Search results for: teaching and learning empathy

Authors: Besma Khalfoun

Abstract:

In many current Human Activity Recognition (HAR) applications, users' data is frequently shared and centrally stored by third parties, posing a significant privacy risk. This practice makes these entities attractive targets for extracting sensitive information about users, including their identity, health status, and location, thereby directly violating users' privacy. To tackle the issue of centralized data storage, a relatively recent paradigm known as federated learning has emerged. In this approach, users' raw data remains on their smartphones, where they train the HAR model locally. However, users still share updates of their local models originating from raw data. These updates are vulnerable to several attacks designed to extract sensitive information, such as determining whether a data sample is used in the training process, recovering the training data with inversion attacks, or inferring a specific attribute or property from the training data. In this paper, we first introduce PUR-Attack, a parameter-based user re-identification attack developed for HAR applications within a federated learning setting. It involves associating anonymous model updates (i.e., local models' weights or parameters) with the originating user's identity using background knowledge. PUR-Attack relies on a simple yet effective machine learning classifier and produces promising results. Specifically, we have found that by considering the weights of a given layer in a HAR model, we can uniquely re-identify users with an attack success rate of almost 100%. This result holds when considering a small attack training set and various data splitting strategies in the HAR model training. Thus, it is crucial to investigate protection methods to mitigate this privacy threat. Along this path, we propose SAFER, a privacy-preserving mechanism based on adaptive local differential privacy. Before sharing the model updates with the FL server, SAFER adds the optimal noise based on the re-identification risk assessment. Our approach can achieve a promising tradeoff between privacy, in terms of reducing re-identification risk, and utility, in terms of maintaining acceptable accuracy for the HAR model.

Keywords: federated learning, privacy risk assessment, re-identification risk, privacy preserving mechanisms, local differential privacy, human activity recognition

Procedia PDF Downloads 14

Authors: Liam Martin, Martha Watson

Abstract:

Patients with learning disabilities (LD) are at increased risk of physical and mental illness due to health inequality. To address this, NICE recommends that people from the age of 14 with a learning disability should have an annual LD health check. This consultation should include a holistic review of the patient’s physical, mental and social health needs with a view of creating an action plan to support the patient’s care. The expected standard set by the Quality and Outcomes Framework (QOF) is that each general practice should review at least 75% of their LD patients annually. During COVID-19, there have been barriers to primary care, including health anxiety, the shift to online general practice and the increase in GP workloads. A surgery in North London wanted to assess whether they were falling short of the expected standard for LD patient annual reviews in order to optimize care post Covid-19. A baseline audit was completed to assess how many LD patients were receiving their annual reviews over the period of 29th September 2020 to 29th September 2021. This information was accessed using EMIS Web Health Care System (EMIS). Patients included were aged 14 and over as per QOF standards. Doctors were not notified of this audit taking place. Following the results of this audit, the creation of learning disability clinics was recommended. These clinics were recommended to be on the ground floor and should be a dedicated time for LD reviews. A re-audit was performed via the same process 6 months later in March 2022. At the time of the baseline audit, there were 71 patients aged 14 and over that were on the LD register. 54% of these LD patients were found to have documentation of an annual LD review within the last 12 months. None of the LD patients between the ages of 14-18 years old had received their annual review. The results were discussed with the practice, and dedicated clinics were set up to review their LD patients. A second pass of the audit was completed 6 months later. This showed an improvement, with 84% of the LD patients registered at the surgery now having a documented annual review within the last 12 months. 78% of the patients between the ages of 14-18 years old had now been reviewed. The baseline audit revealed that the practice was not meeting the expected standard for LD patient’s annual health checks as outlined by QOF, with the most neglected patients being between the ages of 14-18. Identification and awareness of this vulnerable cohort is important to ensure measures can be put into place to support their physical, mental and social wellbeing. Other practices could consider an audit of their annual LD health checks to make sure they are practicing within QOF standards, and if there is a shortfall, they could consider implementing similar actions as used here; dedicated clinics for LD patient reviews.

Keywords: COVID-19, learning disability, learning disability health review, quality and outcomes framework

Procedia PDF Downloads 88

Authors: Zhikal Qadir Salih, Hanife Bensen

Abstract:

As the advent of modern technology continues to make towering impacts on everything, its relevance permeates to all spheres, language learning, and writing skills in particular not an exception. This study aimed at finding out how EFL learners perceive online tools to improve their writing skills. The study was carried out at Tishk University. Copies of the questionnaire were distributed to the participants, in order to elicit their perceptions. The collected data were subjected to descriptive and inferential statistics. The outcome revealed that the participants have positive perceptions about online tools in using them to enhance their writing skills. The study however found out that both gender and the class level of the participants do not make any significant difference in their perceptions about the use of online tools, as far as writing skill is concerned. Based on these outcomes, relevant recommendations were made.

