Search results for: supervised classifiers
78 Machine Learning in Gravity Models: An Application to International Recycling Trade Flow
Authors: Shan Zhang, Peter Suechting
Abstract:
Predicting trade patterns is critical to decision-making in public and private domains, especially in the current context of trade disputes among major economies. In the past, U.S. recycling has relied heavily on strong demand for recyclable materials overseas. However, starting in 2017, a series of new recycling policies (bans and higher inspection standards) was enacted by multiple countries that were the primary importers of recyclables from the U.S. prior to that point. As the global trade flow of recycling shifts, some new importers, mostly developing countries in South and Southeast Asia, have been overwhelmed by the sheer quantities of scrap materials they have received. As the leading exporter of recyclable materials, the U.S. now has a pressing need to build its recycling industry domestically. With respect to the global trade in scrap materials used for recycling, the interest in this paper is (1) predicting how the export of recyclable materials from the U.S. might vary over time, and (2) predicting how international trade flows for recyclables might change in the future. Focusing on three major recyclable materials with a history of trade, this study uses data-driven and machine learning (ML) algorithms---supervised (shrinkage and tree methods) and unsupervised (neural network method)---to decipher the international trade pattern of recycling. Forecasting the potential trade values of recyclables in the future could help importing countries, to which those materials will shift next, to prepare related trade policies. Such policies can assist policymakers in minimizing negative environmental externalities and in finding the optimal amount of recyclables needed by each country. Such forecasts can also help exporting countries, like the U.S understand the importance of healthy domestic recycling industry. The preliminary result suggests that gravity models---in addition to particular selection macroeconomic predictor variables--are appropriate predictors of the total export value of recyclables. With the inclusion of variables measuring aspects of the political conditions (trade tariffs and bans), predictions show that recyclable materials are shifting from more policy-restricted countries to less policy-restricted countries in international recycling trade. Those countries also tend to have high manufacturing activities as a percentage of their GDP.Keywords: environmental economics, machine learning, recycling, international trade
Procedia PDF Downloads 16077 Educational Sport and Quality of Life for Children and Teenagers from Brazilian Northeast
Authors: Ricardo Hugo Gonzalez, Amanda Figueiredo Vasconcelos, Francisco Loureiro Neto Monteiro, Yara Luiza Freitas Silva, Ana Cristina Lindsay, Márcia Maria Tavares Machado
Abstract:
The use of sport as an integration mean is a very important tool regarding the social involvement of children and teenagers in a vulnerability situation. This study aims to report the experiences of a multidisciplinary program that intends to improve the quality of life of children and teenagers in Fortaleza, in the Northeast of Brazil. More than 400 children and teenagers aging 11 and 16 years participated in this study. Poor communities experience many particular difficulties in the urban centers such as violence, poor housing conditions, unemployment, lack in health care and deficient physical education in school. Physical education, physiotherapy, odontology, medicine and pharmacy students are responsible for the activities in the project supervised by a general coordinator and a counselor teacher of each academic unit. There are classes about team sports like basketball and soccer. Lectures about sexual behavior and sexually transmitted diseases are ministered beside the ones about oral health education, basic life support education, first aids, use and care with pharmaceuticals and orientations about healthy nutrition. In order to get the children’s family closer, monthly informative lectures are ministered. There is also the concern about reflecting the actions and producing academic paperwork such as graduation final projects and books. The number of participants has oscillated lately, and one of the causes is the lack of practicing physical activities and sports regularly. However, 250 teenagers have participated regularly for at least two years. These teenagers have shown a healthier lifestyle and a better physical fitness profile. The resources for maintaining the project come from the Pro-Reitoria of Extension, Federal University of Ceara, as well as from the PROEXT/MEC, Federal Government. Actions of this nature need to be done thinking for long periods so the effects results can become effective. Public and private investments are needed due to low socioeconomic families who are most vulnerable and have fewer opportunities to enhance to health prevention services.Keywords: children and teenagers, health, multidisciplinary program, quality of life
Procedia PDF Downloads 22776 Data Model to Predict Customize Skin Care Product Using Biosensor
Authors: Ashi Gautam, Isha Shukla, Akhil Seghal
Abstract:
Biosensors are analytical devices that use a biological sensing element to detect and measure a specific chemical substance or biomolecule in a sample. These devices are widely used in various fields, including medical diagnostics, environmental monitoring, and food analysis, due to their high specificity, sensitivity, and selectivity. In this research paper, a machine learning model is proposed for predicting the suitability of skin care products based on biosensor readings. The proposed model takes in features extracted from biosensor readings, such as biomarker concentration, skin hydration level, inflammation presence, sensitivity, and free radicals, and outputs the most appropriate skin care product for an individual. This model is trained on a dataset of biosensor readings and corresponding skin care product information. The model's performance is evaluated using several metrics, including accuracy, precision, recall, and F1 score. The aim of this research is to develop a personalised skin care product recommendation system using biosensor data. By leveraging the power of machine learning, the proposed model can accurately predict the most suitable skin care product for an individual based on their biosensor readings. This is particularly useful in the skin care industry, where personalised recommendations can lead to better outcomes for consumers. The developed model is based on supervised learning, which means that it is trained on a labeled dataset of biosensor readings and corresponding skin care product information. The model uses these labeled data to learn patterns and relationships between the biosensor readings and skin care products. Once trained, the model can predict the most suitable skin care product for an individual based on their biosensor readings. The results of this study show that the proposed machine learning model can accurately predict the most appropriate skin care product for an individual based on their biosensor readings. The evaluation metrics used in this study demonstrate the effectiveness of the model in predicting skin care products. This model has significant potential for practical use in the skin care industry for personalised skin care product recommendations. The proposed machine learning model for predicting the suitability of skin care products based on biosensor readings is a promising development in the skin care industry. The model's ability to accurately predict the most appropriate skin care product for an individual based on their biosensor readings can lead to better outcomes for consumers. Further research can be done to improve the model's accuracy and effectiveness.Keywords: biosensors, data model, machine learning, skin care
Procedia PDF Downloads 8475 Reasons to Redesign: Teacher Education for a Brighter Tomorrow
Authors: Deborah L. Smith
Abstract:
To review our program and determine the best redesign options, department members gathered feedback and input through focus groups, analysis of data, and a review of the current research to ensure that the changes proposed were not based solely on the state’s new professional standards. In designing course assignments and assessments, we listened to a variety of constituents, including students, other institutions of higher learning, MDE webinars, host teachers, literacy clinic personnel, and other disciplinary experts. As a result, we are designing a program that is more inclusive of a variety of field experiences for growth. We have determined ways to improve our program by connecting academic disciplinary knowledge, educational psychology, and community building both inside and outside the classroom for professional learning communities. The state’s release of new professional standards led my department members to question what is working and what needs improvement in our program. One aspect of our program that continues to be supported by research and data analysis is the function of supervised field experiences with meaningful feedback. We seek to expand in this area. Other data indicate that we have strengths in modeling a variety of approaches such as cooperative learning, discussions, literacy strategies, and workshops. In the new program, field assignments will be connected to multiple courses, and efforts to scaffold student learning to guide them toward best evidence-based practices will be continuous. Despite running a program that meets multiple sets of standards, there are areas of need that we directly address in our redesign proposal. Technology is ever-changing, so it’s inevitable that improving digital skills is a focus. In addition, scaffolding procedures for English Language Learners (ELL) or other students who struggle is imperative. Diversity, equity, and inclusion (DEI) has been an integral part of our curriculum, but the research indicates that more self-reflection and a deeper understanding of culturally relevant practices would help the program improve. Connections with professional learning communities will be expanded, as will leadership components, so that teacher candidates understand their role in changing the face of education. A pilot program will run in academic year 22/23, and additional data will be collected each semester through evaluations and continued program review.Keywords: DEI, field experiences, program redesign, teacher preparation
