Search results for: machine learning algorithms

Authors: Ava Dodd, Jonathan Adams

Abstract:

The purpose of this study is to explore the characteristics of developing a machine learning application using synthetic data. The study is structured to develop the application for the purpose of deploying the computer vision model. The findings discuss the realities of attempting to develop a computer vision model for practical purpose, and detail the processes, tools, and techniques that were used to meet accuracy requirements. The research reveals that synthetic data represents another variable that can be adjusted to improve the performance of a computer vision model. Further, a suite of tools and tuning recommendations are provided.

Keywords: computer vision, machine learning, synthetic data, YOLOv4

Procedia PDF Downloads 220

Authors: Wanyi Zhu, Xia Ming, Huafeng Wang, Junda Chen, Lu Liu, Jiangwei Jiang, Guohua Liu

Abstract:

Anomaly detection is a first and imperative step needed to respond to unexpected problems and to assure high performance and security in large data center management. This paper presents an online anomaly detection system through an innovative approach of ensemble machine learning and adaptive differentiation algorithms, and applies them to performance data collected from a continuous monitoring system for multi-tier web applications running in Alibaba data centers. We evaluate the effectiveness and efficiency of this algorithm with production traffic data and compare with the traditional anomaly detection approaches such as a static threshold and other deviation-based detection techniques. The experiment results show that our algorithm correctly identifies the unexpected performance variances of any running application, with an acceptable false positive rate. This proposed approach has already been deployed in real-time production environments to enhance the efficiency and stability in daily data center operations.

Keywords: Alibaba data centers, anomaly detection, big data computation, dynamic ensemble learning

Procedia PDF Downloads 196

Authors: Animish Jain

Abstract:

This study deals with using Multiplicative Weight Update within artificial intelligence and machine learning to create models that can diagnose skin cancer using microscopic images of cancer samples. In this study, the multiplicative weight update method is used to take the predictions of multiple models to try and acquire more accurate results. Logistic Regression, Convolutional Neural Network (CNN), and Support Vector Machine Classifier (SVMC) models are employed within the Multiplicative Weight Update system. These models are trained on pictures of skin cancer from the ISIC-Archive, to look for patterns to label unseen scans as either benign or malignant. These models are utilized in a multiplicative weight update algorithm which takes into account the precision and accuracy of each model through each successive guess to apply weights to their guess. These guesses and weights are then analyzed together to try and obtain the correct predictions. The research hypothesis for this study stated that there would be a significant difference in the accuracy of the three models and the Multiplicative Weight Update system. The SVMC model had an accuracy of 77.88%. The CNN model had an accuracy of 85.30%. The Logistic Regression model had an accuracy of 79.09%. Using Multiplicative Weight Update, the algorithm received an accuracy of 72.27%. The final conclusion that was drawn was that there was a significant difference in the accuracy of the three models and the Multiplicative Weight Update system. The conclusion was made that using a CNN model would be the best option for this problem rather than a Multiplicative Weight Update system. This is due to the possibility that Multiplicative Weight Update is not effective in a binary setting where there are only two possible classifications. In a categorical setting with multiple classes and groupings, a Multiplicative Weight Update system might become more proficient as it takes into account the strengths of multiple different models to classify images into multiple categories rather than only two categories, as shown in this study. This experimentation and computer science project can help to create better algorithms and models for the future of artificial intelligence in the medical imaging field.

Keywords: artificial intelligence, machine learning, multiplicative weight update, skin cancer

Procedia PDF Downloads 75

Authors: Shaan Khosla, Jon Krohn

Abstract:

In a recruiting context, machine learning models are valuable for recommendations: to predict the best candidates for a vacancy, to match the best vacancies for a candidate, and compile a set of similar candidates for any given candidate. While useful to create these models, validating their accuracy in a recommendation context is difficult due to a sparsity of data. In this report, we use network graph data to generate useful representations for candidates and vacancies. We use candidates and vacancies as network nodes and designate a bi-directional link between them based on the candidate interviewing for the vacancy. After using node2vec, the embeddings are used to construct a validation dataset with a ranked order, which will help validate new recommender systems.

Keywords: AI, machine learning, NLP, recruiting

Procedia PDF Downloads 82

Authors: Larry Powell, Seth Polsley, Drew Casey, Tracy Hammond

Abstract:

Human activity recognition (HAR) systems have shown positive performance when recognizing repetitive activities like walking, running, and sleeping. Water-based activities are a reasonably new area for activity recognition. However, water-based activity recognition has largely focused on supporting the elite and competitive swimming population, which already has amazing coordination and proper form. Beginner swimmers are not perfect, and activity recognition needs to support the individual motions to help beginners. Activity recognition algorithms are traditionally built around short segments of timed sensor data. Using a time window input can cause performance issues in the machine learning model. The window’s size can be too small or large, requiring careful tuning and precise data segmentation. In this work, we present a method that uses a time window as the initial segmentation, then separates the data based on the change in the sensor value. Our system uses a multi-phase segmentation method that pulls all peaks and valleys for each axis of an accelerometer placed on the swimmer’s lower back. This results in high recognition performance using leave-one-subject-out validation on our study with 20 beginner swimmers, with our model optimized from our final dataset resulting in an F-Score of 0.95.

