Search results for: deep machine learning

Authors: Mirjana Ruppel, Rajendra Persad, Amit Bahl, Sanja Dogramadzi, Chris Melhuish, Lyndon Smith

Abstract:

Multimodal image registration is a profoundly complex task which is why deep learning has been used widely to address it in recent years. However, two main challenges remain: Firstly, the lack of ground truth data calls for an unsupervised learning approach, which leads to the second challenge of defining a feasible loss function that can compare two images of different modalities to judge their level of alignment. To avoid this issue altogether we implement a generative adversarial network consisting of two registration networks GAB, GBA and two discrimination networks DA, DB connected by spatial transformation layers. GAB learns to generate a deformation field which registers an image of the modality B to an image of the modality A. To do that, it uses the feedback of the discriminator DB which is learning to judge the quality of alignment of the registered image B. GBA and DA learn a mapping from modality A to modality B. Additionally, a cycle-consistency loss is implemented. For this, both registration networks are employed twice, therefore resulting in images ˆA, ˆB which were registered to ˜B, ˜A which were registered to the initial image pair A, B. Thus the resulting and initial images of the same modality can be easily compared. A dataset of liver CT and MRI was used to evaluate the quality of our approach and to compare it against learning and non-learning based registration algorithms. Our approach leads to dice scores of up to 0.80 ± 0.01 and is therefore comparable to and slightly more successful than algorithms like SimpleElastix and VoxelMorph.

Keywords: cycle consistency, deformable multimodal image registration, deep learning, GAN

Procedia PDF Downloads 106

Authors: Edward Holupka, John Rossman, Tye Morancy, Joseph Aronovitz, Irving Kaplan

Abstract:

A common modality for the treatment of early stage prostate cancer is the implantation of radioactive seeds directly into the prostate. The radioactive seeds are positioned inside the prostate to achieve optimal radiation dose coverage to the prostate. These radioactive seeds are positioned inside the prostate using Transrectal ultrasound imaging. Once all of the planned seeds have been implanted, two dimensional transaxial transrectal ultrasound images separated by 2 mm are obtained through out the prostate, beginning at the base of the prostate up to and including the apex. A common deep neural network, called DetectNet was trained to automatically determine the position of the implanted radioactive seeds within the prostate under ultrasound imaging. The results of the training using 950 training ultrasound images and 90 validation ultrasound images. The commonly used metrics for successful training were used to evaluate the efficacy and accuracy of the trained deep neural network and resulted in an loss_bbox (train) = 0.00, loss_coverage (train) = 1.89e-8, loss_bbox (validation) = 11.84, loss_coverage (validation) = 9.70, mAP (validation) = 66.87%, precision (validation) = 81.07%, and a recall (validation) = 82.29%, where train and validation refers to the training image set and validation refers to the validation training set. On the hardware platform used, the training expended 12.8 seconds per epoch. The network was trained for over 10,000 epochs. In addition, the seed locations as determined by the Deep Neural Network were compared to the seed locations as determined by a commercial software based on a one to three months after implant CT. The Deep Learning approach was within \strikeout off\uuline off\uwave off2.29\uuline default\uwave default mm of the seed locations determined by the commercial software. The Deep Learning approach to the determination of radioactive seed locations is robust, accurate, and fast and well within spatial agreement with the gold standard of CT determined seed coordinates.

Keywords: prostate, deep neural network, seed implant, ultrasound

Procedia PDF Downloads 175

Authors: Rosdyana Mangir Irawan Kusuma, Wei-Chun Kao, Ho-Thi Trang, Yu-Yen Ou, Kai-Lung Hua

Abstract:

Stock market prediction is still a challenging problem because there are many factors that affect the stock market price such as company news and performance, industry performance, investor sentiment, social media sentiment, and economic factors. This work explores the predictability in the stock market using deep convolutional network and candlestick charts. The outcome is utilized to design a decision support framework that can be used by traders to provide suggested indications of future stock price direction. We perform this work using various types of neural networks like convolutional neural network, residual network and visual geometry group network. From stock market historical data, we converted it to candlestick charts. Finally, these candlestick charts will be feed as input for training a convolutional neural network model. This convolutional neural network model will help us to analyze the patterns inside the candlestick chart and predict the future movements of the stock market. The effectiveness of our method is evaluated in stock market prediction with promising results; 92.2% and 92.1 % accuracy for Taiwan and Indonesian stock market dataset respectively.

