Search results for: interpreting deep learning
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 8255

Search results for: interpreting deep learning

7955 AI-Driven Forecasting Models for Anticipating Oil Market Trends and Demand

Authors: Gaurav Kumar Sinha

Abstract:

The volatility of the oil market, influenced by geopolitical, economic, and environmental factors, presents significant challenges for stakeholders in predicting trends and demand. This article explores the application of artificial intelligence (AI) in developing robust forecasting models to anticipate changes in the oil market more accurately. We delve into various AI techniques, including machine learning, deep learning, and time series analysis, that have been adapted to analyze historical data and current market conditions to forecast future trends. The study evaluates the effectiveness of these models in capturing complex patterns and dependencies in market data, which traditional forecasting methods often miss. Additionally, the paper discusses the integration of external variables such as political events, economic policies, and technological advancements that influence oil prices and demand. By leveraging AI, stakeholders can achieve a more nuanced understanding of market dynamics, enabling better strategic planning and risk management. The article concludes with a discussion on the potential of AI-driven models in enhancing the predictive accuracy of oil market forecasts and their implications for global economic planning and strategic resource allocation.

Keywords: AI forecasting, oil market trends, machine learning, deep learning, time series analysis, predictive analytics, economic factors, geopolitical influence, technological advancements, strategic planning

Procedia PDF Downloads 5
7954 Optimizing Perennial Plants Image Classification by Fine-Tuning Deep Neural Networks

Authors: Khairani Binti Supyan, Fatimah Khalid, Mas Rina Mustaffa, Azreen Bin Azman, Amirul Azuani Romle

Abstract:

Perennial plant classification plays a significant role in various agricultural and environmental applications, assisting in plant identification, disease detection, and biodiversity monitoring. Nevertheless, attaining high accuracy in perennial plant image classification remains challenging due to the complex variations in plant appearance, the diverse range of environmental conditions under which images are captured, and the inherent variability in image quality stemming from various factors such as lighting conditions, camera settings, and focus. This paper proposes an adaptation approach to optimize perennial plant image classification by fine-tuning the pre-trained DNNs model. This paper explores the efficacy of fine-tuning prevalent architectures, namely VGG16, ResNet50, and InceptionV3, leveraging transfer learning to tailor the models to the specific characteristics of perennial plant datasets. A subset of the MYLPHerbs dataset consisted of 6 perennial plant species of 13481 images under various environmental conditions that were used in the experiments. Different strategies for fine-tuning, including adjusting learning rates, training set sizes, data augmentation, and architectural modifications, were investigated. The experimental outcomes underscore the effectiveness of fine-tuning deep neural networks for perennial plant image classification, with ResNet50 showcasing the highest accuracy of 99.78%. Despite ResNet50's superior performance, both VGG16 and InceptionV3 achieved commendable accuracy of 99.67% and 99.37%, respectively. The overall outcomes reaffirm the robustness of the fine-tuning approach across different deep neural network architectures, offering insights into strategies for optimizing model performance in the domain of perennial plant image classification.

Keywords: perennial plants, image classification, deep neural networks, fine-tuning, transfer learning, VGG16, ResNet50, InceptionV3

Procedia PDF Downloads 34
7953 Enhanced Image Representation for Deep Belief Network Classification of Hyperspectral Images

Authors: Khitem Amiri, Mohamed Farah

Abstract:

Image classification is a challenging task and is gaining lots of interest since it helps us to understand the content of images. Recently Deep Learning (DL) based methods gave very interesting results on several benchmarks. For Hyperspectral images (HSI), the application of DL techniques is still challenging due to the scarcity of labeled data and to the curse of dimensionality. Among other approaches, Deep Belief Network (DBN) based approaches gave a fair classification accuracy. In this paper, we address the problem of the curse of dimensionality by reducing the number of bands and replacing the HSI channels by the channels representing radiometric indices. Therefore, instead of using all the HSI bands, we compute the radiometric indices such as NDVI (Normalized Difference Vegetation Index), NDWI (Normalized Difference Water Index), etc, and we use the combination of these indices as input for the Deep Belief Network (DBN) based classification model. Thus, we keep almost all the pertinent spectral information while reducing considerably the size of the image. In order to test our image representation, we applied our method on several HSI datasets including the Indian pines dataset, Jasper Ridge data and it gave comparable results to the state of the art methods while reducing considerably the time of training and testing.