Keywords: time window, peak/valley segmentation, feature extraction, beginner swimming, activity recognition

Procedia PDF Downloads 113

Authors: Donald Wright

Abstract:

The ultimate goal of this study is to reinvigorate the philosophical underpinnings the study of urbanization with scientific data with the goal of circumventing what seems an inevitable future clash between rural and urban populations. To that end urban infrastructure must be sustainable economically, politically and ecologically over the course of several generations as cities continue to grow with the incorporation of climate refugees. Our research will provide data concerning the projected increase in population over the coming two decades in Morocco, and the population will shift from rural areas to urban centers during that period of time. As a result, urban infrastructure will need to be adapted, developed or built to fit the demand of future internal migrations from rural to urban centers in Morocco. This paper will also examine how past experiences of internally displaced people give insight into the challenges faced by future migrants and, beyond the gathering of data, how people react to internal migration. This study employs four different sets of research tools. First, a large part of this study is archival, which involves compiling the relevant literature on the topic and its complex history. This step also includes gathering data bout migrations in Morocco from public data sources. Once the datasets are collected, the next part of the project involves populating the attribute fields and preprocessing the data to make it understandable and usable by machine learning algorithms. In tandem with the mathematical interpretation of data and projected migrations, this study benefits from a theoretical understanding of the critical apparatus existing around urban development of the 20th and 21st centuries that give us insight into past infrastructure development and the rationale behind it. Once the data is ready to be analyzed, different machine learning algorithms will be experimented (k-clustering, support vector regression, random forest analysis) and the results compared for visualization of the data. The final computational part of this study involves analyzing the data and determining what we can learn from it. This paper helps us to understand future trends of population movements within and between regions of North Africa, which will have an impact on various sectors such as urban development, food distribution and water purification, not to mention the creation of public policy in the countries of this region. One of the strengths of this project is the multi-pronged and cross-disciplinary methodology to the research question, which enables an interchange of knowledge and experiences to facilitate innovative solutions to this complex problem. Multiple and diverse intersecting viewpoints allow an exchange of methodological models that provide fresh and informed interpretations of otherwise objective data.

Keywords: climate change, machine learning, migration, Morocco, urban development

Procedia PDF Downloads 145

Authors: Benalia Nadia, Zerzouri Nora, Ben Si Ali Nadia

Abstract:

Abstract: Among the many different modern heuristic optimization methods, genetic algorithms (GA) and the particle swarm optimization (PSO) technique have been attracting a lot of interest. The GA has gained popularity in academia and business mostly because to its simplicity, ability to solve highly nonlinear mixed integer optimization problems that are typical of complex engineering systems, and intuitiveness. The mechanics of the PSO methodology, a relatively recent heuristic search tool, are modeled after the swarming or cooperative behavior of biological groups. It is suitable to compare the performance of the two techniques since they both aim to solve a particular objective function but make use of distinct computing methods. In this article, PSO and GA optimization approaches are used for the parameter tuning of the power system stabilizer and Proportional integral derivative regulator. Load angle and rotor speed variations in the single machine infinite bus bar system is used to measure the performance of the suggested solution.

Keywords: SMIB, genetic algorithm, PSO, transient stability, power system stabilizer, PID

Procedia PDF Downloads 75

Authors: Adrian Ionita, Ana-Maria Ghimes

Abstract:

The lack of features, design and the lack of promoting an integrated booking application are some of the reasons why most online travel platforms only offer automation of old booking processes, being limited to the integration of a smaller number of services without addressing the user experience. This paper represents a practical study on how to improve travel applications creating user-profiles through data-mining based on neural networks and genetic algorithms. Choices made by users and their ‘friends’ in the ‘social’ network context can be considered input data for a recommendation engine. The purpose of using these algorithms and this design is to improve user experience and to deliver more features to the users. The paper aims to highlight a broader range of improvements that could be applied to travel applications in terms of design and service integration, while the main scientific approach remains the technical implementation of the neural network solution. The motivation of the technologies used is also related to the initiative of some online booking providers that have made the fact that they use some ‘neural network’ related designs public. These companies use similar Big-Data technologies to provide recommendations for hotels, restaurants, and cinemas with a neural network based recommendation engine for building a user ‘DNA profile’. This implementation of the ‘profile’ a collection of neural networks trained from previous user choices, can improve the usability and design of any type of application.