Keywords: candlestick chart, deep learning, neural network, stock market prediction

Procedia PDF Downloads 417

Authors: Rimma Dzhusupova, Jan Bosch, Helena Holmström Olsson

Abstract:

Artificial Intelligence (AI) in the Engineering, Procurement, and Construction (EPC) industry has not yet a proven track record in large-scale projects. Since AI solutions for industrial applications became available only recently, deployment experience and lessons learned are still to be built up. Nevertheless, AI has become an attractive technology for organizations looking to automate repetitive tasks to reduce manual work. Meanwhile, the current AI market has started offering various solutions and services. The contribution of this research is that we explore in detail the challenges and obstacles faced in developing and deploying AI in a large-scale project in the EPC industry based on real-life use cases performed in an EPC company. Those identified challenges are not linked to a specific technology or a company's know-how and, therefore, are universal. The findings in this paper aim to provide feedback to academia to reduce the gap between research and practice experience. They also help reveal the hidden stones when implementing AI solutions in the industry.

Keywords: artificial intelligence, machine learning, deep learning, innovation, engineering, procurement and construction industry, AI in the EPC industry

Procedia PDF Downloads 98

Authors: Loulwah Bokhari, Jori Nazer, Hala Sultan

Abstract:

Nowadays, artificial intelligence (AI) is used as a foundation for many activities in modern computing applications at home, in vehicles, and in businesses. Many modern machines are built to carry out a specific activity or purpose. This is where the Amazon Alexa application comes in, as it is used as a virtual assistant. The purpose of this paper is to explore the use of Amazon Alexa among people and how it has improved and made simple daily tasks easier for many people. We gave our participants several questions regarding Amazon Alexa and if they had recently used or heard of it, as well as the different tasks it provides and whether it successfully satisfied their needs. Overall, we found that participants who have recently used Alexa have found it to be helpful in their daily tasks.

Keywords: artificial intelligence, Echo system, machine learning, feature for feature match

Procedia PDF Downloads 101

Authors: Cao Jiayu, Lan Ximing, Huang Jingjia, Burra Venkata Durga Kumar

Abstract:

The first virus to attack personal computers was born in early 1986, called C-Brain, written by a pair of Pakistani brothers. In those days, people still used dos systems, manipulating computers with the most basic command lines. In the 21st century today, computer performance has grown geometrically. But computer viruses are also evolving and escalating. We never stop fighting against security problems. Stack overflow is one of the most common security vulnerabilities in operating systems. It may result in serious security issues for an operating system if a program in it has a vulnerability with administrator privileges. Certain viruses change the value of specific memory through a stack overflow, allowing computers to run harmful programs. This study developed a mechanism to detect and respond to time whenever a stack overflow occurs. We demonstrate the effectiveness of standard machine learning algorithms and control flow enforcement techniques in predicting computer OS security using generating suspicious vulnerability functions (SVFS) and associated suspect areas (SAS). The method can minimize the possibility of stack overflow attacks occurring.

Keywords: operating system, security, stack overflow, buffer overflow, machine learning, control-flow enforcement technology

Procedia PDF Downloads 99

Authors: L. S. Chathurika

Abstract:

Early prediction of student performance is an important factor to be gained academic excellence. Whatever the study stream in secondary education, students lay the foundation for higher studies during the first year of their degree or diploma program in Sri Lanka. The information technology (IT) field has certain improvements in the education domain by selecting specialization areas to show the talents and skills of students. These specializations can be software engineering, network administration, database administration, multimedia design, etc. After completing the first-year, students attempt to select the best path by considering numerous factors. The purpose of this experiment is to predict the best study path using machine learning algorithms. Five classification algorithms: decision tree, support vector machine, artificial neural network, Naïve Bayes, and logistic regression are selected and tested. The support vector machine obtained the highest accuracy, 82.4%. Then affecting features are recognized to select the best study path.

Keywords: algorithm, classification, evaluation, features, testing, training

Procedia PDF Downloads 106

Authors: David Ming Liu, Benjamin Hirsch, Bashir Aden

Abstract:

Syndromic surveillance is to detect or predict disease outbreaks through the analysis of medical sources of data. Using social media data like tweets to do syndromic surveillance becomes more and more popular with the aid of open platform to collect data and the advantage of microblogging text and mobile geographic location features. In this paper, a Syndromic Surveillance Framework is presented with machine learning kernel using tweets data analytics. Influenza and the three cities Abu Dhabi, Al Ain and Dubai of United Arabic Emirates are used as the test disease and trial areas. Hospital cases data provided by the Health Authority of Abu Dhabi (HAAD) are used for the correlation purpose. In our model, Latent Dirichlet allocation (LDA) engine is adapted to do supervised learning classification and N-Fold cross validation confusion matrix are given as the simulation results with overall system recall 85.595% performance achieved.

