Search results for: deep machine learning

Authors: Engin Eyceyurt, Josko Zec

Abstract:

The current and future cellular mobile communication networks generate enormous amounts of data. Networks have become extremely complex with extensive space of parameters, features and counters. These networks are unmanageable with legacy methods and an enhanced design and optimization approach is necessary that is increasingly reliant on machine learning. This paper proposes that machine learning as a viable approach for uplink throughput prediction. LTE radio metric, such as Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), and Signal to Noise Ratio (SNR) are used to train models to estimate expected uplink throughput. The prediction accuracy with high determination coefficient of 91.2% is obtained from measurements collected with a simple smartphone application.

Keywords: drive test, LTE, machine learning, uplink throughput prediction

Procedia PDF Downloads 131

Authors: Nurhak Altın, Ayhan Kucukmanisa, Oguzhan Urhan

Abstract:

It is important that highways are in good condition for traffic safety. Road crashes (road cracks, erosion of lane markings, etc.) can cause accidents by affecting driving. Image processing based methods for detecting road cracks are available in the literature. In this paper, a deep learning based road crack detection approach is proposed. YOLO (You Look Only Once) is adopted as core component of the road crack detection approach presented. The YOLO network structure, which is developed for object detection, is trained with road crack images as a new class that is not previously used in YOLO. The performance of the proposed method is compared using different training methods: using randomly generated weights and training their own pre-trained weights (transfer learning). A similar training approach is applied to the simplified version of the YOLO network model (tiny yolo) and the results of the performance are examined. The developed system is able to process 8 fps on NVIDIA Jetson TX1 development kit.

Keywords: deep learning, embedded platform, real-time processing, road crack detection

Procedia PDF Downloads 318

Authors: Jay L. Fu

Abstract:

Patients with Alzheimer's disease progressively lose their memory and thinking skills and, eventually, the ability to carry out simple daily tasks. The disease is irreversible, but early detection and treatment can slow down the disease progression. In this research, publicly available MRI data and demographic data from 373 MRI imaging sessions were utilized to build models to predict dementia. Various machine learning models, including logistic regression, k-nearest neighbor, support vector machine, random forest, and neural network, were developed. Data were divided into training and testing sets, where training sets were used to build the predictive model, and testing sets were used to assess the accuracy of prediction. Key risk factors were identified, and various models were compared to come forward with the best prediction model. Among these models, the random forest model appeared to be the best model with an accuracy of 90.34%. MMSE, nWBV, and gender were the three most important contributing factors to the detection of Alzheimer’s. Among all the models used, the percent in which at least 4 of the 5 models shared the same diagnosis for a testing input was 90.42%. These machine learning models allow early detection of Alzheimer’s with good accuracy, which ultimately leads to early treatment of these patients.

Keywords: Alzheimer's disease, clinical diagnosis, magnetic resonance imaging, machine learning prediction

Procedia PDF Downloads 120

Authors: Anita Khadka, Gregory Epiphaniou, Carsten Maple

Abstract:

There is a dramatic surge in the adoption of machine learning (ML) techniques in many areas, including the nuclear industry (such as fault diagnosis and fuel management in nuclear power plants), autonomous systems (including self-driving vehicles), space systems (space debris recovery, for example), medical surgery, network intrusion detection, malware detection, to name a few. With the application of learning methods in such diverse domains, artificial intelligence (AI) has become a part of everyday modern human life. To date, the predominant focus has been on developing underpinning ML algorithms that can improve accuracy, while factors such as resiliency and robustness of algorithms have been largely overlooked. If an adversarial attack is able to compromise the learning method or data, the consequences can be fatal, especially but not exclusively in safety-critical applications. In this paper, we present an in-depth analysis of five adversarial attacks and three defence methods on a crack detection ML model. Our analysis shows that it can be dangerous to adopt machine learning techniques in security-critical areas such as the nuclear industry without rigorous testing since they may be vulnerable to adversarial attacks. While common defence methods can effectively defend against different attacks, none of the three considered can provide protection against all five adversarial attacks analysed.