Keywords: artificial intelligence, big data, cloud computing, DNA profile, genetic algorithms, machine learning, neural networks, optimization, recommendation system, user profiling

Procedia PDF Downloads 161

Authors: Kuei-Ling Sun, Emily Chia-Yu Su

Abstract:

Allergy is a hypersensitive overreaction of the immune system to environmental stimuli, and a major health problem. These overreactions include rashes, sneezing, fever, food allergies, anaphylaxis, asthmatic, shock, or other abnormal conditions. Allergies can be caused by food, insect stings, pollen, animal wool, and other allergens. Their development of allergies is due to both genetic and environmental factors. Allergies involve immunoglobulin E antibodies, a part of the body’s immune system. Immunoglobulin E antibodies will bind to an allergen and then transfer to a receptor on mast cells or basophils triggering the release of inflammatory chemicals such as histamine. Based on the increasingly serious problem of environmental change, changes in lifestyle, air pollution problem, and other factors, in this study, we both collect allergens and non-allergens from several databases and use several machine learning methods for classification, including logistic regression (LR), stepwise regression, decision tree (DT) and neural networks (NN) to do the model comparison and determine the permutations of allergen amino acid’s sequence.

Keywords: allergy, classification, decision tree, logistic regression, machine learning

Procedia PDF Downloads 300

Authors: Emanuel Koseos

Abstract:

Data-Driven Decision Making (DDDM) refers to making decisions that are based on historical data in order to inform practice, develop strategies and implement policies that benefit organizational settings. In educational technology, DDDM facilitates the implementation of differential educational learning approaches such as Educational Data Mining (EDM) and Competency-Based Education (CBE), which commonly target university classrooms. There is a current need for DDDM models applied to middle and secondary schools from a concern for assessing the needs, progress and performance of students and educators with respect to regional standards, policies and evolution of curriculums. To address these concerns, we propose a DDDM reference model developed using educational key process initiatives as inputs to a machine learning framework implemented with statistical software (SAS, R) to provide a best-practices, complex-free and automated approach for educators at their regional level. We assessed the efficiency of the model over a six-year period using data from 45 schools and grades K-12 in the Langley, BC, Canada regional school district. We concluded that the model has wider appeal, such as business learning systems.

Keywords: competency-based learning, data-driven decision making, machine learning, secondary schools

Procedia PDF Downloads 167

Authors: Michael R. Phangtriastu, Herriyandi Herriyandi, Diaz D. Santika

Abstract:

This paper presents a comparison of the implementation of metaheuristic algorithms to train the antecedent parameters and consequence parameters in the adaptive network-based fuzzy inference system (ANFIS). The algorithms compared are genetic algorithm (GA), particle swarm optimization (PSO), and artificial bee colony (ABC). The objective of this paper is to benchmark well-known metaheuristic algorithms. The algorithms are applied to several data set with different nature. The combinations of the algorithms' parameters are tested. In all algorithms, a different number of populations are tested. In PSO, combinations of velocity are tested. In ABC, a different number of limit abandonment are tested. Experiments find out that ABC is more reliable than other algorithms, ABC manages to get better mean square error (MSE) than other algorithms in all data set.

Keywords: ANFIS, artificial bee colony, genetic algorithm, metaheuristic algorithm, particle swarm optimization

Procedia PDF Downloads 348

Authors: Derssie Mebratu

Abstract:

As a large variety of micro services, web services, social graphic applications, and media applications are continuously developed, it is substantially vital to design and build a reliable, efficient, and faster memory tiering system. Despite limited design, implementation, and deployment in the last few years, several techniques are currently developed to improve a memory tiering system in a cloud. Some of these techniques are to develop an optimal scanning frequency; improve and track pages movement; identify pages that recently accessed; store pages across each tiering, and then identify pages as a hot, warm, and cold so that hot pages can store in the first tiering Dynamic Random Access Memory (DRAM) and warm pages store in the second tiering Compute Express Link(CXL) and cold pages store in the third tiering Non-Volatile Memory (NVM). Apart from the current proposal and implementation, we also develop a new technique based on a machine learning algorithm in that the throughput produced 25% improved performance compared to the performance produced by the baseline as well as the latency produced 95% improved performance compared to the performance produced by the baseline.

Keywords: machine learning, bayesian optimization, memory tiering, CXL, DRAM

Procedia PDF Downloads 92

Authors: Luyao Zhang, Tianyu Wu, Jiayi Li, Carlos-Gustavo Salas-Flores, Saad Lahrichi

Abstract:

Recent advances in AI have made algorithmic trading a central role in finance. However, current research and applications are disconnected information islands. We propose a generally applicable pipeline for designing, programming, and evaluating algorithmic trading of stock and crypto tokens. Moreover, we provide comparative case studies for four conventional algorithms, including moving average crossover, volume-weighted average price, sentiment analysis, and statistical arbitrage. Our study offers a systematic way to program and compare different trading strategies. Moreover, we implement our algorithms by object-oriented programming in Python3, which serves as open-source software for future academic research and applications.