Procedia PDF Downloads 15674 Consumer Preferences Concerning Food from Carob: A Survey in Crete, Greece
Authors: Georgios A. Fragkiadakis, Antonia Psaroudaki, Theodora Mouratidou, Eirini Sfakianaki
Abstract:
Research: The nutritional benefits of eating carob are many and important for the human organism, as it is a food rich in carbohydrates and low in fat and contains multiple nutrients, making it a "superfood". Within the framework of the project "Actions for the optimal utilization of the potential of carob in the Region of Crete" which is financed-supervised by the Region of Crete, a second-grade local self-government authority, with the collaboration of the University of Crete and of the Hellenic Mediterranean University, an online survey was carried out with the aim of evaluating dietary habits and views related to the consumption of carob and its products in a sample of local residents. Results and Conclusions: Of the 351 participants, 259 (73.8%) stated that they consume carob products, and 26.2% stated that they do not. Difficult access and limited availability of carob-food products (33.7%), high price (20.7%), and difficulties of use and preparation (15.2%) were cited as the main reasons for non-consumption. Other reasons, to a lesser extent, concern the taste, especially the sweet aftertaste of some products. Concerning the behavior and eating habits related to the consumption of carob products (n=259), 57.9% of the sample report that they buy carob products "sometimes"; 21.2% report "often"; 19.7% report "rarely", and a very small percentage of 1.2% report "constantly". With reference to the reasons for choosing carob products, the participants mention the main reason for their high nutritional value (51.7%), followed by 32.4% of nutritional claims and health claims, and the organoleptic characteristics (10.8%). Other positive factors are the final price of the product, the ease of use, and the respect for the local environment and producers. Some bakery products show the highest percentage of consumption among carob-food consumers, mainly in the form of rusks (86.1%) and breadsticks (70.3%). They are followed, in descending order, by bread (63.3%), toast (52.1%), and flour (50.6%). More specifically: 40.5% consume carob rusks less than once a month; 22% consume less than once a week; up to twice a week 12.4%; 6.6%, consume rusks 3 to 4 times a week, and daily 3.9%. It is worth mentioning that a high percentage of consumers of carob products recommend the consumption to their family and friends. Only a small percentage, in the range of 5%, does not recommend the consumption of carob products in their close family/social circle. The main motivating factors for the consumption of carob products are the expected effects they may have on health (74.1%) and the organoleptic characteristics with a percentage of 21.6%.Keywords: food, consumer, preferences, carob, Crete, Greece
Procedia PDF Downloads 5873 Predictive Modelling of Aircraft Component Replacement Using Imbalanced Learning and Ensemble Method
Authors: Dangut Maren David, Skaf Zakwan
Abstract:
Adequate monitoring of vehicle component in other to obtain high uptime is the goal of predictive maintenance, the major challenge faced by businesses in industries is the significant cost associated with a delay in service delivery due to system downtime. Most of those businesses are interested in predicting those problems and proactively prevent them in advance before it occurs, which is the core advantage of Prognostic Health Management (PHM) application. The recent emergence of industry 4.0 or industrial internet of things (IIoT) has led to the need for monitoring systems activities and enhancing system-to-system or component-to- component interactions, this has resulted to a large generation of data known as big data. Analysis of big data represents an increasingly important, however, due to complexity inherently in the dataset such as imbalance classification problems, it becomes extremely difficult to build a model with accurate high precision. Data-driven predictive modeling for condition-based maintenance (CBM) has recently drowned research interest with growing attention to both academics and industries. The large data generated from industrial process inherently comes with a different degree of complexity which posed a challenge for analytics. Thus, imbalance classification problem exists perversely in industrial datasets which can affect the performance of learning algorithms yielding to poor classifier accuracy in model development. Misclassification of faults can result in unplanned breakdown leading economic loss. In this paper, an advanced approach for handling imbalance classification problem is proposed and then a prognostic model for predicting aircraft component replacement is developed to predict component replacement in advanced by exploring aircraft historical data, the approached is based on hybrid ensemble-based method which improves the prediction of the minority class during learning, we also investigate the impact of our approach on multiclass imbalance problem. We validate the feasibility and effectiveness in terms of the performance of our approach using real-world aircraft operation and maintenance datasets, which spans over 7 years. Our approach shows better performance compared to other similar approaches. We also validate our approach strength for handling multiclass imbalanced dataset, our results also show good performance compared to other based classifiers.Keywords: prognostics, data-driven, imbalance classification, deep learning
Procedia PDF Downloads 16272 DTI Connectome Changes in the Acute Phase of Aneurysmal Subarachnoid Hemorrhage Improve Outcome Classification
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 18071 Modernization of Translation Studies Curriculum at Higher Education Level in Armenia
Authors: A. Vahanyan
Abstract:
The paper touches upon the problem of revision and modernization of the current curriculum on translation studies at the Armenian Higher Education Institutions (HEIs). In the contemporary world where quality and speed of services provided are mostly valued, certain higher education centers in Armenia though do not demonstrate enough flexibility in terms of the revision and amendment of courses taught. This issue is present for various curricula at the university level and Translation Studies related curriculum, in particular. Technological innovations that are of great help for translators have been long ago smoothly implemented into the global Translation Industry. According to the European Master's in Translation (EMT) framework, translation service provision comprises linguistic, intercultural, information mining, thematic, and technological competencies. Therefore, to form the competencies mentioned above, the curriculum should be seriously restructured to meet the modern education and job market requirements, relevant courses should be proposed. New courses, in particular, should focus on the formation of technological competences. These suggestions have been made upon the author’s research of the problem across various HEIs in Armenia. The updated curricula should include courses aimed at familiarization with various computer-assisted translation (CAT) tools (MemoQ, Trados, OmegaT, Wordfast, etc.) in the translation process, creation of glossaries and termbases compatible with different platforms), which will ensure consistency in translation of similar texts and speeding up the translation process itself. Another aspect that may be strengthened via curriculum modification is the introduction of interdisciplinary and Project-Based Learning courses, which will enable info mining and thematic competences, which are of great importance as well. Of course, the amendment of the existing curriculum with the mentioned courses will require corresponding faculty development via training, workshops, and seminars. Finally, the provision of extensive internship with translation agencies is strongly recommended as it will ensure the synthesis of theoretical background and practical skills highly required for the specific area. Summing up, restructuring and modernization of the existing curricula on Translation Studies should focus on three major aspects, i.e., introduction of new courses that meet the global quality standards of education, professional development for faculty, and integration of extensive internship supervised by experts in the field.Keywords: competencies, curriculum, modernization, technical literacy, translation studies
Procedia PDF Downloads 12470 Sensitivity and Commitment: A View on Parenthood in a Context of Placement Trajectory
Authors: A. De Serres-Lafontaine, S. Porlier, K. Poitras
Abstract:
Introduction: Placement is, without doubt, a challenging experience for both foster children and biological parents who witness their child being removed from their care. Yet, few studies have examined parenting in such a context through critical parental skills such as parental sensitivity and commitment. Sensitivity is described as the capacity of parents to respond accurately to their child’s needs in a warm, predictable and consistent way, whereas commitment is the ability of the parent to get involved physically and emotionally in an enduring relationship with his child. The research confirms the important role of parental sensitivity and parental commitment on child development following placement in foster care. Nevertheless, these studies were mainly conducted with foster parents, and few studies have examined these components of parenthood with biological parents. Method: This study evolves in two times. At first, 17 parents participated throughout a 90-minutes interview. It allowed to collect information regarding the sociodemographic situation, contacts, placement trajectory. Parental sensitivity is observed during a supervised parent-child contact. The second time occurred one to two years later and implied an at-home 90-minutes interview where we updated the information from the first interview and were able to assess the level of parental commitment. In this ongoing part of the study, five parents have already participated in implying the rest of them remain to be interviewed in the coming months - from October through December 2018. Results: Descriptive analysis from the first part of the study suggests the examination of two groups: 11 children have been reunified whereas six are still in foster care. Qualitative analysis allows to compare themes of sensitivity and commitment regarding if the reunification project occurs or not. Preliminary analysis about thematic content shows key components of parental commitment through parent’s reveal of the way they nurture a relationship with their child. Furthermore, preliminary analysis suggests that parental sensitivity is not associated with family reunification (r = 0,11, p = 0,74). Further analysis will be assessed with the date from the second part of the study to examine the potential association between commitment and reunification. Discussion: Parental sensitivity and commitment are fundamental to the well-being of the child in a placement trajectory. They need to be understood better as two different complex concepts and as two parenting skills that might have a way of echoing to one another when engaged in a specific context. Above all, a more accurate comprehension of parenting in a placement trajectory allows to sustain adequate intervention practices for birth parents and could change the way parental adequacy is assessed when reaching for reunification.Keywords: child welfare, foster care, intervention practices, parenthood
Procedia PDF Downloads 16969 Predicting Daily Patient Hospital Visits Using Machine Learning
Authors: Shreya Goyal
Abstract:
The study aims to build user-friendly software to understand patient arrival patterns and compute the number of potential patients who will visit a particular health facility for a given period by using a machine learning algorithm. The underlying machine learning algorithm used in this study is the Support Vector Machine (SVM). Accurate prediction of patient arrival allows hospitals to operate more effectively, providing timely and efficient care while optimizing resources and improving patient experience. It allows for better allocation of staff, equipment, and other resources. If there's a projected surge in patients, additional staff or resources can be allocated to handle the influx, preventing bottlenecks or delays in care. Understanding patient arrival patterns can also help streamline processes to minimize waiting times for patients and ensure timely access to care for patients in need. Another big advantage of using this software is adhering to strict data protection regulations such as the Health Insurance Portability and Accountability Act (HIPAA) in the United States as the hospital will not have to share the data with any third party or upload it to the cloud because the software can read data locally from the machine. The data needs to be arranged in. a particular format and the software will be able to read the data and provide meaningful output. Using software that operates locally can facilitate compliance with these regulations by minimizing data exposure. Keeping patient data within the hospital's local systems reduces the risk of unauthorized access or breaches associated with transmitting data over networks or storing it in external servers. This can help maintain the confidentiality and integrity of sensitive patient information. Historical patient data is used in this study. The input variables used to train the model include patient age, time of day, day of the week, seasonal variations, and local events. The algorithm uses a Supervised learning method to optimize the objective function and find the global minima. The algorithm stores the values of the local minima after each iteration and at the end compares all the local minima to find the global minima. The strength of this study is the transfer function used to calculate the number of patients. The model has an output accuracy of >95%. The method proposed in this study could be used for better management planning of personnel and medical resources.Keywords: machine learning, SVM, HIPAA, data
Procedia PDF Downloads 5768 Comparing Deep Architectures for Selecting Optimal Machine Translation
Authors: Despoina Mouratidis, Katia Lida Kermanidis
Abstract:
Machine translation (MT) is a very important task in Natural Language Processing (NLP). MT evaluation is crucial in MT development, as it constitutes the means to assess the success of an MT system, and also helps improve its performance. Several methods have been proposed for the evaluation of (MT) systems. Some of the most popular ones in automatic MT evaluation are score-based, such as the BLEU score, and others are based on lexical similarity or syntactic similarity between the MT outputs and the reference involving higher-level information like part of speech tagging (POS). This paper presents a language-independent machine learning framework for classifying pairwise translations. This framework uses vector representations of two machine-produced translations, one from a statistical machine translation model (SMT) and one from a neural machine translation model (NMT). The vector representations consist of automatically extracted word embeddings and string-like language-independent features. These vector representations used as an input to a multi-layer neural network (NN) that models the similarity between each MT output and the reference, as well as between the two MT outputs. To evaluate the proposed approach, a professional translation and a "ground-truth" annotation are used. The parallel corpora used are English-Greek (EN-GR) and English-Italian (EN-IT), in the educational domain and of informal genres (video lecture subtitles, course forum text, etc.) that are difficult to be reliably translated. They have tested three basic deep learning (DL) architectures to this schema: (i) fully-connected dense, (ii) Convolutional Neural Network (CNN), and (iii) Long Short-Term Memory (LSTM). Experiments show that all tested architectures achieved better results when compared against those of some of the well-known basic approaches, such as Random Forest (RF) and Support Vector Machine (SVM). Better accuracy results are obtained when LSTM layers are used in our schema. In terms of a balance between the results, better accuracy results are obtained when dense layers are used. The reason for this is that the model correctly classifies more sentences of the minority class (SMT). For a more integrated analysis of the accuracy results, a qualitative linguistic analysis is carried out. In this context, problems have been identified about some figures of speech, as the metaphors, or about certain linguistic phenomena, such as per etymology: paronyms. It is quite interesting to find out why all the classifiers led to worse accuracy results in Italian as compared to Greek, taking into account that the linguistic features employed are language independent.Keywords: machine learning, machine translation evaluation, neural network architecture, pairwise classification
Procedia PDF Downloads 11767 The Application of Video Segmentation Methods for the Purpose of Action Detection in Videos
Authors: Nassima Noufail, Sara Bouhali
Abstract:
In this work, we develop a semi-supervised solution for the purpose of action detection in videos and propose an efficient algorithm for video segmentation. The approach is divided into video segmentation, feature extraction, and classification. In the first part, a video is segmented into clips, and we used the K-means algorithm for this segmentation; our goal is to find groups based on similarity in the video. The application of k-means clustering into all the frames is time-consuming; therefore, we started by the identification of transition frames where the scene in the video changes significantly, and then we applied K-means clustering into these transition frames. We used two image filters, the gaussian filter and the Laplacian of Gaussian. Each filter extracts a set of features from the frames. The Gaussian filter blurs the image and omits the higher frequencies, and the Laplacian of gaussian detects regions of rapid intensity changes; we then used this vector of filter responses as an input to our k-means algorithm. The output is a set of cluster centers. Each video frame pixel is then mapped to the nearest cluster center and painted with a corresponding color to form a visual map. The resulting visual map had similar pixels grouped. We then computed a cluster score indicating how clusters are near each other and plotted a signal representing frame number vs. clustering score. Our hypothesis was that the evolution of the signal would not change if semantically related events were happening in the scene. We marked the breakpoints at which the root mean square level of the signal changes significantly, and each breakpoint is an indication of the beginning of a new video segment. In the second part, for each segment from part 1, we randomly selected a 16-frame clip, then we extracted spatiotemporal features using convolutional 3D network C3D for every 16 frames using a pre-trained model. The C3D final output is a 512-feature vector dimension; hence we used principal component analysis (PCA) for dimensionality reduction. The final part is the classification. The C3D feature vectors are used as input to a multi-class linear support vector machine (SVM) for the training model, and we used a multi-classifier to detect the action. We evaluated our experiment on the UCF101 dataset, which consists of 101 human action categories, and we achieved an accuracy that outperforms the state of art by 1.2%.Keywords: video segmentation, action detection, classification, Kmeans, C3D
