Search results for: hybrid learning algorithm

Authors: Halil Ibrahim Demir, Caner Erden, Abdullah Hulusi Kokcam, Mumtaz Ipek

Abstract:

Process planning, scheduling, and due date assignment are three important manufacturing functions which are studied independently in literature. There are hundreds of works on IPPS and SWDDA problems but a few works on IPPSDDA problem. Integrating these three functions is very crucial due to the high relationship between them. Since the scheduling problem is in the NP-Hard problem class without any integration, an integrated problem is even harder to solve. This study focuses on the integration of these functions. Sum of weighted tardiness, earliness, and due date related costs are used as a penalty function. Random search and hybrid metaheuristics are used to solve the integrated problem. Marginal improvement in random search is very high in the early iterations and reduces enormously in later iterations. At that point directed search contribute to marginal improvement more than random search. In this study, random and genetic search methods are combined to find better solutions. Results show that overall performance becomes better as the integration level increases.

Keywords: process planning, genetic algorithm, hybrid search, random search, weighted due-date assignment, weighted scheduling

Procedia PDF Downloads 353

Authors: Cemil Turan, Mohammad Shukri Salman

Abstract:

The convergence rate of the least-mean-square (LMS) algorithm deteriorates if the input signal to the filter is correlated. In a system identification problem, this convergence rate can be improved if the signal is white and/or if the system is sparse. We recently proposed a sparse transform domain LMS-type algorithm that uses a variable step-size for a sparse system identification. The proposed algorithm provided high performance even if the input signal is highly correlated. In this work, we investigate the performance of the proposed TD-LMS algorithm for a large number of filter tap which is also a critical issue for standard LMS algorithm. Additionally, the optimum value of the most important parameter is calculated for all experiments. Moreover, the convergence analysis of the proposed algorithm is provided. The performance of the proposed algorithm has been compared to different algorithms in a sparse system identification setting of different sparsity levels and different number of filter taps. Simulations have shown that the proposed algorithm has prominent performance compared to the other algorithms.

Keywords: adaptive filtering, sparse system identification, TD-LMS algorithm, VSSLMS algorithm

Procedia PDF Downloads 337

Authors: Mohammad Vahed, Ana Sadeghitohidi, Majid Vahed, Hiroki Takahashi

Abstract:

In the genomics field, the huge amounts of data have produced by the next-generation sequencers (NGS). Data volumes are very rapidly growing, as it is postulated that more than one billion bases will be produced per year in 2020. The growth rate of produced data is much faster than Moore's law in computer technology. This makes it more difficult to deal with genomics data, such as storing data, searching information, and finding the hidden information. It is required to develop the analysis platform for genomics big data. Cloud computing newly developed enables us to deal with big data more efficiently. Hadoop is one of the frameworks distributed computing and relies upon the core of a Big Data as a Service (BDaaS). Although many services have adopted this technology, e.g. amazon, there are a few applications in the biology field. Here, we propose a new algorithm to more efficiently deal with the genomics big data, e.g. sequencing data. Our algorithm consists of two parts: First is that BDaaS is applied for handling the data more efficiently. Second is that the hybrid method of MapReduce and Fuzzy logic is applied for data processing. This step can be parallelized in implementation. Our algorithm has great potential in computational analysis of genomics big data, e.g. de novo genome assembly and sequence similarity search. We will discuss our algorithm and its feasibility.

Keywords: big data, fuzzy logic, MapReduce, Hadoop, cloud computing

Procedia PDF Downloads 282

Authors: Lee Bih Ni

Abstract:

This paper discusses that good learning involves all academic groups in the school. Blended learning is learning outside the classroom. Google Classroom is a free service learning app for schools, non-profit organizations and anyone with a personal Google account. Facilities accessed through computers and mobile phones are very useful for school teachers and students. Blended learning classrooms using both traditional and technology-based methods for teaching have become the norm for many educators. Using Google Classroom gives students access to online learning. Even if the teacher is not in the classroom, the teacher can provide learning. This is the supervision of the form of the teacher when the student is outside the school.

Keywords: blended learning, learning app, google classroom, schools

Procedia PDF Downloads 127

Authors: Hritwik Ghosh, Irfan Sadiq Rahat, Sachi Nandan Mohanty, J. V. R. Ravindra

Abstract:

In the rapidly evolving landscape of medical diagnostics, the early detection and accurate classification of skin cancer remain paramount for effective treatment outcomes. This research delves into the transformative potential of Artificial Intelligence (AI), specifically Deep Learning (DL), as a tool for discerning and categorizing various skin conditions. Utilizing a diverse dataset of 3,000 images representing nine distinct skin conditions, we confront the inherent challenge of class imbalance. This imbalance, where conditions like melanomas are over-represented, is addressed by incorporating class weights during the model training phase, ensuring an equitable representation of all conditions in the learning process. Our pioneering approach introduces a hybrid model, amalgamating the strengths of two renowned Convolutional Neural Networks (CNNs), VGG16 and ResNet50. These networks, pre-trained on the ImageNet dataset, are adept at extracting intricate features from images. By synergizing these models, our research aims to capture a holistic set of features, thereby bolstering classification performance. Preliminary findings underscore the hybrid model's superiority over individual models, showcasing its prowess in feature extraction and classification. Moreover, the research emphasizes the significance of rigorous data pre-processing, including image resizing, color normalization, and segmentation, in ensuring data quality and model reliability. In essence, this study illuminates the promising role of AI and DL in revolutionizing skin cancer diagnostics, offering insights into its potential applications in broader medical domains.

Keywords: artificial intelligence, machine learning, deep learning, skin cancer, dermatology, convolutional neural networks, image classification, computer vision, healthcare technology, cancer detection, medical imaging

Procedia PDF Downloads 61

Authors: C. Iraklis, G. Evmiridis, A. Iraklis

Abstract:

Renewable energy sources and distributed power generation units already have an important role in electrical power generation. A mixture of different technologies penetrating the electrical grid, adds complexity in the management of distribution networks. High penetration of distributed power generation units creates node over-voltages, huge power losses, unreliable power management, reverse power flow and congestion. This paper presents an optimization algorithm capable of reducing congestion and power losses, both described as a function of weighted sum. Two factors that describe congestion are being proposed. An upgraded selective particle swarm optimization algorithm (SPSO) is used as a solution tool focusing on the technique of network reconfiguration. The upgraded SPSO algorithm is achieved with the addition of a heuristic algorithm specializing in reduction of power losses, with several scenarios being tested. Results show significant improvement in minimization of losses and congestion while achieving very small calculation times.

Keywords: congestion, distribution networks, loss reduction, particle swarm optimization, smart grid

Procedia PDF Downloads 429

Authors: Jalal Maqbool, Gyu Myoung Lee

Abstract:

Using smart devices for context aware mobile learning is becoming increasingly popular. This has led to mobile learning technology becoming an indispensable part of today’s learning environment and platforms. However, some fundamental issues remain - namely, mobile learning still lacks the ability to truly understand human reaction and user behaviour. This is due to the fact that current mobile learning systems are passive and not aware of learners’ changing contextual situations. They rely on static information about mobile learners. In addition, current mobile learning platforms lack the capability to incorporate dynamic contextual situations into learners’ preferences. Thus, this thesis aims to address these issues highlighted by designing a context aware framework which is able to sense learner’s contextual situations, handle data dynamically, and which can use contextual information to suggest bespoke learning content according to a learner’s preferences. This is to be underpinned by a robust recommendation system, which has the capability to perform these functions, thus providing learners with a truly context-aware mobile learning experience, delivering learning contents using smart devices and adapting to learning preferences as and when it is required. In addition, part of designing an algorithm for the recommendation engine has to be based on learner and application needs, personal characteristics and circumstances, as well as being able to comprehend human cognitive processes which would enable the technology to interact effectively and deliver mobile learning content which is relevant, according to the learner’s contextual situations. The concept of this proposed project is to provide a new method of smart learning, based on a capable recommendation engine for providing an intuitive mobile learning model based on learner actions.

Keywords: aware, context, learning, mobile

Procedia PDF Downloads 233

Authors: Vincent Liu

Abstract:

Machine learning algorithms (ML) can achieve high accuracy in predicting outcomes compared to classical models. Metaheuristic, nature-inspired algorithms can enhance traditional ML algorithms by optimizing them such as by performing feature selection. We compare ten ML algorithms to predict 30-day hospital readmission rates for diabetes patients in the US using a dataset from UCI Machine Learning Repository with feature selection performed by Greywolf nature-inspired algorithm. The baseline accuracy for the initial random forest model was 65%. After performing feature engineering, SMOTE for class balancing, and Greywolf optimization, the machine learning algorithms showed better metrics, including F1 scores, accuracy, and confusion matrix with improvements ranging in 10%-30%, and a best model of XGBoost with an accuracy of 95%. Applying machine learning this way can improve patient outcomes as unnecessary rehospitalizations can be prevented by focusing on patients that are at a higher risk of readmission.

Keywords: diabetes, machine learning, 30-day readmission, metaheuristic

Procedia PDF Downloads 35

Authors: Pimploi Tirastittam, Suppara Charoenpoom

Abstract:

Nowadays the asynchronous learning has granted the permission to the anywhere and anything learning via the technology and E-media which give the learner more convenient. This research is about the design of the blended and online learning for the asynchronous learning of the process management subject in order to create the prototype of this subject asynchronous learning which will create the easiness and increase capability in the learning. The pattern of learning is the integration between the in-class learning and online learning via the internet. This research is mainly focused on the online learning and the online learning can be divided into 5 parts which are virtual classroom, online content, collaboration, assessment and reference material. After the system design was finished, it was evaluated and tested by 5 experts in blended learning design and 10 students which the user’s satisfaction level is good. The result is as good as the assumption so the system can be used in the process management subject for a real usage.