Keywords: algorithmic trading, AI for finance, fintech, machine learning, moving average crossover, volume weighted average price, sentiment analysis, statistical arbitrage, pair trading, object-oriented programming, python3

Procedia PDF Downloads 137

Authors: Ioannis P. Panapakidis, Marios N. Moschakis

Abstract:

With the continuous increment of smart meter installations across the globe, the need for processing of the load data is evident. Clustering-based load profiling is built upon the utilization of unsupervised machine learning tools for the purpose of formulating the typical load curves or load profiles. The most commonly used algorithm in the load profiling literature is the K-means. While the algorithm has been successfully tested in a variety of applications, its drawback is the strong dependence in the initialization phase. This paper proposes a novel modified form of the K-means that addresses the aforementioned problem. Simulation results indicate the superiority of the proposed algorithm compared to the K-means.

Keywords: clustering, load profiling, load modeling, machine learning, energy efficiency and quality

Procedia PDF Downloads 160

Authors: Pedro Martinez-Santos, Víctor Gómez-Escalonilla, Silvia Díaz-Alcaide, Esperanza Montero, Miguel Martín-Loeches

Abstract:

Groundwater monitoring networks are critical in evaluating the vulnerability of groundwater resources to depletion and contamination, both in space and time. Groundwater monitoring networks typically grow over decades, often in organic fashion, with relatively little overall planning. The groundwater monitoring networks in the Madrid area, Spain, were reviewed for the purpose of identifying gaps and opportunities for improvement. Spatial analysis reveals the presence of various monitoring networks belonging to different institutions, with several hundred observation wells in an area of approximately 4000 km2. This represents several thousand individual data entries, some going back to the early 1970s. Major issues included overlap between the networks, unknown screen depth/vertical distribution for many observation boreholes, uneven time series, uneven monitored species, and potentially suboptimal locations. Results also reveal there is sufficient information to carry out a spatial and temporal analysis of groundwater vulnerability based on machine learning applications. These can contribute to improve the overall planning of monitoring networks’ expansion into the future.

Keywords: groundwater monitoring, observation networks, machine learning, madrid

Procedia PDF Downloads 72

Authors: Reham Banwair, Lana Alshehri, Sara Hadrawi

Abstract:

The purpose of this project is to identify user satisfaction with the AI functions on Snapchat, in order to generate improvement proposals that allow its development within the app. To achieve this, a qualitative analysis was carried out through interviews to people who usually use the application, revealing their satisfaction or dissatisfaction with the usefulness of the AI. In addition, the background of the company and its introduction in these algorithms were analyzed. Furthermore, the characteristics of the three main functions of AI were explained: identify songs, solve mathematical problems, and recognize plants. As a result, it was obtained that 50% still do not know the characteristics of AI, 50% still believe song recognition is not always correct, 41.7% believe that math problems are usually accurate and 91.7% believes the plant detection tool is working properly.

Keywords: artificial intelligence, scanning, Snapchat, machine learning

Procedia PDF Downloads 127

Authors: Ursula Das, Manavjit Singh Dhindsa, Kshirasagar Naik, Marzia Zaman, Richard Purcell, Srinivas Sampalli, Abdul Mutakabbir, Chung-Horng Lung, Thambirajah Ravichandran

Abstract:

Wildland fires, also known as forest fires or wildfires, are exhibiting an alarming surge in frequency in recent times, further adding to its perennial global concern. Forest fires often lead to devastating consequences ranging from loss of healthy forest foliage and wildlife to substantial economic losses and the tragic loss of human lives. Despite the existence of substantial literature on the detection of active forest fires, numerous potential research avenues in forest fire management, such as preventative measures and ancillary effects of forest fires, remain largely underexplored. This paper undertakes a systematic review of these underexplored areas in forest fire research, meticulously categorizing them into distinct phases, namely pre-fire, during-fire, and post-fire stages. The pre-fire phase encompasses the assessment of fire risk, analysis of fuel properties, and other activities aimed at preventing or reducing the risk of forest fires. The during-fire phase includes activities aimed at reducing the impact of active forest fires, such as the detection and localization of active fires, optimization of wildfire suppression methods, and prediction of the behavior of active fires. The post-fire phase involves analyzing the impact of forest fires on various aspects, such as the extent of damage in forest areas, post-fire regeneration of forests, impact on wildlife, economic losses, and health impacts from byproducts produced during burning. A comprehensive understanding of the three stages is imperative for effective forest fire management and mitigation of the impact of forest fires on both ecological systems and human well-being. Artificial intelligence and machine learning (AI/ML) methods have garnered much attention in the cyber-physical systems domain in recent times leading to their adoption in decision-making in diverse applications including disaster management. This paper explores the current state of AI/ML applications for managing the activities in the aforementioned phases of forest fire. While conventional machine learning and deep learning methods have been extensively explored for the prevention, detection, and management of forest fires, a systematic classification of these methods into distinct AI research domains is conspicuously absent. This paper gives a comprehensive overview of the state of forest fire research across more recent and prominent AI/ML disciplines, including big data, classical machine learning, computer vision, explainable AI, generative AI, natural language processing, optimization algorithms, and time series forecasting. By providing a detailed overview of the potential areas of research and identifying the diverse ways AI/ML can be employed in forest fire research, this paper aims to serve as a roadmap for future investigations in this domain.