Keywords: Syndromic surveillance, Tweets, Machine Learning, data mining, Latent Dirichlet allocation (LDA), Influenza

Procedia PDF Downloads 93

Authors: Oumaima Khlifati, Khadija Baba

Abstract:

Pavement distress is the main factor responsible for the deterioration of road structure durability, damage vehicles, and driver comfort. Transportation agencies spend a high proportion of their funds on pavement monitoring and maintenance. The auscultation of pavement distress was based on the manual survey, which was extremely time consuming, labor intensive, and required domain expertise. Therefore, the automatic distress detection is needed to reduce the cost of manual inspection and avoid more serious damage by implementing the appropriate remediation actions at the right time. Inspired by recent deep learning applications, this paper proposes an algorithm for automatic road distress detection and classification using on the Deep Convolutional Neural Network (DCNN). In this study, the types of pavement distress are classified as transverse or longitudinal cracking, alligator, pothole, and intact pavement. The dataset used in this work is composed of public asphalt pavement images. In order to learn the structure of the different type of distress, the DCNN models are trained and tested as a multi-label classification task. In addition, to get the highest accuracy for our model, we adjust the structural optimization hyper parameters such as the number of convolutions and max pooling, filers, size of filters, loss functions, activation functions, and optimizer and fine-tuning hyper parameters that conclude batch size and learning rate. The optimization of the model is executed by checking all feasible combinations and selecting the best performing one. The model, after being optimized, performance metrics is calculated, which describe the training and validation accuracies, precision, recall, and F1 score.

Keywords: distress pavement, hyperparameters, automatic classification, deep learning

Procedia PDF Downloads 63

Authors: Grienggrai Rajchakit

Abstract:

As we all know that coronavirus is announced as a pandemic in the world by WHO. It is speeded all over the world with few days of time. To control this spreading, every citizen maintains social distance and self-preventive measures are the best strategies. As of now, many researchers and scientists are continuing their research in finding out the exact vaccine. The machine learning model finds that the coronavirus disease behaves in an exponential manner. To abolish the consequence of this pandemic, an efficient step should be taken to analyze this disease. In this paper, a recurrent neural network model is chosen to predict the number of active cases in a particular state. To make this prediction of active cases, we need a database. The database of COVID-19 is downloaded from the KAGGLE website and is analyzed by applying a recurrent LSTM neural network with univariant features to predict the number of active cases of patients suffering from the corona virus. The downloaded database is divided into training and testing the chosen neural network model. The model is trained with the training data set and tested with a testing dataset to predict the number of active cases in a particular state; here, we have concentrated on Andhra Pradesh state.

Keywords: COVID-19, coronavirus, KAGGLE, LSTM neural network, machine learning

Procedia PDF Downloads 140

Authors: Sami M. Alshareef

Abstract:

The rapid growth of smart grid technology has brought significant advancements to the power industry. However, with the increasing interconnectivity and reliance on information and communication technologies, smart grids have become vulnerable to cyber-attacks, posing significant threats to the reliable operation of power systems. Among the critical components of smart grids, the Automatic Generation Control (AGC) system plays a vital role in maintaining the balance between generation and load demand. Therefore, protecting the AGC system from cyber threats is of paramount importance to maintain grid stability and prevent disruptions. Traditional security measures often fall short in addressing sophisticated and evolving cyber threats, necessitating the exploration of innovative approaches. Machine learning, with its ability to analyze vast amounts of data and learn patterns, has emerged as a promising solution to enhance AGC system security. Therefore, this research proposal aims to address the challenges associated with detecting and mitigating cyber-attacks on AGC in smart grids by leveraging machine learning techniques on automatic generation control of two-area power systems. By utilizing historical data, the proposed system will learn the normal behavior patterns of AGC and identify deviations caused by cyber-attacks. Once an attack is detected, appropriate mitigation strategies will be employed to safeguard the AGC system. The outcomes of this research will provide power system operators and administrators with valuable insights into the vulnerabilities of AGC systems in smart grids and offer practical solutions to enhance their cyber resilience.

Keywords: machine learning, cyber-attacks, automatic generation control, smart grid

Procedia PDF Downloads 64

Authors: Boumediene Hamzi, Turky N. AlOtaiby, Saleh AlShebeili, Arwa AlAnqary

Abstract:

We introduce a data-driven method for seizure detection drawing on recent progress in Machine Learning. The method is based on embedding probability measures in a high (or infinite) dimensional reproducing kernel Hilbert space (RKHS) where the Maximum Mean Discrepancy (MMD) is computed. The MMD is metric between probability measures that are computed as the difference between the means of probability measures after being embedded in an RKHS. Working in RKHS provides a convenient, general functional-analytical framework for theoretical understanding of data. We apply this approach to the problem of seizure detection.