Procedia PDF Downloads 6766 Air Handling Units Power Consumption Using Generalized Additive Model for Anomaly Detection: A Case Study in a Singapore Campus
Authors: Ju Peng Poh, Jun Yu Charles Lee, Jonathan Chew Hoe Khoo
Abstract:
The emergence of digital twin technology, a digital replica of physical world, has improved the real-time access to data from sensors about the performance of buildings. This digital transformation has opened up many opportunities to improve the management of the building by using the data collected to help monitor consumption patterns and energy leakages. One example is the integration of predictive models for anomaly detection. In this paper, we use the GAM (Generalised Additive Model) for the anomaly detection of Air Handling Units (AHU) power consumption pattern. There is ample research work on the use of GAM for the prediction of power consumption at the office building and nation-wide level. However, there is limited illustration of its anomaly detection capabilities, prescriptive analytics case study, and its integration with the latest development of digital twin technology. In this paper, we applied the general GAM modelling framework on the historical data of the AHU power consumption and cooling load of the building between Jan 2018 to Aug 2019 from an education campus in Singapore to train prediction models that, in turn, yield predicted values and ranges. The historical data are seamlessly extracted from the digital twin for modelling purposes. We enhanced the utility of the GAM model by using it to power a real-time anomaly detection system based on the forward predicted ranges. The magnitude of deviation from the upper and lower bounds of the uncertainty intervals is used to inform and identify anomalous data points, all based on historical data, without explicit intervention from domain experts. Notwithstanding, the domain expert fits in through an optional feedback loop through which iterative data cleansing is performed. After an anomalously high or low level of power consumption detected, a set of rule-based conditions are evaluated in real-time to help determine the next course of action for the facilities manager. The performance of GAM is then compared with other approaches to evaluate its effectiveness. Lastly, we discuss the successfully deployment of this approach for the detection of anomalous power consumption pattern and illustrated with real-world use cases.Keywords: anomaly detection, digital twin, generalised additive model, GAM, power consumption, supervised learning
Procedia PDF Downloads 14265 Creatine Associated with Resistance Training Increases Muscle Mass in the Elderly
Authors: Camila Lemos Pinto, Juliana Alves Carneiro, Patrícia Borges Botelho, João Felipe Mota
Abstract:
Sarcopenia, a syndrome characterized by progressive and generalized loss of skeletal muscle mass and strength, currently affects over 50 million people and increases the risk of adverse outcomes such as physical disability, poor quality of life and death. The aim of this study was to examine the efficacy of creatine supplementation associated with resistance training on muscle mass in the elderly. A 12-week, double blind, randomized, parallel group, placebo controlled trial was conducted. Participants were randomly allocated into one of the following groups: placebo with resistance training (PL+RT, n=14) and creatine supplementation with resistance training (CR + RT, n=13). The subjects from CR+RT group received 5 g/day of creatine monohydrate and the subjects from the PL+RT group were given the same dose of maltodextrin. Participants were instructed to ingest the supplement on non-training days immediately after lunch and on training days immediately after resistance training sessions dissolved in a beverage comprising 100 g of maltodextrin lemon flavored. Participants of both groups undertook a supervised exercise training program for 12 weeks (3 times per week). The subjects were assessed at baseline and after 12 weeks. The primary outcome was muscle mass, assessed by dual energy X-ray absorptiometry (DXA). The secondary outcome included diagnose participants with one of the three stages of sarcopenia (presarcopenia, sarcopenia and severe sarcopenia) by skeletal muscle mass index (SMI), handgrip strength and gait speed. CR+RT group had a significant increase in SMI and muscle (p<0.0001), a significant decrease in android and gynoid fat (p = 0.028 and p=0.035, respectively) and a tendency of decreasing in body fat (p=0.053) after the intervention. PL+RT only had a significant increase in SMI (p=0.007). The main finding of this clinical trial indicated that creatine supplementation combined with resistance training was capable of increasing muscle mass in our elderly cohort (p=0.02). In addition, the number of subjects diagnosed with one of the three stages of sarcopenia at baseline decreased in the creatine supplemented group in comparison with the placebo group (CR+RT, n=-3; PL+RT, n=0). In summary, 12 weeks of creatine supplementation associated with resistance training resulted in increases in muscle mass. This is the first research with elderly of both sexes that show the same increase in muscle mass with a minor quantity of creatine supplementation in a short period. Future long-term research should investigate the effects of these interventions in sarcopenic elderly.Keywords: creatine, dietetic supplement, elderly, resistance training
Procedia PDF Downloads 46764 High Altitude Glacier Surface Mapping in Dhauliganga Basin of Himalayan Environment Using Remote Sensing Technique
Authors: Aayushi Pandey, Manoj Kumar Pandey, Ashutosh Tiwari, Kireet Kumar
Abstract:
Glaciers play an important role in climate change and are sensitive phenomena of global climate change scenario. Glaciers in Himalayas are unique as they are predominantly valley type and are located in tropical, high altitude regions. These glaciers are often covered with debris which greatly affects ablation rate of glaciers and work as a sensitive indicator of glacier health. The aim of this study is to map high altitude Glacier surface with a focus on glacial lake and debris estimation using different techniques in Nagling glacier of dhauliganga basin in Himalayan region. Different Image Classification techniques i.e. thresholding on different band ratios and supervised classification using maximum likelihood classifier (MLC) have been used on high resolution sentinel 2A level 1c satellite imagery of 14 October 2017.Here Near Infrared (NIR)/Shortwave Infrared (SWIR) ratio image was used to extract the glaciated classes (Snow, Ice, Ice Mixed Debris) from other non-glaciated terrain classes. SWIR/BLUE Ratio Image was used to map valley rock and Debris while Green/NIR ratio image was found most suitable for mapping Glacial Lake. Accuracy assessment was performed using high resolution (3 meters) Planetscope Imagery using 60 stratified random points. The overall accuracy of MLC was 85 % while the accuracy of Band Ratios was 96.66 %. According to Band Ratio technique total areal extent of glaciated classes (Snow, Ice ,IMD) in Nagling glacier was 10.70 km2 nearly 38.07% of study area comprising of 30.87 % Snow covered area, 3.93% Ice and 3.27 % IMD covered area. Non-glaciated classes (vegetation, glacial lake, debris and valley rock) covered 61.93 % of the total area out of which valley rock is dominant with 33.83% coverage followed by debris covering 27.7 % of the area in nagling glacier. Glacial lake and Debris were accurately mapped using Band ratio technique Hence, Band Ratio approach appears to be useful for the mapping of debris covered glacier in Himalayan Region.Keywords: band ratio, Dhauliganga basin, glacier mapping, Himalayan region, maximum likelihood classifier (MLC), Sentinel-2 satellite image
Procedia PDF Downloads 21963 Land Cover Mapping Using Sentinel-2, Landsat-8 Satellite Images, and Google Earth Engine: A Study Case of the Beterou Catchment
Authors: Ella Sèdé Maforikan
Abstract:
Accurate land cover mapping is essential for effective environmental monitoring and natural resources management. This study focuses on assessing the classification performance of two satellite datasets and evaluating the impact of different input feature combinations on classification accuracy in the Beterou catchment, situated in the northern part of Benin. Landsat-8 and Sentinel-2 images from June 1, 2020, to March 31, 2021, were utilized. Employing the Random Forest (RF) algorithm on Google Earth Engine (GEE), a supervised classification categorized the land into five classes: forest, savannas, cropland, settlement, and water bodies. GEE was chosen due to its high-performance computing capabilities, mitigating computational burdens associated with traditional land cover classification methods. By eliminating the need for individual satellite image downloads and providing access to an extensive archive of remote sensing data, GEE facilitated efficient model training on remote sensing data. The study achieved commendable overall accuracy (OA), ranging from 84% to 85%, even without incorporating spectral indices and terrain metrics into the model. Notably, the inclusion of additional input sources, specifically terrain features like slope and elevation, enhanced classification accuracy. The highest accuracy was achieved with Sentinel-2 (OA = 91%, Kappa = 0.88), slightly surpassing Landsat-8 (OA = 90%, Kappa = 0.87). This underscores the significance of combining diverse input sources for optimal accuracy in land cover mapping. The methodology presented herein not only enables the creation of precise, expeditious land cover maps but also demonstrates the prowess of cloud computing through GEE for large-scale land cover mapping with remarkable accuracy. The study emphasizes the synergy of different input sources to achieve superior accuracy. As a future recommendation, the application of Light Detection and Ranging (LiDAR) technology is proposed to enhance vegetation type differentiation in the Beterou catchment. Additionally, a cross-comparison between Sentinel-2 and Landsat-8 for assessing long-term land cover changes is suggested.Keywords: land cover mapping, Google Earth Engine, random forest, Beterou catchment