Keywords: adversarial machine learning, attacks, defences, nuclear industry, crack detection

Procedia PDF Downloads 133

Authors: Pawan Kumar Mishra, Ganesh Singh Bisht

Abstract:

Super-resolution is the technique that is being used in computer vision to construct high-resolution images from a single low-resolution image. It is used to increase the frequency component, recover the lost details and removing the down sampling and noises that caused by camera during image acquisition process. High-resolution images or videos are desired part of all image processing tasks and its analysis in most of digital imaging application. The target behind super-resolution is to combine non-repetition information inside single or multiple low-resolution frames to generate a high-resolution image. Many methods have been proposed where multiple images are used as low-resolution images of same scene with different variation in transformation. This is called multi-image super resolution. And another family of methods is single image super-resolution that tries to learn redundancy that presents in image and reconstruction the lost information from a single low-resolution image. Use of deep learning is one of state of art method at present for solving reconstruction high-resolution image. In this research, we proposed Deep Denoising Super Resolution (DDSR) that is a deep neural network for effectively reconstruct the high-resolution image from low-resolution image.

Keywords: resolution, deep-learning, neural network, de-blurring

Procedia PDF Downloads 488

Authors: Konstantinos Perifanos, Eirini Florou, Dionysis Goutsos

Abstract:

This paper presents and benchmarks a number of end-to-end Deep Learning based models for metaphor detection in Greek. We combine Convolutional Neural Networks and Recurrent Neural Networks with representation learning to bear on the metaphor detection problem for the Greek language. The models presented achieve exceptional accuracy scores, significantly improving the previous state-of-the-art results, which had already achieved accuracy 0.82. Furthermore, no special preprocessing, feature engineering or linguistic knowledge is used in this work. The methods presented achieve accuracy of 0.92 and F-score 0.92 with Convolutional Neural Networks (CNNs) and bidirectional Long Short Term Memory networks (LSTMs). Comparable results of 0.91 accuracy and 0.91 F-score are also achieved with bidirectional Gated Recurrent Units (GRUs) and Convolutional Recurrent Neural Nets (CRNNs). The models are trained and evaluated only on the basis of training tuples, the related sentences and their labels. The outcome is a state-of-the-art collection of metaphor detection models, trained on limited labelled resources, which can be extended to other languages and similar tasks.

Keywords: metaphor detection, deep learning, representation learning, embeddings

Procedia PDF Downloads 124

Authors: Oscar E. Cariceo, Claudia V. Casal

Abstract:

Machine learning offers a set of techniques to promote social work interventions and can lead to support decisions of practitioners in order to predict new behaviors based on data produced by the organizations, services agencies, users, clients or individuals. Machine learning techniques include a set of generalizable algorithms that are data-driven, which means that rules and solutions are derived by examining data, based on the patterns that are present within any data set. In other words, the goal of machine learning is teaching computers through 'examples', by training data to test specifics hypothesis and predict what would be a certain outcome, based on a current scenario and improve that experience. Machine learning can be classified into two general categories depending on the nature of the problem that this technique needs to tackle. First, supervised learning involves a dataset that is already known in terms of their output. Supervising learning problems are categorized, into regression problems, which involve a prediction from quantitative variables, using a continuous function; and classification problems, which seek predict results from discrete qualitative variables. For social work research, machine learning generates predictions as a key element to improving social interventions on complex social issues by providing better inference from data and establishing more precise estimated effects, for example in services that seek to improve their outcomes. This paper exposes the results of a classification algorithm to predict cyberbullying among adolescents. Data were retrieved from the National Polyvictimization Survey conducted by the government of Chile in 2017. A logistic regression model was created to predict if an adolescent would experience cyberbullying based on the interaction and behavior of gender, age, grade, type of school, and self-esteem sentiments. The model can predict with an accuracy of 59.8% if an adolescent will suffer cyberbullying. These results can help to promote programs to avoid cyberbullying at schools and improve evidence based practice.

Keywords: cyberbullying, evidence based practice, machine learning, social work research

Procedia PDF Downloads 145

Authors: Waqas Ahmed Khan Afridi, Subhas Chandra Mukhopadhyay, Bandita Mainali

Abstract:

The research paper presents a unique approach to evapotranspiration (ET) prediction using a Support Vector Machine (SVM) learning algorithm. The study leverages real-time sensor node data to develop an accurate and adaptable prediction model, addressing the inherent challenges of traditional ET estimation methods. The integration of the SVM algorithm with real-time sensor node data offers great potential to improve spatial and temporal resolution in ET predictions. In the model development, key input features are measured and computed using mathematical equations such as Penman-Monteith (FAO56) and soil water balance (SWB), which include soil-environmental parameters such as; solar radiation (Rs), air temperature (T), atmospheric pressure (P), relative humidity (RH), wind speed (u2), rain (R), deep percolation (DP), soil temperature (ST), and change in soil moisture (∆SM). The one-year field data are split into combinations of three proportions i.e. train, test, and validation sets. While kernel functions with tuning hyperparameters have been used to train and improve the accuracy of the prediction model with multiple iterations. This paper also outlines the existing methods and the machine learning techniques to determine Evapotranspiration, data collection and preprocessing, model construction, and evaluation metrics, highlighting the significance of SVM in advancing the field of ET prediction. The results demonstrate the robustness and high predictability of the developed model on the basis of performance evaluation metrics (R2, RMSE, MAE). The effectiveness of the proposed model in capturing complex relationships within soil and environmental parameters provide insights into its potential applications for water resource management and hydrological ecosystem.