Keywords: artificial intelligence, computer vision, deep learning, during-fire activities, forest fire management, machine learning, pre-fire activities, post-fire activities

Procedia PDF Downloads 65

Authors: Milad Abbasi

Abstract:

Carbon fiber-reinforced polymer (CFRP) composite structures are increasingly being utilized in the automotive industry due to their lightweight and specific energy absorption capabilities. Although it is impossible to predict composite mechanical properties directly using theoretical methods, various research has been conducted so far in the literature for accurate simulation of CFRP structures' energy-absorbing behavior. In this research, axial compression experiments were carried out on hand lay-up unidirectional CFRP composite tubes. The fabrication method allowed the authors to extract the material properties of the CFRPs using ASTM D3039, D3410, and D3518 standards. A neural network machine learning algorithm was then utilized to build a robust prediction model to forecast the axial compressive properties of CFRP tubes while reducing high-cost experimental efforts. The predicted results have been compared with the experimental outcomes in terms of load-carrying capacity and energy absorption capability. The results showed high accuracy and precision in the prediction of the energy-absorption capacity of the CFRP tubes. This research also demonstrates the effectiveness and challenges of machine learning techniques in the robust simulation of composites' energy-absorption behavior. Interestingly, the proposed method considerably condensed numerical and experimental efforts in the simulation and calibration of CFRP composite tubes subjected to compressive loading.

Keywords: CFRP composite tubes, energy absorption, crushing behavior, machine learning, neural network

Procedia PDF Downloads 148

Authors: Ferah Tesfaye Admasu

Abstract:

Autism Spectrum Disorder (ASD) often presents significant communication challenges, particularly for non-verbal individuals who struggle to express their needs and emotions effectively. Assistive technologies (AT) have emerged as vital tools in enhancing communication abilities for this population. Recent advancements in artificial intelligence (AI) hold the potential to revolutionize the design and functionality of these technologies. This study explores the application of AI in developing intelligent, adaptive, and user-centered assistive technologies for non-verbal individuals with autism. Through a review of current AI-driven tools, including speech-generating devices, predictive text systems, and emotion-recognition software, this research investigates how AI can bridge communication gaps, improve engagement, and support independence. Machine learning algorithms, natural language processing (NLP), and facial recognition technologies are examined as core components in creating more personalized and responsive communication aids. The study also discusses the challenges and ethical considerations involved in deploying AI-based AT, such as data privacy and the risk of over-reliance on technology. Findings suggest that integrating AI into assistive technologies can significantly enhance the quality of life for non-verbal individuals with autism, providing them with greater opportunities for social interaction and participation in daily activities. However, continued research and development are needed to ensure these technologies are accessible, affordable, and culturally sensitive.

Keywords: artificial intelligence, autism spectrum disorder, non-verbal communication, assistive technology, machine learning

Procedia PDF Downloads 10

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 72

Authors: Sriraman Kothuri, Komal Teja Mattupalli

Abstract:

In this paper we proposed a novel algorithm for recognizing hulls in a hand written digits. This is an extension to the work on “Digit Recognition Using Freeman Chain code”. In order to find out the hulls in a user given digit it is necessary to follow three steps. Those are pre-processing, Boundary Extraction and at last apply the Hull Detection system in a way to attain the better results. The detection of Hull Regions is mainly intended to increase the machine learning capability in detection of characters or digits. This can also extend this in order to get the hull regions and their intensities in Black Holes in Space Exploration.

