Search results for: computational machine learning
9301 Smart Textiles Integration for Monitoring Real-time Air Pollution
Authors: Akshay Dirisala
Abstract:
Humans had developed a highly organized and efficient civilization to live in by improving the basic needs of humans like housing, transportation, and utilities. These developments have made a huge impact on major environmental factors. Air pollution is one prominent environmental factor that needs to be addressed to maintain a sustainable and healthier lifestyle. Textiles have always been at the forefront of helping humans shield from environmental conditions. With the growth in the field of electronic textiles, we now have the capability of monitoring the atmosphere in real time to understand and analyze the environment that a particular person is mostly spending their time at. Integrating textiles with the particulate matter sensors that measure air quality and pollutants that have a direct impact on human health will help to understand what type of air we are breathing. This research idea aims to develop a textile product and a process of collecting the pollutants through particulate matter sensors, which are equipped inside a smart textile product and store the data to develop a machine learning model to analyze the health conditions of the person wearing the garment and periodically notifying them not only will help to be cautious of airborne diseases but will help to regulate the diseases and could also help to take care of skin conditions.Keywords: air pollution, e-textiles, particulate matter sensors, environment, machine learning models
Procedia PDF Downloads 1009300 Advancing Power Network Maintenance: The Development and Implementation of a Robotic Cable Splicing Machine
Authors: Ali Asmari, Alex Symington, Htaik Than, Austin Caradonna, John Senft
Abstract:
This paper presents the collaborative effort between ULC Technologies and Con Edison in developing a groundbreaking robotic cable splicing machine. The focus is on the machine's design, which integrates advanced robotics and automation to enhance safety and efficiency in power network maintenance. The paper details the operational steps of the machine, including cable grounding, cutting, and removal of different insulation layers, and discusses its novel technological approach. The significant benefits over traditional methods, such as improved worker safety and reduced outage times, are highlighted based on the field data collected during the validation phase of the project. The paper also explores the future potential and scalability of this technology, emphasizing its role in transforming the landscape of power network maintenance.Keywords: cable splicing machine, power network maintenance, electric distribution, electric transmission, medium voltage cable
Procedia PDF Downloads 589299 Developing a Machine Learning-based Cost Prediction Model for Construction Projects using Particle Swarm Optimization
Authors: Soheila Sadeghi
Abstract:
Accurate cost prediction is essential for effective project management and decision-making in the construction industry. This study aims to develop a cost prediction model for construction projects using Machine Learning techniques and Particle Swarm Optimization (PSO). The research utilizes a comprehensive dataset containing project cost estimates, actual costs, resource details, and project performance metrics from a road reconstruction project. The methodology involves data preprocessing, feature selection, and the development of an Artificial Neural Network (ANN) model optimized using PSO. The study investigates the impact of various input features, including cost estimates, resource allocation, and project progress, on the accuracy of cost predictions. The performance of the optimized ANN model is evaluated using metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared. The results demonstrate the effectiveness of the proposed approach in predicting project costs, outperforming traditional benchmark models. The feature selection process identifies the most influential variables contributing to cost variations, providing valuable insights for project managers. However, this study has several limitations. Firstly, the model's performance may be influenced by the quality and quantity of the dataset used. A larger and more diverse dataset covering different types of construction projects would enhance the model's generalizability. Secondly, the study focuses on a specific optimization technique (PSO) and a single Machine Learning algorithm (ANN). Exploring other optimization methods and comparing the performance of various ML algorithms could provide a more comprehensive understanding of the cost prediction problem. Future research should focus on several key areas. Firstly, expanding the dataset to include a wider range of construction projects, such as residential buildings, commercial complexes, and infrastructure projects, would improve the model's applicability. Secondly, investigating the integration of additional data sources, such as economic indicators, weather data, and supplier information, could enhance the predictive power of the model. Thirdly, exploring the potential of ensemble learning techniques, which combine multiple ML algorithms, may further improve cost prediction accuracy. Additionally, developing user-friendly interfaces and tools to facilitate the adoption of the proposed cost prediction model in real-world construction projects would be a valuable contribution to the industry. The findings of this study have significant implications for construction project management, enabling proactive cost estimation, resource allocation, budget planning, and risk assessment, ultimately leading to improved project performance and cost control. This research contributes to the advancement of cost prediction techniques in the construction industry and highlights the potential of Machine Learning and PSO in addressing this critical challenge. However, further research is needed to address the limitations and explore the identified future research directions to fully realize the potential of ML-based cost prediction models in the construction domain.Keywords: cost prediction, construction projects, machine learning, artificial neural networks, particle swarm optimization, project management, feature selection, road reconstruction
Procedia PDF Downloads 379298 Information Disclosure And Financial Sentiment Index Using a Machine Learning Approach
Authors: Alev Atak
Abstract:
In this paper, we aim to create a financial sentiment index by investigating the company’s voluntary information disclosures. We retrieve structured content from BIST 100 companies’ financial reports for the period 1998-2018 and extract relevant financial information for sentiment analysis through Natural Language Processing. We measure strategy-related disclosures and their cross-sectional variation and classify report content into generic sections using synonym lists divided into four main categories according to their liquidity risk profile, risk positions, intra-annual information, and exposure to risk. We use Word Error Rate and Cosin Similarity for comparing and measuring text similarity and derivation in sets of texts. In addition to performing text extraction, we will provide a range of text analysis options, such as the readability metrics, word counts using pre-determined lists (e.g., forward-looking, uncertainty, tone, etc.), and comparison with reference corpus (word, parts of speech and semantic level). Therefore, we create an adequate analytical tool and a financial dictionary to depict the importance of granular financial disclosure for investors to identify correctly the risk-taking behavior and hence make the aggregated effects traceable.Keywords: financial sentiment, machine learning, information disclosure, risk
Procedia PDF Downloads 879297 Heuristic for Scheduling Correlated Parallel Machine to Minimize Maximum Lateness and Total Weighed Completion Time
Authors: Yang-Kuei Lin, Yun-Xi Zhang
Abstract:
This research focuses on the bicriteria correlated parallel machine scheduling problem. The two objective functions considered in this problem are to minimize maximum lateness and total weighted completion time. We first present a mixed integer programming (MIP) model that can find the entire efficient frontier for the studied problem. Next, we have proposed a bicriteria heuristic that can find non-dominated solutions for the studied problem. The performance of the proposed bicriteria heuristic is compared with the efficient frontier generated by solving the MIP model. Computational results indicate that the proposed bicriteria heuristic can solve the problem efficiently and find a set of diverse solutions that are uniformly distributed along the efficient frontier.Keywords: bicriteria, correlated parallel machines, heuristic, scheduling
Procedia PDF Downloads 1349296 CompleX-Machine: An Automated Testing Tool Using X-Machine Theory
Authors: E. K. A. Ogunshile
Abstract:
This paper is aimed at creating an Automatic Java X-Machine testing tool for software development. The nature of software development is changing; thus, the type of software testing tools required is also changing. Software is growing increasingly complex and, in part due to commercial impetus for faster software releases with new features and value, increasingly in danger of containing faults. These faults can incur huge cost for software development organisations and users; Cambridge Judge Business School’s research estimated the cost of software bugs to the global economy is $312 billion. Beyond the cost, faster software development methodologies and increasing expectations on developers to become testers is driving demand for faster, automated, and effective tools to prevent potential faults as early as possible in the software development lifecycle. Using X-Machine theory, this paper will explore a new tool to address software complexity, changing expectations on developers, faster development pressures and methodologies, with a view to reducing the huge cost of fixing software bugs.Keywords: conformance testing, finite state machine, software testing, x-machine
Procedia PDF Downloads 2639295 The Convergence of IoT and Machine Learning: A Survey of Real-time Stress Detection System
Authors: Shreyas Gambhirrao, Aditya Vichare, Aniket Tembhurne, Shahuraj Bhosale
Abstract:
In today's rapidly evolving environment, stress has emerged as a significant health concern across different age groups. Stress that isn't controlled, whether it comes from job responsibilities, health issues, or the never-ending news cycle, can have a negative effect on our well-being. The problem is further aggravated by the ongoing connection to technology. In this high-tech age, identifying and controlling stress is vital. In order to solve this health issue, the study focuses on three key metrics for stress detection: body temperature, heart rate, and galvanic skin response (GSR). These parameters along with the Support Vector Machine classifier assist the system to categorize stress into three groups: 1) Stressed, 2) Not stressed, and 3) Moderate stress. Proposed training model, a NodeMCU combined with particular sensors collects data in real-time and rapidly categorizes individuals based on their stress levels. Real-time stress detection is made possible by this creative combination of hardware and software.Keywords: real time stress detection, NodeMCU, sensors, heart-rate, body temperature, galvanic skin response (GSR), support vector machine
Procedia PDF Downloads 659294 Social Learning and the Flipped Classroom
Authors: Albin Wallace
Abstract:
This paper examines the use of social learning platforms in conjunction with the emergent pedagogy of the ‘flipped classroom’. In particular the attributes of the social learning platform “Edmodo” is considered alongside the changes in the way in which online learning environments are being implemented, especially within British education. Some observations are made regarding the use and usefulness of these platforms along with a consideration of the increasingly decentralized nature of education in the United Kingdom.Keywords: education, Edmodo, Internet, learning platforms
Procedia PDF Downloads 5329293 New Advanced Medical Software Technology Challenges and Evolution of the Regulatory Framework in Expert Software, Artificial Intelligence, and Machine Learning
Authors: Umamaheswari Shanmugam, Silvia Ronchi
Abstract:
Software, artificial intelligence, and machine learning can improve healthcare through innovative and advanced technologies that can use the large amount and variety of data generated during healthcare services every day; one of the significant advantages of these new technologies is the ability to get experience and knowledge from real-world use and to improve their performance continuously. Healthcare systems and institutions can significantly benefit because the use of advanced technologies improves the efficiency and efficacy of healthcare. Software-defined as a medical device, is stand-alone software that is intended to be used for patients for one or more of these specific medical intended uses: - diagnosis, prevention, monitoring, prediction, prognosis, treatment or alleviation of a disease, any other health conditions, replacing or modifying any part of a physiological or pathological process–manage the received information from in vitro specimens derived from the human samples (body) and without principal main action of its principal intended use by pharmacological, immunological or metabolic definition. Software qualified as medical devices must comply with the general safety and performance requirements applicable to medical devices. These requirements are necessary to ensure high performance and quality and protect patients' safety. The evolution and the continuous improvement of software used in healthcare must consider the increase in regulatory requirements, which are becoming more complex in each market. The gap between these advanced technologies and the new regulations is the biggest challenge for medical device manufacturers. Regulatory requirements can be considered a market barrier, as they can delay or obstacle the device's approval. Still, they are necessary to ensure performance, quality, and safety. At the same time, they can be a business opportunity if the manufacturer can define the appropriate regulatory strategy in advance. The abstract will provide an overview of the current regulatory framework, the evolution of the international requirements, and the standards applicable to medical device software in the potential market all over the world.Keywords: artificial intelligence, machine learning, SaMD, regulatory, clinical evaluation, classification, international requirements, MDR, 510k, PMA, IMDRF, cyber security, health care systems
Procedia PDF Downloads 829292 Mobile Learning in Teacher Education: A Review in Context of Developing Countries
Authors: Mehwish Raza
Abstract:
Mobile learning (m-learning) offers unique affordances to learners, setting them free of limitations posed by time and geographic space; thus becoming an affordable device for convenient distant learning. There is a plethora of research available on mobile learning projects planned, implemented and evaluated across disciplines in the context of developed countries, however, the potential of m-learning at different educational levels remain unexplored with little evidence of research carried out in developing countries. Despite the favorable technical infrastructure offered by cellular networks and boom in mobile subscriptions in the developing world, there is limited focus on utilizing m-learning for education and development purposes. The objective of this review is to unify findings from m-learning projects that have been implemented in developing countries such as Pakistan, Bangladesh, Philippines, India, and Tanzania for teachers’ in-service training. The purpose is to draw upon key characteristics of mobile learning that would be useful for future researchers to inform conceptualizations of mobile learning for developing countries.Keywords: design model, developing countries, key characteristics, mobile learning
Procedia PDF Downloads 4349291 An Investigation on Engineering Students’ Perceptions towards E-Learning in the UK
Authors: Razzaghifard P., Arya F., Chen S. Chien-I, Abdi B., Razzaghifard V., Arya A. H., Nazary A., Hosseinpour H., Ghabelnezam K.
Abstract:
E-learning, also known as online learning, has indicated increased growth in recent years. One of the critical factors in the successful application of e-learning in higher education is students’ perceptions towards it. The main purpose of this paper is to investigate the perceptions of engineering students about e-learning in the UK. For the purpose of the present study, 145 second-year engineering students were randomly selected from the total population of 1280 participants. The participants were asked to complete a questionnaire containing 16 items. The data collected from the questionnaire were analyzed through the Statistical Package for Social Science (SPSS) software. The findings of the study revealed that the majority of participants have negative perceptions of e-learning. Most of the students had trouble interacting effectively during online classes. Furthermore, the majority of participants had negative experiences with the learning platform they used during e-learning. Suggestions were made on what could be done to improve the students’ perceptions of e-learning.Keywords: e-learning, higher, education, engineering education, online learning
Procedia PDF Downloads 1149290 Item Response Calibration/Estimation: An Approach to Adaptive E-Learning System Development
Authors: Adeniran Adetunji, Babalola M. Florence, Akande Ademola
Abstract:
In this paper, we made an overview on the concept of adaptive e-Learning system, enumerates the elements of adaptive learning concepts e.g. A pedagogical framework, multiple learning strategies and pathways, continuous monitoring and feedback on student performance, statistical inference to reach final learning strategy that works for an individual learner by “mass-customization”. Briefly highlights the motivation of this new system proposed for effective learning teaching. E-Review literature on the concept of adaptive e-learning system and emphasises on the Item Response Calibration, which is an important approach to developing an adaptive e-Learning system. This paper write-up is concluded on the justification of item response calibration/estimation towards designing a successful and effective adaptive e-Learning system.Keywords: adaptive e-learning system, pedagogical framework, item response, computer applications
Procedia PDF Downloads 5829289 1-D Convolutional Neural Network Approach for Wheel Flat Detection for Freight Wagons
Authors: Dachuan Shi, M. Hecht, Y. Ye
Abstract:
With the trend of digitalization in railway freight transport, a large number of freight wagons in Germany have been equipped with telematics devices, commonly placed on the wagon body. A telematics device contains a GPS module for tracking and a 3-axis accelerometer for shock detection. Besides these basic functions, it is desired to use the integrated accelerometer for condition monitoring without any additional sensors. Wheel flats as a common type of failure on wheel tread cause large impacts on wagons and infrastructure as well as impulsive noise. A large wheel flat may even cause safety issues such as derailments. In this sense, this paper proposes a machine learning approach for wheel flat detection by using car body accelerations. Due to suspension systems, impulsive signals caused by wheel flats are damped significantly and thus could be buried in signal noise and disturbances. Therefore, it is very challenging to detect wheel flats using car body accelerations. The proposed algorithm considers the envelope spectrum of car body accelerations to eliminate the effect of noise and disturbances. Subsequently, a 1-D convolutional neural network (CNN), which is well known as a deep learning method, is constructed to automatically extract features in the envelope-frequency domain and conduct classification. The constructed CNN is trained and tested on field test data, which are measured on the underframe of a tank wagon with a wheel flat of 20 mm length in the operational condition. The test results demonstrate the good performance of the proposed algorithm for real-time fault detection.Keywords: fault detection, wheel flat, convolutional neural network, machine learning