Keywords: hyperspectral images, deep belief network, radiometric indices, image classification

Procedia PDF Downloads 250
7952 IoT and Deep Learning approach for Growth Stage Segregation and Harvest Time Prediction of Aquaponic and Vermiponic Swiss Chards

Authors: Praveen Chandramenon, Andrew Gascoyne, Fideline Tchuenbou-Magaia

Abstract:

Aquaponics offers a simple conclusive solution to the food and environmental crisis of the world. This approach combines the idea of Aquaculture (growing fish) to Hydroponics (growing vegetables and plants in a soilless method). Smart Aquaponics explores the use of smart technology including artificial intelligence and IoT, to assist farmers with better decision making and online monitoring and control of the system. Identification of different growth stages of Swiss Chard plants and predicting its harvest time is found to be important in Aquaponic yield management. This paper brings out the comparative analysis of a standard Aquaponics with a Vermiponics (Aquaponics with worms), which was grown in the controlled environment, by implementing IoT and deep learning-based growth stage segregation and harvest time prediction of Swiss Chards before and after applying an optimal freshwater replenishment. Data collection, Growth stage classification and Harvest Time prediction has been performed with and without water replenishment. The paper discusses the experimental design, IoT and sensor communication with architecture, data collection process, image segmentation, various regression and classification models and error estimation used in the project. The paper concludes with the results comparison, including best models that performs growth stage segregation and harvest time prediction of the Aquaponic and Vermiponic testbed with and without freshwater replenishment.

Keywords: aquaponics, deep learning, internet of things, vermiponics

Procedia PDF Downloads 49
7951 Analysis of Biomarkers Intractable Epileptogenic Brain Networks with Independent Component Analysis and Deep Learning Algorithms: A Comprehensive Framework for Scalable Seizure Prediction with Unimodal Neuroimaging Data in Pediatric Patients

Authors: Bliss Singhal

Abstract:

Epilepsy is a prevalent neurological disorder affecting approximately 50 million individuals worldwide and 1.2 million Americans. There exist millions of pediatric patients with intractable epilepsy, a condition in which seizures fail to come under control. The occurrence of seizures can result in physical injury, disorientation, unconsciousness, and additional symptoms that could impede children's ability to participate in everyday tasks. Predicting seizures can help parents and healthcare providers take precautions, prevent risky situations, and mentally prepare children to minimize anxiety and nervousness associated with the uncertainty of a seizure. This research proposes a comprehensive framework to predict seizures in pediatric patients by evaluating machine learning algorithms on unimodal neuroimaging data consisting of electroencephalogram signals. The bandpass filtering and independent component analysis proved to be effective in reducing the noise and artifacts from the dataset. Various machine learning algorithms’ performance is evaluated on important metrics such as accuracy, precision, specificity, sensitivity, F1 score and MCC. The results show that the deep learning algorithms are more successful in predicting seizures than logistic Regression, and k nearest neighbors. The recurrent neural network (RNN) gave the highest precision and F1 Score, long short-term memory (LSTM) outperformed RNN in accuracy and convolutional neural network (CNN) resulted in the highest Specificity. This research has significant implications for healthcare providers in proactively managing seizure occurrence in pediatric patients, potentially transforming clinical practices, and improving pediatric care.

Keywords: intractable epilepsy, seizure, deep learning, prediction, electroencephalogram channels

Procedia PDF Downloads 59
7950 Near-Miss Deep Learning Approach for Neuro-Fuzzy Risk Assessment in Pipelines

Authors: Alexander Guzman Urbina, Atsushi Aoyama

Abstract:

The sustainability of traditional technologies employed in energy and chemical infrastructure brings a big challenge for our society. Making decisions related with safety of industrial infrastructure, the values of accidental risk are becoming relevant points for discussion. However, the challenge is the reliability of the models employed to get the risk data. Such models usually involve large number of variables and with large amounts of uncertainty. The most efficient techniques to overcome those problems are built using Artificial Intelligence (AI), and more specifically using hybrid systems such as Neuro-Fuzzy algorithms. Therefore, this paper aims to introduce a hybrid algorithm for risk assessment trained using near-miss accident data. As mentioned above the sustainability of traditional technologies related with energy and chemical infrastructure constitutes one of the major challenges that today’s societies and firms are facing. Besides that, the adaptation of those technologies to the effects of the climate change in sensible environments represents a critical concern for safety and risk management. Regarding this issue argue that social consequences of catastrophic risks are increasing rapidly, due mainly to the concentration of people and energy infrastructure in hazard-prone areas, aggravated by the lack of knowledge about the risks. Additional to the social consequences described above, and considering the industrial sector as critical infrastructure due to its large impact to the economy in case of a failure the relevance of industrial safety has become a critical issue for the current society. Then, regarding the safety concern, pipeline operators and regulators have been performing risk assessments in attempts to evaluate accurately probabilities of failure of the infrastructure, and consequences associated with those failures. However, estimating accidental risks in critical infrastructure involves a substantial effort and costs due to number of variables involved, complexity and lack of information. Therefore, this paper aims to introduce a well trained algorithm for risk assessment using deep learning, which could be capable to deal efficiently with the complexity and uncertainty. The advantage point of the deep learning using near-miss accidents data is that it could be employed in risk assessment as an efficient engineering tool to treat the uncertainty of the risk values in complex environments. The basic idea of using a Near-Miss Deep Learning Approach for Neuro-Fuzzy Risk Assessment in Pipelines is focused in the objective of improve the validity of the risk values learning from near-miss accidents and imitating the human expertise scoring risks and setting tolerance levels. In summary, the method of Deep Learning for Neuro-Fuzzy Risk Assessment involves a regression analysis called group method of data handling (GMDH), which consists in the determination of the optimal configuration of the risk assessment model and its parameters employing polynomial theory.

Keywords: deep learning, risk assessment, neuro fuzzy, pipelines

Procedia PDF Downloads 271
7949 Detecting Memory-Related Gene Modules in sc/snRNA-seq Data by Deep-Learning

Authors: Yong Chen

Abstract:

To understand the detailed molecular mechanisms of memory formation in engram cells is one of the most fundamental questions in neuroscience. Recent single-cell RNA-seq (scRNA-seq) and single-nucleus RNA-seq (snRNA-seq) techniques have allowed us to explore the sparsely activated engram ensembles, enabling access to the molecular mechanisms that underlie experience-dependent memory formation and consolidation. However, the absence of specific and powerful computational methods to detect memory-related genes (modules) and their regulatory relationships in the sc/snRNA-seq datasets has strictly limited the analysis of underlying mechanisms and memory coding principles in mammalian brains. Here, we present a deep-learning method named SCENTBOX, to detect memory-related gene modules and causal regulatory relationships among themfromsc/snRNA-seq datasets. SCENTBOX first constructs codifferential expression gene network (CEGN) from case versus control sc/snRNA-seq datasets. It then detects the highly correlated modules of differential expression genes (DEGs) in CEGN. The deep network embedding and attention-based convolutional neural network strategies are employed to precisely detect regulatory relationships among DEG genes in a module. We applied them on scRNA-seq datasets of TRAP; Ai14 mouse neurons with fear memory and detected not only known memory-related genes, but also the modules and potential causal regulations. Our results provided novel regulations within an interesting module, including Arc, Bdnf, Creb, Dusp1, Rgs4, and Btg2. Overall, our methods provide a general computational tool for processing sc/snRNA-seq data from case versus control studie and a systematic investigation of fear-memory-related gene modules.

Keywords: sc/snRNA-seq, memory formation, deep learning, gene module, causal inference

Procedia PDF Downloads 102
7948 Leveraging Learning Analytics to Inform Learning Design in Higher Education

Authors: Mingming Jiang

Abstract:

This literature review aims to offer an overview of existing research on learning analytics and learning design, the alignment between the two, and how learning analytics has been leveraged to inform learning design in higher education. Current research suggests a need to create more alignment and integration between learning analytics and learning design in order to not only ground learning analytics on learning sciences but also enable data-driven decisions in learning design to improve learning outcomes. In addition, multiple conceptual frameworks have been proposed to enhance the synergy and alignment between learning analytics and learning design. Future research should explore this synergy further in the unique context of higher education, identifying learning analytics metrics in higher education that can offer insight into learning processes, evaluating the effect of learning analytics outcomes on learning design decision-making in higher education, and designing learning environments in higher education that make the capturing and deployment of learning analytics outcomes more efficient.

Keywords: learning analytics, learning design, big data in higher education, online learning environments

Procedia PDF Downloads 137
7947 Numerical Modeling of Various Support Systems to Stabilize Deep Excavations

Authors: M. Abdallah

Abstract:

Urban development requires deep excavations near buildings and other structures. Deep excavation has become more a necessity for better utilization of space as the population of the world has dramatically increased. In Lebanon, some urban areas are very crowded and lack spaces for new buildings and underground projects, which makes the usage of underground space indispensable. In this paper, a numerical modeling is performed using the finite element method to study the deep excavation-diaphragm wall soil-structure interaction in the case of nonlinear soil behavior. The study is focused on a comparison of the results obtained using different support systems. Furthermore, a parametric study is performed according to the remoteness of the structure.