Procedia PDF Downloads 5362 Urban Heat Island Intensity Assessment through Comparative Study on Land Surface Temperature and Normalized Difference Vegetation Index: A Case Study of Chittagong, Bangladesh
Authors: Tausif A. Ishtiaque, Zarrin T. Tasin, Kazi S. Akter
Abstract:
Current trend of urban expansion, especially in the developing countries has caused significant changes in land cover, which is generating great concern due to its widespread environmental degradation. Energy consumption of the cities is also increasing with the aggravated heat island effect. Distribution of land surface temperature (LST) is one of the most significant climatic parameters affected by urban land cover change. Recent increasing trend of LST is causing elevated temperature profile of the built up area with less vegetative cover. Gradual change in land cover, especially decrease in vegetative cover is enhancing the Urban Heat Island (UHI) effect in the developing cities around the world. Increase in the amount of urban vegetation cover can be a useful solution for the reduction of UHI intensity. LST and Normalized Difference Vegetation Index (NDVI) have widely been accepted as reliable indicators of UHI and vegetation abundance respectively. Chittagong, the second largest city of Bangladesh, has been a growth center due to rapid urbanization over the last several decades. This study assesses the intensity of UHI in Chittagong city by analyzing the relationship between LST and NDVI based on the type of land use/land cover (LULC) in the study area applying an integrated approach of Geographic Information System (GIS), remote sensing (RS), and regression analysis. Land cover map is prepared through an interactive supervised classification using remotely sensed data from Landsat ETM+ image along with NDVI differencing using ArcGIS. LST and NDVI values are extracted from the same image. The regression analysis between LST and NDVI indicates that within the study area, UHI is directly correlated with LST while negatively correlated with NDVI. It interprets that surface temperature reduces with increase in vegetation cover along with reduction in UHI intensity. Moreover, there are noticeable differences in the relationship between LST and NDVI based on the type of LULC. In other words, depending on the type of land usage, increase in vegetation cover has a varying impact on the UHI intensity. This analysis will contribute to the formulation of sustainable urban land use planning decisions as well as suggesting suitable actions for mitigation of UHI intensity within the study area.Keywords: land cover change, land surface temperature, normalized difference vegetation index, urban heat island
Procedia PDF Downloads 26761 Modeling Floodplain Vegetation Response to Groundwater Variability Using ArcSWAT Hydrological Model, Moderate Resolution Imaging Spectroradiometer - Normalised Difference Vegetation Index Data, and Machine Learning
Authors: Newton Muhury, Armando A. Apan, Tek Maraseni
Abstract:
This study modelled the relationships between vegetation response and available water below the soil surface using the Terra’s Moderate Resolution Imaging Spectroradiometer (MODIS) generated Normalised Difference Vegetation Index (NDVI) and soil water content (SWC) data. The Soil & Water Assessment Tool (SWAT) interface known as ArcSWAT was used in ArcGIS for the groundwater analysis. The SWAT model was calibrated and validated in SWAT-CUP software using 10 years (2001-2010) of monthly streamflow data. The average Nash-Sutcliffe Efficiency during the calibration and validation was 0.54 and 0.51, respectively, indicating that the model performances were good. Twenty years (2001-2020) of monthly MODIS NDVI data for three different types of vegetation (forest, shrub, and grass) and soil water content for 43 sub-basins were analysed using the WEKA, machine learning tool with a selection of two supervised machine learning algorithms, i.e., support vector machine (SVM) and random forest (RF). The modelling results show that different types of vegetation response and soil water content vary in the dry and wet season. For example, the model generated high positive relationships (r=0.76, 0.73, and 0.81) between the measured and predicted NDVI values of all vegetation in the study area against the groundwater flow (GW), soil water content (SWC), and the combination of these two variables, respectively, during the dry season. However, these relationships were reduced by 36.8% (r=0.48) and 13.6% (r=0.63) against GW and SWC, respectively, in the wet season. On the other hand, the model predicted a moderate positive relationship (r=0.63) between shrub vegetation type and soil water content during the dry season, which was reduced by 31.7% (r=0.43) during the wet season. Our models also predicted that vegetation in the top location (upper part) of the sub-basin is highly responsive to GW and SWC (r=0.78, and 0.70) during the dry season. The results of this study indicate the study region is suitable for seasonal crop production in dry season. Moreover, the results predicted that the growth of vegetation in the top-point location is highly dependent on groundwater flow in both dry and wet seasons, and any instability or long-term drought can negatively affect these floodplain vegetation communities. This study has enriched our knowledge of vegetation responses to groundwater in each season, which will facilitate better floodplain vegetation management.Keywords: ArcSWAT, machine learning, floodplain vegetation, MODIS NDVI, groundwater
Procedia PDF Downloads 10560 Dimensionality Reduction in Modal Analysis for Structural Health Monitoring
Authors: Elia Favarelli, Enrico Testi, Andrea Giorgetti
Abstract:
Autonomous structural health monitoring (SHM) of many structures and bridges became a topic of paramount importance for maintenance purposes and safety reasons. This paper proposes a set of machine learning (ML) tools to perform automatic feature selection and detection of anomalies in a bridge from vibrational data and compare different feature extraction schemes to increase the accuracy and reduce the amount of data collected. As a case study, the Z-24 bridge is considered because of the extensive database of accelerometric data in both standard and damaged conditions. The proposed framework starts from the first four fundamental frequencies extracted through operational modal analysis (OMA) and clustering, followed by density-based time-domain filtering (tracking). The fundamental frequencies extracted are then fed to a dimensionality reduction block implemented through two different approaches: feature selection (intelligent multiplexer) that tries to estimate the most reliable frequencies based on the evaluation of some statistical features (i.e., mean value, variance, kurtosis), and feature extraction (auto-associative neural network (ANN)) that combine the fundamental frequencies to extract new damage sensitive features in a low dimensional feature space. Finally, one class classifier (OCC) algorithms perform anomaly detection, trained with standard condition points, and tested with normal and anomaly ones. In particular, a new anomaly detector strategy is proposed, namely one class classifier neural network two (OCCNN2), which exploit the classification capability of standard classifiers in an anomaly detection problem, finding the standard class (the boundary of the features space in normal operating conditions) through a two-step approach: coarse and fine boundary estimation. The coarse estimation uses classics OCC techniques, while the fine estimation is performed through a feedforward neural network (NN) trained that exploits the boundaries estimated in the coarse step. The detection algorithms vare then compared with known methods based on principal component analysis (PCA), kernel principal component analysis (KPCA), and auto-associative neural network (ANN). In many cases, the proposed solution increases the performance with respect to the standard OCC algorithms in terms of F1 score and accuracy. In particular, by evaluating the correct features, the anomaly can be detected with accuracy and an F1 score greater than 96% with the proposed method.Keywords: anomaly detection, frequencies selection, modal analysis, neural network, sensor network, structural health monitoring, vibration measurement
Procedia PDF Downloads 11859 An Adaptive Oversampling Technique for Imbalanced Datasets
Authors: Shaukat Ali Shahee, Usha Ananthakumar
Abstract:
A data set exhibits class imbalance problem when one class has very few examples compared to the other class, and this is also referred to as between class imbalance. The traditional classifiers fail to classify the minority class examples correctly due to its bias towards the majority class. Apart from between-class imbalance, imbalance within classes where classes are composed of a different number of sub-clusters with these sub-clusters containing different number of examples also deteriorates the performance of the classifier. Previously, many methods have been proposed for handling imbalanced dataset problem. These methods can be classified into four categories: data preprocessing, algorithmic based, cost-based methods and ensemble of classifier. Data preprocessing techniques have shown great potential as they attempt to improve data distribution rather than the classifier. Data preprocessing technique handles class imbalance either by increasing the minority class examples or by decreasing the majority class examples. Decreasing the majority class examples lead to loss of information and also when minority class has an absolute rarity, removing the majority class examples is generally not recommended. Existing methods available for handling class imbalance do not address both between-class imbalance and within-class imbalance simultaneously. In this paper, we propose a method that handles between class imbalance and within class imbalance simultaneously for binary classification problem. Removing between class imbalance and within class imbalance simultaneously eliminates the biases of the classifier towards bigger sub-clusters by minimizing the error domination of bigger sub-clusters in total error. The proposed method uses model-based clustering to find the presence of sub-clusters or sub-concepts in the dataset. The number of examples oversampled among the sub-clusters is determined based on the complexity of sub-clusters. The method also takes into consideration the scatter of the data in the feature space and also adaptively copes up with unseen test data using Lowner-John ellipsoid for increasing the accuracy of the classifier. In this study, neural network is being used as this is one such classifier where the total error is minimized and removing the between-class imbalance and within class imbalance simultaneously help the classifier in giving equal weight to all the sub-clusters irrespective of the classes. The proposed method is validated on 9 publicly available data sets and compared with three existing oversampling techniques that rely on the spatial location of minority class examples in the euclidean feature space. The experimental results show the proposed method to be statistically significantly superior to other methods in terms of various accuracy measures. Thus the proposed method can serve as a good alternative to handle various problem domains like credit scoring, customer churn prediction, financial distress, etc., that typically involve imbalanced data sets.Keywords: classification, imbalanced dataset, Lowner-John ellipsoid, model based clustering, oversampling
Procedia PDF Downloads 40858 Assessment of Agricultural Land Use Land Cover, Land Surface Temperature and Population Changes Using Remote Sensing and GIS: Southwest Part of Marmara Sea, Turkey
Authors: Melis Inalpulat, Levent Genc
Abstract:
Land Use Land Cover (LULC) changes due to human activities and natural causes have become a major environmental concern. Assessment of temporal remote sensing data provides information about LULC impacts on environment. Land Surface Temperature (LST) is one of the important components for modeling environmental changes in climatological, hydrological, and agricultural studies. In this study, LULC changes (September 7, 1984 and July 8, 2014) especially in agricultural lands together with population changes (1985-2014) and LST status were investigated using remotely sensed and census data in South Marmara Watershed, Turkey. LULC changes were determined using Landsat TM and Landsat OLI data acquired in 1984 and 2014 summers. Six-band TM and OLI images were classified using supervised classification method to prepare LULC map including five classes including Forest (F), Grazing Land (G), Agricultural Land (A), Water Surface (W), and Residential Area-Bare Soil (R-B) classes. The LST image was also derived from thermal bands of the same dates. LULC classification results showed that forest areas, agricultural lands, water surfaces and residential area-bare soils were increased as 65751 ha, 20163 ha, 1924 ha and 20462 ha respectively. In comparison, a dramatic decrement occurred in grazing land (107985 ha) within three decades. The population increased % 29 between years 1984-2014 in whole study area. Along with the natural causes, migration also caused this increase since the study area has an important employment potential. LULC was transformed among the classes due to the expansion in residential, commercial and industrial areas as well as political decisions. In the study, results showed that agricultural lands around the settlement areas transformed to residential areas in 30 years. The LST images showed that mean temperatures were ranged between 26-32 °C in 1984 and 27-33 °C in 2014. Minimum temperature of agricultural lands was increased 3 °C and reached to 23 °C. In contrast, maximum temperature of A class decreased to 41 °C from 44 °C. Considering temperatures of the 2014 R-B class and 1984 status of same areas, it was seen that mean, min and max temperatures increased by 2 °C. As a result, the dynamism of population, LULC and LST resulted in increasing mean and maximum surface temperatures, living spaces/industrial areas and agricultural lands.Keywords: census data, landsat, land surface temperature (LST), land use land cover (LULC)
Procedia PDF Downloads 38357 Adaptation of Extra Early Maize 'Zea Mays L.' Varieties for Climate Change Mitigation in South Western Nigeria
Authors: Akinwumi Omotayo, Badu-B Apraku, Joseph Olobasola, Petra Abdul Saghir, Yinka Sobowale
Abstract:
In southwestern Nigeria, climate change has led to loss of at least two months of rainfall. Consequently, only one cycle of maize can now be grown because of the shorter duration of rainy season as against two cycles in the past. The Early and Extra-early maturing varieties of maize were originally developed for the semi-arid and arid zones of West and Central Africa where there are seasonal challenges of water threatening optimum performance of the traditional maize grown, which are commonly late in maturity (115 to 120 days). The early varieties of maize mature in 90 to 95 days; while the Extra-Early maize varieties reach physiological maturity in less than 90 days. It was broadly hypothesized that the extra early varieties of maize could mitigate the effects of climate change in southwestern Nigeria with higher levels of rainfall by reinstating the original two cycles of rain-fed maize crop. Trials were therefore carried out in southwestern Nigeria on the possibility of adapting the extra early maize to mitigate the effects of climate change. The trial was the Mother/Baby design. The mother trial involves the evaluation of extra-early varieties following ideal recommendations and closely supervised centrally at the University research farm and the Agricultural Development Programmes (ADPs). This requires farmers to observe and evaluate the technology and the management regime meant to precede the second stage of evaluation at several satellite farmers field managed by selected farmers. The Baby Trial is expected to provide a realistic assessment of the technology by farmers in their own environment. A stratified selection of thirty farmers for the Baby Trial ensured appropriate representation across the different categories of the farming population by age and gender. Data from the trials indicate that extra early maize can be grown in two cycles rain fed in south west Nigeria and a third and fourth cycle could be obtained with irrigation. However the long duration varieties outyielded the extra early maize in both the mother and baby trials. When harvested green, the extra early maize served as source of food between March and May when there was scarcity of food. This represents a major advantage. The study recommends that further work needs to be done to improve the yield of extra early maize to encourage farmers to adopt.Keywords: adaptation, climate change, extra early, maize varieties, mitigation
Procedia PDF Downloads 18856 Analyzing Growth Trends of the Built Area in the Precincts of Various Types of Tourist Attractions in India: 2D and 3D Analysis
Authors: Yarra Sulina, Nunna Tagore Sai Priya, Ankhi Banerjee
Abstract:
With the rapid growth in tourist arrivals, there has been a huge demand for the growth of infrastructure in the destinations. With the increasing preference of tourists to stay near attractions, there has been a considerable change in the land use around tourist sites. However, with the inclusion of certain regulations and guidelines provided by the authorities based on the nature of tourism activity and geographical constraints, the pattern of growth of built form is different for various tourist sites. Therefore, this study explores the patterns of growth of built-up for a decade from 2009 to 2019 through two-dimensional and three-dimensional analysis. Land use maps are created through supervised classification of satellite images obtained from LANDSAT 4-5 and LANDSAT 8 for 2009 and 2019, respectively. The overall expansion of the built-up area in the region is analyzed in relation to the distance from the city's geographical center and the tourism-related growth regions are identified which are influenced by the proximity of tourist attractions. The primary tourist sites of various destinations with different geographical characteristics and tourism activities, that have undergone a significant increase in built-up area and are occupied with tourism-related infrastructure are selected for further study. Proximity analysis of the tourism-related growth sites is carried out to delineate the influence zone of the tourist site in a destination. Further, a temporal analysis of volumetric growth of built form is carried out to understand the morphology of the tourist precincts over time. The Digital Surface Model (DSM) and Digital Terrain Model (DTM) are used to extract the building footprints along with building height. Factors such as building height, and building density are evaluated to understand the patterns of three-dimensional growth of the built area in the region. The study also explores the underlying reasons for such changes in built form around various tourist sites and predicts the impact of such growth patterns in the region. The building height and building density around tourist site creates a huge impact on the appeal of the destination. The surroundings that are incompatible with the theme of the tourist site have a negative impact on the attractiveness of the destination that leads to negative feedback by the tourists, which is not a sustainable form of development. Therefore, proper spatial measures are necessary in terms of area and volume of the built environment for a healthy and sustainable environment around the tourist sites in the destination.Keywords: sustainable tourism, growth patterns, land-use changes, 3-dimensional analysis of built-up area