Procedia PDF Downloads 1239288 An Efficient Machine Learning Model to Detect Metastatic Cancer in Pathology Scans Using Principal Component Analysis Algorithm, Genetic Algorithm, and Classification Algorithms
Authors: Bliss Singhal
Abstract:
Machine learning (ML) is a branch of Artificial Intelligence (AI) where computers analyze data and find patterns in the data. The study focuses on the detection of metastatic cancer using ML. Metastatic cancer is the stage where cancer has spread to other parts of the body and is the cause of approximately 90% of cancer-related deaths. Normally, pathologists spend hours each day to manually classifying whether tumors are benign or malignant. This tedious task contributes to mislabeling metastasis being over 60% of the time and emphasizes the importance of being aware of human error and other inefficiencies. ML is a good candidate to improve the correct identification of metastatic cancer, saving thousands of lives and can also improve the speed and efficiency of the process, thereby taking fewer resources and time. So far, the deep learning methodology of AI has been used in research to detect cancer. This study is a novel approach to determining the potential of using preprocessing algorithms combined with classification algorithms in detecting metastatic cancer. The study used two preprocessing algorithms: principal component analysis (PCA) and the genetic algorithm, to reduce the dimensionality of the dataset and then used three classification algorithms: logistic regression, decision tree classifier, and k-nearest neighbors to detect metastatic cancer in the pathology scans. The highest accuracy of 71.14% was produced by the ML pipeline comprising of PCA, the genetic algorithm, and the k-nearest neighbor algorithm, suggesting that preprocessing and classification algorithms have great potential for detecting metastatic cancer.Keywords: breast cancer, principal component analysis, genetic algorithm, k-nearest neighbors, decision tree classifier, logistic regression
Procedia PDF Downloads 739287 Development of Locally Fabricated Honey Extracting Machine
Authors: Akinfiresoye W. A., Olarewaju O. O., Okunola, Okunola I. O.
Abstract:
An indigenous honey-extracting machine was designed, fabricated and evaluated at the workshop of the department of Agricultural Technology, Federal Polytechnic, Ile-Oluji, Nigeria using locally available materials. It has the extraction unit, the presser, the honey collector and the frame. The harvested honeycomb is placed inside the cylindrical extraction unit with perforated holes. The press plate was then placed on the comb while the hydraulic press of 3 tons was placed on it, supported by the frame. The hydraulic press, which is manually operated, forces the oil out of the extraction chamber through the perforated holes into the honey collector positioned at the lowest part of the extraction chamber. The honey-extracting machine has an average throughput of 2.59 kg/min and an efficiency of about 91%. The cost of producing the honey extracting machine is NGN 31, 700: 00, thirty-one thousand and seven hundred nairas only or $70 at NGN 452.8 to a dollar. This cost is affordable to beekeepers and would-be honey entrepreneurs. The honey-extracting machine is easy to operate and maintain without any complex technical know-how.Keywords: honey, extractor, cost, efficiency
Procedia PDF Downloads 679286 Exploring Data Leakage in EEG Based Brain-Computer Interfaces: Overfitting Challenges
Authors: Khalida Douibi, Rodrigo Balp, Solène Le Bars
Abstract:
In the medical field, applications related to human experiments are frequently linked to reduced samples size, which makes the training of machine learning models quite sensitive and therefore not very robust nor generalizable. This is notably the case in Brain-Computer Interface (BCI) studies, where the sample size rarely exceeds 20 subjects or a few number of trials. To address this problem, several resampling approaches are often used during the data preparation phase, which is an overly critical step in a data science analysis process. One of the naive approaches that is usually applied by data scientists consists in the transformation of the entire database before the resampling phase. However, this can cause model’ s performance to be incorrectly estimated when making predictions on unseen data. In this paper, we explored the effect of data leakage observed during our BCI experiments for device control through the real-time classification of SSVEPs (Steady State Visually Evoked Potentials). We also studied potential ways to ensure optimal validation of the classifiers during the calibration phase to avoid overfitting. The results show that the scaling step is crucial for some algorithms, and it should be applied after the resampling phase to avoid data leackage and improve results.Keywords: data leackage, data science, machine learning, SSVEP, BCI, overfitting
Procedia PDF Downloads 1479285 Integration of Virtual Learning of Induction Machines for Undergraduates
Authors: Rajesh Kumar, Puneet Aggarwal
Abstract:
In context of understanding problems faced by undergraduate students while carrying out laboratory experiments dealing with high voltages, it was found that most of the students are hesitant to work directly on machine. The reason is that error in the circuitry might lead to deterioration of machine and laboratory instruments. So, it has become inevitable to include modern pedagogic techniques for undergraduate students, which would help them to first carry out experiment in virtual system and then to work on live circuit. Further advantages include that students can try out their intuitive ideas and perform in virtual environment, hence leading to new research and innovations. In this paper, virtual environment used is of MATLAB/Simulink for three-phase induction machines. The performance analysis of three-phase induction machine is carried out using virtual environment which includes Direct Current (DC) Test, No-Load Test, and Block Rotor Test along with speed torque characteristics for different rotor resistances and input voltage, respectively. Further, this paper carries out computer aided teaching of basic Voltage Source Inverter (VSI) drive circuitry. Hence, this paper gave undergraduates a clearer view of experiments performed on virtual machine (No-Load test, Block Rotor test and DC test, respectively). After successful implementation of basic tests, VSI circuitry is implemented, and related harmonic distortion (THD) and Fast Fourier Transform (FFT) of current and voltage waveform are studied.Keywords: block rotor test, DC test, no load test, virtual environment, voltage source inverter