Keywords: deep excavation, ground anchors, interaction soil-structure, struts

Procedia PDF Downloads 387
7946 Incorporating Lexical-Semantic Knowledge into Convolutional Neural Network Framework for Pediatric Disease Diagnosis

Authors: Xiaocong Liu, Huazhen Wang, Ting He, Xiaozheng Li, Weihan Zhang, Jian Chen

Abstract:

The utilization of electronic medical record (EMR) data to establish the disease diagnosis model has become an important research content of biomedical informatics. Deep learning can automatically extract features from the massive data, which brings about breakthroughs in the study of EMR data. The challenge is that deep learning lacks semantic knowledge, which leads to impracticability in medical science. This research proposes a method of incorporating lexical-semantic knowledge from abundant entities into a convolutional neural network (CNN) framework for pediatric disease diagnosis. Firstly, medical terms are vectorized into Lexical Semantic Vectors (LSV), which are concatenated with the embedded word vectors of word2vec to enrich the feature representation. Secondly, the semantic distribution of medical terms serves as Semantic Decision Guide (SDG) for the optimization of deep learning models. The study evaluate the performance of LSV-SDG-CNN model on four kinds of Chinese EMR datasets. Additionally, CNN, LSV-CNN, and SDG-CNN are designed as baseline models for comparison. The experimental results show that LSV-SDG-CNN model outperforms baseline models on four kinds of Chinese EMR datasets. The best configuration of the model yielded an F1 score of 86.20%. The results clearly demonstrate that CNN has been effectively guided and optimized by lexical-semantic knowledge, and LSV-SDG-CNN model improves the disease classification accuracy with a clear margin.

Keywords: convolutional neural network, electronic medical record, feature representation, lexical semantics, semantic decision

Procedia PDF Downloads 112
7945 A U-Net Based Architecture for Fast and Accurate Diagram Extraction

Authors: Revoti Prasad Bora, Saurabh Yadav, Nikita Katyal

Abstract:

In the context of educational data mining, the use case of extracting information from images containing both text and diagrams is of high importance. Hence, document analysis requires the extraction of diagrams from such images and processes the text and diagrams separately. To the author’s best knowledge, none among plenty of approaches for extracting tables, figures, etc., suffice the need for real-time processing with high accuracy as needed in multiple applications. In the education domain, diagrams can be of varied characteristics viz. line-based i.e. geometric diagrams, chemical bonds, mathematical formulas, etc. There are two broad categories of approaches that try to solve similar problems viz. traditional computer vision based approaches and deep learning approaches. The traditional computer vision based approaches mainly leverage connected components and distance transform based processing and hence perform well in very limited scenarios. The existing deep learning approaches either leverage YOLO or faster-RCNN architectures. These approaches suffer from a performance-accuracy tradeoff. This paper proposes a U-Net based architecture that formulates the diagram extraction as a segmentation problem. The proposed method provides similar accuracy with a much faster extraction time as compared to the mentioned state-of-the-art approaches. Further, the segmentation mask in this approach allows the extraction of diagrams of irregular shapes.

Keywords: computer vision, deep-learning, educational data mining, faster-RCNN, figure extraction, image segmentation, real-time document analysis, text extraction, U-Net, YOLO

Procedia PDF Downloads 108
7944 Nonparametric Sieve Estimation with Dependent Data: Application to Deep Neural Networks

Authors: Chad Brown

Abstract:

This paper establishes general conditions for the convergence rates of nonparametric sieve estimators with dependent data. We present two key results: one for nonstationary data and another for stationary mixing data. Previous theoretical results often lack practical applicability to deep neural networks (DNNs). Using these conditions, we derive convergence rates for DNN sieve estimators in nonparametric regression settings with both nonstationary and stationary mixing data. The DNN architectures considered adhere to current industry standards, featuring fully connected feedforward networks with rectified linear unit activation functions, unbounded weights, and a width and depth that grows with sample size.