Keywords: kernel methods, maximum mean discrepancy, seizure detection, machine learning

Procedia PDF Downloads 217

Authors: Bandar Alahmadi, Lethia Jackson

Abstract:

Machine Learning model is used today in many real-life applications. The safety and security of such model is important, so the results of the model are as accurate as possible. One challenge of machine learning model security is the adversarial examples attack. Adversarial examples are designed by the attacker to cause the machine learning model to misclassify the input. We propose a method to generate adversarial examples to attack image classifiers. We are modifying the successfully classified images, so a classifier misclassifies them after the modification. In our method, we do not update the whole image, but instead we detect the important region, modify it, place it back to the original image, and then run it through a classifier. The algorithm modifies the detected region using two methods. First, it will add abstract image matrix on back of the detected image matrix. Then, it will perform a rotation attack to rotate the detected region around its axes, and embed the trace of image in image background. Finally, the attacked region is placed in its original position, from where it was removed, and a smoothing filter is applied to smooth the background with foreground. We test our method in cascade classifier, and the algorithm is efficient, the classifier confident has dropped to almost zero. We also try it in CNN (Convolutional neural network) with higher setting and the algorithm was successfully worked.

Keywords: adversarial examples, attack, computer vision, image processing

Procedia PDF Downloads 320

Authors: Kwangmin Joo

Abstract:

Automatic detection of lumbar vertebrae and classification method is proposed for evaluating the degree of disc narrowing. Prior to classification, deep learning based segmentation is applied to detect individual lumbar vertebra. M-net is applied to segment five lumbar vertebrae and fine-tuning segmentation is employed to improve the accuracy of segmentation. Using the features extracted from previous step, clustering technique, k-means clustering, is applied to estimate the degree of disc space narrowing under four grade scoring system. As preliminary study, techniques proposed in this research could help building an automatic scoring system to diagnose the severity of disc narrowing from X-ray images.

Keywords: Disc space narrowing, Degenerative disc disorders, Deep learning based segmentation, Clustering technique

Procedia PDF Downloads 110

Authors: Ghazala Hcini, Imen Jdey, Hela Ltifi

Abstract:

Malaria disease should be considered and handled as a potential restorative catastrophe. One of the most challenging tasks in the field of microscopy image processing is due to differences in test design and vulnerability of cell classifications. In this article, we focused on applying deep learning to classify patients by identifying images of infected and uninfected cells. We performed multiple forms, counting a classification approach using the Hue, Saturation, Value (HSV) color space. HSV is used since of its superior ability to speak to image brightness; at long last, for classification, a convolutional neural network (CNN) architecture is created. Clusters of focus were used to deliver the classification. The highlights got to be forbidden, and a few more clamor sorts are included in the information. The suggested method has a precision of 99.79%, a recall value of 99.55%, and provides 99.96% accuracy.

Keywords: deep learning, convolutional neural network, image classification, color transformation, HSV color, malaria diagnosis, malaria cells images

Procedia PDF Downloads 69

Authors: Tomas Premoli, Sareh Rowlands

Abstract:

In this study, we investigate the impact of various convolutional neural network (CNN) architectures on the accuracy of diagnosing Alzheimer’s disease (AD) using patient MRI scans. Alzheimer’s disease is a debilitating neurodegenerative disorder that affects millions worldwide. Early, accurate, and non-invasive diagnostic methods are required for providing optimal care and symptom management. Deep learning techniques, particularly CNNs, have shown great promise in enhancing this diagnostic process. We aim to contribute to the ongoing research in this field by comparing the effectiveness of different CNN architectures and providing insights for future studies. Our methodology involved preprocessing MRI data, implementing multiple CNN architectures, and evaluating the performance of each model. We employed intensity normalization, linear registration, and skull stripping for our preprocessing. The selected architectures included VGG, ResNet, and DenseNet models, all implemented using the Keras library. We employed transfer learning and trained models from scratch to compare their effectiveness. Our findings demonstrated significant differences in performance among the tested architectures, with DenseNet201 achieving the highest accuracy of 86.4%. Transfer learning proved to be helpful in improving model performance. We also identified potential areas for future research, such as experimenting with other architectures, optimizing hyperparameters, and employing fine-tuning strategies. By providing a comprehensive analysis of the selected CNN architectures, we offer a solid foundation for future research in Alzheimer’s disease diagnosis using deep learning techniques. Our study highlights the potential of CNNs as a valuable diagnostic tool and emphasizes the importance of ongoing research to develop more accurate and effective models.

