet the community needs. The department has roughly 70% of indigenous people. They live in a very scattered landscape, with no access to clean water and energy. They use polluted surface water for direct consumption and diesel for energy purposes. OASIS pilot will ensure basic needs for a 400-students education center. In this case, OASIS will provide 20 kW of solar energy potential and 40 liters per student per day. Water will be treated form groundwater, with two qualities. A conventional one with chlorine, and as the indigenous people are not used to chlorine for direct consumption, second train is with reverse osmosis to bring conservable safe water without taste. OASIS offers a solution to supply basic needs, shifting from fossil fuels, timber, to a no-GHG-emission solution. This solution is part of the mitigation strategy against Climate Change for the communities in low-density areas of the tropics. OASIS is a learning center to teach how to convert natural resources into utilizable ones. It is also a meeting point for the community with high pedagogic impact that promotes the efficient and sustainable use of resources. OASIS system is adaptable to any tropical area and competes technically and economically with any conventional solution, that needs transport of energy, treated water and food. It is a fully automatic, replicable and sustainable solution to sort out the issue of access to basic needs in rural areas. OASIS is also a solution to undernourishment, ensuring a responsible use of resources, to prevent long-term pollution of soils and groundwater. It promotes the closure of the nutrient cycle, and the optimal use of the land whilst ensuring food security in depressed low-density regions of the tropics. OASIS is under optimization to Vichada conditions, and will be available to any other tropical area in the following months.

Keywords: climate change adaptation and mitigation, rural development, sustainable access to clean and renewable resources, social inclusion

Procedia PDF Downloads 225

Authors: Monica Racha, Siva Chandrasekaran, Alex Stojcevski

Abstract:

The engineering programs focus on promoting students' personal and professional development by ensuring that students acquire technical and professional competencies during four-year studies. The traditional engineering laboratory provides an opportunity for students to "practice by doing," and laboratory facilities aid them in obtaining insight and understanding of their discipline. Due to rapid technological advancements and the current COVID-19 outbreak, the traditional labs were transforming into virtual learning environments. Aim: To better understand the limitations of the physical laboratory, this research study aims to use a Machine Learning (ML) algorithm that interfaces with the Augmented Reality HoloLens and predicts the image behavior to classify and detect the electronic components. The automated electronic components error classification and detection automatically detect and classify the position of all components on a breadboard by using the ML algorithm. This research will assist first-year undergraduate engineering students in conducting laboratory practices without any supervision. With the help of HoloLens, and ML algorithm, students will reduce component placement error on a breadboard and increase the efficiency of simple laboratory practices virtually. Method: The images of breadboards, resistors, capacitors, transistors, and other electrical components will be collected using HoloLens 2 and stored in a database. The collected image dataset will then be used for training a machine learning model. The raw images will be cleaned, processed, and labeled to facilitate further analysis of components error classification and detection. For instance, when students conduct laboratory experiments, the HoloLens captures images of students placing different components on a breadboard. The images are forwarded to the server for detection in the background. A hybrid Convolutional Neural Networks (CNNs) and Support Vector Machines (SVMs) algorithm will be used to train the dataset for object recognition and classification. The convolution layer extracts image features, which are then classified using Support Vector Machine (SVM). By adequately labeling the training data and classifying, the model will predict, categorize, and assess students in placing components correctly. As a result, the data acquired through HoloLens includes images of students assembling electronic components. It constantly checks to see if students appropriately position components in the breadboard and connect the components to function. When students misplace any components, the HoloLens predicts the error before the user places the components in the incorrect proportion and fosters students to correct their mistakes. This hybrid Convolutional Neural Networks (CNNs) and Support Vector Machines (SVMs) algorithm automating electronic component error classification and detection approach eliminates component connection problems and minimizes the risk of component damage. Conclusion: These augmented reality smart glasses powered by machine learning provide a wide range of benefits to supervisors, professionals, and students. It helps customize the learning experience, which is particularly beneficial in large classes with limited time. It determines the accuracy with which machine learning algorithms can forecast whether students are making the correct decisions and completing their laboratory tasks.