Keywords: blended learning, asynchronous learning, design, process management

Procedia PDF Downloads 387

Authors: Ariful Islam, Showkat Ahmad Lone

Abstract:

Statistical distributions have long been employed in the assessment of semiconductor devices and product reliability. The power function-distribution is one of the most important distributions in the modern reliability practice and can be frequently preferred over mathematically more complex distributions, such as the Weibull and the lognormal, because of its simplicity. Moreover, it may exhibit a better fit for failure data and provide more appropriate information about reliability and hazard rates in some circumstances. This study deals with estimating information about failure times of items under step-stress partially accelerated life tests for competing risk based on adoptive type-I progressive hybrid censoring criteria. The life data of the units under test is assumed to follow Mukherjee-Islam distribution. The point and interval maximum-likelihood estimations are obtained for distribution parameters and tampering coefficient. The performances of the resulting estimators of the developed model parameters are evaluated and investigated by using a simulation algorithm.

Keywords: adoptive progressive hybrid censoring, competing risk, mukherjee-islam distribution, partially accelerated life testing, simulation study

Procedia PDF Downloads 331

Authors: Jeryes Danial, Yosi Ben Asher

Abstract:

Algorithms for controlling a swarm of robots is an active research field, out of which cattle herding is one of the most complex problems to solve. In this paper, we derive an independent herding algorithm that is specifically designed for a swarm of quadcopters. The algorithm works by devising flight trajectories that cause the cows to run-away in the desired direction and hence herd cows that are distributed in a given field towards a common gathering point. Unlike previously proposed swarm herding algorithms, this algorithm does not use a flocking model but rather stars each cow separately. The effectiveness of this algorithm is verified experimentally using a simulator. We use a special set of experiments attempting to demonstrate that the herding times of this algorithm correspond to field diameter small constant regardless of the number of cows in the field. This is an optimal result indicating that the algorithm groups the cows into intermediate groups and herd them as one forming ever closing bigger groups.

Keywords: swarm, independent, distributed, algorithm

Procedia PDF Downloads 161

Authors: Bassem Nassar, Wessam Hussein, Medhat Mokhtar

Abstract:

The crucial concern of satellite operations is to ensure the health and safety of satellites. The worst case in this perspective is probably the loss of a mission but the more common interruption of satellite functionality can result in compromised mission objectives. All the data acquiring from the spacecraft are known as Telemetry (TM), which contains the wealth information related to the health of all its subsystems. Each single item of information is contained in a telemetry parameter, which represents a time-variant property (i.e. a status or a measurement) to be checked. As a consequence, there is a continuous improvement of TM monitoring systems in order to reduce the time required to respond to changes in a satellite's state of health. A fast conception of the current state of the satellite is thus very important in order to respond to occurring failures. Statistical multivariate latent techniques are one of the vital learning tools that are used to tackle the aforementioned problem coherently. Information extraction from such rich data sources using advanced statistical methodologies is a challenging task due to the massive volume of data. To solve this problem, in this paper, we present a proposed unsupervised learning algorithm based on Principle Component Analysis (PCA) technique. The algorithm is particularly applied on an actual remote sensing spacecraft. Data from the Attitude Determination and Control System (ADCS) was acquired under two operation conditions: normal and faulty states. The models were built and tested under these conditions and the results shows that the algorithm could successfully differentiate between these operations conditions. Furthermore, the algorithm provides competent information in prediction as well as adding more insight and physical interpretation to the ADCS operation.

Keywords: space telemetry monitoring, multivariate analysis, PCA algorithm, space operations

Procedia PDF Downloads 399

Authors: Heesuk Seo, Yongtae Kim

Abstract:

Online learning started in the 1990s, the spread of the Internet has been through the era of e-learning paradigm of online education in the era of smart learning change. Reflecting the different nature of the mobile to anywhere anytime, anywhere was also allows the form of learning, it was also available through the learning content and interaction. We are developing a cloud system, 'TLINKS CLOUD' that allows you to configure the environment of the smart learning without the need for additional infrastructure. Using the big-data analysis for e-learning contents, we provide an integrated solution for e-learning tailored to individual study.