Procedia PDF Downloads 3429284 Semantic Platform for Adaptive and Collaborative e-Learning
Authors: Massra M. Sabeima, Myriam lamolle, Mohamedade Farouk Nanne
Abstract:
Adapting the learning resources of an e-learning system to the characteristics of the learners is an important aspect to consider when designing an adaptive e-learning system. However, this adaptation is not a simple process; it requires the extraction, analysis, and modeling of user information. This implies a good representation of the user's profile, which is the backbone of the adaptation process. Moreover, during the e-learning process, collaboration with similar users (same geographic province or knowledge context) is important. Productive collaboration motivates users to continue or not abandon the course and increases the assimilation of learning objects. The contribution of this work is the following: we propose an adaptive e-learning semantic platform to recommend learning resources to learners, using ontology to model the user profile and the course content, furthermore an implementation of a multi-agent system able to progressively generate the learning graph (taking into account the user's progress, and the changes that occur) for each user during the learning process, and to synchronize the users who collaborate on a learning object.Keywords: adaptative learning, collaboration, multi-agent, ontology
Procedia PDF Downloads 1649283 Blockchain-Resilient Framework for Cloud-Based Network Devices within the Architecture of Self-Driving Cars
Authors: Mirza Mujtaba Baig
Abstract:
Artificial Intelligence (AI) is evolving rapidly, and one of the areas in which this field has influenced is automation. The automobile, healthcare, education, and robotic industries deploy AI technologies constantly, and the automation of tasks is beneficial to allow time for knowledge-based tasks and also introduce convenience to everyday human endeavors. The paper reviews the challenges faced with the current implementations of autonomous self-driving cars by exploring the machine learning, robotics, and artificial intelligence techniques employed for the development of this innovation. The controversy surrounding the development and deployment of autonomous machines, e.g., vehicles, begs the need for the exploration of the configuration of the programming modules. This paper seeks to add to the body of knowledge of research assisting researchers in decreasing the inconsistencies in current programming modules. Blockchain is a technology of which applications are mostly found within the domains of financial, pharmaceutical, manufacturing, and artificial intelligence. The registering of events in a secured manner as well as applying external algorithms required for the data analytics are especially helpful for integrating, adapting, maintaining, and extending to new domains, especially predictive analytics applications.Keywords: artificial intelligence, automation, big data, self-driving cars, machine learning, neural networking algorithm, blockchain, business intelligence
Procedia PDF Downloads 1119282 A Theoretical Framework for Design Theories in Mobile Learning: A Higher Education Perspective
Authors: Paduri Veerabhadram, Antoinette Lombard
Abstract:
In this paper a framework for hypothesizing about mobile learning to complement theories of formal and informal learning is presented. As such, activity theory will form the main theoretical lens through which the elements involved in formal and informal learning for mobile learning will be explored, specifically related to context-aware mobile learning application. The author believes that the complexity of the relationships involved can best be analysed using activity theory. Activity theory, as a social, cultural and activity theory can be used as a mobile learning framework in an academic environment, but to develop an optimal artifact, through investigation of inherent system's contradictions. As such, it serves as a powerful modelling tool to explore and understand the design of a mobile learning environment in the study’s environment. The Academic Tool Kit Framework (ATKF) as also employed for designing of a constructivism learning environment, effective in assisting universities to facilitate lecturers to effectively implement learning through utilizing mobile devices. Results indicate a positive perspective of students in the use of mobile devices for formal and informal learning, based on the context-aware learning environment developed through the use of activity theory and ATKF.Keywords: collaborative learning, cooperative learning, context-aware learning environment, mobile learning, pedagogy
Procedia PDF Downloads 5489281 Technology in English Language Teaching and Its Benefits in Improving Language Skills
Authors: Yasir Naseem
Abstract:
In this fast-growing and evolving world, usage and adoption of technology have displayed an essential component of the learning process, both in and out of the class, which converges and incorporates every domain of the learning aspects. It aids in learning distinct entities irrespective of their levels of challenge. It also incorporates both viewpoints of learning, i.e., competence as well as the performances of the learner. In today's learning scenario, nearly every language class ordinarily uses some form of technology. It integrates with various teaching methodologies and transforms in a way that now it grew as an integral part of the language learning courses. It has been employed to facilitate, promote, and enhances language learning. It facilitates educators in numerous ways and enhances their methodologies by equipping them to modify classroom activities, which covers every aspect of language learning.Keywords: communication, methodology, technology, skills
Procedia PDF Downloads 1649280 Fast Approximate Bayesian Contextual Cold Start Learning (FAB-COST)
Authors: Jack R. McKenzie, Peter A. Appleby, Thomas House, Neil Walton
Abstract:
Cold-start is a notoriously difficult problem which can occur in recommendation systems, and arises when there is insufficient information to draw inferences for users or items. To address this challenge, a contextual bandit algorithm – the Fast Approximate Bayesian Contextual Cold Start Learning algorithm (FAB-COST) – is proposed, which is designed to provide improved accuracy compared to the traditionally used Laplace approximation in the logistic contextual bandit, while controlling both algorithmic complexity and computational cost. To this end, FAB-COST uses a combination of two moment projection variational methods: Expectation Propagation (EP), which performs well at the cold start, but becomes slow as the amount of data increases; and Assumed Density Filtering (ADF), which has slower growth of computational cost with data size but requires more data to obtain an acceptable level of accuracy. By switching from EP to ADF when the dataset becomes large, it is able to exploit their complementary strengths. The empirical justification for FAB-COST is presented, and systematically compared to other approaches on simulated data. In a benchmark against the Laplace approximation on real data consisting of over 670, 000 impressions from autotrader.co.uk, FAB-COST demonstrates at one point increase of over 16% in user clicks. On the basis of these results, it is argued that FAB-COST is likely to be an attractive approach to cold-start recommendation systems in a variety of contexts.Keywords: cold-start learning, expectation propagation, multi-armed bandits, Thompson Sampling, variational inference
Procedia PDF Downloads 1019279 Hybrid GNN Based Machine Learning Forecasting Model For Industrial IoT Applications
Authors: Atish Bagchi, Siva Chandrasekaran
Abstract:
Background: According to World Bank national accounts data, the estimated global manufacturing value-added output in 2020 was 13.74 trillion USD. These manufacturing processes are monitored, modelled, and controlled by advanced, real-time, computer-based systems, e.g., Industrial IoT, PLC, SCADA, etc. These systems measure and manipulate a set of physical variables, e.g., temperature, pressure, etc. Despite the use of IoT, SCADA etc., in manufacturing, studies suggest that unplanned downtime leads to economic losses of approximately 864 billion USD each year. Therefore, real-time, accurate detection, classification and prediction of machine behaviour are needed to minimise financial losses. Although vast literature exists on time-series data processing using machine learning, the challenges faced by the industries that lead to unplanned downtimes are: The current algorithms do not efficiently handle the high-volume streaming data from industrial IoTsensors and were tested on static and simulated datasets. While the existing algorithms can detect significant 'point' outliers, most do not handle contextual outliers (e.g., values within normal range but happening at an unexpected time of day) or subtle changes in machine behaviour. Machines are revamped periodically as part of planned maintenance programmes, which change the assumptions on which original AI models were created and trained. Aim: This research study aims to deliver a Graph Neural Network(GNN)based hybrid forecasting model that interfaces with the real-time machine control systemand can detect, predict machine behaviour and behavioural changes (anomalies) in real-time. This research will help manufacturing industries and utilities, e.g., water, electricity etc., reduce unplanned downtimes and consequential financial losses. Method: The data stored within a process control system, e.g., Industrial-IoT, Data Historian, is generally sampled during data acquisition from the sensor (source) and whenpersistingin the Data Historian to optimise storage and query performance. The sampling may inadvertently discard values that might contain subtle aspects of behavioural changes in machines. This research proposed a hybrid forecasting and classification model which combines the expressive and extrapolation capability of GNN enhanced with the estimates of entropy and spectral changes in the sampled data and additional temporal contexts to reconstruct the likely temporal trajectory of machine behavioural changes. The proposed real-time model belongs to the Deep Learning category of machine learning and interfaces with the sensors directly or through 'Process Data Historian', SCADA etc., to perform forecasting and classification tasks. Results: The model was interfaced with a Data Historianholding time-series data from 4flow sensors within a water treatment plantfor45 days. The recorded sampling interval for a sensor varied from 10 sec to 30 min. Approximately 65% of the available data was used for training the model, 20% for validation, and the rest for testing. The model identified the anomalies within the water treatment plant and predicted the plant's performance. These results were compared with the data reported by the plant SCADA-Historian system and the official data reported by the plant authorities. The model's accuracy was much higher (20%) than that reported by the SCADA-Historian system and matched the validated results declared by the plant auditors. Conclusions: The research demonstrates that a hybrid GNN based approach enhanced with entropy calculation and spectral information can effectively detect and predict a machine's behavioural changes. The model can interface with a plant's 'process control system' in real-time to perform forecasting and classification tasks to aid the asset management engineers to operate their machines more efficiently and reduce unplanned downtimes. A series of trialsare planned for this model in the future in other manufacturing industries.Keywords: GNN, Entropy, anomaly detection, industrial time-series, AI, IoT, Industry 4.0, Machine Learning
Procedia PDF Downloads 1379278 Research on the Online Learning Activities Design and Students’ Experience Based on APT Model
Authors: Wang Yanli, Cheng Yun, Yang Jiarui
Abstract:
Due to the separation of teachers and students, online teaching during the COVID-19 epidemic was faced with many problems, such as low enthusiasm of students, distraction, low learning atmosphere, and insufficient interaction between teachers and students. The essay designed the elaborate online learning activities of the course 'Research Methods of Educational Science' based on the APT model from three aspects of multiple assessment methods, a variety of teaching methods, and online learning environment and technology. Student's online learning experience was examined from the perception of online course, the perception of the online learning environment, and satisfaction after the course’s implementation. The research results showed that students have a positive overall evaluation of online courses, a high degree of engagement in learning, positive acceptance of online learning, and high satisfaction with it, but students hold a relatively neutral attitude toward online learning. And some dimensions in online learning experience were found to have positive influence on students' satisfaction with online learning. We suggest making the good design of online courses, selecting proper learning platforms, and conducting blended learning to improve students’ learning experience. This study has both theoretical and practical significance for the design, implementation, effect feedback, and sustainable development of online teaching in the post-epidemic era.Keywords: APT model, online learning, online learning activities, learning experience
Procedia PDF Downloads 1249277 An Augmented Reality Based Self-Learning Support System for Skills Training
Authors: Chinlun Lai, Yu-Mei Chang
Abstract:
In this paper, an augmented reality learning support system is proposed to replace the traditional teaching tool thus to help students improve their learning motivation, effectiveness, and efficiency. The system can not only reduce the exhaust of educational hardware and realistic material, but also provide an eco-friendly and self-learning practical environment in any time and anywhere with immediate practical experiences feedback. To achieve this, an interactive self-training methodology which containing step by step operation directions is designed using virtual 3D scenario and wearable device platforms. The course of nasogastric tube care of nursing skills is selected as the test example for self-learning and online test. From the experimental results, it is observed that the support system can not only increase the student’s learning interest but also improve the learning performance than the traditional teaching methods. Thus, it fulfills the strategy of learning by practice while reducing the related cost and effort significantly and is practical in various fields.Keywords: augmented reality technology, learning support system, self-learning, simulation learning method
Procedia PDF Downloads 1599276 Interpretation of the Russia-Ukraine 2022 War via N-Gram Analysis
Authors: Elcin Timur Cakmak, Ayse Oguzlar
Abstract:
This study presents the results of the tweets sent by Twitter users on social media about the Russia-Ukraine war by bigram and trigram methods. On February 24, 2022, Russian President Vladimir Putin declared a military operation against Ukraine, and all eyes were turned to this war. Many people living in Russia and Ukraine reacted to this war and protested and also expressed their deep concern about this war as they felt the safety of their families and their futures were at stake. Most people, especially those living in Russia and Ukraine, express their views on the war in different ways. The most popular way to do this is through social media. Many people prefer to convey their feelings using Twitter, one of the most frequently used social media tools. Since the beginning of the war, it is seen that there have been thousands of tweets about the war from many countries of the world on Twitter. These tweets accumulated in data sources are extracted using various codes for analysis through Twitter API and analysed by Python programming language. The aim of the study is to find the word sequences in these tweets by the n-gram method, which is known for its widespread use in computational linguistics and natural language processing. The tweet language used in the study is English. The data set consists of the data obtained from Twitter between February 24, 2022, and April 24, 2022. The tweets obtained from Twitter using the #ukraine, #russia, #war, #putin, #zelensky hashtags together were captured as raw data, and the remaining tweets were included in the analysis stage after they were cleaned through the preprocessing stage. In the data analysis part, the sentiments are found to present what people send as a message about the war on Twitter. Regarding this, negative messages make up the majority of all the tweets as a ratio of %63,6. Furthermore, the most frequently used bigram and trigram word groups are found. Regarding the results, the most frequently used word groups are “he, is”, “I, do”, “I, am” for bigrams. Also, the most frequently used word groups are “I, do, not”, “I, am, not”, “I, can, not” for trigrams. In the machine learning phase, the accuracy of classifications is measured by Classification and Regression Trees (CART) and Naïve Bayes (NB) algorithms. The algorithms are used separately for bigrams and trigrams. We gained the highest accuracy and F-measure values by the NB algorithm and the highest precision and recall values by the CART algorithm for bigrams. On the other hand, the highest values for accuracy, precision, and F-measure values are achieved by the CART algorithm, and the highest value for the recall is gained by NB for trigrams.Keywords: classification algorithms, machine learning, sentiment analysis, Twitter
Procedia PDF Downloads 669275 IoT Based Soil Moisture Monitoring System for Indoor Plants
Authors: Gul Rahim Rahimi
Abstract:
The IoT-based soil moisture monitoring system for indoor plants is designed to address the challenges of maintaining optimal moisture levels in soil for plant growth and health. The system utilizes sensor technology to collect real-time data on soil moisture levels, which is then processed and analyzed using machine learning algorithms. This allows for accurate and timely monitoring of soil moisture levels, ensuring plants receive the appropriate amount of water to thrive. The main objectives of the system are twofold: to keep plants fresh and healthy by preventing water deficiency and to provide users with comprehensive insights into the water content of the soil on a daily and hourly basis. By monitoring soil moisture levels, users can identify patterns and trends in water consumption, allowing for more informed decision-making regarding watering schedules and plant care. The scope of the system extends to the agriculture industry, where it can be utilized to minimize the efforts required by farmers to monitor soil moisture levels manually. By automating the process of soil moisture monitoring, farmers can optimize water usage, improve crop yields, and reduce the risk of plant diseases associated with over or under-watering. Key technologies employed in the system include the Capacitive Soil Moisture Sensor V1.2 for accurate soil moisture measurement, the Node MCU ESP8266-12E Board for data transmission and communication, and the Arduino framework for programming and development. Additionally, machine learning algorithms are utilized to analyze the collected data and provide actionable insights. Cloud storage is utilized to store and manage the data collected from multiple sensors, allowing for easy access and retrieval of information. Overall, the IoT-based soil moisture monitoring system offers a scalable and efficient solution for indoor plant care, with potential applications in agriculture and beyond. By harnessing the power of IoT and machine learning, the system empowers users to make informed decisions about plant watering, leading to healthier and more vibrant indoor environments.Keywords: IoT-based, soil moisture monitoring, indoor plants, water management