Keywords: augmented reality, machine learning, object recognition, virtual laboratories

Procedia PDF Downloads 108

Authors: Marcial Blondet, Malena Serrano, Álvaro Rubiños, Elin Mattsson

Abstract:

In Peru, there are more than two million houses made of adobe (sun dried mud bricks) or rammed earth (35% of the total houses), in which almost 9 million people live, mainly because they cannot afford to purchase industrialized construction materials. Although adobe houses are cheap to build and thermally comfortable, their seismic performance is very poor, and they usually suffer significant damage or collapse with tragic loss of life. Therefore, over the years, researchers at the Pontifical Catholic University of Peru and other institutions have developed many reinforcement techniques as an effort to improve the structural safety of earthen houses located in seismic areas. However, most rural communities live under unacceptable seismic risk conditions because these techniques have not been adopted massively, mainly due to high cost and lack of diffusion. The nylon rope mesh reinforcement technique is simple and low-cost, and two technological transference tools have been developed to diffuse it among rural communities: 1) Scale seismic simulations using a portable shaking table have been designed to prove its effectiveness to protect adobe houses; 2) A step-by-step illustrated construction manual has been developed to guide the complete building process of a nylon rope mesh reinforced adobe house. As a study case, it was selected the district of Pullo: a small rural community in the Peruvian Andes where more than 80% of its inhabitants live in adobe houses and more than 60% are considered to live in poverty or extreme poverty conditions. The research team carried out a one-day workshop in May 2015 and a two-day workshop in September 2015. Results were positive: First, the nylon rope mesh reinforcement procedure was proven simple enough to be replicated by adults, both young and seniors, and participants handled ropes and knots easily as they use them for daily livestock activity. In addition, nylon ropes were proven highly available in the study area as they were found at two local stores in variety of color and size.. Second, the portable shaking table demonstration successfully showed the effectiveness of the nylon rope mesh reinforcement and generated interest on learning about it. On the first workshop, more than 70% of the participants were willing to formally subscribe and sign up for practical training lessons. On the second workshop, more than 80% of the participants returned the second day to receive introductory practical training. Third, community members found illustrations on the construction manual simple and friendly but the roof system illustrations led to misinterpretation so they were improved. The technological transfer tools developed in this project can be used to train rural dwellers on earthquake-resistant self-construction with adobe, which is still very common in the Peruvian Andes. This approach would allow community members to develop skills and capacities to improve safety of their households on their own, thus, mitigating their high seismic risk and preventing tragic losses. Furthermore, proper training in earthquake-resistant self-construction with adobe would prevent rural dwellers from depending on external aid after an earthquake and become agents of their own development.

Keywords: adobe, Peruvian Andes, safe housing, technological transference

Procedia PDF Downloads 267

Authors: Zachary Blanks, Solomon Sonya

Abstract:

Poaching presents a serious threat to endangered animal species, environment conservations, and human life. Additionally, some poaching activity has even been linked to supplying funds to support terrorist networks elsewhere around the world. Consequently, agencies dedicated to protecting wildlife habitats have a near intractable task of adequately patrolling an entire area (spanning several thousand kilometers) given limited resources, funds, and personnel at their disposal. Thus, agencies need predictive tools that are both high-performing and easily implementable by the user to help in learning how the significant features (e.g. animal population densities, topography, behavior patterns of the criminals within the area, etc) interact with each other in hopes of abating poaching. This research develops a classification model using machine learning algorithms to aid in forecasting future attacks that is both easy to train and performs well when compared to other models. In this research, we demonstrate how data imputation methods (specifically predictive mean matching, gradient boosting, and random forest multiple imputation) can be applied to analyze data and create significant predictions across a varied data set. Specifically, we apply these methods to improve the accuracy of adopted prediction models (Logistic Regression, Support Vector Machine, etc). Finally, we assess the performance of the model and the accuracy of our data imputation methods by learning on a real-world data set constituting four years of imputed data and testing on one year of non-imputed data. This paper provides three main contributions. First, we extend work done by the Teamcore and CREATE (Center for Risk and Economic Analysis of Terrorism Events) research group at the University of Southern California (USC) working in conjunction with the Department of Homeland Security to apply game theory and machine learning algorithms to develop more efficient ways of reducing poaching. This research introduces ensemble methods (Random Forests and Stochastic Gradient Boosting) and applies it to real-world poaching data gathered from the Ugandan rain forest park rangers. Next, we consider the effect of data imputation on both the performance of various algorithms and the general accuracy of the method itself when applied to a dependent variable where a large number of observations are missing. Third, we provide an alternate approach to predict the probability of observing poaching both by season and by month. The results from this research are very promising. We conclude that by using Stochastic Gradient Boosting to predict observations for non-commercial poaching by season, we are able to produce statistically equivalent results while being orders of magnitude faster in computation time and complexity. Additionally, when predicting potential poaching incidents by individual month vice entire seasons, boosting techniques produce a mean area under the curve increase of approximately 3% relative to previous prediction schedules by entire seasons.