Keywords: sieve extremum estimates, nonparametric estimation, deep learning, neural networks, rectified linear unit, nonstationary processes

Procedia PDF Downloads 11
7943 Predicting Shortage of Hospital Beds during COVID-19 Pandemic in United States

Authors: Saba Ebrahimi, Saeed Ahmadian, Hedie Ashrafi

Abstract:

World-wide spread of coronavirus grows the concern about planning for the excess demand of hospital services in response to COVID-19 pandemic. The surge in the hospital services demand beyond the current capacity leads to shortage of ICU beds and ventilators in some parts of US. In this study, we forecast the required number of hospital beds and possible shortage of beds in US during COVID-19 pandemic to be used in the planning and hospitalization of new cases. In this paper, we used a data on COVID-19 deaths and patients’ hospitalization besides the data on hospital capacities and utilization in US from publicly available sources and national government websites. we used a novel ensemble modelling of deep learning networks, based on stacking different linear and non-linear layers to predict the shortage in hospital beds. The results showed that our proposed approach can predict the excess hospital beds demand very well and this can be helpful in developing strategies and plans to mitigate this gap.

Keywords: COVID-19, deep learning, ensembled models, hospital capacity planning

Procedia PDF Downloads 135
7942 Decoding Kinematic Characteristics of Finger Movement from Electrocorticography Using Classical Methods and Deep Convolutional Neural Networks

Authors: Ksenia Volkova, Artur Petrosyan, Ignatii Dubyshkin, Alexei Ossadtchi

Abstract:

Brain-computer interfaces are a growing research field producing many implementations that find use in different fields and are used for research and practical purposes. Despite the popularity of the implementations using non-invasive neuroimaging methods, radical improvement of the state channel bandwidth and, thus, decoding accuracy is only possible by using invasive techniques. Electrocorticography (ECoG) is a minimally invasive neuroimaging method that provides highly informative brain activity signals, effective analysis of which requires the use of machine learning methods that are able to learn representations of complex patterns. Deep learning is a family of machine learning algorithms that allow learning representations of data with multiple levels of abstraction. This study explores the potential of deep learning approaches for ECoG processing, decoding movement intentions and the perception of proprioceptive information. To obtain synchronous recording of kinematic movement characteristics and corresponding electrical brain activity, a series of experiments were carried out, during which subjects performed finger movements at their own pace. Finger movements were recorded with a three-axis accelerometer, while ECoG was synchronously registered from the electrode strips that were implanted over the contralateral sensorimotor cortex. Then, multichannel ECoG signals were used to track finger movement trajectory characterized by accelerometer signal. This process was carried out both causally and non-causally, using different position of the ECoG data segment with respect to the accelerometer data stream. The recorded data was split into training and testing sets, containing continuous non-overlapping fragments of the multichannel ECoG. A deep convolutional neural network was implemented and trained, using 1-second segments of ECoG data from the training dataset as input. To assess the decoding accuracy, correlation coefficient r between the output of the model and the accelerometer readings was computed. After optimization of hyperparameters and training, the deep learning model allowed reasonably accurate causal decoding of finger movement with correlation coefficient r = 0.8. In contrast, the classical Wiener-filter like approach was able to achieve only 0.56 in the causal decoding mode. In the noncausal case, the traditional approach reached the accuracy of r = 0.69, which may be due to the presence of additional proprioceptive information. This result demonstrates that the deep neural network was able to effectively find a representation of the complex top-down information related to the actual movement rather than proprioception. The sensitivity analysis shows physiologically plausible pictures of the extent to which individual features (channel, wavelet subband) are utilized during the decoding procedure. In conclusion, the results of this study have demonstrated that a combination of a minimally invasive neuroimaging technique such as ECoG and advanced machine learning approaches allows decoding motion with high accuracy. Such setup provides means for control of devices with a large number of degrees of freedom as well as exploratory studies of the complex neural processes underlying movement execution.

Keywords: brain-computer interface, deep learning, ECoG, movement decoding, sensorimotor cortex

Procedia PDF Downloads 147
7941 Graph Clustering Unveiled: ClusterSyn - A Machine Learning Framework for Predicting Anti-Cancer Drug Synergy Scores

Authors: Babak Bahri, Fatemeh Yassaee Meybodi, Changiz Eslahchi

Abstract:

In the pursuit of effective cancer therapies, the exploration of combinatorial drug regimens is crucial to leverage synergistic interactions between drugs, thereby improving treatment efficacy and overcoming drug resistance. However, identifying synergistic drug pairs poses challenges due to the vast combinatorial space and limitations of experimental approaches. This study introduces ClusterSyn, a machine learning (ML)-powered framework for classifying anti-cancer drug synergy scores. ClusterSyn employs a two-step approach involving drug clustering and synergy score prediction using a fully connected deep neural network. For each cell line in the training dataset, a drug graph is constructed, with nodes representing drugs and edge weights denoting synergy scores between drug pairs. Drugs are clustered using the Markov clustering (MCL) algorithm, and vectors representing the similarity of drug pairs to each cluster are input into the deep neural network for synergy score prediction (synergy or antagonism). Clustering results demonstrate effective grouping of drugs based on synergy scores, aligning similar synergy profiles. Subsequently, neural network predictions and synergy scores of the two drugs on others within their clusters are used to predict the synergy score of the considered drug pair. This approach facilitates comparative analysis with clustering and regression-based methods, revealing the superior performance of ClusterSyn over state-of-the-art methods like DeepSynergy and DeepDDS on diverse datasets such as Oniel and Almanac. The results highlight the remarkable potential of ClusterSyn as a versatile tool for predicting anti-cancer drug synergy scores.

Keywords: drug synergy, clustering, prediction, machine learning., deep learning

Procedia PDF Downloads 50
7940 Assisting Dating of Greek Papyri Images with Deep Learning

Authors: Asimina Paparrigopoulou, John Pavlopoulos, Maria Konstantinidou

Abstract:

Dating papyri accurately is crucial not only to editing their texts but also for our understanding of palaeography and the history of writing, ancient scholarship, material culture, networks in antiquity, etc. Most ancient manuscripts offer little evidence regarding the time of their production, forcing papyrologists to date them on palaeographical grounds, a method often criticized for its subjectivity. By experimenting with data obtained from the Collaborative Database of Dateable Greek Bookhands and the PapPal online collections of objectively dated Greek papyri, this study shows that deep learning dating models, pre-trained on generic images, can achieve accurate chronological estimates for a test subset (67,97% accuracy for book hands and 55,25% for documents). To compare the estimates of these models with those of humans, experts were asked to complete a questionnaire with samples of literary and documentary hands that had to be sorted chronologically by century. The same samples were dated by the models in question. The results are presented and analysed.

Keywords: image classification, papyri images, dating

Procedia PDF Downloads 60
7939 FMR1 Gene Carrier Screening for Premature Ovarian Insufficiency in Females: An Indian Scenario

Authors: Sarita Agarwal, Deepika Delsa Dean

Abstract:

Like the task of transferring photo images to artistic images, image-to-image translation aims to translate the data to the imitated data which belongs to the target domain. Neural Style Transfer and CycleGAN are two well-known deep learning architectures used for photo image-to-art image transfer. However, studies involving these two models concentrate on one-to-one domain translation, not one-to-multi domains translation. Our study tries to investigate deep learning architectures, which can be controlled to yield multiple artistic style translation only by adding a conditional vector. We have expanded CycleGAN and constructed Conditional CycleGAN for 5 kinds of categories translation. Our study found that the architecture inserting conditional vector into the middle layer of the Generator could output multiple artistic images.

Keywords: genetic counseling, FMR1 gene, fragile x-associated primary ovarian insufficiency, premutation

Procedia PDF Downloads 104
7938 Optimizing Privacy, Accuracy and Calibration in Deep Learning Models

Authors: Rizwan Rizwan

Abstract:

Differentially private ({DP}) training preserves the data privacy but often leads to slower convergence and lower accuracy, along with notable mis-calibration compared to non-private training. Analyzing {DP} training through a continuous-time approach with the neural tangent kernel ({NTK}). The {NTK} helps characterize per sample {(PS)} gradient clipping and the incorporation of noise during {DP} training across arbitrary network architectures as well as loss functions. Our analysis reveals that noise addition impacts privacy risk exclusively, leaving convergence and calibration unaffected. In contrast, {PS} gradient clipping (flat styles, layerwise styles) influences convergence as well as calibration but not privacy risk. Models with a small clipping norm generally achieve optimal accuracy but exhibit poor calibration, making them less reliable. Conversely, {DP} models that are trained with a large clipping norm maintain the similar accuracy and same privacy guarantee, yet they demonstrate notably improved calibration.