Keywords: authority tool, big data analysis, e-learning, HTML5

Procedia PDF Downloads 386

Authors: Muhammet Baldan, Emel Timuçin

Abstract:

Molecular solubility prediction plays a crucial role in various fields, such as drug discovery, environmental science, and material science. In this study, we compare the performance of five machine learning algorithms—linear regression, support vector machines (SVM), random forests, gradient boosting machines (GBM), and neural networks—for predicting molecular solubility using the AqSolDB dataset. The dataset consists of 9981 data points with their corresponding solubility values. MACCS keys (166 bits), RDKit properties (20 properties), and structural properties(3) features are extracted for every smile representation in the dataset. A total of 189 features were used for training and testing for every molecule. Each algorithm is trained on a subset of the dataset and evaluated using metrics accuracy scores. Additionally, computational time for training and testing is recorded to assess the efficiency of each algorithm. Our results demonstrate that random forest model outperformed other algorithms in terms of predictive accuracy, achieving an 0.93 accuracy score. Gradient boosting machines and neural networks also exhibit strong performance, closely followed by support vector machines. Linear regression, while simpler in nature, demonstrates competitive performance but with slightly higher errors compared to ensemble methods. Overall, this study provides valuable insights into the performance of machine learning algorithms for molecular solubility prediction, highlighting the importance of algorithm selection in achieving accurate and efficient predictions in practical applications.

Keywords: random forest, machine learning, comparison, feature extraction

Procedia PDF Downloads 20

Authors: Pratama R. Yunia, Firmansyah, I., Ariani, Ulfa R. Maharani, Fikri M. Al

Abstract:

Nowadays, notwithstanding that the role of SMS as a means of communication has been largely replaced by online applications such as WhatsApp, Telegram, and others, the fact that SMS is still used for certain and important communication needs is indisputable. Among them is for sending one time password (OTP) as an authentication media for various online applications ranging from chatting, shopping to online banking applications. However, the usage of SMS does not pretty much guarantee the security of transmitted messages. As a matter of fact, the transmitted messages between BTS is still in the form of plaintext, making it extremely vulnerable to eavesdropping, especially if the message is confidential, for instance, the OTP. One solution to overcome this problem is to use an SMS application which provides security services for each transmitted message. Responding to this problem, in this study, an automatic key SMS encryption scheme was designed as a means to secure SMS communication. The proposed scheme allows SMS sending, which is automatically encrypted with keys that are constantly changing (automatic key update), automatic key exchange, and automatic key generation. In terms of the security method, the proposed scheme applies cryptographic techniques with a hybrid cryptosystem mechanism. Proofing the proposed scheme, a client to client SMS encryption application was developed using Java platform with AES-256 as encryption algorithm, RSA-768 as public and private key generator and SHA-256 for message hashing function. The result of this study is a secure automatic key SMS encryption scheme using hybrid cryptosystem which can guarantee the security of every transmitted message, so as to become a reliable solution in sending confidential messages through SMS although it still has weaknesses in terms of processing time.

Keywords: encryption scheme, hybrid cryptosystem, one time password, SMS security

Procedia PDF Downloads 111

Authors: Lei Zhang, Tingting Xu, Jun He, Zhenyu Yan

Abstract:

Email marketing is one of the most important segments of online marketing. It has been proved to be the most effective way to acquire and retain customers. The email content is vital to customers. Different customers may have different familiarity with a product, so a successful marketing strategy must personalize email content based on individual customers’ product affinity. In this study, we build our personalized email marketing strategy with three types of emails: nurture, promotion, and conversion. Each type of email has a different influence on customers. We investigate this difference by analyzing customers’ open rates, click rates and opt-out rates. Feature importance from response models is also analyzed. The goal of the marketing strategy is to improve the click rate on conversion-type emails. To build the personalized strategy, we formulate the problem as a reinforcement learning problem and adopt a Q-learning algorithm with variations. The simulation results show that our model-based strategy outperforms the current marketer’s strategy.

Keywords: email marketing, email content, reinforcement learning, machine learning, Q-learning

Procedia PDF Downloads 178

Authors: Tamanna Jethava, Rahul Joshi

Abstract:

Frequent Item sets play an essential role in many data Mining tasks that try to find interesting patterns from the database. Typically it refers to a set of items that frequently appear together in transaction dataset. There are several mining algorithm being used for frequent item set mining, yet most do not scale to the type of data we presented with today, so called “BIG DATA”. Big Data is a collection of large data sets. Our approach is to work on the frequent item set mining over the large dataset with scalable and speedy way. Big Data basically works with Map Reduce along with HDFS is used to find out frequent item sets from Big Data on large cluster. This paper focuses on using pre-processing & mining algorithm as hybrid approach for big data over Hadoop platform.

Keywords: frequent item set mining, big data, Hadoop, MapReduce

Procedia PDF Downloads 399

Authors: Sikander Singh Cheema, Jasmeen Kaur

Abstract:

In this paper, the concept of data mining is summarized and its one of the important process i.e KDD is summarized. The data mining based on Genetic Algorithm is researched in and ways to achieve the data mining Genetic Algorithm are surveyed. This paper also conducts a formal review on the area of data mining tasks and genetic algorithm in various fields.