Keywords: online tools, writing skills, EFL learners, language learning

Procedia PDF Downloads 102

Authors: Kishor T. Zingre, Seshadhri Srinivasan

Abstract:

Energy consumption by the building sector is increasing at an alarming rate throughout the world and leading to more building-related CO₂ emissions into the environment. In buildings, the main contributors to energy consumption are heating, ventilation, and air-conditioning (HVAC) systems, lighting, and electrical appliances. It is hypothesised that the energy efficiency in buildings can be achieved by implementing sustainable technologies such as i) enhancing the thermal resistance of fabric materials for reducing heat gain (in hotter climates) and heat loss (in colder climates), ii) enhancing daylight and lighting system, iii) HVAC system and iv) occupant localization. Energy performance of various sustainable technologies is highly dependent on climatic conditions. This paper investigated the use of machine learning techniques for accurate prediction of air-conditioning energy in seasonal climates. The data required to train the machine learning techniques is obtained using the computational simulations performed on a 3-story commercial building using EnergyPlus program plugged-in with OpenStudio and Google SketchUp. The EnergyPlus model was calibrated against experimental measurements of surface temperatures and heat flux prior to employing for the simulations. It has been observed from the simulations that the performance of sustainable fabric materials (for walls, roof, and windows) such as phase change materials, insulation, cool roof, etc. vary with the climate conditions. Various renewable technologies were also used for the building flat roofs in various climates to investigate the potential for electricity generation. It has been observed that the proposed technique overcomes the shortcomings of existing approaches, such as local linearization or over-simplifying assumptions. In addition, the proposed method can be used for real-time estimation of building air-conditioning energy.

Keywords: building energy efficiency, energyplus, machine learning techniques, seasonal climates

Procedia PDF Downloads 114

Authors: Ali Kirkbas

Abstract:

R peaks in an electrocardiogram (ECG) are signs of cardiac activity in individuals that reveal valuable information about cardiac abnormalities, which can lead to mortalities in some cases. This paper examines the problem of detecting R-peaks in ECG signals, which is a two-class pattern classification problem in fact. To handle this problem with a reliable high accuracy, we propose to use the common vector approach which is a successful machine learning algorithm. The dataset used in the proposed method is obtained from MIT-BIH, which is publicly available. The results are compared with the other popular methods under the performance metrics. The obtained results show that the proposed method shows good performance than that of the other. methods compared in the meaning of diagnosis accuracy and simplicity which can be operated on wearable devices.

Keywords: ECG, R-peak classification, common vector approach, machine learning

Procedia PDF Downloads 65

Authors: Julio Jesus Salazar, Julio Jesus De Lama

Abstract:

the fundamental objective of hydrological studies applied to the engineering field is to determine the statistically consistent volumes or water flows that, in each case, allow us to size or design a series of elements or structures to effectively manage and develop a river basin. To determine these values, there are several ways of working within the framework of traditional hydrology: (1) Study each of the factors that influence the hydrological cycle, (2) Study the historical behavior of the hydrology of the area, (3) Study the historical behavior of hydrologically similar zones, and (4) Other studies (rain simulators or experimental basins). Of course, this range of studies in a certain basin is very varied and complex and presents the difficulty of collecting the data in real time. In this complex space, the study of variables can only be overcome by collecting and transmitting data to decision centers through the Internet of things and artificial intelligence. Thus, this research work implemented the learning project of the sub-basin of the Shullcas river in the Andean basin of the Mantaro river in Peru. The sensor firmware to collect and communicate hydrological parameter data was programmed and tested in similar basins of the European Union. The Machine Learning applications was programmed to choose the algorithms that direct the best solution to the determination of the rainfall-runoff relationship captured in the different polygons of the sub-basin. Tests were carried out in the mountains of Europe, and in the sub-basins of the Shullcas river (Huancayo) and the Yauli river (Jauja) with heights close to 5000 m.a.s.l., giving the following conclusions: to guarantee a correct communication, the distance between devices should not pass the 15 km. It is advisable to minimize the energy consumption of the devices and avoid collisions between packages, the distances oscillate between 5 and 10 km, in this way the transmission power can be reduced and a higher bitrate can be used. In case the communication elements of the devices of the network (internet of things) installed in the basin do not have good visibility between them, the distance should be reduced to the range of 1-3 km. The energy efficiency of the Atmel microcontrollers present in Arduino is not adequate to meet the requirements of system autonomy. To increase the autonomy of the system, it is recommended to use low consumption systems, such as the Ashton Raggatt McDougall or ARM Cortex L (Ultra Low Power) microcontrollers or even the Cortex M; and high-performance direct current (DC) to direct current (DC) converters. The Machine Learning System has initiated the learning of the Shullcas system to generate the best hydrology of the sub-basin. This will improve as machine learning and the data entered in the big data coincide every second. This will provide services to each of the applications of the complex system to return the best data of determined flows.

Keywords: hydrology, internet of things, machine learning, river basin

Procedia PDF Downloads 161

Authors: Shiuh-Jer Huang, Chen-Zon Yan, C. K. Huang, Chun-Chien Ting

Abstract:

Since the vision system application in industrial environment for autonomous purposes is required intensely, the image recognition technique becomes an important research topic. Here, deep learning algorithm is employed in image system to recognize the industrial object and integrate with a 7A6 Series Manipulator for object automatic gripping task. PC and Graphic Processing Unit (GPU) are chosen to construct the 3D Vision Recognition System. Depth Camera (Intel RealSense SR300) is employed to extract the image for object recognition and coordinate derivation. The YOLOv2 scheme is adopted in Convolution neural network (CNN) structure for object classification and center point prediction. Additionally, image processing strategy is used to find the object contour for calculating the object orientation angle. Then, the specified object location and orientation information are sent to robotic controller. Finally, a six-axis manipulator can grasp the specific object in a random environment based on the user command and the extracted image information. The experimental results show that YOLOv2 has been successfully employed to detect the object location and category with confidence near 0.9 and 3D position error less than 0.4 mm. It is useful for future intelligent robotic application in industrial 4.0 environment.