Keywords: deep learning, convergence, differential privacy, calibration

Procedia PDF Downloads 18
7937 Exploratory Analysis of A Review of Nonexistence Polarity in Native Speech

Authors: Deawan Rakin Ahamed Remal, Sinthia Chowdhury, Sharun Akter Khushbu, Sheak Rashed Haider Noori

Abstract:

Native Speech to text synthesis has its own leverage for the purpose of mankind. The extensive nature of art to speaking different accents is common but the purpose of communication between two different accent types of people is quite difficult. This problem will be motivated by the extraction of the wrong perception of language meaning. Thus, many existing automatic speech recognition has been placed to detect text. Overall study of this paper mentions a review of NSTTR (Native Speech Text to Text Recognition) synthesis compared with Text to Text recognition. Review has exposed many text to text recognition systems that are at a very early stage to comply with the system by native speech recognition. Many discussions started about the progression of chatbots, linguistic theory another is rule based approach. In the Recent years Deep learning is an overwhelming chapter for text to text learning to detect language nature. To the best of our knowledge, In the sub continent a huge number of people speak in Bangla language but they have different accents in different regions therefore study has been elaborate contradictory discussion achievement of existing works and findings of future needs in Bangla language acoustic accent.

Keywords: TTR, NSTTR, text to text recognition, deep learning, natural language processing

Procedia PDF Downloads 107
7936 Electrocardiogram-Based Heartbeat Classification Using Convolutional Neural Networks

Authors: Jacqueline Rose T. Alipo-on, Francesca Isabelle F. Escobar, Myles Joshua T. Tan, Hezerul Abdul Karim, Nouar Al Dahoul

Abstract:

Electrocardiogram (ECG) signal analysis and processing are crucial in the diagnosis of cardiovascular diseases, which are considered one of the leading causes of mortality worldwide. However, the traditional rule-based analysis of large volumes of ECG data is time-consuming, labor-intensive, and prone to human errors. With the advancement of the programming paradigm, algorithms such as machine learning have been increasingly used to perform an analysis of ECG signals. In this paper, various deep learning algorithms were adapted to classify five classes of heartbeat types. The dataset used in this work is the synthetic MIT-BIH Arrhythmia dataset produced from generative adversarial networks (GANs). Various deep learning models such as ResNet-50 convolutional neural network (CNN), 1-D CNN, and long short-term memory (LSTM) were evaluated and compared. ResNet-50 was found to outperform other models in terms of recall and F1 score using a five-fold average score of 98.88% and 98.87%, respectively. 1-D CNN, on the other hand, was found to have the highest average precision of 98.93%.

Keywords: heartbeat classification, convolutional neural network, electrocardiogram signals, generative adversarial networks, long short-term memory, ResNet-50

Procedia PDF Downloads 100
7935 Parkinson’s Disease Hand-Eye Coordination and Dexterity Evaluation System

Authors: Wann-Yun Shieh, Chin-Man Wang, Ya-Cheng Shieh

Abstract:

This study aims to develop an objective scoring system to evaluate hand-eye coordination and hand dexterity for Parkinson’s disease. This system contains three boards, and each of them is implemented with the sensors to sense a user’s finger operations. The operations include the peg test, the block test, and the blind block test. A user has to use the vision, hearing, and tactile abilities to finish these operations, and the board will record the results automatically. These results can help the physicians to evaluate a user’s reaction, coordination, dexterity function. The results will be collected to a cloud database for further analysis and statistics. A researcher can use this system to obtain systematic, graphic reports for an individual or a group of users. Particularly, a deep learning model is developed to learn the features of the data from different users. This model will help the physicians to assess the Parkinson’s disease symptoms by a more intellective algorithm.

Keywords: deep learning, hand-eye coordination, reaction, hand dexterity

Procedia PDF Downloads 45
7934 Feature Engineering Based Detection of Buffer Overflow Vulnerability in Source Code Using Deep Neural Networks

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 63
7933 Comparative Study of Deep Reinforcement Learning Algorithm Against Evolutionary Algorithms for Finding the Optimal Values in a Simulated Environment Space

Authors: Akshay Paranjape, Nils Plettenberg, Robert Schmitt

Abstract:

Traditional optimization methods like evolutionary algorithms are widely used in production processes to find an optimal or near-optimal solution of control parameters based on the simulated environment space of a process. These algorithms are computationally intensive and therefore do not provide the opportunity for real-time optimization. This paper utilizes the Deep Reinforcement Learning (DRL) framework to find an optimal or near-optimal solution for control parameters. A model based on maximum a posteriori policy optimization (Hybrid-MPO) that can handle both numerical and categorical parameters is used as a benchmark for comparison. A comparative study shows that DRL can find optimal solutions of similar quality as compared to evolutionary algorithms while requiring significantly less time making them preferable for real-time optimization. The results are confirmed in a large-scale validation study on datasets from production and other fields. A trained XGBoost model is used as a surrogate for process simulation. Finally, multiple ways to improve the model are discussed.