Keywords: Alzheimer’s disease, convolutional neural networks, deep learning, medical imaging, MRI

Procedia PDF Downloads 51

Authors: S. Chami, J. Chauvin, T. Demarest, Stan Ng, M. Straus, W. Jahner

Abstract:

Biometrics tools such as fingerprint and iris are widely used in industry to protect critical assets. However, their vulnerability and lack of robustness raise several worries about the protection of highly critical assets. Biometrics based on Electrocardiographic (ECG) signals is a robust identification tool. However, most of the state-of-the-art techniques have worked on clinical signals, which are of high quality and less noisy, extracted from wearable devices like a smartwatch. In this paper, we are presenting a complete machine learning pipeline that identifies people using ECG extracted from an off-person device. An off-person device is a wearable device that is not used in a medical context such as a smartwatch. In addition, one of the main challenges of ECG biometrics is the variability of the ECG of different persons and different situations. To solve this issue, we proposed two different approaches: per person classifier, and one-for-all classifier. The first approach suggests making binary classifier to distinguish one person from others. The second approach suggests a multi-classifier that distinguishes the selected set of individuals from non-selected individuals (others). The preliminary results, the binary classifier obtained a performance 90% in terms of accuracy within a balanced data. The second approach has reported a log loss of 0.05 as a multi-class score.

Keywords: biometrics, electrocardiographic, machine learning, signals processing

Procedia PDF Downloads 124

Authors: Shreya Goyal

Abstract:

The study aims to build user-friendly software to understand patient arrival patterns and compute the number of potential patients who will visit a particular health facility for a given period by using a machine learning algorithm. The underlying machine learning algorithm used in this study is the Support Vector Machine (SVM). Accurate prediction of patient arrival allows hospitals to operate more effectively, providing timely and efficient care while optimizing resources and improving patient experience. It allows for better allocation of staff, equipment, and other resources. If there's a projected surge in patients, additional staff or resources can be allocated to handle the influx, preventing bottlenecks or delays in care. Understanding patient arrival patterns can also help streamline processes to minimize waiting times for patients and ensure timely access to care for patients in need. Another big advantage of using this software is adhering to strict data protection regulations such as the Health Insurance Portability and Accountability Act (HIPAA) in the United States as the hospital will not have to share the data with any third party or upload it to the cloud because the software can read data locally from the machine. The data needs to be arranged in. a particular format and the software will be able to read the data and provide meaningful output. Using software that operates locally can facilitate compliance with these regulations by minimizing data exposure. Keeping patient data within the hospital's local systems reduces the risk of unauthorized access or breaches associated with transmitting data over networks or storing it in external servers. This can help maintain the confidentiality and integrity of sensitive patient information. Historical patient data is used in this study. The input variables used to train the model include patient age, time of day, day of the week, seasonal variations, and local events. The algorithm uses a Supervised learning method to optimize the objective function and find the global minima. The algorithm stores the values of the local minima after each iteration and at the end compares all the local minima to find the global minima. The strength of this study is the transfer function used to calculate the number of patients. The model has an output accuracy of >95%. The method proposed in this study could be used for better management planning of personnel and medical resources.

Keywords: machine learning, SVM, HIPAA, data

Procedia PDF Downloads 50

Authors: James Ladzekpo

Abstract:

Background: The urgent need to identify new pharmacological targets for diabetes treatment and prevention has been amplified by the disease's extensive impact on individuals and healthcare systems. A deeper insight into the biological underpinnings of diabetes is crucial for the creation of therapeutic strategies aimed at these biological processes. Current predictive models based on genetic variations fall short of accurately forecasting diabetes. Objectives: Our study aims to pinpoint key epigenetic factors that predispose individuals to diabetes. These factors will inform the development of an advanced predictive model that estimates diabetes risk from genetic profiles, utilizing state-of-the-art statistical and data mining methods. Methodology: We have implemented a recursive feature elimination with cross-validation using the support vector machine (SVM) approach for refined feature selection. Building on this, we developed six machine learning models, including logistic regression, k-Nearest Neighbors (k-NN), Naive Bayes, Random Forest, Gradient Boosting, and Multilayer Perceptron Neural Network, to evaluate their performance. Findings: The Gradient Boosting Classifier excelled, achieving a median recall of 92.17% and outstanding metrics such as area under the receiver operating characteristics curve (AUC) with a median of 68%, alongside median accuracy and precision scores of 76%. Through our machine learning analysis, we identified 31 genes significantly associated with diabetes traits, highlighting their potential as biomarkers and targets for diabetes management strategies. Conclusion: Particularly noteworthy were the Gradient Boosting Classifier and Multilayer Perceptron Neural Network, which demonstrated potential in diabetes outcome prediction. We recommend future investigations to incorporate larger cohorts and a wider array of predictive variables to enhance the models' predictive capabilities.