Procedia PDF Downloads 409274 A Long Short-Term Memory Based Deep Learning Model for Corporate Bond Price Predictions
Authors: Vikrant Gupta, Amrit Goswami
Abstract:
The fixed income market forms the basis of the modern financial market. All other assets in financial markets derive their value from the bond market. Owing to its over-the-counter nature, corporate bonds have relatively less data publicly available and thus is researched upon far less compared to Equities. Bond price prediction is a complex financial time series forecasting problem and is considered very crucial in the domain of finance. The bond prices are highly volatile and full of noise which makes it very difficult for traditional statistical time-series models to capture the complexity in series patterns which leads to inefficient forecasts. To overcome the inefficiencies of statistical models, various machine learning techniques were initially used in the literature for more accurate forecasting of time-series. However, simple machine learning methods such as linear regression, support vectors, random forests fail to provide efficient results when tested on highly complex sequences such as stock prices and bond prices. hence to capture these intricate sequence patterns, various deep learning-based methodologies have been discussed in the literature. In this study, a recurrent neural network-based deep learning model using long short term networks for prediction of corporate bond prices has been discussed. Long Short Term networks (LSTM) have been widely used in the literature for various sequence learning tasks in various domains such as machine translation, speech recognition, etc. In recent years, various studies have discussed the effectiveness of LSTMs in forecasting complex time-series sequences and have shown promising results when compared to other methodologies. LSTMs are a special kind of recurrent neural networks which are capable of learning long term dependencies due to its memory function which traditional neural networks fail to capture. In this study, a simple LSTM, Stacked LSTM and a Masked LSTM based model has been discussed with respect to varying input sequences (three days, seven days and 14 days). In order to facilitate faster learning and to gradually decompose the complexity of bond price sequence, an Empirical Mode Decomposition (EMD) has been used, which has resulted in accuracy improvement of the standalone LSTM model. With a variety of Technical Indicators and EMD decomposed time series, Masked LSTM outperformed the other two counterparts in terms of prediction accuracy. To benchmark the proposed model, the results have been compared with traditional time series models (ARIMA), shallow neural networks and above discussed three different LSTM models. In summary, our results show that the use of LSTM models provide more accurate results and should be explored more within the asset management industry.Keywords: bond prices, long short-term memory, time series forecasting, empirical mode decomposition
Procedia PDF Downloads 1289273 On an Approach for Rule Generation in Association Rule Mining
Authors: B. Chandra
Abstract:
In Association Rule Mining, much attention has been paid for developing algorithms for large (frequent/closed/maximal) itemsets but very little attention has been paid to improve the performance of rule generation algorithms. Rule generation is an important part of Association Rule Mining. In this paper, a novel approach named NARG (Association Rule using Antecedent Support) has been proposed for rule generation that uses memory resident data structure named FCET (Frequent Closed Enumeration Tree) to find frequent/closed itemsets. In addition, the computational speed of NARG is enhanced by giving importance to the rules that have lower antecedent support. Comparative performance evaluation of NARG with fast association rule mining algorithm for rule generation has been done on synthetic datasets and real life datasets (taken from UCI Machine Learning Repository). Performance analysis shows that NARG is computationally faster in comparison to the existing algorithms for rule generation.Keywords: knowledge discovery, association rule mining, antecedent support, rule generation
Procedia PDF Downloads 3149272 Customer Preference in the Textile Market: Fabric-Based Analysis
Authors: Francisca Margarita Ocran
Abstract:
Underwear, and more particularly bras and panties, are defined as intimate clothing. Strictly speaking, they enhance the place of women in the public or private satchel. Therefore, women's lingerie is a complex garment with a high involvement profile, motivating consumers to buy it not only by its functional utility but also by the multisensory experience it provides them. Customer behavior models are generally based on customer data mining, and each model is designed to answer questions at a specific time. Predicting the customer experience is uncertain and difficult. Thus, knowledge of consumers' tastes in lingerie deserves to be treated as an experiential product, where the dimensions of the experience motivating consumers to buy a lingerie product and to remain faithful to it must be analyzed in detail by the manufacturers and retailers to engage and retain consumers, which is why this research aims to identify the variables that push consumers to choose their lingerie product, based on an in-depth analysis of the types of fabrics used to make lingerie. The data used in this study comes from online purchases. Machine learning approach with the use of Python programming language and Pycaret gives us a precision of 86.34%, 85.98%, and 84.55% for the three algorithms to use concerning the preference of a buyer in front of a range of lingerie. Gradient Boosting, random forest, and K Neighbors were used in this study; they are very promising and rich in the classification of preference in the textile industry.Keywords: consumer behavior, data mining, lingerie, machine learning, preference
Procedia PDF Downloads 77