Keywords: deep learning, image processing, convolution neural network, YOLOv2, 7A6 series manipulator

Procedia PDF Downloads 250

Authors: Wei Li, Tuo Yang

Abstract:

In order to satisfy the real-time and accurate requirements of cigarette smoke detection in complex scenes, a cigarette smoke detection technology based on the combination of deep learning and color features was proposed. Firstly, based on the color features of cigarette smoke, the suspicious cigarette smoke area in the image is extracted. Secondly, combined with the efficiency of cigarette smoke detection and the problem of network overfitting, a network model for cigarette smoke detection was designed according to YOLOV3 algorithm to reduce the false detection rate. The experimental results show that the method is feasible and effective, and the accuracy of cigarette smoke detection is up to 99.13%, which satisfies the requirements of real-time cigarette smoke detection in complex scenes.

Keywords: deep learning, computer vision, cigarette smoke detection, YOLOV3, color feature extraction

Procedia PDF Downloads 88

Authors: Shankar Dhakal, Andrew Jones, Geoffrey W. Lummis

Abstract:

The Federal Democratic Republic of Nepal is a linguistically, culturally, and ethnically diverse country with approximately 123 different spoken languages that represent several ethnic, cultural, and religious groups of people. With a population of about 30 million, long-standing disparities and inequalities in access and achievement in education have constantly been challenging to provide equitable educational opportunities for all students. While the new constitution of federal Nepal (2015) stipulates that all schools serve the interests of diverse communities, leadership practices have failed to adopt local contextual sensitivities, leading to traditional, authoritarian approaches and entrenched inequalities. However, little is known about how Nepali secondary school principals can adapt and implement context-responsive and equitable strategies to ensure equity and inclusiveness in its enormously diverse socio-cultural contexts. To fill this gap, this study explores how educational leadership approaches and philosophies are transformed using a multi-case automated/ethnographic research methodology underpinned by the paradigm of critical constructivism. This paper reconstructs to see if school leadership in Nepal can produce more equitable and contextual outcomes. The results of this study highlight the need for a paradigm shift and the adoption of innovative leadership approaches that foster humility, empathy, and compassion in school leaders to achieve better school outcomes. This research provides valuable insights into existing literary gaps and provides guidance for future school leadership policies and practices at the personal, cultural, and political levels.

Keywords: school leadership, auto/ethnography, equitable and context-responsive leadership, Nepal

Procedia PDF Downloads 74

Authors: Sumit Sen, Sohan Khedekar, Umang Shinde, Shivam Bhargava

Abstract:

This study has been undertaken to investigate whether the deep learning models are able to predict the future stock prices by training the model with the historical stock price data. Since this work required time series analysis, various models are present today to perform time series analysis such as Recurrent Neural Network LSTM, ARIMA and Facebook Prophet. Applying these models the movement of stock price of stocks are predicted and also tried to provide the future prediction of the stock price of a stock. Final product will be a stock price prediction web application that is developed for providing the user the ease of analysis of the stocks and will also provide the predicted stock price for the next seven days.

Keywords: Autoregressive Integrated Moving Average, Deep Learning, Long Short Term Memory, Time-series

Procedia PDF Downloads 143

Authors: Ezgiamn Abraha Hagos

Abstract:

The primary objective of this study was to assess the existential concerns and related manifestations of higher learning students by investigating their perception of meaningful life and evaluating their purpose in life. In addition, this study was aimed at assessing the manifestations of existential pain among the students. Data was procured using Purpose in Life test (PIL), Well-being Manifestation Measure Scale (WBMMS), and focus group discussion. The total numbers of participants was 478, of which 299 were males and the remaining 179 females. They were selected using a simple random sampling technique. Data was analyzed using two ways. SPSS-version 20 was used to analyze the quantitative part, and narrative modes were utilized to analyze the qualitative data. The research finding revealed that students are involved in risk taking behaviors like alcohol ingestion, drug use, Khat (chat) chewing, and unsafe sex. In line with this it is found out that life in campus was perceived as temporary and as a result the sense of hedonism was prevalent at any cost. Of course, the most important thing for the majority of the students was to know about the purpose of life. Regarding WBMMS, there was no statistically significant difference among males and females and with the exception of the sub-scale of happiness; in all the sub-scales the mean is low. At last, assisting adolescents to develop holistically in terms of body, mind, and spirit is recommended.