Procedia PDF Downloads 7155 Optimized Deep Learning-Based Facial Emotion Recognition System
Authors: Erick C. Valverde, Wansu Lim
Abstract:
Facial emotion recognition (FER) system has been recently developed for more advanced computer vision applications. The ability to identify human emotions would enable smart healthcare facility to diagnose mental health illnesses (e.g., depression and stress) as well as better human social interactions with smart technologies. The FER system involves two steps: 1) face detection task and 2) facial emotion recognition task. It classifies the human expression in various categories such as angry, disgust, fear, happy, sad, surprise, and neutral. This system requires intensive research to address issues with human diversity, various unique human expressions, and variety of human facial features due to age differences. These issues generally affect the ability of the FER system to detect human emotions with high accuracy. Early stage of FER systems used simple supervised classification task algorithms like K-nearest neighbors (KNN) and artificial neural networks (ANN). These conventional FER systems have issues with low accuracy due to its inefficiency to extract significant features of several human emotions. To increase the accuracy of FER systems, deep learning (DL)-based methods, like convolutional neural networks (CNN), are proposed. These methods can find more complex features in the human face by means of the deeper connections within its architectures. However, the inference speed and computational costs of a DL-based FER system is often disregarded in exchange for higher accuracy results. To cope with this drawback, an optimized DL-based FER system is proposed in this study.An extreme version of Inception V3, known as Xception model, is leveraged by applying different network optimization methods. Specifically, network pruning and quantization are used to enable lower computational costs and reduce memory usage, respectively. To support low resource requirements, a 68-landmark face detector from Dlib is used in the early step of the FER system.Furthermore, a DL compiler is utilized to incorporate advanced optimization techniques to the Xception model to improve the inference speed of the FER system. In comparison to VGG-Net and ResNet50, the proposed optimized DL-based FER system experimentally demonstrates the objectives of the network optimization methods used. As a result, the proposed approach can be used to create an efficient and real-time FER system.Keywords: deep learning, face detection, facial emotion recognition, network optimization methods
Procedia PDF Downloads 11454 Walking Cadence to Attain a Minimum of Moderate Aerobic Intensity in People at Risk of Cardiovascular Diseases
Authors: Fagner O. Serrano, Danielle R. Bouchard, Todd A. Duhame
Abstract:
Walking cadence (steps/min) is an effective way to prescribe exercise so an individual can reach a moderate intensity, which is recommended to optimize health benefits. To our knowledge, there is no study on the required walking cadence to reach a moderate intensity for people that present chronic conditions or risk factors for chronic conditions such as Cardiovascular Diseases (CVD). The objectives of this study were: 1- to identify the walking cadence needed for people at risk of CVD to a reach moderate intensity, and 2- to develop and test an equation using clinical variables to help professionals working with individuals at risk of CVD to estimate the walking cadence needed to reach moderate intensity. Ninety-one people presenting a minimum of two risk factors for CVD completed a medically supervised graded exercise test to assess maximum oxygen consumption at the first visit. The last visit consisted of recording walking cadence using a foot pod Garmin FR-60 and a Polar heart rate monitor, aiming to get participants to reach 40% of their maximal oxygen consumption using a portable metabolic cart on an indoor flat surface. The equation to predict the walking cadence needed to reach moderate intensity in this sample was developed as follows: The sample was randomly split in half and the equation was developed with one half of the participants, and validated using the other half. Body mass index, height, stride length, leg height, body weight, fitness level (VO2max), and self-selected cadence (over 200 meters) were measured using objective measured. Mean walking cadence to reach moderate intensity for people age 64.3 ± 10.3 years old at risk of CVD was 115.8 10.3 steps per minute. Body mass index, height, body weight, fitness level, and self-selected cadence were associated with walking cadence at moderate intensity when evaluated in bivariate analyses (r ranging from 0.22 to 0.52; all P values ≤0.05). Using linear regression analysis including all clinical variables associated in the bivariate analyses, body weight was the significant predictor of walking cadence for reaching a moderate intensity (ß=0.24; P=.018) explaining 13% of walking cadence to reach moderate intensity. The regression model created was Y = 134.4-0.24 X body weight (kg).Our findings suggest that people presenting two or more risk factors for CVD are reaching moderate intensity while walking at a cadence above the one officially recommended (116 steps per minute vs. 100 steps per minute) for healthy adults.Keywords: cardiovascular disease, moderate intensity, older adults, walking cadence
Procedia PDF Downloads 43753 The Impact of Physical Activity for Recovering Cancer Patients
Authors: Martyn Queen, Diane Crone, Andrew Parker, Saul Bloxham
Abstract:
Rationale: There is a growing body of evidence that supports the use of physical activity during and after cancer treatment. However, activity levels for patients remain low. As more cancer patients are treated successfully, and treatment costs continue to escalate, physical activity may be a promising adjunct to a person-centred healthcare approach to recovery. Aim: The aim was to further understand how physical activity may enhance the recovery process for a group of mixed-site cancer patients. Objectives: The research investigated longitudinal changes in physical activity and perceived the quality of life between two and six month’s post-exercise interventions. It also investigated support systems that enabled patients to sustain these perceived changes. Method: The respondent cohort comprised 14 mixed-site cancer patients aged 43-70 (11 women, 3 men), who participated in a two-phase physical activity intervention that took place at a university in the South West of England. Phase 1 consisted of an eight-week structured physical activity programme; Phase 2 consisted of four months of non-supervised physical activity. Semi-structured interviews took place three times over six months with each participant. Grounded theory informed the data collection and analysis which, in turn, facilitated theoretical development. Findings: Our findings propose three theories on the impact of physical activity for recovering cancer patients: 1) Knowledge gained through a structured exercise programme can enable recovering cancer patients to independently sustain physical activity to four-month follow-up. 2) Sustaining physical activity for six months promotes positive changes in the quality of life indicators of chronic fatigue, self-efficacy, the ability to self-manage and energy levels. 3) Peer support from patients facilitates adherence to a structured exercise programme and support from a spouse, or life partner facilitates independently sustained physical activity to four-month follow-up. Conclusions: This study demonstrates that qualitative research can provide an evidence base that could be used to support future care plans for cancer patients. Findings also demonstrate that a physical activity intervention can be effective at helping cancer patients recover from the side effects of their treatment, and recommends that physical activity should become an adjunct therapy alongside traditional cancer treatments.Keywords: physical activity, health, cancer recovery, quality of life, support systems, qualitative, grounded theory, person-centred healthcare
Procedia PDF Downloads 28252 Decision-Making Process Based on Game Theory in the Process of Urban Transformation
Authors: Cemil Akcay, Goksun Yerlikaya
Abstract:
Buildings are the living spaces of people with an active role in every aspect of life in today's world. While some structures have survived from the early ages, most of the buildings that completed their lifetime have not transported to the present day. Nowadays, buildings that do not meet the social, economic, and safety requirements of the age return to life with a transformation process. This transformation is called urban transformation. Urban transformation is the renewal of the areas with a risk of disaster and the technological infrastructure required by the structure. The transformation aims to prevent damage to earthquakes and other disasters by rebuilding buildings that have completed their non-earthquake-resistant economic life. It is essential to decide on other issues related to conversion and transformation in places where most of the building stock should transform into the first-degree earthquake belt, such as Istanbul. In urban transformation, property owners, local authority, and contractor must deal at a common point. Considering that hundreds of thousands of property owners are sometimes in the areas of transformation, it is evident how difficult it is to make the deal and decide. For the optimization of these decisions, the use of game theory is foreseeing. The main problem in this study is that the urban transformation is carried out in place, or the building or buildings are transport to a different location. There are many stakeholders in the Istanbul University Cerrahpaşa Medical Faculty Campus, which is planned to be carried out in the process of urban transformation, was tried to solve the game theory applications. An analysis of the decisions given on a real urban transformation project and the logical suitability of decisions taken without the use of game theory were also supervised using game theory. In each step of this study, many decision-makers are classifying according to a specific logical sequence, and in the game trees that emerged as a result of this classification, Nash balances were tried to observe, and optimum decisions were determined. All decisions taken for this project have been subjected to two significant differentiated comparisons using game theory, and as decisions are taken without the use of game theory, and according to the results, solutions for the decision phase of the urban transformation process introduced. The game theory model developed from beginning to the end of the urban transformation process, particularly as a solution to the difficulty of making rational decisions in large-scale projects with many participants in the decision-making process. The use of a decision-making mechanism can provide an optimum answer to the demands of the stakeholders. In today's world for the construction sector, it is also seeing that the game theory is a non-surprising consequence of the fact that it is the most critical issues of planning and making the right decision in future years.Keywords: urban transformation, the game theory, decision making, multi-actor project
Procedia PDF Downloads 12951 Robust Electrical Segmentation for Zone Coherency Delimitation Base on Multiplex Graph Community Detection
Authors: Noureddine Henka, Sami Tazi, Mohamad Assaad
Abstract:
The electrical grid is a highly intricate system designed to transfer electricity from production areas to consumption areas. The Transmission System Operator (TSO) is responsible for ensuring the efficient distribution of electricity and maintaining the grid's safety and quality. However, due to the increasing integration of intermittent renewable energy sources, there is a growing level of uncertainty, which requires a faster responsive approach. A potential solution involves the use of electrical segmentation, which involves creating coherence zones where electrical disturbances mainly remain within the zone. Indeed, by means of coherent electrical zones, it becomes possible to focus solely on the sub-zone, reducing the range of possibilities and aiding in managing uncertainty. It allows faster execution of operational processes and easier learning for supervised machine learning algorithms. Electrical segmentation can be applied to various applications, such as electrical control, minimizing electrical loss, and ensuring voltage stability. Since the electrical grid can be modeled as a graph, where the vertices represent electrical buses and the edges represent electrical lines, identifying coherent electrical zones can be seen as a clustering task on graphs, generally called community detection. Nevertheless, a critical criterion for the zones is their ability to remain resilient to the electrical evolution of the grid over time. This evolution is due to the constant changes in electricity generation and consumption, which are reflected in graph structure variations as well as line flow changes. One approach to creating a resilient segmentation is to design robust zones under various circumstances. This issue can be represented through a multiplex graph, where each layer represents a specific situation that may arise on the grid. Consequently, resilient segmentation can be achieved by conducting community detection on this multiplex graph. The multiplex graph is composed of multiple graphs, and all the layers share the same set of vertices. Our proposal involves a model that utilizes a unified representation to compute a flattening of all layers. This unified situation can be penalized to obtain (K) connected components representing the robust electrical segmentation clusters. We compare our robust segmentation to the segmentation based on a single reference situation. The robust segmentation proves its relevance by producing clusters with high intra-electrical perturbation and low variance of electrical perturbation. We saw through the experiences when robust electrical segmentation has a benefit and in which context.Keywords: community detection, electrical segmentation, multiplex graph, power grid
Procedia PDF Downloads 6550 Unveiling Comorbidities in Irritable Bowel Syndrome: A UK BioBank Study utilizing Supervised Machine Learning
Authors: Uswah Ahmad Khan, Muhammad Moazam Fraz, Humayoon Shafique Satti, Qasim Aziz
Abstract:
Approximately 10-14% of the global population experiences a functional disorder known as irritable bowel syndrome (IBS). The disorder is defined by persistent abdominal pain and an irregular bowel pattern. IBS significantly impairs work productivity and disrupts patients' daily lives and activities. Although IBS is widespread, there is still an incomplete understanding of its underlying pathophysiology. This study aims to help characterize the phenotype of IBS patients by differentiating the comorbidities found in IBS patients from those in non-IBS patients using machine learning algorithms. In this study, we extracted samples coding for IBS from the UK BioBank cohort and randomly selected patients without a code for IBS to create a total sample size of 18,000. We selected the codes for comorbidities of these cases from 2 years before and after their IBS diagnosis and compared them to the comorbidities in the non-IBS cohort. Machine learning models, including Decision Trees, Gradient Boosting, Support Vector Machine (SVM), AdaBoost, Logistic Regression, and XGBoost, were employed to assess their accuracy in predicting IBS. The most accurate model was then chosen to identify the features associated with IBS. In our case, we used XGBoost feature importance as a feature selection method. We applied different models to the top 10% of features, which numbered 50. Gradient Boosting, Logistic Regression and XGBoost algorithms yielded a diagnosis of IBS with an optimal accuracy of 71.08%, 71.427%, and 71.53%, respectively. Among the comorbidities most closely associated with IBS included gut diseases (Haemorrhoids, diverticular diseases), atopic conditions(asthma), and psychiatric comorbidities (depressive episodes or disorder, anxiety). This finding emphasizes the need for a comprehensive approach when evaluating the phenotype of IBS, suggesting the possibility of identifying new subsets of IBS rather than relying solely on the conventional classification based on stool type. Additionally, our study demonstrates the potential of machine learning algorithms in predicting the development of IBS based on comorbidities, which may enhance diagnosis and facilitate better management of modifiable risk factors for IBS. Further research is necessary to confirm our findings and establish cause and effect. Alternative feature selection methods and even larger and more diverse datasets may lead to more accurate classification models. Despite these limitations, our findings highlight the effectiveness of Logistic Regression and XGBoost in predicting IBS diagnosis.Keywords: comorbidities, disease association, irritable bowel syndrome (IBS), predictive analytics
Procedia PDF Downloads 10349 Landslide Hazard Zonation Using Satellite Remote Sensing and GIS Technology
Authors: Ankit Tyagi, Reet Kamal Tiwari, Naveen James
Abstract:
Landslide is the major geo-environmental problem of Himalaya because of high ridges, steep slopes, deep valleys, and complex system of streams. They are mainly triggered by rainfall and earthquake and causing severe damage to life and property. In Uttarakhand, the Tehri reservoir rim area, which is situated in the lesser Himalaya of Garhwal hills, was selected for landslide hazard zonation (LHZ). The study utilized different types of data, including geological maps, topographic maps from the survey of India, Landsat 8, and Cartosat DEM data. This paper presents the use of a weighted overlay method in LHZ using fourteen causative factors. The various data layers generated and co-registered were slope, aspect, relative relief, soil cover, intensity of rainfall, seismic ground shaking, seismic amplification at surface level, lithology, land use/land cover (LULC), normalized difference vegetation index (NDVI), topographic wetness index (TWI), stream power index (SPI), drainage buffer and reservoir buffer. Seismic analysis is performed using peak horizontal acceleration (PHA) intensity and amplification factors in the evaluation of the landslide hazard index (LHI). Several digital image processing techniques such as topographic correction, NDVI, and supervised classification were widely used in the process of terrain factor extraction. Lithological features, LULC, drainage pattern, lineaments, and structural features are extracted using digital image processing techniques. Colour, tones, topography, and stream drainage pattern from the imageries are used to analyse geological features. Slope map, aspect map, relative relief are created by using Cartosat DEM data. DEM data is also used for the detailed drainage analysis, which includes TWI, SPI, drainage buffer, and reservoir buffer. In the weighted overlay method, the comparative importance of several causative factors obtained from experience. In this method, after multiplying the influence factor with the corresponding rating of a particular class, it is reclassified, and the LHZ map is prepared. Further, based on the land-use map developed from remote sensing images, a landslide vulnerability study for the study area is carried out and presented in this paper.Keywords: weighted overlay method, GIS, landslide hazard zonation, remote sensing
Procedia PDF Downloads 118