Keywords: diabetes, machine learning, prediction, biomarkers

Procedia PDF Downloads 35

Authors: Esra Ece Var

Abstract:

Beekeeping plays essential role both in terms of agricultural yields and agricultural economy; they produce honey, wax, royal jelly, apitoxin, pollen, and propolis. Nowadays, these natural products become more importantly suitable and preferable for nutrition, food supplement, medicine, and industry. However, to produce organic honey, majority of the apiaries are located in remote or distant rural areas where utilities such as electricity and Internet network are not available. Additionally, due to colony failures, world honey production decreases year by year despite the increase in the number of beehives. The objective of this paper is to develop a smart beehive monitoring system for apiaries including those that do not have access to Internet network. In this context, temperature and humidity inside the beehive, and ambient temperature were measured with RFID sensors. Control center, where all sensor data was sent and stored at, has a GSM module used to warn the beekeeper via SMS when an anomaly is detected. Simultaneously, using the collected data, an unsupervised machine learning algorithm is used for detecting anomalies and calibrating the warning system. The results show that the smart beehive monitoring system can detect fatal anomalies up to 4 weeks prior to colony loss.

Keywords: beekeeping, smart systems, machine learning, anomaly detection, apiculture

Procedia PDF Downloads 209

Authors: Jiwan Kumar, Pooja, Sandeep Negi, Anjum Rouf, Amit Kumar, Naveen Lakra

Abstract:

In modern times where, health issues are increasing day by day, breast cancer is also one of them, which is very crucial and really important to find in the early stages. Doctors can use this model in order to tell their patients whether a cancer is not harmful (benign) or harmful (malignant). We have used the knowledge of machine learning in order to produce the model. we have used algorithms like Logistic Regression, Random forest, support Vector Classifier, Bayesian Network and Radial Basis Function. We tried to use the data of crucial parts and show them the results in pictures in order to make it easier for doctors. By doing this, we're making ML better at finding breast cancer, which can lead to saving more lives and better health care.

Keywords: Bayesian network, radial basis function, ensemble learning, understandable, data making better, random forest, logistic regression, breast cancer

Procedia PDF Downloads 27

Authors: Mario Isaza-Ruget, Claudia C. Colmenares-Mejia, Nancy Yomayusa, Camilo A. González, Andres Cely, Jossie Murcia

Abstract:

Quantification of risks associated with complications development from chronic kidney disease (CKD) through accurate survival models can help with patient management. A retrospective cohort that included patients diagnosed with CKD from a primary care program and followed up between 2013 and 2018 was carried out. Time-dependent and static covariates associated with demographic, clinical, and laboratory factors were included. Deep Learning (DL) survival analyzes were developed for three CKD outcomes: CKD stage progression, >25% decrease in Estimated Glomerular Filtration Rate (eGFR), and Renal Replacement Therapy (RRT). Models were evaluated and compared with Random Survival Forest (RSF) based on concordance index (C-index) metric. 2.143 patients were included. Two models were developed for each outcome, Deep Neural Network (DNN) model reported C-index=0.9867 for CKD stage progression; C-index=0.9905 for reduction in eGFR; C-index=0.9867 for RRT. Regarding the RSF model, C-index=0.6650 was reached for CKD stage progression; decreased eGFR C-index=0.6759; RRT C-index=0.8926. DNN models applied in survival analysis context with considerations of longitudinal covariates at the start of follow-up can predict renal stage progression, a significant decrease in eGFR and RRT. The success of these survival models lies in the appropriate definition of survival times and the analysis of covariates, especially those that vary over time.

Keywords: artificial intelligence, chronic kidney disease, deep neural networks, survival analysis

Procedia PDF Downloads 116

Authors: Christos Chaschatzis, Chrysoula Karaiskou, Pantelis Angelidis, Sotirios K. Goudos, Igor Kotsiuba, Panagiotis Sarigiannidis

Abstract:

Over the past few decades, the rapid growth of the global population has led to the need to increase agricultural production and improve the quality of agricultural goods. There is a growing focus on environmentally eco-friendly solutions, sustainable production, and biologically minimally fertilized products in contemporary society. Precision agriculture has the potential to incorporate a wide range of innovative solutions with the development of machine learning algorithms. YOLOv5 and YOLOv8 are two of the most advanced object detection algorithms capable of accurately recognizing objects in real time. Detecting tree diseases is crucial for improving the food production rate and ensuring sustainability. This research aims to evaluate the efficacy of YOLOv5 and YOLOv8 in detecting the symptoms of Armillaria spp. in sweet cherry trees and determining their health status, with the goal of enhancing the robustness of precision agriculture. Additionally, this study will explore Computer Vision (CV) techniques with machine learning algorithms to improve the detection process’s efficiency.