Keywords: ensemble methods, imputation, machine learning, random forests, statistical analysis, stochastic gradient boosting, wildlife protection

Procedia PDF Downloads 262

Authors: Meiyan Gao, Zongmin Wang, Haibo Yang, Qiuhua Liang

Abstract:

Under the background of global climate change and rapid development of modern urbanization, the frequency of climate disasters such as extreme precipitation in cities around the world is gradually increasing. In this paper, Hi-PIMS model is used to simulate the "720" flood in Zhengzhou, and the continuous stages of flood resilience are determined with the urban flood stages are divided. The flood resilience curve under the influence of multiple factors were determined and the urban flood toughness was evaluated by combining the results of resilience curves. The flood resilience of urban unit grid was evaluated based on economy, population, road network, hospital distribution and land use type. Firstly, the rainfall data of meteorological stations near Zhengzhou and the remote sensing rainfall data from July 17 to 22, 2021 were collected. The Kriging interpolation method was used to expand the rainfall data of Zhengzhou. According to the rainfall data, the flood process generated by four rainfall events in Zhengzhou was reproduced. Based on the results of the inundation range and inundation depth in different areas, the flood process was divided into four stages: absorption, resistance, overload and recovery based on the once in 50 years rainfall standard. At the same time, based on the levels of slope, GDP, population, hospital affected area, land use type, road network density and other aspects, the resilience curve was applied to evaluate the urban flood resilience of different regional units, and the difference of flood process of different precipitation in "720" rainstorm in Zhengzhou was analyzed. Faced with more than 1,000 years of rainstorm, most areas are quickly entering the stage of overload. The influence levels of factors in different areas are different, some areas with ramps or higher terrain have better resilience, and restore normal social order faster, that is, the recovery stage needs shorter time. Some low-lying areas or special terrain, such as tunnels, will enter the overload stage faster in the case of heavy rainfall. As a result, high levels of flood protection, water level warning systems and faster emergency response are needed in areas with low resilience and high risk. The building density of built-up area, population of densely populated area and road network density all have a certain negative impact on urban flood resistance, and the positive impact of slope on flood resilience is also very obvious. While hospitals can have positive effects on medical treatment, they also have negative effects such as population density and asset density when they encounter floods. The result of a separate comparison of the unit grid of hospitals shows that the resilience of hospitals in the distribution range is low when they encounter floods. Therefore, in addition to improving the flood resistance capacity of cities, through reasonable planning can also increase the flood response capacity of cities. Changes in these influencing factors can further improve urban flood resilience, such as raise design standards and the temporary water storage area when floods occur, train the response speed of emergency personnel and adjust emergency support equipment.

Keywords: urban flood resilience, resilience assessment, hydrodynamic model, resilience curve

Procedia PDF Downloads 18

Authors: Fouzia Arif, Arif S. Mohammad, Hifsa Altaf, Lubna Raees

Abstract:

Introduction: The term "disability", refers to any condition that impedes the completion of daily tasks using traditional methods. In developing countries like Pakistan, disable population is usually excluded from the mainstream. In squatter settlements the situation is more critical. Sultanabad is one of the squatter settlements of Karachi. Purpose of case study is to improve the health of disabled children’s, and create awareness among the parents and community. Through a household visit, Shiraz, a young disabled boy of 15.5 years old was identified. Her mother articulated that her son was living normally and happily with his parents two years back. When he was 13 years old and student of class 8th, both his legs were traumatized in a Railway Train Accident while playing cricket. He got both femoral shaft fractured severely. He was taken to Jinnah Post Graduate Medical Centre (JPMC) where his left leg was amputated at above knee level and right leg was opened & fixed by reduction internally, luckily bone healed moderately with the passage of time. Methods: In Squatter settlements of Karachi Sultanabad, a survey was conducted in two sectors. Disability screening questionnaire was developed, collaboration with community through household visits, outreach sessions 23cases of disabled were identified who were socialized through sports, Musical program and get-together was organized with stockholder for creating awareness among community and parent’s. Collaboration was established with different NGOs, Government, stakeholders and community support for establishment of Physiotherapy Center. During home visit it was identified that Shiraz was on bed since last 1 year, his family could not afforded cost of physiotherapist and medical consultation due to poverty. Parents counseling was done mentioning that Shiraz needed to take treatment. After motivation his parents agreed for treatment. He was consulted by an orthopedic surgeon in AKUH, Who referred to DMC University of Health Science for rehabilitation service. There he was assessed and referred for Community Based Physiotherapy Centre Sultanabad. Physiotherapist visited home along with Coordinator for Special children and assessed him regularly, planned Physiotherapy treatment for abdominal, high muscles strutting exercise foot muscles strengthening exercise, knee mobilization weight bearing from partial to full weight gradually, also strengthen exercise were given for residual limb as the boy was dependent on it. He was also provided by an artificial leg and training was done. Result: Shiraz is now fully mobile, he can walk independently even out of home, functional ability progress improved and dependency factors reduced. It was difficult but not impossible. We all have sympathy but if we have empathy then we can rehabilitate the community in a better way. His parents are very happy and also the community is surprised to see him in such better condition. Conclusion: Combined efforts of physiotherapist, Coordinator of special children, community and parents made a drastic change in Shiraz’s case by continuously motivating him for better outcome. He is going to school regularly without support. Since he belongs to a poor family he faces financial constraints for education and clinical follow ups regularly.