Keywords: chain code, machine learning, hull regions, hull recognition system, SASK algorithm

Procedia PDF Downloads 398

Authors: Jacob Green, Cecilia Cabrera, Maximilian Jakobs, Andrea Dimitracopoulos, Mark van der Wilk, Ryan Greenhalgh

Abstract:

Predicting drug properties is key in drug discovery to enable de-risking of assets before expensive clinical trials and to find highly active compounds faster. Interest from the machine learning community has led to the release of a variety of benchmark datasets and proposed methods. However, it remains unclear for practitioners which method or approach is most suitable, as different papers benchmark on different datasets and methods, leading to varying conclusions that are not easily compared. Our large-scale empirical study links together numerous earlier works on different datasets and methods, thus offering a comprehensive overview of the existing property classes, datasets, and their interactions with different methods. We emphasise the importance of uncertainty quantification and the time and, therefore, cost of applying these methods in the drug development decision-making cycle. To the best of the author's knowledge, it has been observed that the optimal approach varies depending on the dataset and that engineered features with classical machine learning methods often outperform deep learning. Specifically, QSAR datasets are typically best analysed with classical methods such as Gaussian Processes, while ADMET datasets are sometimes better described by Trees or deep learning methods such as Graph Neural Networks or language models. Our work highlights that practitioners do not yet have a straightforward, black-box procedure to rely on and sets a precedent for creating practitioner-relevant benchmarks. Deep learning approaches must be proven on these benchmarks to become the practical method of choice in drug property prediction.

Keywords: activity (QSAR), ADMET, classical methods, drug property prediction, empirical study, machine learning

Procedia PDF Downloads 77

Authors: Rajvir Kaur, Jeewani Anupama Ginige

Abstract:

With recent trends in Big Data and advancements in Information and Communication Technologies, the healthcare industry is at the stage of its transition from clinician oriented to technology oriented. Many people around the world die of cancer because the diagnosis of disease was not done at an early stage. Nowadays, the computational methods in the form of Machine Learning (ML) are used to develop automated decision support systems that can diagnose cancer with high confidence in a timely manner. This paper aims to carry out the comparative evaluation of a selected set of ML classifiers on two existing datasets: breast cancer and cervical cancer. The ML classifiers compared in this study are Decision Tree (DT), Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), Logistic Regression, Ensemble (Bagged Tree) and Artificial Neural Networks (ANN). The evaluation is carried out based on standard evaluation metrics Precision (P), Recall (R), F1-score and Accuracy. The experimental results based on the evaluation metrics show that ANN showed the highest-level accuracy (99.4%) when tested with breast cancer dataset. On the other hand, when these ML classifiers are tested with the cervical cancer dataset, Ensemble (Bagged Tree) technique gave better accuracy (93.1%) in comparison to other classifiers.

Keywords: artificial neural networks, breast cancer, classifiers, cervical cancer, f-score, machine learning, precision, recall

Procedia PDF Downloads 274

Authors: Chandu Rathnayake, Isuri Anuradha

Abstract:

Early detection and accurate diagnosis of lung diseases play a crucial role in improving patient prognosis. However, conventional diagnostic methods heavily rely on subjective symptom assessments and medical imaging, often causing delays in diagnosis and treatment. To overcome this challenge, we propose a novel lung disease prediction system that integrates patient symptoms and X-ray images to provide a comprehensive and reliable diagnosis.In this project, develop a mobile application specifically designed for detecting lung diseases. Our application leverages both patient symptoms and X-ray images to facilitate diagnosis. By combining these two sources of information, our application delivers a more accurate and comprehensive assessment of the patient's condition, minimizing the risk of misdiagnosis. Our primary aim is to create a user-friendly and accessible tool, particularly important given the current circumstances where many patients face limitations in visiting healthcare facilities. To achieve this, we employ several state-of-the-art algorithms. Firstly, the Decision Tree algorithm is utilized for efficient symptom-based classification. It analyzes patient symptoms and creates a tree-like model to predict the presence of specific lung diseases. Secondly, we employ the Random Forest algorithm, which enhances predictive power by aggregating multiple decision trees. This ensemble technique improves the accuracy and robustness of the diagnosis. Furthermore, we incorporate a deep learning model using Convolutional Neural Network (CNN) with the RestNet50 pre-trained model. CNNs are well-suited for image analysis and feature extraction. By training CNN on a large dataset of X-ray images, it learns to identify patterns and features indicative of lung diseases. The RestNet50 architecture, known for its excellent performance in image recognition tasks, enhances the efficiency and accuracy of our deep learning model. By combining the outputs of the decision tree-based algorithms and the deep learning model, our mobile application generates a comprehensive lung disease prediction. The application provides users with an intuitive interface to input their symptoms and upload X-ray images for analysis. The prediction generated by the system offers valuable insights into the likelihood of various lung diseases, enabling individuals to take appropriate actions and seek timely medical attention. Our proposed mobile application has significant potential to address the rising prevalence of lung diseases, particularly among young individuals with smoking addictions. By providing a quick and user-friendly approach to assessing lung health, our application empowers individuals to monitor their well-being conveniently. This solution also offers immense value in the context of limited access to healthcare facilities, enabling timely detection and intervention. In conclusion, our research presents a comprehensive lung disease prediction system that combines patient symptoms and X-ray images using advanced algorithms. By developing a mobile application, we provide an accessible tool for individuals to assess their lung health conveniently. This solution has the potential to make a significant impact on the early detection and management of lung diseases, benefiting both patients and healthcare providers.