Keywords: evapotranspiration, FAO56, KNIME, machine learning, RStudio, SVM, sensors

Procedia PDF Downloads 37

Authors: Aragorn Joaquin Pineda Dela Cruz

Abstract:

Road traffic congestion is continually deteriorating in Hong Kong. The largest contributing factor is the increase in vehicle fleet size, resulting in higher competition over the utilisation of road space. This study proposes a project that can process closed-circuit television images and videos to provide real-time traffic detection and prediction capabilities. Specifically, a deep-learning model involving computer vision techniques for video and image-based vehicle counting, then a separate model to detect and predict traffic congestion levels based on said data. State-of-the-art object detection models such as You Only Look Once and Faster Region-based Convolutional Neural Networks are tested and compared on closed-circuit television data from various major roads in Hong Kong. It is then used for training in long short-term memory networks to be able to predict traffic conditions in the near future, in an effort to provide more precise and quicker overviews of current and future traffic conditions relative to current solutions such as navigation apps.

Keywords: intelligent transportation system, vehicle detection, traffic analysis, deep learning, machine learning, computer vision, traffic prediction

Procedia PDF Downloads 75

Authors: Melody Yin

Abstract:

Concussions impact a large amount of adolescents; they make up as much as half of the diagnosed concussions in America. This research proposes a hybrid machine learning model based on the combination of human/knowledge-based domains and computer-generated feature rankings to improve the accuracy of diagnosing sports related concussion (SRC). Using a data set of symptoms collected on the sideline post-SRC events, the symptom selection criteria method has been developed by using Google AutoML's important score function to identify the top 10 symptom features. In addition, symptom domains have been introduced as another parameter, categorizing the symptoms into physical, cognitive, sleep, and emotional domains. The hybrid machine learning model has been trained with a combination of the top 10 symptoms and 4 domains. From the results, the hybrid model was the best performer for symptom resolution time prediction in 2 and 4-week thresholds. This research is a proof of concept study in the use of domains along with machine learning in order to improve concussion prediction accuracy. It is also possible that the use of domains can make the model more efficient due to reduced training time. This research examines the use of a hybrid method in predicting sports-related concussion. This achievement is based on data preprocessing, using a hybrid method to select criteria to achieve high performance.

Keywords: hybrid model, machine learning, sports related concussion, symptom resolution time

Procedia PDF Downloads 146

Authors: Neerav Kumar, Naumaan Nayyar, Sharath Kashyap

Abstract:

Most companies see an increase in the adoption of machine learning (ML) applications across internal and external-facing use cases. ML applications vend output either in batch or real-time patterns. A complete batch ML pipeline architecture comprises data sourcing, feature engineering, model training, model deployment, model output vending into a data store for downstream application. Due to unclear role expectations, we have observed that scientists specializing in building and optimizing models are investing significant efforts into building the other components of the architecture, which we do not believe is the best use of scientists’ bandwidth. We propose a system architecture created using AWS services that bring industry best practices to managing the workflow and simplifies the process of model deployment and end-to-end data integration for an ML application. This narrows down the scope of scientists’ work to model building and refinement while specialized data engineers take over the deployment, pipeline orchestration, data quality, data permission system, etc. The pipeline infrastructure is built and deployed as code (using terraform, cdk, cloudformation, etc.) which makes it easy to replicate and/or extend the architecture to other models that are used in an organization.

Keywords: data pipeline, machine learning, AWS, architecture, batch machine learning

Procedia PDF Downloads 35

Authors: Simon Espigolé, Igor Shalyminov, Helen Hastie

Abstract:

Deep machine learning techniques including deep neural networks (DNN) have been used to model language and dialogue for conversational agents to perform tasks, such as giving technical support and also for general chit-chat. They have been shown to be capable of generating long, diverse and coherent sentences in end-to-end dialogue systems and natural language generation. However, these systems tend to imitate the training data and will only generate the concepts and language within the scope of what they have been trained on. This work explores how deep neural networks can be used in a task that would normally require human creativity, whereby the human would read the movie description and/or watch the movie and come up with a compelling, interesting movie title. This task differs from simple summarization in that the movie title may not necessarily be derivable from the content or semantics of the movie description. Here, we train a type of DNN called a sequence-to-sequence model (seq2seq) that takes as input a short textual movie description and some information on e.g. genre of the movie. It then learns to output a movie title. The idea is that the DNN will learn certain techniques and approaches that the human movie titler may deploy that may not be immediately obvious to the human-eye. To give an example of a generated movie title, for the movie synopsis: ‘A hitman concludes his legacy with one more job, only to discover he may be the one getting hit.’; the original, true title is ‘The Driver’ and the one generated by the model is ‘The Masquerade’. A human evaluation was conducted where the DNN output was compared to the true human-generated title, as well as a number of baselines, on three 5-point Likert scales: ‘creativity’, ‘naturalness’ and ‘suitability’. Subjects were also asked which of the two systems they preferred. The scores of the DNN model were comparable to the scores of the human-generated movie title, with means m=3.11, m=3.12, respectively. There is room for improvement in these models as they were rated significantly less ‘natural’ and ‘suitable’ when compared to the human title. In addition, the human-generated title was preferred overall 58% of the time when pitted against the DNN model. These results, however, are encouraging given the comparison with a highly-considered, well-crafted human-generated movie title. Movie titles go through a rigorous process of assessment by experts and focus groups, who have watched the movie. This process is in place due to the large amount of money at stake and the importance of creating an effective title that captures the audiences’ attention. Our work shows progress towards automating this process, which in turn may lead to a better understanding of creativity itself.

Keywords: creativity, deep machine learning, natural language generation, movies

Procedia PDF Downloads 304

Authors: Itamir de Morais Barroca Filho, Cephas A. S. Barreto, Ramon Malaquias, Cezar Miranda Paula de Souza, Arthur Costa Gorgônio, João C. Xavier-Júnior, Mateus Firmino, Fellipe Matheus Costa Barbosa

Abstract:

Information and Communication Technologies (ICT) in healthcare are crucial for efficiently delivering medical healthcare services to patients. These ICTs are also known as e-health and comprise technologies such as electronic record systems, telemedicine systems, and personalized devices for diagnosis. The focus of e-health is to improve the quality of health information, strengthen national health systems, and ensure accessible, high-quality health care for all. All the data gathered by these technologies make it possible to help clinical staff with automated decisions using machine learning. In this context, we collected patient data, such as heart rate, oxygen saturation (SpO2), blood pressure, respiration, and others. With this data, we were able to develop machine learning models for patients’ risk of death and estimate the length of stay in ICU beds. Thus, this paper presents the methodology for applying machine learning techniques to develop these models. As a result, although we implemented these models on an IoT healthcare platform, helping clinical staff in healthcare in an ICU, it is essential to create a robust clinical validation process and monitoring of the proposed models.

Keywords: ICT, e-health, machine learning, ICU, healthcare

Procedia PDF Downloads 75

Authors: Ksenia Meshkova

Abstract:

With increasing amount of multimedia data, it is very important to automate and speed up the process of obtaining meta. This process means not just recognition of some object or its movement, but recognition of the entire scene versus separate frames and having timeline segmentation as a final result. Labeling datasets is time consuming, besides, attributing characteristics to particular scenes is clearly difficult due to their nature. In this article, we will consider autoencoders application to unsupervised scene recognition and clusterization based on interpretable features. Further, we will focus on particular types of auto encoders that relevant to our study. We will take a look at the specificity of deep learning related to information theory and rate-distortion theory and describe the solutions empowering poor interpretability of deep learning in media content processing. As a conclusion, we will present the results of the work of custom framework, based on autoencoders, capable of scene recognition as was deeply studied above, with highlights generation resulted out of this recognition. We will not describe in detail the mathematical description of neural networks work but will clarify the necessary concepts and pay attention to important nuances.

Keywords: neural networks, computer vision, representation learning, autoencoders

Procedia PDF Downloads 98

Authors: Khalil Bachiri, Ali Yahyaouy, Nicoleta Rogovschi

Abstract:

Improved user experience is a goal of contemporary recommender systems. Recommender systems are starting to incorporate reinforcement learning since it easily satisfies this goal of increasing a user’s reward every session. In this paper, we examine the most effective Reinforcement Learning agent tactics on the Movielens (1M) dataset, balancing precision and a variety of recommendations. The absence of variability in final predictions makes simplistic techniques, although able to optimize ranking quality criteria, worthless for consumers of the recommendation system. Utilizing the stochasticity of Leonard-Ornstein processes, our suggested strategy encourages the agent to investigate its surroundings. Research demonstrates that raising the NDCG (Discounted Cumulative Gain) and HR (HitRate) criterion without lowering the Ornstein-Uhlenbeck process drift coefficient enhances the diversity of suggestions.