Keywords: Armillaria spp., machine learning, precision agriculture, smart farming, sweet cherries trees, YOLOv5, YOLOv8

Procedia PDF Downloads 90

Authors: Sujata Kulkarni, Udhav Bhosle, Vijaykumar T.

Abstract:

Due to the closeness between seismic signals and non-seismic signals, it is vital to detect earthquakes using conventional methods. In order to distinguish between seismic events and non-seismic events depending on their amplitude, our study processes the data that come from seismic sensors. The authors suggest a robust noise suppression technique that makes use of a bandpass filter, an IIR Wiener filter, recursive short-term average/long-term average (STA/LTA), and Carl short-term average (STA)/long-term average for event identification (LTA). The trigger ratio used in the proposed study to differentiate between seismic and non-seismic activity is determined. The proposed work focuses on significant feature extraction for machine learning-based seismic event detection. This serves as motivation for compiling a dataset of all features for the identification and forecasting of seismic signals. We place a focus on feature vector dimension reduction techniques due to the temporal complexity. The proposed notable features were experimentally tested using a machine learning model, and the results on unseen data are optimal. Finally, a presentation using a hybrid dataset (captured by different sensors) demonstrates how this model may also be employed in a real-time setting while lowering false alarm rates. The planned study is based on the examination of seismic signals obtained from both individual sensors and sensor networks (SN). A wideband seismic signal from BSVK and CUKG station sensors, respectively located near Basavakalyan, Karnataka, and the Central University of Karnataka, makes up the experimental dataset.

Keywords: Carl STA/LTA, features extraction, real time, dataset, machine learning, seismic detection

Procedia PDF Downloads 95

Authors: Ahmet Faruk Akyuz, Hasan Sakir Bilge

Abstract:

Depth estimation using stereo images is a challenging problem in computer vision. Many different studies have been carried out to solve this problem. With advancing machine learning, tackling this problem is often done with neural network-based solutions. The images used in these studies are mostly in the visible spectrum. However, the need to use the Infrared (IR) spectrum for depth estimation has emerged because it gives better results than visible spectra in some conditions. At this point, we recommend using thermal-thermal (IR) image pairs for depth estimation. In this study, we used two well-known networks (PSMNet, FADNet) with minor modifications to demonstrate the viability of this idea.

Keywords: thermal stereo matching, deep neural networks, CNN, Depth estimation

Procedia PDF Downloads 249

Authors: Redouane Larbi Boufeniza, Jing-Jia Luo

Abstract:

This study assesses the suitability of deep learning (DL) for downscaling sea surface temperature (SST) over the Mediterranean Sea in the context of seasonal forecasting. We design a set of experiments that compare different DL configurations and deploy the best-performing architecture to downscale one-month lead forecasts of June–September (JJAS) SST from the Nanjing University of Information Science and Technology Climate Forecast System version 1.0 (NUIST-CFS1.0) for the period of 1982–2020. We have also introduced predictors over a larger area to include information about the main large-scale circulations that drive SST over the Mediterranean Sea region, which improves the downscaling results. Finally, we validate the raw model and downscaled forecasts in terms of both deterministic and probabilistic verification metrics, as well as their ability to reproduce the observed precipitation extreme and spell indicator indices. The results showed that the convolutional neural network (CNN)-based downscaling consistently improves the raw model forecasts, with lower bias and more accurate representations of the observed mean and extreme SST spatial patterns. Besides, the CNN-based downscaling yields a much more accurate forecast of extreme SST and spell indicators and reduces the significant relevant biases exhibited by the raw model predictions. Moreover, our results show that the CNN-based downscaling yields better skill scores than the raw model forecasts over most portions of the Mediterranean Sea. The results demonstrate the potential usefulness of CNN in downscaling seasonal SST predictions over the Mediterranean Sea, particularly in providing improved forecast products.