Keywords: existential concerns, higher learning institutions, Ethiopia, Aksum University

Procedia PDF Downloads 429

Authors: K. Doi, T. Nishimura, H. Fujimoto

Abstract:

The number of people who become visually impaired and do not have sufficient tactile experiences has increased by various disease. Especially, many acquired visually impaired persons due to accidents, disorders, and aging cannot adequately read Braille. It is known that learning Braille requires a great deal of time and the acquisition of various skills. In our previous studies, we reported one of the problems in learning Braille. Concretely, the standard Braille size is too small for Braille beginners. And also we are short of the objective data regarding easily readable Braille size. Therefore, it is necessary to conduct various experiments for evaluating Braille size that would make learning easier for beginners. In this study, for the purpose of investigating easy-to-read conditions of vertical and horizontal dot spacing for beginners, we conducted one Braille reading experiment. In this our experiment, we prepared test pieces by use of our original Braille printer with controlling function of Braille size. We specifically considered Braille beginners with acquired visual impairments who were unfamiliar with Braille. Therefore, ten sighted subjects with no experience of reading Braille participated in this experiment. Size of vertical and horizontal dot spacing was following conditions. Each dot spacing was 2.0, 2.3, 2.5, 2.7, 2.9, 3.1mm. The subjects were asked to read one Braille character with controlled Braille size. The results of this experiment reveal that Braille beginners can read Braille accurately and quickly when both vertical and horizontal dot spacing are 3.1 mm or more. This knowledge will be helpful data in considering Braille size for acquired visually impaired persons.

Keywords: paper-based Braille, vertical and horizontal dot spacing, readability, acquired visual impairment, Braille beginner

Procedia PDF Downloads 178

Authors: Saahith M. S., Sivakami R.

Abstract:

In the realm of football analytics, particularly focusing on predicting football player performance, the ability to forecast player success accurately is of paramount importance for teams, managers, and fans. This study introduces an elaborate examination of predicting football player performance through the integration of data visualization methods and machine learning algorithms. The research entails the compilation of an extensive dataset comprising player attributes, conducting data preprocessing, feature selection, model selection, and model training to construct predictive models. The analysis within this study will involve delving into feature significance using methodologies like Select Best and Recursive Feature Elimination (RFE) to pinpoint pertinent attributes for predicting player performance. Various machine learning algorithms, including Random Forest, Decision Tree, Linear Regression, Support Vector Regression (SVR), and Artificial Neural Networks (ANN), will be explored to develop predictive models. The evaluation of each model's performance utilizing metrics such as Mean Squared Error (MSE) and R-squared will be executed to gauge their efficacy in predicting player performance. Furthermore, this investigation will encompass a top player analysis to recognize the top-performing players based on the anticipated overall performance scores. Nationality analysis will entail scrutinizing the player distribution based on nationality and investigating potential correlations between nationality and player performance. Positional analysis will concentrate on examining the player distribution across various positions and assessing the average performance of players in each position. Age analysis will evaluate the influence of age on player performance and identify any discernible trends or patterns associated with player age groups. The primary objective is to predict a football player's overall performance accurately based on their individual attributes, leveraging data-driven insights to enrich the comprehension of player success on the field. By amalgamating data visualization and machine learning methodologies, the aim is to furnish valuable tools for teams, managers, and fans to effectively analyze and forecast player performance. This research contributes to the progression of sports analytics by showcasing the potential of machine learning in predicting football player performance and offering actionable insights for diverse stakeholders in the football industry.

Keywords: football analytics, player performance prediction, data visualization, machine learning algorithms, random forest, decision tree, linear regression, support vector regression, artificial neural networks, model evaluation, top player analysis, nationality analysis, positional analysis

Procedia PDF Downloads 39

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 66

Authors: Revoti Prasad Bora, Nikita Katyal

Abstract:

Promotion is a key element in the retail business. Thus, analysis of promotions to quantify their effectiveness in terms of Revenue and/or Margin is an essential activity in the retail industry. However, measuring the sales/revenue uplift is based on estimations, as the actual sales/revenue without the promotion is not present. Further, the presence of Halo and Cannibalization in a multiple parallel promotions’ scenario complicates the problem. Calculating Baseline by considering inter-brand/competitor items or using Halo and Cannibalization's impact on Revenue calculations by considering Baseline as an interpretation of items’ unit sales in neighboring nonpromotional weeks individually may not capture the overall Revenue uplift in the case of multiple parallel promotions. Hence, this paper proposes a Machine Learning based method for calculating the Revenue uplift by considering the Halo and Cannibalization impact on the Baseline and the Revenue. In the first section of the proposed methodology, Baseline of an item is calculated by incorporating the impact of the promotions on its related items. In the later section, the Revenue of an item is calculated by considering both Halo and Cannibalization impacts. Hence, this methodology enables correct calculation of the overall Revenue uplift due a given promotion.

Keywords: Halo, Cannibalization, promotion, Baseline, temporary price reduction, retail, elasticity, cross price elasticity, machine learning, random forest, linear regression

Procedia PDF Downloads 181

Authors: Maha Jazouli

Abstract:

Suicide is one of the most important causes of death in the prison environment, both in Canada and internationally. Rates of attempts of suicide and self-harm have been on the rise in recent years, with hangings being the most frequent method resorted to. The objective of this article is to propose a method to automatically detect in real time suicidal behaviors. We present a gesture recognition system that consists of three modules: model-based movement tracking, feature extraction, and gesture recognition using machine learning algorithms (MLA). Our proposed system gives us satisfactory results. This smart video surveillance system can help assist staff responsible for the safety and health of inmates by alerting them when suicidal behavior is detected, which helps reduce mortality rates and save lives.