Keywords: data mining, KDD, genetic algorithm, descriptive mining, predictive mining

Procedia PDF Downloads 575

Authors: Monojit Manna, Arpan Adhikary

Abstract:

In Mobile cloud sensing across the globe, an emerging paradigm is selected by the user to compute sensing tasks. In urban cities current days, Mobile vehicles are adapted to perform the task of data sensing and data collection for universality and mobility. In this work, we focused on the optimality and mobile nodes that can be selected in order to collect the maximum amount of data from urban areas and fulfill the required data in the future period within a couple of minutes. We map out the requirement of the vehicle to configure the maximum data optimization problem and budget. The Application implementation is basically set up to generalize a realistic online platform in which real-time vehicles are moving apparently in a continuous manner. The data center has the authority to select a set of vehicles immediately. A deep learning-based scheme with the help of mobile vehicles (DLMV) will be proposed to collect sensing data from the urban environment. From the future time perspective, this work proposed a deep learning-based offline algorithm to predict mobility. Therefore, we proposed a greedy approach applying an online algorithm step into a subset of vehicles for an NP-complete problem with a limited budget. Real dataset experimental extensive evaluations are conducted for the real mobility dataset in Rome. The result of the experiment not only fulfills the efficiency of our proposed solution but also proves the validity of DLMV and improves the quantity of collecting the sensing data compared with other algorithms.

Keywords: mobile crowdsensing, deep learning, vehicle recruitment, sensing coverage, data collection

Procedia PDF Downloads 58

Authors: A. U. Haque, W. Asrar, A. A. Omar, E. Sulaeman, J. S Mohamed Ali

Abstract:

Open jet testing is a valuable testing technique which provides the desired results with reasonable accuracy. It has been used in past for the airships and now has recently been applied for the hybrid ones, having more non-buoyant force coming from the wings, empennage and the fuselage. In the present review work, an effort has been done to review the challenges involved in open jet testing. In order to shed light on the application of this technique, the experimental results of two different configurations are presented. Although, the aerodynamic results of such vehicles are unique to its own design; however, it will provide a starting point for planning any future testing. Few important testing areas which need more attention are also highlighted. Most of the hybrid buoyant aerial vehicles are unconventional in shape and there experimental data is generated, which is unique to its own design.

Keywords: open jet testing, aerodynamics, hybrid buoyant aerial vehicles, airships

Procedia PDF Downloads 557

Authors: Budhvin T. Withana, Sulochana Rupasinghe

Abstract:

The educational system faces a significant concern with regards to Dyslexia and Dysgraphia, which are learning disabilities impacting reading and writing abilities. This is particularly challenging for children who speak the Sinhala language due to its complexity and uniqueness. Commonly used methods to detect the risk of Dyslexia and Dysgraphia rely on subjective assessments, leading to limited coverage and time-consuming processes. Consequently, delays in diagnoses and missed opportunities for early intervention can occur. To address this issue, the project developed a hybrid model that incorporates various deep learning techniques to detect the risk of Dyslexia and Dysgraphia. Specifically, Resnet50, VGG16, and YOLOv8 models were integrated to identify handwriting issues. The outputs of these models were then combined with other input data and fed into an MLP model. Hyperparameters of the MLP model were fine-tuned using Grid Search CV, enabling the identification of optimal values for the model. This approach proved to be highly effective in accurately predicting the risk of Dyslexia and Dysgraphia, providing a valuable tool for early detection and intervention. The Resnet50 model exhibited a training accuracy of 0.9804 and a validation accuracy of 0.9653. The VGG16 model achieved a training accuracy of 0.9991 and a validation accuracy of 0.9891. The MLP model demonstrated impressive results with a training accuracy of 0.99918, a testing accuracy of 0.99223, and a loss of 0.01371. These outcomes showcase the high accuracy achieved by the proposed hybrid model in predicting the risk of Dyslexia and Dysgraphia.

Keywords: neural networks, risk detection system, dyslexia, dysgraphia, deep learning, learning disabilities, data science

Procedia PDF Downloads 44

Authors: F. Erdal, E. Dogan, F. E. Uz

Abstract:

In this study, firefly optimization based optimum design algorithm is presented for the grillage systems. Naming of the algorithm is derived from the fireflies, whose sense of movement is taken as a model in the development of the algorithm. Fireflies’ being unisex and attraction between each other constitute the basis of the algorithm. The design algorithm considers the displacement and strength constraints which are implemented from LRFD-AISC (Load and Resistance Factor Design-American Institute of Steel Construction). It selects the appropriate W (Wide Flange)-sections for the transverse and longitudinal beams of the grillage system among 272 discrete W-section designations given in LRFD-AISC so that the design limitations described in LRFD are satisfied and the weight of the system is confined to be minimal. Number of design examples is considered to demonstrate the efficiency of the algorithm presented.