Keywords: Mediterranean Sea, sea surface temperature, seasonal forecasting, downscaling, deep learning

Procedia PDF Downloads 59

Authors: Ashi Gautam, Isha Shukla, Akhil Seghal

Abstract:

Biosensors are analytical devices that use a biological sensing element to detect and measure a specific chemical substance or biomolecule in a sample. These devices are widely used in various fields, including medical diagnostics, environmental monitoring, and food analysis, due to their high specificity, sensitivity, and selectivity. In this research paper, a machine learning model is proposed for predicting the suitability of skin care products based on biosensor readings. The proposed model takes in features extracted from biosensor readings, such as biomarker concentration, skin hydration level, inflammation presence, sensitivity, and free radicals, and outputs the most appropriate skin care product for an individual. This model is trained on a dataset of biosensor readings and corresponding skin care product information. The model's performance is evaluated using several metrics, including accuracy, precision, recall, and F1 score. The aim of this research is to develop a personalised skin care product recommendation system using biosensor data. By leveraging the power of machine learning, the proposed model can accurately predict the most suitable skin care product for an individual based on their biosensor readings. This is particularly useful in the skin care industry, where personalised recommendations can lead to better outcomes for consumers. The developed model is based on supervised learning, which means that it is trained on a labeled dataset of biosensor readings and corresponding skin care product information. The model uses these labeled data to learn patterns and relationships between the biosensor readings and skin care products. Once trained, the model can predict the most suitable skin care product for an individual based on their biosensor readings. The results of this study show that the proposed machine learning model can accurately predict the most appropriate skin care product for an individual based on their biosensor readings. The evaluation metrics used in this study demonstrate the effectiveness of the model in predicting skin care products. This model has significant potential for practical use in the skin care industry for personalised skin care product recommendations. The proposed machine learning model for predicting the suitability of skin care products based on biosensor readings is a promising development in the skin care industry. The model's ability to accurately predict the most appropriate skin care product for an individual based on their biosensor readings can lead to better outcomes for consumers. Further research can be done to improve the model's accuracy and effectiveness.

Keywords: biosensors, data model, machine learning, skin care

Procedia PDF Downloads 74

Authors: Dayo Samuel Banjo, Connice Trimmingham, Niloofar Yousefi, Nitin Agarwal

Abstract:

Technological advancement and its omnipresent connection have pushed humans past the boundaries and limitations of a computer screen, physical state, or geographical location. It has provided a depth of avenues that facilitate human-computer interaction that was once inconceivable such as audio and body language detection. Given the complex modularities of emotions, it becomes vital to study human-computer interaction, as it is the commencement of a thorough understanding of the emotional state of users and, in the context of social networks, the producers of multimodal information. This study first acknowledges the accuracy of classification found within multimodal emotion detection systems compared to unimodal solutions. Second, it explores the characterization of multimedia content produced based on their emotions and the coherence of emotion in different modalities by utilizing deep learning models to classify emotion across different modalities.

Keywords: affective computing, deep learning, emotion recognition, multimodal

Procedia PDF Downloads 129

Authors: Majid Habib Khan, Jinwei Zhao, Xinhong Hei, Liu Jiedong, Rana Shahzad Noor, Muhammad Imran

Abstract:

Deep learning is increasingly employed in image classification, yet the scarcity and high cost of labeled data for training remain a challenge. Limited samples often lead to overfitting due to biased sample distribution. This paper introduces a dynamic distribution calibration method for few-shot learning. Initially, base and new class samples undergo normalization to mitigate disparate feature magnitudes. A pre-trained model then extracts feature vectors from both classes. The method dynamically selects distribution characteristics from base classes (both adjacent and remote) in the embedding space, using a threshold value approach for new class samples. Given the propensity of similar classes to share feature distributions like mean and variance, this research assumes a Gaussian distribution for feature vectors. Subsequently, distributional features of new class samples are calibrated using a corrected hyperparameter, derived from the distribution features of both adjacent and distant base classes. This calibration augments the new class sample set. The technique demonstrates significant improvements, with up to 4% accuracy gains in few-shot classification challenges, as evidenced by tests on miniImagenet and CUB datasets.

Keywords: deep learning, computer vision, image classification, few-shot learning, threshold

Procedia PDF Downloads 42

Authors: Claus N. Holm, Oliver F. Grooss, Robert A. Alphinas

Abstract:

This research strives to predict the remaining product life cycle of a song on radio after it has been played for one or two months. The best results were achieved using a k-d tree to calculate the most similar songs to the test songs and use a Random Forest model to forecast radio plays. An 82.78% and 83.44% accuracy is achieved for the two time periods, respectively. This explorative research leads to over 4500 test metrics to find the best combination of models and pre-processing techniques. Other algorithms tested are KNN, MLP and CNN. The features only consist of daily radio plays and use no musical features.

Keywords: hit song science, product life cycle, machine learning, radio

Procedia PDF Downloads 135