Keywords: suicide detection, Kinect azure, RGB-D camera, SVM, machine learning, gesture recognition

Procedia PDF Downloads 190

Authors: Arpit Patil, Atharav Bhagwat, Rajas Bhope, Pramod Bide

Abstract:

This research integrates IoT and ML to predict heart failure risks, utilizing the Framingham dataset. IoT devices gather real-time physiological data, focusing on heart rate dynamics, while ML, specifically Random Forest, predicts heart failure. Rigorous feature selection enhances accuracy, achieving over 90% prediction rate. This amalgamation marks a transformative step in proactive healthcare, highlighting early detection's critical role in cardiovascular risk mitigation. Challenges persist, necessitating continual refinement for improved predictive capabilities.

Keywords: cardiovascular diseases, internet of things, machine learning, cardiac risk assessment, heart failure prediction, early detection, cardio data analysis

Procedia PDF Downloads 15

Authors: Georgios Charizanos, Haydar Demirhan, Duygu Icen

Abstract:

Two of the most impactful issues in classical logistic regression are class imbalance and complete separation. These can result in model predictions heavily leaning towards the imbalanced class on the binary response variable or over-fitting issues. Fuzzy methodology offers key solutions for handling these problems. However, most studies propose the transformation of the binary responses into a continuous format limited within [0,1]. This is called the possibilistic approach within fuzzy logistic regression. Following this approach is more aligned with straightforward regression since a logit-link function is not utilized, and fuzzy probabilities are not generated. In contrast, we propose a method of fuzzifying binary response variables that allows for the use of the logit-link function; hence, a probabilistic fuzzy logistic regression model with the Monte Carlo method. The fuzzy probabilities are then classified by selecting a fuzzy threshold. Different combinations of fuzzy and crisp input, output, and coefficients are explored, aiming to understand which of these perform better under different conditions of imbalance and separation. We conduct numerical experiments using both synthetic and real datasets to demonstrate the performance of the fuzzy logistic regression framework against seven crisp machine learning methods. The proposed framework shows better performance irrespective of the degree of imbalance and presence of separation in the data, while the considered machine learning methods are significantly impacted.

Keywords: fuzzy logistic regression, fuzzy, logistic, machine learning

Procedia PDF Downloads 76

Authors: Abhivardhan, Ritu Agarwal

Abstract:

The role of entrepreneurial ethics is connected with materializing the core components of human life, and the flexible and gullible attributions dominate the materialization of human lifestyle and outreach in the age of the internet and globalization. One of the key bi-products of the age of information – Artificial Intelligence has become a relevant mechanism to materialize and understand human empathy and originality via various algorithmic policing methodologies with specific intricacies. Since it has a special connection with ethnocentrism – it has the potential to influence the approach of international law and politics owed to the rise of and approach towards perception and communication via populism in progressive and third world countries. The paper argues about the cultural persona of artificial intelligence, and its ontological resemblance in human life is connected with the ethnocentric treatment of cyberspace, with an analysis of the influence of the ethics of entrepreneurship in international politics. The paper further provides an analysis of fake news and misinformation as the sub-strata of communication strategies involving populism determined as a communication strategy and about the legal case of constitutional redemption in recent legislative developments in Europe, the U.S, and Asia with reference to certain important strategies, policy documentation, declarations, and legal instruments. The paper concludes that the capillaries of the anthropomorphic developments of cultural perception via towards artificial intelligence have a hidden and unstable connection with the common approach of entrepreneurial ethics, which influences populism to disrupt the peaceful order of international politics via some minor backlashes in the technological, legal and social realm of human life. Suggestions with the conclusion are hereby provided.

Keywords: ethnocentrism, perception politics, populism, international law, slacktivism, artificial intelligence ethics, enculturation

Procedia PDF Downloads 130

Authors: Shayan Mohajer Hamidi

Abstract:

Federated Learning (FL) has emerged as a promising paradigm for training machine learning models on distributed data without the need for centralized data aggregation. In the realm of wireless communications, FL has the potential to leverage the vast amounts of data generated by wireless devices to improve model performance and enable intelligent applications. However, the fairness aspect of FL in wireless communications remains largely unexplored. This abstract presents an idea for fair federated learning in wireless communications, addressing the challenges of imbalanced data distribution, privacy preservation, and resource allocation. Firstly, the proposed approach aims to tackle the issue of imbalanced data distribution in wireless networks. In typical FL scenarios, the distribution of data across wireless devices can be highly skewed, resulting in unfair model updates. To address this, we propose a weighted aggregation strategy that assigns higher importance to devices with fewer samples during the aggregation process. By incorporating fairness-aware weighting mechanisms, the proposed approach ensures that each participating device's contribution is proportional to its data distribution, thereby mitigating the impact of data imbalance on model performance. Secondly, privacy preservation is a critical concern in federated learning, especially in wireless communications where sensitive user data is involved. The proposed approach incorporates privacy-enhancing techniques, such as differential privacy, to protect user privacy during the model training process. By adding carefully calibrated noise to the gradient updates, the proposed approach ensures that the privacy of individual devices is preserved without compromising the overall model accuracy. Moreover, the approach considers the heterogeneity of devices in terms of computational capabilities and energy constraints, allowing devices to adaptively adjust the level of privacy preservation to strike a balance between privacy and utility. Thirdly, efficient resource allocation is crucial for federated learning in wireless communications, as devices operate under limited bandwidth, energy, and computational resources. The proposed approach leverages optimization techniques to allocate resources effectively among the participating devices, considering factors such as data quality, network conditions, and device capabilities. By intelligently distributing the computational load, communication bandwidth, and energy consumption, the proposed approach minimizes resource wastage and ensures a fair and efficient FL process in wireless networks. To evaluate the performance of the proposed fair federated learning approach, extensive simulations and experiments will be conducted. The experiments will involve a diverse set of wireless devices, ranging from smartphones to Internet of Things (IoT) devices, operating in various scenarios with different data distributions and network conditions. The evaluation metrics will include model accuracy, fairness measures, privacy preservation, and resource utilization. The expected outcomes of this research include improved model performance, fair allocation of resources, enhanced privacy preservation, and a better understanding of the challenges and solutions for fair federated learning in wireless communications. The proposed approach has the potential to revolutionize wireless communication systems by enabling intelligent applications while addressing fairness concerns and preserving user privacy.