Keywords: femoral shaft fracture, trauma, orthopedic surgeon, physiotherapy treatment

Procedia PDF Downloads 212

Authors: Dana Zelicha

Abstract:

The objective of this paper is to present innovative mindfulness tools specifically designed by OWBA—The Well Being Agency for organisations and corporate wellness programmes. The OWBA Mindfulness Tools (OWBA-MT) consist of practical mindfulness exercises to educate and train employees and business leaders to think, feel, and act more mindfully. Among these cutting-edge interventions are Mindful Meetings, Mindful Decision Making and Unitasking activities, intended to cultivate mindful communication and compassion in the workplace and transform organisational culture. In addition to targeting CEO’s and leaders within large corporations, OWBA-MT is also directed at the needs of specific populations such as entrepreneurs’ resilience and women empowerment. The goals of the OWBA-MT are threefold: to inform, inspire and implement. The first goal is to inform participants about the relationship between workplace stress, distractibility and miscommunication in the framework of mindfulness. The second goal is for the audience to be inspired to share those practices with other members of their organisation. The final objective is to equip participants with the tools to foster a compassionate, mindful and well-balanced work environment. To assess these tools, a 6-week case study was conducted as part of an employee wellness programme for a large international corporation. The OWBA-MT were introduced in a workshop forum once-a-week, with participants practicing these tools both in the office and at home. The workshops occurred 1 day a week (2 hours each), with themes and exercises varying weekly. To reinforce practice at home, participants received reflection forms and guided meditations online. Materials were sent via-email at the same time each day to ensure consistency and participation. To evaluate the effectiveness of the mindfulness intervention, improvements in four categories were measured: listening skills, mindfulness levels, prioritising skills and happiness levels. These factors were assessed using online self-reported questionnaires administered at the start of the intervention, and then again 4-weeks following completion. The measures included the Mindfulness Attention Awareness Scale (MAAS), Listening Skills Inventory (LSI), Time Management Behaviour Scale (TMBS) and a modified version of the Oxford Happiness Questionnaire (OHQ). All four parameters showed significant improvements from the start of the programme to the 4-week follow-up. Participant testimonials exhibited high levels of satisfaction and the overall results indicate that the OWBA-MT intervention substantially impacted the corporation in a positive way. The implications of these results suggest that OWBA-MT can improve employees’ capacities to listen and work well with others, to manage time effectively, and to experience enhanced satisfaction both at work and in life. Although corporate mindfulness programmes have proven to be effective, the challenge remains the low engagement levels at home in between training sessions and to implement the tools beyond the scope of the intervention. OWBA-MT has offered an innovative approach to enforce engagement levels at home by sending daily online materials outside the workshop forum with a personalised response. The limitations also noteworthy to consider for future research include the afterglow effect and lack of generalisability, as this study was conducted on a small and fairly homogenous sample.

Keywords: corporate mindfulness, listening skills, mindful leadership, mindfulness tools, organisational well being

Procedia PDF Downloads 213

Authors: Qianwei Cheng, A. K. M. Mahbubur Rahman, Anis Sarker, Abu Bakar Siddik Nayem, Ovi Paul, Amin Ahsan Ali, M. Ashraful Amin, Ryosuke Shibasaki, Moinul Zaber

Abstract:

Thomas Friedman, in his famous book, argued that the world in this 21st century is flat and will continue to be flatter. This is attributed to rapid globalization and the interdependence of humanity that engendered tremendous in-flow of human migration towards the urban spaces. In order to keep the urban environment sustainable, policy makers need to plan based on extensive analysis of the urban environment. With the advent of high definition satellite images, high resolution data, computational methods such as deep neural network analysis, and hardware capable of high-speed analysis; urban planning is seeing a paradigm shift. Legacy data on urban environments are now being complemented with high-volume, high-frequency data. However, the first step of understanding urban space lies in useful categorization of the space that is usable for data collection, analysis, and visualization. In this paper, we propose a pragmatic categorization method that is readily usable for machine analysis and show applicability of the methodology on a developing world setting. Categorization to plan sustainable urban spaces should encompass the buildings and their surroundings. However, the state-of-the-art is mostly dominated by classification of building structures, building types, etc. and largely represents the developed world. Hence, these methods and models are not sufficient for developing countries such as Bangladesh, where the surrounding environment is crucial for the categorization. Moreover, these categorizations propose small-scale classifications, which give limited information, have poor scalability and are slow to compute in real time. Our proposed method is divided into two steps-categorization and automation. We categorize the urban area in terms of informal and formal spaces and take the surrounding environment into account. 50 km × 50 km Google Earth image of Dhaka, Bangladesh was visually annotated and categorized by an expert and consequently a map was drawn. The categorization is based broadly on two dimensions-the state of urbanization and the architectural form of urban environment. Consequently, the urban space is divided into four categories: 1) highly informal area; 2) moderately informal area; 3) moderately formal area; and 4) highly formal area. In total, sixteen sub-categories were identified. For semantic segmentation and automatic categorization, Google’s DeeplabV3+ model was used. The model uses Atrous convolution operation to analyze different layers of texture and shape. This allows us to enlarge the field of view of the filters to incorporate larger context. Image encompassing 70% of the urban space was used to train the model, and the remaining 30% was used for testing and validation. The model is able to segment with 75% accuracy and 60% Mean Intersection over Union (mIoU). In this paper, we propose a pragmatic categorization method that is readily applicable for automatic use in both developing and developed world context. The method can be augmented for real-time socio-economic comparative analysis among cities. It can be an essential tool for the policy makers to plan future sustainable urban spaces.