Keywords: firefly algorithm, steel grillage systems, optimum design, stochastic search techniques

Procedia PDF Downloads 407

Authors: Hervice Roméo Fogno Fotsoa, Germaine Djuidje Kenmoe, Claude Vidal Aloyem Kazé

Abstract:

One of the main applications of machine learning is the prediction of time series. But a more accurate prediction requires a more optimal model of machine learning. Several optimization techniques have been developed, but without considering the input variables disposition of the system. Thus, this work aims to present a new machine learning architecture optimization technique based on their optimal input variables disposition. The validations are done on the prediction of wind time series, using data collected in Cameroon. The number of possible dispositions with four input variables is determined, i.e., twenty-four. Each of the dispositions is used to perform the prediction, with the main criteria being the training and prediction performances. The results obtained from a static architecture and a dynamic architecture of neural networks have shown that these performances are a function of the input variable's disposition, and this is in a different way from the architectures. This analysis revealed that it is necessary to take into account the input variable's disposition for the development of a more optimal neural network model. Thus, a new neural network training algorithm is proposed by introducing the search for the optimal input variables disposition in the traditional back-propagation algorithm. The results of the application of this new optimization approach on the two single neural network architectures are compared with the previously obtained results step by step. Moreover, this proposed approach is validated in a collaborative optimization method with a single objective optimization technique, i.e., genetic algorithm back-propagation neural networks. From these comparisons, it is concluded that each proposed model outperforms its traditional model in terms of training and prediction performance of time series. Thus the proposed optimization approach can be useful in improving the accuracy of time series forecasts. This proves that the proposed optimization approach can be useful in improving the accuracy of time series prediction based on machine learning.

Keywords: input variable disposition, machine learning, optimization, performance, time series prediction

Procedia PDF Downloads 83

Authors: Seyed Mehdi Ghezi, Hesam Hasanpoor

Abstract:

This scientific article explores enhancement methods for ensemble learning with the aim of improving the performance of classifiers in the analysis and classification of brain signals. The research approach in this field consists of two main parts, each with its own strengths and weaknesses. The choice of approach depends on the specific research question and available resources. By combining these approaches and leveraging their respective strengths, researchers can enhance the accuracy and reliability of classification results, consequently advancing our understanding of the brain and its functions. The first approach focuses on utilizing machine learning methods to identify the best features among the vast array of features present in brain signals. The selection of features varies depending on the research objective, and different techniques have been employed for this purpose. For instance, the genetic algorithm has been used in some studies to identify the best features, while optimization methods have been utilized in others to identify the most influential features. Additionally, machine learning techniques have been applied to determine the influential electrodes in classification. Ensemble learning plays a crucial role in identifying the best features that contribute to learning, thereby improving the overall results. The second approach concentrates on designing and implementing methods for selecting the best classifier or utilizing meta-classifiers to enhance the final results in ensemble learning. In a different section of the research, a single classifier is used instead of multiple classifiers, employing different sets of features to improve the results. The article provides an in-depth examination of each technique, highlighting their advantages and limitations. By integrating these techniques, researchers can enhance the performance of classifiers in the analysis and classification of brain signals. This advancement in ensemble learning methodologies contributes to a better understanding of the brain and its functions, ultimately leading to improved accuracy and reliability in brain signal analysis and classification.

Keywords: ensemble learning, brain signals, classification, feature selection, machine learning, genetic algorithm, optimization methods, influential features, influential electrodes, meta-classifiers

Procedia PDF Downloads 59

Authors: Kamyar Tolouei, Ehsan Moosavi

Abstract:

In open-pit mines, the long-term production scheduling optimization problem (LTPSOP) is a complicated problem that contains constraints, large datasets, and uncertainties. Uncertainty in the output is caused by several geological, economic, or technical factors. Due to its dimensions and NP-hard nature, it is usually difficult to find an ideal solution to the LTPSOP. The optimal schedule generally restricts the ore, metal, and waste tonnages, average grades, and cash flows of each period. Past decades have witnessed important measurements of long-term production scheduling and optimal algorithms since researchers have become highly cognizant of the issue. In fact, it is not possible to consider LTPSOP as a well-solved problem. Traditional production scheduling methods in open-pit mines apply an estimated orebody model to produce optimal schedules. The smoothing result of some geostatistical estimation procedures causes most of the mine schedules and production predictions to be unrealistic and imperfect. With the expansion of simulation procedures, the risks from grade uncertainty in ore reserves can be evaluated and organized through a set of equally probable orebody realizations. In this paper, to synthesize grade uncertainty into the strategic mine schedule, a stochastic integer programming framework is presented to LTPSOP. The objective function of the model is to maximize the net present value and minimize the risk of deviation from the production targets considering grade uncertainty simultaneously while satisfying all technical constraints and operational requirements. Instead of applying one estimated orebody model as input to optimize the production schedule, a set of equally probable orebody realizations are applied to synthesize grade uncertainty in the strategic mine schedule and to produce a more profitable and risk-based production schedule. A mixture of metaheuristic procedures and mathematical methods paves the way to achieve an appropriate solution. This paper introduced a hybrid model between the augmented Lagrangian relaxation (ALR) method and the metaheuristic algorithm, the Harris Hawks optimization (HHO), to solve the LTPSOP under grade uncertainty conditions. In this study, the HHO is experienced to update Lagrange coefficients. Besides, a machine learning method called Random Forest is applied to estimate gold grade in a mineral deposit. The Monte Carlo method is used as the simulation method with 20 realizations. The results specify that the progressive versions have been considerably developed in comparison with the traditional methods. The outcomes were also compared with the ALR-genetic algorithm and ALR-sub-gradient. To indicate the applicability of the model, a case study on an open-pit gold mining operation is implemented. The framework displays the capability to minimize risk and improvement in the expected net present value and financial profitability for LTPSOP. The framework could control geological risk more effectively than the traditional procedure considering grade uncertainty in the hybrid model framework.

Keywords: grade uncertainty, metaheuristic algorithms, open-pit mine, production scheduling optimization

Procedia PDF Downloads 85

Authors: Benson Ade Eniola Afere

Abstract:

This paper introduces a family of fourth-order hybrid beta polynomial kernels developed for statistical analysis. The assessment of these kernels' performance centers on two critical metrics: asymptotic mean integrated squared error (AMISE) and kernel efficiency. Through the utilization of both simulated and real-world datasets, a comprehensive evaluation was conducted, facilitating a thorough comparison with conventional fourth-order polynomial kernels. The evaluation procedure encompassed the computation of AMISE and efficiency values for both the proposed hybrid kernels and the established classical kernels. The consistently observed trend was the superior performance of the hybrid kernels when compared to their classical counterparts. This trend persisted across diverse datasets, underscoring the resilience and efficacy of the hybrid approach. By leveraging these performance metrics and conducting evaluations on both simulated and real-world data, this study furnishes compelling evidence in favour of the superiority of the proposed hybrid beta polynomial kernels. The discernible enhancement in performance, as indicated by lower AMISE values and higher efficiency scores, strongly suggests that the proposed kernels offer heightened suitability for statistical analysis tasks when compared to traditional kernels.

Keywords: AMISE, efficiency, fourth-order Kernels, hybrid Kernels, Kernel density estimation

Procedia PDF Downloads 58

Authors: Budhvin T. Withana, Sulochana Rupasinghe

Abstract:

The problem of Dyslexia and Dysgraphia, two learning disabilities that affect reading and writing abilities, respectively, is a major concern for the educational system. Due to the complexity and uniqueness of the Sinhala language, these conditions are especially difficult for children who speak it. The traditional risk detection methods for Dyslexia and Dysgraphia frequently rely on subjective assessments, making it difficult to cover a wide range of risk detection and time-consuming. As a result, diagnoses may be delayed and opportunities for early intervention may be lost. The project was approached by developing a hybrid model that utilized various deep learning techniques for detecting risk of Dyslexia and Dysgraphia. Specifically, Resnet50, VGG16 and YOLOv8 were integrated to detect the handwriting issues, and their outputs were fed into an MLP model along with several other input data. The hyperparameters of the MLP model were fine-tuned using Grid Search CV, which allowed for the optimal values to be identified for the model. This approach proved to be effective in accurately predicting the risk of Dyslexia and Dysgraphia, providing a valuable tool for early detection and intervention of these conditions. The Resnet50 model achieved an accuracy of 0.9804 on the training data and 0.9653 on the validation data. The VGG16 model achieved an accuracy of 0.9991 on the training data and 0.9891 on the validation data. The MLP model achieved an impressive training accuracy of 0.99918 and a testing accuracy of 0.99223, with a loss of 0.01371. These results demonstrate that the proposed hybrid model achieved a high level of accuracy in predicting the risk of Dyslexia and Dysgraphia.