Keywords: federated learning, wireless communications, fairness, imbalanced data, privacy preservation, resource allocation, differential privacy, optimization

Procedia PDF Downloads 77

Authors: Yelena Mazour-Matusevich, Jean-Robert Ancheta

Abstract:

This study is based on more than fifteen years of experience of teaching a foreign language, in my case French, to the English-speaking students. It represents a qualitative research on foreign language learners’ reaction and their gains in terms of vocabulary and listening comprehension through repeatedly viewing foreign feature films with the original sountrack but without English subtitles. The initial idea emerged upon realization that the first challenge faced by my students when they find themselves in a francophone environment has been their lack of listening comprehension. Their inability to understand colloquial speech affects not only their academic performance, but their psychological health as well. To remedy this problem, I have designed and applied for many years my own teaching method based on one particular French film, exceptionally suited, for the reasons described in detail in the paper, for the intermediate-advanced level foreign language learners. This project, conducted together with my undergraduate assistant and mentoree J-R Ancheta, aims at showing how the paralinguistic features, such as characters’ facial expressions, settings, music, historical background, images provided before the actual viewing, etc., offer crucial support and enhance students’ listening comprehension. The study, based on students’ interviews, also offers special pedagogical techniques, such as ‘anticipatory’ vocabulary lists and exercises, drills, quizzes and composition topics that have proven to boost students’ performance. For this study, only the listening proficiency and vocabulary gains of the interviewed participants were assessed.

Keywords: comprehension, film, listening, subtitles, vocabulary

Procedia PDF Downloads 625

Authors: Marla Wendy Spergel

Abstract:

The purpose of this qualitative study is to showcase graduated high school students’ to voice on the impact past teachers had on their motivation to learn, and if this impact has affected their post-high-school lives. Through a focus group strategy, 21 graduated high school alumni participated in three separate focus groups. Participants discussed their former teacher’s emotional intelligence skills, which influenced their motivation to learn or not. A focused review of the literature revealed that teachers are a major factor in a student’s motivation to learn. This research was guided by Bandura’s Social Cognitive Theory of Motivation and constructs related to learning and motivation from Carl Rogers’ Humanistic Views of Personality, and from Brain-Based Learning perspectives with a major focus on the area of Emotional Intelligence. Findings revealed that the majority of participants identified teachers who most motivated them to learn and demonstrated skills associated with emotional intelligence. An important and disturbing finding relates to the saliency of negative experiences. Further work is recommended to expand this line of study in Higher Education, perform a long-term study to better gain insight into long-term benefits attributable to experiencing positive teachers, study the negative impact teachers have on students’ motivation to learn, specifically focusing on student anxiety and acquired helplessness.

Keywords: emotional intelligence, learning, motivation, pedagogy

Procedia PDF Downloads 158

Authors: Bruce X. B. Yu, Yan Liu, Keith C. C. Chan

Abstract:

We propose to record Activities of Daily Living (ADLs) of elderly people using a vision-based system so as to provide better assistive and personalization technologies. Current ADL-related research is based on data collected with help from non-elderly subjects in laboratory environments and the activities performed are predetermined for the sole purpose of data collection. To obtain more realistic datasets for the application, we recorded ADLs for the elderly with data collected from real-world environment involving real elderly subjects. Motivated by the need to collect data for more effective research related to elderly care, we chose to collect data in the room of an elderly person. Specifically, we installed Kinect, a vision-based sensor on the ceiling, to capture the activities that the elderly subject performs in the morning every day. Based on the data, we identified 12 morning activities that the elderly person performs daily. To recognize these activities, we created a HARELCARE framework to investigate into the effectiveness of existing Human Activity Recognition (HAR) algorithms and propose the use of a transfer learning algorithm for HAR. We compared the performance, in terms of accuracy, and training progress. Although the collected dataset is relatively small, the proposed algorithm has a good potential to be applied to all daily routine activities for healthcare purposes such as evidence-based diagnosis and treatment.

Keywords: daily activity recognition, healthcare, IoT sensors, transfer learning

Procedia PDF Downloads 132

Authors: Ahcene Habbi, Yassine Boudouaoui

Abstract:

This paper deals with the problem of automatic rule generation for fuzzy systems design. The proposed approach is based on hybrid artificial bee colony (ABC) optimization and weighted least squares (LS) method and aims to find the structure and parameters of fuzzy systems simultaneously. More precisely, two ABC based fuzzy modeling strategies are presented and compared. The first strategy uses global optimization to learn fuzzy models, the second one hybridizes ABC and weighted least squares estimate method. The performances of the proposed ABC and ABC-LS fuzzy modeling strategies are evaluated on complex modeling problems and compared to other advanced modeling methods.