Keywords: recommender systems, reinforcement learning, deep learning, DDPG, Leonard-Ornstein process

Procedia PDF Downloads 112

Authors: Federico Pittino, Thomas Arnold

Abstract:

The shredding of waste materials is a key step in the recycling process towards the circular economy. Industrial shredders for waste processing operate in very harsh operating conditions, leading to the need for frequent maintenance of critical components. Maintenance optimization is particularly important also to increase the machine’s efficiency, thereby reducing the operational costs. In this work, a monitoring system has been developed and deployed on an industrial shredder located at a waste recycling plant in Austria. The machine has been monitored for one year, and methods for predictive maintenance have been developed for two key components: the cutting knives and the drive belt. The large amount of collected data is leveraged by statistical machine learning techniques, thereby not requiring very detailed knowledge of the machine or its live operating conditions. The results show that, despite the wide range of operating conditions, a reliable estimate of the optimal time for maintenance can be derived. Moreover, the trade-off between the cost of maintenance and the increase in power consumption due to the wear state of the monitored components of the machine is investigated. This work proves the benefits of real-time monitoring system for the efficient operation of industrial shredders.

Keywords: predictive maintenance, circular economy, industrial shredder, cost optimization, statistical machine learning

Procedia PDF Downloads 103

Authors: Haya Salah, Srinivas Sharan

Abstract:

Healthcare facilities use appointment systems to schedule their appointments and to manage access to their medical services. With the growing demand for outpatient care, it is now imperative to manage physician's time effectively. However, high variation in consultation duration affects the clinical scheduler's ability to estimate the appointment duration and allocate provider time appropriately. Underestimating consultation times can lead to physician's burnout, misdiagnosis, and patient dissatisfaction. On the other hand, appointment durations that are longer than required lead to doctor idle time and fewer patient visits. Therefore, a good estimation of consultation duration has the potential to improve timely access to care, resource utilization, quality of care, and patient satisfaction. Although the literature on factors influencing consultation length abound, little work has done to predict it using based data-driven approaches. Therefore, this study aims to predict consultation duration using supervised machine learning algorithms (ML), which predicts an outcome variable (e.g., consultation) based on potential features that influence the outcome. In particular, ML algorithms learn from a historical dataset without explicitly being programmed and uncover the relationship between the features and outcome variable. A subset of the data used in this study has been obtained from the electronic medical records (EMR) of four different outpatient clinics located in central Pennsylvania, USA. Also, publicly available information on doctor's characteristics such as gender and experience has been extracted from online sources. This research develops three popular ML algorithms (deep learning, random forest, gradient boosting machine) to predict the treatment time required for a patient and conducts a comparative analysis of these algorithms with respect to predictive performance. The findings of this study indicate that ML algorithms have the potential to predict the provider service time with superior accuracy. While the current approach of experience-based appointment duration estimation adopted by the clinic resulted in a mean absolute percentage error of 25.8%, the Deep learning algorithm developed in this study yielded the best performance with a MAPE of 12.24%, followed by gradient boosting machine (13.26%) and random forests (14.71%). Besides, this research also identified the critical variables affecting consultation duration to be patient type (new vs. established), doctor's experience, zip code, appointment day, and doctor's specialty. Moreover, several practical insights are obtained based on the comparative analysis of the ML algorithms. The machine learning approach presented in this study can serve as a decision support tool and could be integrated into the appointment system for effectively managing patient scheduling.

Keywords: clinical decision support system, machine learning algorithms, patient scheduling, prediction models, provider service time

Procedia PDF Downloads 95

Authors: Sangeeta Palekar, Neeraj Rangwani, Akash Poddar, Jayu Kalambe

Abstract:

The bio-medical analysis is an indispensable procedure for identifying health-related diseases like diabetes. Monitoring the glucose level in our body regularly helps us identify hyperglycemia and hypoglycemia, which can cause severe medical problems like nerve damage or kidney diseases. This paper presents a method for predicting the glucose concentration in blood samples using image processing and machine learning algorithms. The glucose solution is prepared by the glucose oxidase (GOD) and peroxidase (POD) method. An experimental database is generated based on the colorimetric technique. The image of the glucose solution is captured by the raspberry pi camera and analyzed using image processing by extracting the RGB, HSV, LUX color space values. Regression algorithms like multiple linear regression, decision tree, RandomForest, and XGBoost were used to predict the unknown glucose concentration. The multiple linear regression algorithm predicts the results with 97% accuracy. The image processing and machine learning-based approach reduce the hardware complexities of existing platforms.