Keywords: neural networks, risk detection system, Dyslexia, Dysgraphia, deep learning, learning disabilities, data science

Procedia PDF Downloads 73

Authors: Emily Moore, Dora Amos, Tracy Ellimah, Natasha Parrott

Abstract:

Postoperative haematoma is a well-recognised complication of thyroid surgery with an incidence of 1-5%. Haematoma formation causes progressive airway obstruction, necessitating emergency bedside haematoma evacuation in up to ¼ of patients. ENT UK, BAETS and DAS have developed consensus guidelines to improve perioperative care, recommending that all healthcare staff interacting with patients undergoing thyroid surgery should be trained in managing post-thyroidectomy haematoma. The aim was to assess the effectiveness of a hybrid simulation model in improving clinician’s confidence in dealing with this surgical emergency. A hybrid simulation was designed, consisting of a standardised patient wearing a part-task trainer to mimic a post-thyroidectomy haematoma in a real patient. The part-task trainer was an adapted C-spine collar with layers of silicone representing the skin and strap muscles and thickened jelly representing the haematoma. Both the skin and strap muscle layers had to be opened in order to evacuate the haematoma. Boxes have been implemented into the appropriate post operative areas (recovery and surgical wards), which contain a printed algorithm designed to assist in remembering a sequence of steps for haematoma evacuation using the ‘SCOOP’ method (skin exposure, cut sutures, open skin, open muscles, pack wound) along with all the necessary equipment to open the front of the neck. Small-group teaching sessions were delivered by ENT and anaesthetic trainees to members of the multidisciplinary team normally involved in perioperative patient care, which included ENT surgeons, anaesthetists, recovery nurses, HCAs and ODPs. The DESATS acronym of signs and symptoms to recognise (difficulty swallowing, EWS score, swelling, anxiety, tachycardia, stridor) was highlighted. Then participants took part in the hybrid simulation in order to practice this ‘SCOOP’ method of haematoma evacuation. Participants were surveyed using a Likert scale to assess their level of confidence pre- and post teaching session. 30 clinicians took part. Confidence (agreed/strongly agreed) in recognition of post thyroidectomy haematoma improved from 58.6% to 96.5%. Confidence in management improved from 27.5% to 89.7%. All participants successfully decompressed the haematoma. All participants agreed/strongly agreed, that the sessions were useful for their learning. Multidisciplinary team simulation teaching is effective at significantly improving confidence in both the recognition and management of postoperative haematoma. Hybrid simulation sessions are useful and should be incorporated into training for clinicians.

Keywords: thyroid surgery, haematoma, teaching, hybrid simulation

Procedia PDF Downloads 80

Authors: Daly M. J, Condron C, Mulhall C, Eppich W, O'Neill J.

Abstract:

Introduction: In contemporary clinical cardiology, comprehensive and holistic bedside evaluation including accurate cardiac auscultation is in decline despite having positive effects on patients and their outcomes. Methods: Scripted histories and scoring checklists for three clinical scenarios in cardiology were co-created and refined through iterative consensus by a panel of clinical experts; these were then paired with recordings of auscultatory findings from three actual patients with known valvular heart disease. A wearable vest with embedded pressure-sensitive panel speakers was developed to transmit these recordings when examined at the standard auscultation points. RCSI medical students volunteered for a series of three formative long case examinations in cardiology (LC1 – LC3) using this hybrid simulation. Participants were randomised into two groups: Group 1 received individual teaching from an expert trainer between LC1 and LC2; Group 2 received the same intervention between LC2 and LC3. Each participant’s long case examination performance was recorded and blindly scored by two peer participants and two RCSI examiners. Results: Sixty-eight participants were included in the study (age 27.6 ± 0.1 years; 74% female) and randomised into two groups; there were no significant differences in baseline characteristics between groups. Overall, the median total faculty examiner score was 39.8% (35.8 – 44.6%) in LC1 and increased to 63.3% (56.9 – 66.4%) in LC3, with those in Group 1 showing a greater improvement in LC2 total score than that observed in Group 2 (p < .001). Using the novel checklist, intraclass correlation coefficients (ICC) were excellent between examiners in all cases: ICC .994 – .997 (p < .001); correlation between peers and examiners improved in LC2 following peer grading of LC1 performances: ICC .857 – .867 (p < .001). Conclusion: Hybrid simulation and quantitative grading improve learning, standardisation of assessment, and direct comparisons of both performance and acumen in clinical cardiology.

Keywords: cardiology, clinical skills, long case examination, hybrid simulation, checklist

Procedia PDF Downloads 95

Authors: Tracy Ho, Huann-Shyang Lin, Mina Lin

Abstract:

This study investigated the different learning path of students with different learning attitude and learning styles in Arts Creation. Based on direct instruction, guided-discovery learning, and discovery learning theories, a tablet app including the following three learning areas were developed for students: (1) replication and remix practice area, (2) guided creation area, and (3) free creation area. Thirty. students with different learning attitude and learning styles were invited to use this app. Students’ learning behaviors were categorized and defined. The results will provide both educators and researchers with insights that can form a useful foundation for designing different content and strategy with the application of new technologies in school teaching. It also sheds light on how an educational App can be designed to enhance Arts Creation.

Keywords: App, arts creation, learning attitude, learning style, tablet

Procedia PDF Downloads 253