Keywords: semantic segmentation, urban environment, deep learning, urban building, classification

Procedia PDF Downloads 151

Authors: Gabrielle Robertson, Matthew Downs, Joseph Dagher

Abstract:

Iron deposition in the brain has been linked with a host of neurological disorders such as Alzheimer’s, Parkinson’s, and Multiple Sclerosis. While some treatment options exist, there are no objective measurement tools that allow for the monitoring of iron levels in the brain in vivo. An emerging Magnetic Resonance Imaging (MRI) method has been recently proposed to deduce iron concentration through quantitative measurement of magnetic susceptibility. This is a multi-step process that involves repeated modeling of physical processes via approximate numerical solutions. For example, the last two steps of this Quantitative Susceptibility Mapping (QSM) method involve I) mapping magnetic field into magnetic susceptibility and II) mapping magnetic susceptibility into iron concentration. Process I involves solving an ill-posed inverse problem by using regularization via injection of prior belief. The end result from Process II highly depends on the model used to describe the molecular content of each voxel (type of iron, water fraction, etc.) Due to these factors, the accuracy and repeatability of QSM have been an active area of research in the MRI and medical imaging community. This work aims to estimate iron concentration in the brain via a single step. A synthetic numerical model of the human head was created by automatically and manually segmenting the human head on a high-resolution grid (640x640x640, 0.4mm³) yielding detailed structures such as microvasculature and subcortical regions as well as bone, soft tissue, Cerebral Spinal Fluid, sinuses, arteries, and eyes. Each segmented region was then assigned tissue properties such as relaxation rates, proton density, electromagnetic tissue properties and iron concentration. These tissue property values were randomly selected from a Probability Distribution Function derived from a thorough literature review. In addition to having unique tissue property values, different synthetic head realizations also possess unique structural geometry created by morphing the boundary regions of different areas within normal physical constraints. This model of the human brain is then used to create synthetic MRI measurements. This is repeated thousands of times, for different head shapes, volume, tissue properties and noise realizations. Collectively, this constitutes a training-set that is similar to in vivo data, but larger than datasets available from clinical measurements. This 3D convolutional U-Net neural network architecture was used to train data-driven Deep Learning models to solve for iron concentrations from raw MRI measurements. The performance was then tested on both synthetic data not used in training as well as real in vivo data. Results showed that the model trained on synthetic MRI measurements is able to directly learn iron concentrations in areas of interest more effectively than other existing QSM reconstruction methods. For comparison, models trained on random geometric shapes (as proposed in the Deep QSM method) are less effective than models trained on realistic synthetic head models. Such an accurate method for the quantitative measurement of iron deposits in the brain would be of important value in clinical studies aiming to understand the role of iron in neurological disease.

Keywords: magnetic resonance imaging, MRI, iron deposition, machine learning, quantitative susceptibility mapping

Procedia PDF Downloads 93

Authors: Ugo Galvanetto, Pirto G. Pavan, Mirco Zaccariotto

Abstract:

The discipline of Computer-integrated surgery (CIS) will provide equipment able to improve the efficiency of healthcare systems and, which is more important, clinical results. Surgeons and machines will cooperate in new ways that will extend surgeons’ ability to train, plan and carry out surgery. Patient specific CIS of the brain requires several steps: 1 - Fast generation of brain models. Based on image recognition of MR images and equipped with artificial intelligence, image recognition techniques should differentiate among all brain tissues and segment them. After that, automatic mesh generation should create the mathematical model of the brain in which the various tissues (white matter, grey matter, cerebrospinal fluid …) are clearly located in the correct positions. 2 – Reliable and fast simulation of the surgical process. Computational mechanics will be the crucial aspect of the entire procedure. New algorithms will be used to simulate the mechanical behaviour of cutting through cerebral tissues. 3 – Real time provision of visual and haptic feedback A sophisticated human-machine interface based on ergonomics and psychology will provide the feedback to the surgeon. The present work will address in particular point 2. Modelling the cutting of soft tissue in a structure as complex as the human brain is an extremely challenging problem in computational mechanics. The finite element method (FEM), that accurately represents complex geometries and accounts for material and geometrical nonlinearities, is the most used computational tool to simulate the mechanical response of soft tissues. However, the main drawback of FEM lies in the mechanics theory on which it is based, classical continuum Mechanics, which assumes matter is a continuum with no discontinuity. FEM must resort to complex tools such as pre-defined cohesive zones, external phase-field variables, and demanding remeshing techniques to include discontinuities. However, all approaches to equip FEM computational methods with the capability to describe material separation, such as interface elements with cohesive zone models, X-FEM, element erosion, phase-field, have some drawbacks that make them unsuitable for surgery simulation. Interface elements require a-priori knowledge of crack paths. The use of XFEM in 3D is cumbersome. Element erosion does not conserve mass. The Phase Field approach adopts a diffusive crack model instead of describing true tissue separation typical of surgical procedures. Modelling discontinuities, so difficult when using computational approaches based on classical continuum Mechanics, is instead easy for novel computational methods based on Peridynamics (PD). PD is a non-local theory of mechanics formulated with no use of spatial derivatives. Its governing equations are valid at points or surfaces of discontinuity, and it is, therefore especially suited to describe crack propagation and fragmentation problems. Moreover, PD does not require any criterium to decide the direction of crack propagation or the conditions for crack branching or coalescence; in the PD-based computational methods, cracks develop spontaneously in the way which is the most convenient from an energy point of view. Therefore, in PD computational methods, crack propagation in 3D is as easy as it is in 2D, with a remarkable advantage with respect to all other computational techniques.

Keywords: computational mechanics, peridynamics, finite element, biomechanics

Procedia PDF Downloads 49

Authors: Utkarsh A. Mishra, Ankit Bansal

Abstract:

At high temperature, radiative heat transfer is the dominant mode of heat transfer. It is governed by various phenomena such as photon emission, absorption, and scattering. The solution of the governing integrodifferential equation of radiative transfer is a complex process, more when the effect of participating medium and wavelength properties are taken into consideration. Although a generic formulation of such radiative transport problem can be modeled for a wide variety of problems with non-gray, non-diffusive surfaces, there is always a trade-off between simplicity and accuracy of the problem. Recently, solutions of complicated mathematical problems with statistical methods based on randomization of naturally occurring phenomena have gained significant importance. Photon bundles with discrete energy can be replicated with random numbers describing the emission, absorption, and scattering processes. Photon Monte Carlo (PMC) is a simple, yet powerful technique, to solve radiative transfer problems in complicated geometries with arbitrary participating medium. The method, on the one hand, increases the accuracy of estimation, and on the other hand, increases the computational cost. The participating media -generally a gas, such as CO₂, CO, and H₂O- present complex emission and absorption spectra. To model the emission/absorption accurately with random numbers requires a weighted sampling as different sections of the spectrum carries different importance. Importance sampling (IS) was implemented to sample random photon of arbitrary wavelength, and the sampled data provided unbiased training of MC estimators for better results. A better replacement to uniform random numbers is using deterministic, quasi-random sequences. Halton, Sobol, and Faure Low-Discrepancy Sequences are used in this study. They possess better space-filling performance than the uniform random number generator and gives rise to a low variance, stable Quasi-Monte Carlo (QMC) estimators with faster convergence. An optimal supervised learning scheme was further considered to reduce the computation costs of the PMC simulation. A one-dimensional plane-parallel slab problem with participating media was formulated. The history of some randomly sampled photon bundles is recorded to train an Artificial Neural Network (ANN), back-propagation model. The flux was calculated using the standard quasi PMC and was considered to be the training target. Results obtained with the proposed model for the one-dimensional problem are compared with the exact analytical and PMC model with the Line by Line (LBL) spectral model. The approximate variance obtained was around 3.14%. Results were analyzed with respect to time and the total flux in both cases. A significant reduction in variance as well a faster rate of convergence was observed in the case of the QMC method over the standard PMC method. However, the results obtained with the ANN method resulted in greater variance (around 25-28%) as compared to the other cases. There is a great scope of machine learning models to help in further reduction of computation cost once trained successfully. Multiple ways of selecting the input data as well as various architectures will be tried such that the concerned environment can be fully addressed to the ANN model. Better results can be achieved in this unexplored domain.