Keywords: artificial intelligence glucose detection, glucose oxidase, peroxidase, image processing, machine learning

Procedia PDF Downloads 171

Authors: Rim Messaoudi, Nogaye-Gueye Gning, François Azelart

Abstract:

Automatic text classification applies mostly natural language processing (NLP) and other AI-guided techniques to automatically classify text in a faster and more accurate manner. This paper discusses the subject of using predictive maintenance to manage incident tickets inside the sociality. It focuses on proposing a tool that treats and analyses comments and notes written by administrators after resolving an incident ticket. The goal here is to increase the quality of these comments. Additionally, this tool is based on NLP and machine learning techniques to realize the textual analytics of the extracted data. This approach was tested using real data taken from the French National Railways (SNCF) company and was given a high-quality result.

Keywords: machine learning, text classification, NLP techniques, semantic representation

Procedia PDF Downloads 66

Authors: Yi-Min Lan, Hung-Wen Cheng, Hsuan-Ling Chang, Jou-Ping Yu

Abstract:

The study applies machine learning models to construct momentum strategies and utilizes the information coefficient as an indicator for selecting stocks with strong and weak momentum characteristics. Through this approach, the study has built investment portfolios capable of generating superior returns and conducted a thorough analysis. Compared to existing research on momentum strategies, machine learning is incorporated to capture non-linear interactions. This approach enhances the conventional stock selection process, which is often impeded by difficulties associated with timeliness, accuracy, and efficiency due to market risk factors. The study finds that implementing bidirectional momentum strategies outperforms unidirectional ones, and momentum factors with longer observation periods exhibit stronger correlations with returns. Optimizing the number of stocks in the portfolio while staying within a certain threshold leads to the highest level of excess returns. The study presents a novel framework for momentum strategies that enhances and improves the operational aspects of asset management. By introducing innovative financial technology applications to traditional investment strategies, this paper can demonstrate significant effectiveness.

Keywords: information coefficient, machine learning, momentum, portfolio, return prediction

Procedia PDF Downloads 32

Authors: Ying Su, Morgan C. Wang

Abstract:

Long-term time series forecasting is an important research area for automated machine learning (AutoML). Currently, forecasting based on either machine learning or statistical learning is usually built by experts, and it requires significant manual effort, from model construction, feature engineering, and hyper-parameter tuning to the construction of the time series model. Automation is not possible since there are too many human interventions. To overcome these limitations, this article proposed to use recurrent neural networks (RNN) through the memory state of RNN to perform long-term time series prediction. We have shown that this proposed approach is better than the traditional Autoregressive Integrated Moving Average (ARIMA). In addition, we also found it is better than other network systems, including Fully Connected Neural Networks (FNN), Convolutional Neural Networks (CNN), and Nonpooling Convolutional Neural Networks (NPCNN).

Keywords: automated machines learning, autoregressive integrated moving average, neural networks, time series analysis

Procedia PDF Downloads 56

Authors: Xi Liu, Fan Yuan

Abstract:

In the evolving landscape of physics-based machine learning (PBML), particularly within fluid dynamics and its applications in electromechanical engineering, robot vision, and robot learning, achieving precision and alignment with researchers' specific needs presents a formidable challenge. In response, this work proposes a methodology that integrates neural transformation with a modified smoothed particle hydrodynamics model for generating transformed 3D fluid simulations. This approach is useful for nanoscale science, where the unique and complex behaviors of viscoelastic medium demand accurate neurally-transformed simulations for materials understanding and manipulation. In electromechanical engineering, the method enhances the design and functionality of fluid-operated systems, particularly microfluidic devices, contributing to advancements in nanomaterial design, drug delivery systems, and more. The proposed approach also aligns with the principles of PBML, offering advantages such as multi-fluid stylization and consistent particle attribute transfer. This capability is valuable in various fields where the interaction of multiple fluid components is significant. Moreover, the application of neurally-transformed hydrodynamical models extends to manufacturing processes, such as the production of microelectromechanical systems, enhancing efficiency and cost-effectiveness. The system's ability to perform neural transfer on 3D fluid scenes using a deep learning algorithm alongside physical models further adds a layer of flexibility, allowing researchers to tailor simulations to specific needs across scientific and engineering disciplines.