Keywords: CNN, random forest, decision tree, machine learning, deep learning

Procedia PDF Downloads 72

Authors: C. J. Rossouw, T. I. van Niekerk

Abstract:

The global manufacturing industry is utilizing the internet and cloud-based services to further explore the anatomy and optimize manufacturing processes in support of the movement into the Fourth Industrial Revolution (4IR). The 4IR from a third world and African perspective is hindered by the fact that many manufacturing systems that were developed in the third industrial revolution are not inherently equipped to utilize the internet and services of the 4IR, hindering the progression of third world manufacturing industries into the 4IR. This research focuses on the development of a non-invasive and cost-effective cyber-physical IoT system that will exploit a machine’s vibration to expose semantic characteristics in the manufacturing process and utilize these results through a real-time cloud-based machine condition monitoring system with the intention to optimize the system. A microcontroller-based IoT sensor was designed to acquire a machine’s mechanical vibration data, process it in real-time, and transmit it to a cloud-based platform via Wi-Fi and the internet. Time-frequency Fourier analysis was applied to the vibration data to form an image representation of the machine’s behaviour. This data was used to train a Convolutional Neural Network (CNN) to learn semantic characteristics in the machine’s behaviour and relate them to a state of operation. The same data was also used to train a Convolutional Autoencoder (CAE) to detect anomalies in the data. Real-time edge-based artificial intelligence was achieved by deploying the CNN and CAE on the sensor to analyse the vibration. A cloud platform was deployed to visualize the vibration data and the results of the CNN and CAE in real-time. The cyber-physical IoT system was deployed on a semi-automated metal granulation machine with a set of trained machine learning models. Using a single sensor, the system was able to accurately visualize three states of the machine’s operation in real-time. The system was also able to detect a variance in the material being granulated. The research demonstrates how non-IoT manufacturing systems can be equipped with edge-based artificial intelligence to establish a remote machine condition monitoring system.

Keywords: IoT, cyber-physical systems, artificial intelligence, manufacturing, vibration analytics, continuous machine condition monitoring

Procedia PDF Downloads 84

Authors: Daniel M. Wolff, Patricia Gray, Rafael de la Parra Venegas

Abstract:

An unsupervised machine listening system is constructed and applied to a dataset of 17,195 30-second marine hydrophone recordings. The system is then heuristically supplemented with anecdotal listening, contextual recording information, and supervised learning techniques to reduce the number of false positives. Features for classification are assembled by extracting the following data from each of the audio files: the spectral centroid, root-mean-squared values for each frequency band of a 10-octave filter bank, and mel-frequency cepstral coefficients in 5-second frames. In this way both time- and frequency-domain information are contained in the features to be passed to a clustering algorithm. Classification is performed using the k-means algorithm and then a k-nearest neighbors search. Different values of k are experimented with, in addition to different combinations of the available feature sets. Hypothesized class labels are 'primarily anthrophony' and 'primarily biophony', where the best class result conforming to the former label has 104 members after heuristic pruning. This demonstrates how a large audio dataset has been made more tractable with machine learning techniques, forming the foundation of a framework designed to acoustically monitor and gauge biological and anthropogenic activity in a marine environment.

Keywords: anthrophony, hydrophone, k-means, machine learning

Procedia PDF Downloads 166

Authors: Ana C. R. P. Ferreira, Adriano H. P. Pereira

Abstract:

Given the frequent variation of mineral properties throughout the Araxá pyrochlore deposit, even if a good homogenization work has been carried out before feeding the processing plants, an operation with quality and performance’s high variety standard is expected. These results could be improved and standardized if the blend composition parameters that most influence the processing route are determined, and then the types of raw materials are grouped by them, finally presenting a great reference with operational settings for each group. Associating the physical and chemical parameters of a unit operation through benchmarking or even an optimal reference of metallurgical recovery and product quality reflects in the reduction of the production costs, optimization of the mineral resource, and guarantee of greater stability in the subsequent processes of the production chain that uses the mineral of interest. Conducting a comprehensive exploratory data analysis to identify which characteristics of the ore are most relevant to the process route, associated with the use of Machine Learning algorithms for grouping the raw material (ore) and associating these with reference variables in the process’ benchmark is a reasonable alternative for the standardization and improvement of mineral processing units. Clustering methods through Decision Tree and K-Means were employed, associated with algorithms based on the theory of benchmarking, with criteria defined by the process team in order to reference the best adjustments for processing the ore piles of each cluster. A clean user interface was created to obtain the outputs of the created algorithm. The results were measured through the average time of adjustment and stabilization of the process after a new pile of homogenized ore enters the plant, as well as the average time needed to achieve the best processing result. Direct gains from the metallurgical recovery of the process were also measured. The results were promising, with a reduction in the adjustment time and stabilization when starting the processing of a new ore pile, as well as reaching the benchmark. Also noteworthy are the gains in metallurgical recovery, which reflect a significant saving in ore consumption and a consequent reduction in production costs, hence a more rational use of the tailings dams and life optimization of the mineral deposit.