Keywords: radiative heat transfer, Monte Carlo Method, pseudo-random numbers, low discrepancy sequences, artificial neural networks

Procedia PDF Downloads 184

Authors: Mian Huang, Chi Ma, Junyu Lin, William Lu

Abstract:

Introduction: Bone health attracts more attention recently and an intelligent question and answer (QA) chatbot for osteoporosis is helpful for science popularization. With Generative Pretrained Transformer (GPT) technology developing, we build an osteoporosis corpus dataset and then fine-tune LLaMA, a famous open-source GPT foundation large language model(LLM), on our self-constructed osteoporosis corpus. Evaluated by clinical orthopedic experts, our fine-tuned model outperforms vanilla LLaMA on osteoporosis QA task in Chinese. Three-dimensional quantitative computed tomography (QCT) measured bone mineral density (BMD) is considered as more accurate than DXA for BMD measurement in recent years. We develop an automatic Phantom-less QCT(PL-QCT) that is more efficient for BMD measurement since no need of an external phantom for calibration. Combined with LLM on osteoporosis, our PL-QCT provides efficient and accurate BMD measurement for our chatbot users. Material and Methods: We build an osteoporosis corpus containing about 30,000 Chinese literatures whose titles are related to osteoporosis. The whole process is done automatically, including crawling literatures in .pdf format, localizing text/figure/table region by layout segmentation algorithm and recognizing text by OCR algorithm. We train our model by continuous pre-training with Low-rank Adaptation (LoRA, rank=10) technology to adapt LLaMA-7B model to osteoporosis domain, whose basic principle is to mask the next word in the text and make the model predict that word. The loss function is defined as cross-entropy between the predicted and ground-truth word. Experiment is implemented on single NVIDIA A800 GPU for 15 days. Our automatic PL-QCT BMD measurement adopt AI-associated region-of-interest (ROI) generation algorithm for localizing vertebrae-parallel cylinder in cancellous bone. Due to no phantom for BMD calibration, we calculate ROI BMD by CT-BMD of personal muscle and fat. Results & Discussion: Clinical orthopaedic experts are invited to design 5 osteoporosis questions in Chinese, evaluating performance of vanilla LLaMA and our fine-tuned model. Our model outperforms LLaMA on over 80% of these questions, understanding ‘Expert Consensus on Osteoporosis’, ‘QCT for osteoporosis diagnosis’ and ‘Effect of age on osteoporosis’. Detailed results are shown in appendix. Future work may be done by training a larger LLM on the whole orthopaedics with more high-quality domain data, or a multi-modal GPT combining and understanding X-ray and medical text for orthopaedic computer-aided-diagnosis. However, GPT model gives unexpected outputs sometimes, such as repetitive text or seemingly normal but wrong answer (called ‘hallucination’). Even though GPT give correct answers, it cannot be considered as valid clinical diagnoses instead of clinical doctors. The PL-QCT BMD system provided by Bone’s QCT(Bone’s Technology(Shenzhen) Limited) achieves 0.1448mg/cm2(spine) and 0.0002 mg/cm2(hip) mean absolute error(MAE) and linear correlation coefficient R2=0.9970(spine) and R2=0.9991(hip)(compared to QCT-Pro(Mindways)) on 155 patients in three-center clinical trial in Guangzhou, China. Conclusion: This study builds a Chinese osteoporosis corpus and develops a fine-tuned and domain-adapted LLM as well as a PL-QCT BMD measurement system. Our fine-tuned GPT model shows better capability than LLaMA model on most testing questions on osteoporosis. Combined with our PL-QCT BMD system, we are looking forward to providing science popularization and early morning screening for potential osteoporotic patients.

Keywords: GPT, phantom-less QCT, large language model, osteoporosis

Procedia PDF Downloads 33

Authors: Subhash Nerella, Ziyuan Guan, Azra Bihorac, Parisa Rashidi

Abstract:

Intensive care units (ICUs) provide care to critically ill patients in severe and life-threatening conditions. However, patient monitoring in the ICU is limited by the time and resource constraints imposed on healthcare providers. Many critical care indices such as mobility are still manually assessed, which can be subjective, prone to human errors, and lack granularity. Other important aspects, such as environmental factors, are not monitored at all. For example, critically ill patients often experience circadian disruptions due to the absence of effective environmental “timekeepers” such as the light/dark cycle and the systemic effect of acute illness on chronobiologic markers. Although the occurrence of delirium is associated with circadian disruption risk factors, these factors are not routinely monitored in the ICU. Hence, there is a critical unmet need to develop systems for precise and real-time assessment through novel enabling technologies. We have developed the mobility and circadian disruption quantification system (Mobi-DiQ) by augmenting biomarker and clinical data with pervasive sensing data to generate mobility and circadian cues related to mobility, nightly disruptions, and light and noise exposure. We hypothesize that Mobi-DiQ can provide accurate mobility and circadian cues that correlate with bedside clinical mobility assessments and circadian biomarkers, ultimately important for delirium risk assessment and prevention. The collected multimodal dataset consists of depth images, Electromyography (EMG) data, patient extremity movement captured by accelerometers, ambient light levels, Sound Pressure Level (SPL), and indoor air quality measured by volatile organic compounds, and the equivalent CO₂ concentration. For delirium risk assessment, the system recognizes mobility cues (axial body movement features and body key points) and circadian cues, including nightly disruptions, ambient SPL, and light intensity, as well as other environmental factors such as indoor air quality. The Mobi-DiQ system consists of three major components: the pervasive sensing system, a data storage and analysis server, and a data annotation system. For data collection, six local pervasive sensing systems were deployed, including a local computer and sensors. A video recording tool with graphical user interface (GUI) developed in python was used to capture depth image frames for analyzing patient mobility. All sensor data is encrypted, then automatically uploaded to the Mobi-DiQ server through a secured VPN connection. Several data pipelines are developed to automate the data transfer, curation, and data preparation for annotation and model training. The data curation and post-processing are performed on the server. A custom secure annotation tool with GUI was developed to annotate depth activity data. The annotation tool is linked to the MongoDB database to record the data annotation and to provide summarization. Docker containers are also utilized to manage services and pipelines running on the server in an isolated manner. The processed clinical data and annotations are used to train and develop real-time pervasive sensing systems to augment clinical decision-making and promote targeted interventions. In the future, we intend to evaluate our system as a clinical implementation trial, as well as to refine and validate it by using other data sources, including neurological data obtained through continuous electroencephalography (EEG).

Keywords: deep learning, delirium, healthcare, pervasive sensing

Procedia PDF Downloads 64

Authors: Pei Yi Lin

Abstract:

Objective: The objective of this study is to use machine learning methods to build an early prediction classifier model for acute delirium to improve the quality of medical care for intensive care patients. Background: Delirium is a common acute and sudden disturbance of consciousness in critically ill patients. After the occurrence, it is easy to prolong the length of hospital stay and increase medical costs and mortality. In 2021, the incidence of delirium in the intensive care unit of internal medicine was as high as 59.78%, which indirectly prolonged the average length of hospital stay by 8.28 days, and the mortality rate is about 2.22% in the past three years. Therefore, it is expected to build a delirium prediction classifier through big data analysis and machine learning methods to detect delirium early. Method: This study is a retrospective study, using the artificial intelligence big data database to extract the characteristic factors related to delirium in intensive care unit patients and let the machine learn. The study included patients aged over 20 years old who were admitted to the intensive care unit between May 1, 2022, and December 31, 2022, excluding GCS assessment <4 points, admission to ICU for less than 24 hours, and CAM-ICU evaluation. The CAMICU delirium assessment results every 8 hours within 30 days of hospitalization are regarded as an event, and the cumulative data from ICU admission to the prediction time point are extracted to predict the possibility of delirium occurring in the next 8 hours, and collect a total of 63,754 research case data, extract 12 feature selections to train the model, including age, sex, average ICU stay hours, visual and auditory abnormalities, RASS assessment score, APACHE-II Score score, number of invasive catheters indwelling, restraint and sedative and hypnotic drugs. Through feature data cleaning, processing and KNN interpolation method supplementation, a total of 54595 research case events were extracted to provide machine learning model analysis, using the research events from May 01 to November 30, 2022, as the model training data, 80% of which is the training set for model training, and 20% for the internal verification of the verification set, and then from December 01 to December 2022 The CU research event on the 31st is an external verification set data, and finally the model inference and performance evaluation are performed, and then the model has trained again by adjusting the model parameters. Results: In this study, XG Boost, Random Forest, Logistic Regression, and Decision Tree were used to analyze and compare four machine learning models. The average accuracy rate of internal verification was highest in Random Forest (AUC=0.86), and the average accuracy rate of external verification was in Random Forest and XG Boost was the highest, AUC was 0.86, and the average accuracy of cross-validation was the highest in Random Forest (ACC=0.77). Conclusion: Clinically, medical staff usually conduct CAM-ICU assessments at the bedside of critically ill patients in clinical practice, but there is a lack of machine learning classification methods to assist ICU patients in real-time assessment, resulting in the inability to provide more objective and continuous monitoring data to assist Clinical staff can more accurately identify and predict the occurrence of delirium in patients. It is hoped that the development and construction of predictive models through machine learning can predict delirium early and immediately, make clinical decisions at the best time, and cooperate with PADIS delirium care measures to provide individualized non-drug interventional care measures to maintain patient safety, and then Improve the quality of care.

Keywords: critically ill patients, machine learning methods, delirium prediction, classifier model

Procedia PDF Downloads 34