Keywords: physics-based machine learning, robot vision, robot learning, hydrodynamics

Procedia PDF Downloads 39

Authors: Lin Li, Farshad Amini

Abstract:

The flipped classroom has been introduced to promote collaborative learning and higher-order learning objectives. In contrast to the traditional classroom, the flipped classroom has students watch prerecorded lecture videos before coming to class and then “class becomes the place to work through problems, advance concepts, and engage in collaborative learning”. In this paper, the active flipped learning combines flipped classroom with active learning that is to establish an active flipped learning (AFL) model, aiming to promote active learning, stress deep learning, encourage student engagement and highlight data-driven personalized learning. Because students have watched the lecture prior to class, contact hours can be devoted to problem-solving and gain a deeper understanding of the subject matter. The instructor is able to provide students with a wide range of learner-centered opportunities in class for greater mentoring and collaboration, increasing the possibility to engage students. Currently, little is known about the extent to which AFL improves engineering students’ performance. This paper presents the preliminary study on the core course of sophomore students in Engineering Mechanics. A series of survey and interviews have been conducted to compare students’ learning engagement, empowerment, self-efficacy, and satisfaction with the AFL. It was found that the AFL model taking advantage of advanced technology is a convenient and professional avenue for engineering students to strengthen their academic confidence and self-efficacy in the Engineering Mechanics by actively participating in learning and fostering their deep understanding of engineering statics and dynamics

Keywords: active learning, engineering mechanics, flipped classroom, performance

Procedia PDF Downloads 266

Authors: Xiaodong Li, Peng Gao, Chao-Jung Huang, Shiying Hao, Xuefeng B. Ling, Yongxia Han, Yaqi Zhang, Le Zheng, Chengyin Ye, Modi Liu, Minjie Xia, Changlin Fu, Bo Jin, Karl G. Sylvester, Eric Widen

Abstract:

Predicting the risk of Pancreatic Adenocarcinoma (PA) in advance can benefit the quality of care and potentially reduce population mortality and morbidity. The aim of this study was to develop and prospectively validate a risk prediction model to identify patients at risk of new incident PA as early as 3 months before the onset of PA in a statewide, general population in Maine. The PA prediction model was developed using Deep Neural Networks, a deep learning algorithm, with a 2-year electronic-health-record (EHR) cohort. Prospective results showed that our model identified 54.35% of all inpatient episodes of PA, and 91.20% of all PA that required subsequent chemoradiotherapy, with a lead-time of up to 3 months and a true alert of 67.62%. The risk assessment tool has attained an improved discriminative ability. It can be immediately deployed to the health system to provide automatic early warnings to adults at risk of PA. It has potential to identify personalized risk factors to facilitate customized PA interventions.

Keywords: cancer prediction, deep learning, electronic health records, pancreatic adenocarcinoma

Procedia PDF Downloads 128

Authors: Y. Kim, H. Lee, M. Park, B. Lee

Abstract:

Planning is understood as the determination of what has to be performed, how, in which sequence, when, what resources are needed, and their cost within the organization before execution. In most construction project, it is evident that the inherent nature of planning is dynamic, and initial planning is subject to be changed due to various uncertain conditions of construction project. Planners take a continuous revision process during the course of a project and until the very end of project. However, current practice lacks reliable, systematic tool for setting variance thresholds to determine when and what corrective actions to be taken. Rather it is heavily dependent on the level of experience and knowledge of the planner. Thus, this paper introduces a machine learning approach to evaluate project control threshold reliability incorporating project-specific data and presents a method to automate the process. The results have shown that the model improves the efficiency and accuracy of the monitoring process as an early warning.

Keywords: machine learning, project control, project progress monitoring, schedule

Procedia PDF Downloads 226

Authors: Matan Cohen, Maxim Shoshany

Abstract:

Climatic, topographic and geological diversity, together with frequent disturbance and recovery cycles, produce highly complex spatial patterns of trees, shrubs, dwarf shrubs and bare ground patches. Assessment of spatial and temporal variations of these life-forms patterns under climate change is of high ecological priority. Here we report on one of the first attempts to discriminate between images of three Mediterranean life-forms patterns at three densities. The development of an extensive database of orthophoto images representing these 9 pattern categories was instrumental for training and testing pre-trained and newly-trained DL models utilizing DenseNet architecture. Both models demonstrated the advantages of using Deep Learning approaches over existing spectral and spatial (pattern or texture) algorithmic methods in differentiation 9 life-form spatial mixtures categories.