Keywords: automatic design, learning, fuzzy rules, hybrid, swarm optimization

Procedia PDF Downloads 440

Authors: Akeel A. Shah, Tong Zhang

Abstract:

Computational approaches to learning the properties of materials are commonplace, motivated by the need to screen or design materials for a given application, e.g., semiconductors and energy storage. Experimental approaches can be both time consuming and costly. Unfortunately, computational approaches such as ab-initio electronic structure calculations and classical or ab-initio molecular dynamics are themselves can be too slow for the rapid evaluation of materials, often involving thousands to hundreds of thousands of candidates. Machine learning assisted approaches have been developed to overcome the time limitations of purely physics-based approaches. These approaches, on the other hand, require large volumes of data for training (hundreds of thousands on many standard data sets such as QM7b). This means that they are limited by how quickly such a large data set of physics-based simulations can be established. At high fidelity, such as configuration interaction, composite methods such as G4, and coupled cluster theory, gathering such a large data set can become infeasible, which can compromise the accuracy of the predictions - many applications require high accuracy, for example band structures and energy levels in semiconductor materials and the energetics of charge transfer in energy storage materials. In order to circumvent this problem, multi-fidelity approaches can be adopted, for example the Δ-ML method, which learns a high-fidelity output from a low-fidelity result such as Hartree-Fock or density functional theory (DFT). The general strategy is to learn a map between the low and high fidelity outputs, so that the high-fidelity output is obtained a simple sum of the physics-based low-fidelity and correction, Although this requires a low-fidelity calculation, it typically requires far fewer high-fidelity results to learn the correction map, and furthermore, the low-fidelity result, such as Hartree-Fock or semi-empirical ZINDO, is typically quick to obtain, For high-fidelity outputs the result can be an order of magnitude or more in speed up. In this work, a new multi-fidelity approach is developed, based on a graph convolutional network (GCN) combined with semi-supervised learning. The GCN allows for the material or molecule to be represented as a graph, which is known to improve accuracy, for example SchNet and MEGNET. The graph incorporates information regarding the numbers of, types and properties of atoms; the types of bonds; and bond angles. They key to the accuracy in multi-fidelity methods, however, is the incorporation of low-fidelity output to learn the high-fidelity equivalent, in this case by learning their difference. Semi-supervised learning is employed to allow for different numbers of low and high-fidelity training points, by using an additional GCN-based low-fidelity map to predict high fidelity outputs. It is shown on 4 different data sets that a significant (at least one order of magnitude) increase in accuracy is obtained, using one to two orders of magnitude fewer low and high fidelity training points. One of the data sets is developed in this work, pertaining to 1000 simulations of quinone molecules (up to 24 atoms) at 5 different levels of fidelity, furnishing the energy, dipole moment and HOMO/LUMO.

Keywords: .materials screening, computational materials, machine learning, multi-fidelity, graph convolutional network, semi-supervised learning

Procedia PDF Downloads 42

Authors: Mst Shapna Akter, Hossain Shahriar

Abstract:

Neural network approaches are machine learning methods used in many domains, such as healthcare and cyber security. Neural networks are mostly known for dealing with image datasets. While training with the images, several fundamental mathematical operations are carried out in the Neural Network. The operation includes a number of algebraic and mathematical functions, including derivative, convolution, and matrix inversion and transposition. Such operations require higher processing power than is typically needed for computer usage. Central Processing Unit (CPU) is not appropriate for a large image size of the dataset as it is built with serial processing. While Graphics Processing Unit (GPU) has parallel processing capabilities and, therefore, has higher speed. This paper uses advanced Neural Network techniques such as VGG16, Resnet50, Densenet, Inceptionv3, Xception, Mobilenet, XGBOOST-VGG16, and our proposed models to compare CPU and GPU resources. A system for classifying autism disease using face images of an autistic and non-autistic child was used to compare performance during testing. We used evaluation matrices such as Accuracy, F1 score, Precision, Recall, and Execution time. It has been observed that GPU runs faster than the CPU in all tests performed. Moreover, the performance of the Neural Network models in terms of accuracy increases on GPU compared to CPU.

Keywords: autism disease, neural network, CPU, GPU, transfer learning

Procedia PDF Downloads 121

Authors: Shyam lamsal

Abstract:

Introduction: Karnali Academy of Health Sciences (KAHS) has been established in 2011, by an Act of parliament of Nepal, in Jumla, to provide health services in easy way in backward areas, to produce skilled health professionals & conduct research. The backward areas mentioned in act of KAHS are Humla, Jumla, Kalikot, Dolpa, Mugu districts of Karnali zone, Jajarkot district of Bheri zone & Bajura, Baghang & Achham districts of Seti zone in Nepal occupying around 25 % of the total national geography. Backward area of Nepal is specific to having worst health indicators with life expectancy (47 years), HDI (0.35), Literacy rate (58%), global acute malnutrition (13%), crude birth rate (33.6), crude death rate (9.6), Total fertility rate (4.2), infant mortality rate (61.5 per 1000 live births), under five mortality rate (59 per 1000 live births) and maternal mortality ratio (400 per 1000 live births). History of health facilities in backward region: All the nine districts of this region have a district hospital with very few grass root level health manpower. Government of Nepal regularly deploys one or two medical officers to each district who generally are not regular to their care. Jumla district itself was having one medical officer before the establishment of KAHS. Development activities: Establishment of 100 bedded specialty teaching hospital with 10 medical officers and five specialists, accredited its own nursing school for running diploma nursing programme, started “Karnali health survey” which covers 55 thousand households of backward region, started community care and school health camps, planning phase completed for 300 bedded teaching hospital construction. Future Plan: Expansion of the teaching hospital to 300 beds within 3 years, start health assistant and bachelor midwifery course in 2015 AD, start bachelor in laboratory and bachelor in public health course in 2016 AD and start MBBS course in 2018 AD. Deploy the medical officers and family physicians to all the district hospitals within 3 years. KAHS provides reservation up to 45% students from backward region with the commitment to stay for at least five years of their service period. Conclusion: This institution may be the example for the rest of the world in providing nursing care, education in remote areas as well as the best model for nursing manpower retention in remote areas of developing countries.

Keywords: backward area, nursing school

Procedia PDF Downloads 322

Authors: M. Tomaschko

Abstract:

The integration of technology in educational settings has gained a lot of interest. Especially the use of mobile devices and accompanying mobile applications can offer great potentials to complement traditional education with new technologies and enrich students’ learning in various ways. Nevertheless, the usability of the deployed mathematics application is an indicative factor to exploit the full potential of technology enhanced learning because directing cognitive load toward using an application will likely inhibit effective learning. For this reason, the purpose of this research study is the identification of possible usability issues of the mobile GeoGebra Graphing Calculator application. Therefore, eye tracking in combination with task scenarios, think aloud method, and a SUS questionnaire were used. Based on the revealed usability issues, the mobile application was iteratively redesigned and assessed in order to verify the success of the usability improvements. In this paper, the identified usability issues are presented, and recommendations on how to overcome these concerns are provided. The main findings relate to the conception of a mathematics keyboard and the interaction design in relation to an equation editor, as well as the representation of geometrical construction tools. In total, 12 recommendations were formed to improve the usability of a mobile graphing calculator application. The benefit to be gained from this research study is not only the improvement of the usability of the existing GeoGebra Graphing Calculator application but also to provide helpful hints that could be considered from designers and developers of mobile math applications.

Keywords: GeoGebra, graphing calculator, math education, smartphone, usability

Procedia PDF Downloads 134

Authors: Shogo Nagano, Yusuke Tanigaki, Hirokazu Fukuda

Abstract:

Vegetables harvested early in the morning or late in the afternoon are valued in plant production, and so the time of harvest is important. The biological functions known as circadian clocks have a significant effect on this harvest timing. The purpose of this study was to non-destructively estimate the circadian clock and so construct a method for determining a suitable harvest time. We took eight samples of green busil (Perilla frutescens var. crispa) every 4 hours, six times for 1 day and analyzed all samples at the same time. A hyperspectral camera was used to collect spectrum intensities at 141 different wavelengths (350–1050 nm). Calculation of correlations between spectrum intensity of each wavelength and harvest time suggested the suitability of the hyperspectral camera for non-destructive estimation. However, even the highest correlated wavelength had a weak correlation, so we used machine learning to raise the accuracy of estimation and constructed a machine learning model to estimate the internal time of the circadian clock. Artificial neural networks (ANN) were used for machine learning because this is an effective analysis method for large amounts of data. Using the estimation model resulted in an error between estimated and real times of 3 min. The estimations were made in less than 2 hours. Thus, we successfully demonstrated this method of non-destructively estimating internal time.

Keywords: artificial neural network (ANN), circadian clock, green busil, hyperspectral camera, non-destructive evaluation

Procedia PDF Downloads 300

Authors: Sepideh Nikounejad, Mostafa Ghaderi, Nematollah Azizi, Per-Olof Thang, Mohamad Reza Neyestani

Abstract:

From an educational perspective, an effective and efficient relationship between university and industry can be considered as an important means by which not only both sides are improved but also it brings many advantages and benefits for both parties. It means more specifically, mutual collaboration between universities and industry can not only reduce youth unemployment, but it can improve the quality of teaching and learning in higher education settings while providing more qualified people to industrial enterprises. Indeed the lack of effective interaction between Iranian universities and industry has confronted the country and created many challenges include in increasing number of unskillful and unemployed graduates. However, in order to suggest appropriate practical strategies, it is very important to see how this issue has been tackled by Swedish universities, which have had a good background in this collaboration and how they are connected to the industry in particular and labour market in general. The research aims to study and compare the mechanisms, processes, and policies of the current model in the relationships between university and industry in Iran and Sweden. As a qualitative study, grounded theory was applied. Data were collected via semi-structured interviews. Participants were selected purposefully and by the snowball sampling method. The findings indicate that despite reported needs from both sides for close collaborations between universities and industries in Iran, current policies and practices, including internship, laboratory, and financial support, need to be revised critically. However, in light of our findings on the Swedish policies and practices for linking universities and industries, some practical strategies will be suggested for the Iranian higher education context. In conclusion, cooperation models between universities and industries in Iran and Sweden will be described.

Keywords: cooperation, higher education, industry, comparative

Procedia PDF Downloads 134