Keywords: mineral clustering, machine learning, process optimization, pyrochlore processing

Procedia PDF Downloads 141

Authors: Lizhi Ma, Chengcheng Hu, Fuxian Wong

Abstract:

Partial reduce (P-Reduce) has set a state-of-the-art performance on distributed machine learning in the heterogeneous environment over the All-Reduce architecture. The dynamic P-Reduce based on the exponential moving average (EMA) approach predicts all the intermediate model parameters, which raises unreliability. It is noticed that the approximation trick leads the wrong way to obtaining model parameters in all the nodes. In this paper, SAP-Reduce is proposed, which is a variant of the All-Reduce distributed training model with staleness-aware dynamic P-Reduce. SAP-Reduce directly utilizes the EMA-like algorithm to generate the normalized weights. To demonstrate the effectiveness of the algorithm, the experiments are set based on a number of deep learning models, comparing the single-step training acceleration ratio and convergence time. It is found that SAP-Reduce simplifying dynamic P-Reduce outperforms the intermediate approximation one. The empirical results show SAP-Reduce is 1.3× −2.1× faster than existing baselines.

Keywords: collective communication, decentralized distributed training, machine learning, P-Reduce

Procedia PDF Downloads 25

Authors: Yangzhi Li

Abstract:

Network transfer of information and performance customization is now a viable method of digital industrial production in the era of Industry 4.0. Robot platforms and network platforms have grown more important in digital design and construction. The pressing need for novel building techniques is driven by the growing labor scarcity problem and increased awareness of construction safety. Robotic approaches in construction research are regarded as an extension of operational and production tools. Several technological theories related to robot autonomous recognition, which include high-performance computing, physical system modeling, extensive sensor coordination, and dataset deep learning, have not been explored using intelligent construction. Relevant transdisciplinary theory and practice research still has specific gaps. Optimizing high-performance computing and autonomous recognition visual guidance technologies improves the robot's grasp of the scene and capacity for autonomous operation. Intelligent vision guidance technology for industrial robots has a serious issue with camera calibration, and the use of intelligent visual guiding and identification technologies for industrial robots in industrial production has strict accuracy requirements. It can be considered that visual recognition systems have challenges with precision issues. In such a situation, it will directly impact the effectiveness and standard of industrial production, necessitating a strengthening of the visual guiding study on positioning precision in recognition technology. To best facilitate the handling of complicated components, an approach for the visual recognition of parts utilizing machine learning algorithms is proposed. This study will identify the position of target components by detecting the information at the boundary and corner of a dense point cloud and determining the aspect ratio in accordance with the guidelines for the modularization of building components. To collect and use components, operational processing systems assign them to the same coordinate system based on their locations and postures. The RGB image's inclination detection and the depth image's verification will be used to determine the component's present posture. Finally, a virtual environment model for the robot's obstacle-avoidance route will be constructed using the point cloud information.

Keywords: robotic construction, robotic assembly, visual guidance, machine learning

Procedia PDF Downloads 84

Authors: Huan Ting Liao

Abstract:

In a typical manufacturing environment, computer numerical control (CNC) machining is essential for automating production through precise computer-controlled tool operations, significantly enhancing efficiency and ensuring consistent product quality. However, traditional CNC production lines often rely on manual loading and unloading, limiting operational efficiency and scalability. Although automated loading systems have been developed, they frequently lack sufficient intelligence and configuration efficiency, requiring extensive setup adjustments for different products and impacting overall productivity. This research addresses the job shop scheduling problem (JSSP) in CNC machining environments, aiming to minimize total completion time (makespan) and maximize CNC machine utilization. We propose a novel approach using reinforcement learning (RL), specifically the Q-learning algorithm, to optimize scheduling decisions. The study simulates the JSSP, incorporating robotic arm operations, machine processing times, and work order demand allocation to determine optimal processing sequences. The Q-learning algorithm enhances machine utilization by dynamically balancing workloads across CNC machines, adapting to varying job demands and machine states. This approach offers robust solutions for complex manufacturing environments by automating decision-making processes for job assignments. Additionally, we evaluate various layout configurations to identify the most efficient setup. By integrating RL-based scheduling optimization with layout analysis, this research aims to provide a comprehensive solution for improving manufacturing efficiency and productivity in CNC-based job shops. The proposed method's adaptability and automation potential promise significant advancements in tackling dynamic manufacturing challenges.

Keywords: job shop scheduling problem, reinforcement learning, operations sequence, layout optimization, q-learning

Procedia PDF Downloads 14