Keywords: texture classification, deep learning, desert fringe ecosystems, climate change

Procedia PDF Downloads 67

Authors: Farshid Hajati, Federico Girosi, Shima Ghassempour

Abstract:

We present a Deep Belief Network (DBN) method for clustering health trajectories. Deep Belief Network (DBN) is a deep architecture that consists of a stack of Restricted Boltzmann Machines (RBM). In a deep architecture, each layer learns more complex features than the past layers. The proposed method depends on DBN in clustering without using back propagation learning algorithm. The proposed DBN has a better a performance compared to the deep neural network due the initialization of the connecting weights. We use Contrastive Divergence (CD) method for training the RBMs which increases the performance of the network. The performance of the proposed method is evaluated extensively on the Health and Retirement Study (HRS) database. The University of Michigan Health and Retirement Study (HRS) is a nationally representative longitudinal study that has surveyed more than 27,000 elderly and near-elderly Americans since its inception in 1992. Participants are interviewed every two years and they collect data on physical and mental health, insurance coverage, financial status, family support systems, labor market status, and retirement planning. The dataset is publicly available and we use the RAND HRS version L, which is easy to use and cleaned up version of the data. The size of sample data set is 268 and the length of the trajectories is equal to 10. The trajectories do not stop when the patient dies and represent 10 different interviews of live patients. Compared to the state-of-the-art benchmarks, the experimental results show the effectiveness and superiority of the proposed method in clustering health trajectories.

Keywords: health trajectory, clustering, deep learning, DBN

Procedia PDF Downloads 345

Authors: Anas H. Aljemely, Jianping Xuan

Abstract:

Rolling bearing fault diagnosis plays a pivotal issue in the rotating machinery of modern manufacturing. In this research, a raw vibration signal and improved deep learning method for bearing fault diagnosis are proposed. The multi-dimensional scales of raw vibration signals are selected for evaluation condition monitoring system, and the deep learning process has shown its effectiveness in fault diagnosis. In the proposed method, employing an Exponential linear unit (ELU) layer in a convolutional neural network (CNN) that conducts the identical function on positive data, an exponential nonlinearity on negative inputs, and a particular convolutional operation to extract valuable features. The identification results show the improved method has achieved the highest accuracy with a 100-dimensional scale and increase the training and testing speed.

Keywords: bearing fault prognostics, developed CNN model, multiple-scale evaluation, deep learning features

Procedia PDF Downloads 176

Authors: Shuai Zhao, Shalendra D. Sharma, Jin Xu

Abstract:

This research uses advanced machine learning models to learn a number of hypotheses regarding political executives. Specifically, it analyses the impact these powerful leaders have on economic growth by using leaders’ data from the Archigos database from 1835 to the end of 2015. The data is processed by the AutoGluon, which was developed by Amazon. Automated Machine Learning (AutoML) and AutoGluon can automatically extract features from the data and then use multiple classifiers to train the data. Use a linear regression model and classification model to establish the relationship between leaders and economic growth (GDP per capita growth), and to clarify the relationship between their characteristics and economic growth from a machine learning perspective. Our work may show as a model or signal for collaboration between the fields of statistics and artificial intelligence (AI) that can light up the way for political researchers and economists.

Keywords: comparative politics, political executives, leaders’ characteristics, artificial intelligence

Procedia PDF Downloads 57

Authors: Mst Shapna Akter, Hossain Shahriar

Abstract:

One of the most important challenges in the field of software code audit is the presence of vulnerabilities in software source code. Every year, more and more software flaws are found, either internally in proprietary code or revealed publicly. These flaws are highly likely exploited and lead to system compromise, data leakage, or denial of service. C and C++ open-source code are now available in order to create a largescale, machine-learning system for function-level vulnerability identification. We assembled a sizable dataset of millions of opensource functions that point to potential exploits. We developed an efficient and scalable vulnerability detection method based on deep neural network models that learn features extracted from the source codes. The source code is first converted into a minimal intermediate representation to remove the pointless components and shorten the dependency. Moreover, we keep the semantic and syntactic information using state-of-the-art word embedding algorithms such as glove and fastText. The embedded vectors are subsequently fed into deep learning networks such as LSTM, BilSTM, LSTM-Autoencoder, word2vec, BERT, and GPT-2 to classify the possible vulnerabilities. Furthermore, we proposed a neural network model which can overcome issues associated with traditional neural networks. Evaluation metrics such as f1 score, precision, recall, accuracy, and total execution time have been used to measure the performance. We made a comparative analysis between results derived from features containing a minimal text representation and semantic and syntactic information. We found that all of the deep learning models provide comparatively higher accuracy when we use semantic and syntactic information as the features but require higher execution time as the word embedding the algorithm puts on a bit of complexity to the overall system.

Keywords: cyber security, vulnerability detection, neural networks, feature extraction

Procedia PDF Downloads 56