Keywords: reinforcement learning, evolutionary algorithms, production process optimization, real-time optimization, hybrid-MPO

Procedia PDF Downloads 89
7932 An Improved Convolution Deep Learning Model for Predicting Trip Mode Scheduling

Authors: Amin Nezarat, Naeime Seifadini

Abstract:

Trip mode selection is a behavioral characteristic of passengers with immense importance for travel demand analysis, transportation planning, and traffic management. Identification of trip mode distribution will allow transportation authorities to adopt appropriate strategies to reduce travel time, traffic and air pollution. The majority of existing trip mode inference models operate based on human selected features and traditional machine learning algorithms. However, human selected features are sensitive to changes in traffic and environmental conditions and susceptible to personal biases, which can make them inefficient. One way to overcome these problems is to use neural networks capable of extracting high-level features from raw input. In this study, the convolutional neural network (CNN) architecture is used to predict the trip mode distribution based on raw GPS trajectory data. The key innovation of this paper is the design of the layout of the input layer of CNN as well as normalization operation, in a way that is not only compatible with the CNN architecture but can also represent the fundamental features of motion including speed, acceleration, jerk, and Bearing rate. The highest prediction accuracy achieved with the proposed configuration for the convolutional neural network with batch normalization is 85.26%.

Keywords: predicting, deep learning, neural network, urban trip

Procedia PDF Downloads 112
7931 Shear Behaviour of RC Deep Beams with Openings Strengthened with Carbon Fiber Reinforced Polymer

Authors: Mannal Tariq

Abstract:

Construction industry is making progress at a high pace. The trend of the world is getting more biased towards the high rise buildings. Deep beams are one of the most common elements in modern construction having small span to depth ratio. Deep beams are mostly used as transfer girders. This experimental study consists of 16 reinforced concrete (RC) deep beams. These beams were divided into two groups; A and B. Groups A and B consist of eight beams each, having 381 mm (15 in) and 457 mm (18 in) depth respectively. Each group was further subdivided into four sub groups each consisting of two identical beams. Each subgroup was comprised of solid/control beam (without opening), opening above neutral axis (NA), at NA and below NA. Except for control beams, all beams with openings were strengthened with carbon fibre reinforced polymer (CFRP) vertical strips. These eight groups differ from each other based on depth and location of openings. For testing sake, all beams have been loaded with two symmetrical point loads. All beams have been designed based on strut and tie model concept. The outcome of experimental investigation elaborates the difference in the shear behaviour of deep beams based on depth and location of circular openings variation. 457 mm (18 in) deep beam with openings above NA show the highest strength and 381 mm (15 in) deep beam with openings below NA show the least strength. CFRP sheets played a vital role in increasing the shear capacity of beams.

Keywords: CFRP, deep beams, openings in deep beams, strut and tie modal, shear behaviour

Procedia PDF Downloads 278
7930 An Electrocardiography Deep Learning Model to Detect Atrial Fibrillation on Clinical Application

Authors: Jui-Chien Hsieh

Abstract:

Background:12-lead electrocardiography(ECG) is one of frequently-used tools to detect atrial fibrillation (AF), which might degenerate into life-threaten stroke, in clinical Practice. Based on this study, the AF detection by the clinically-used 12-lead ECG device has only 0.73~0.77 positive predictive value (ppv). Objective: It is on great demand to develop a new algorithm to improve the precision of AF detection using 12-lead ECG. Due to the progress on artificial intelligence (AI), we develop an ECG deep model that has the ability to recognize AF patterns and reduce false-positive errors. Methods: In this study, (1) 570-sample 12-lead ECG reports whose computer interpretation by the ECG device was AF were collected as the training dataset. The ECG reports were interpreted by 2 senior cardiologists, and confirmed that the precision of AF detection by the ECG device is 0.73.; (2) 88 12-lead ECG reports whose computer interpretation generated by the ECG device was AF were used as test dataset. Cardiologist confirmed that 68 cases of 88 reports were AF, and others were not AF. The precision of AF detection by ECG device is about 0.77; (3) A parallel 4-layer 1 dimensional convolutional neural network (CNN) was developed to identify AF based on limb-lead ECGs and chest-lead ECGs. Results: The results indicated that this model has better performance on AF detection than traditional computer interpretation of the ECG device in 88 test samples with 0.94 ppv, 0.98 sensitivity, 0.80 specificity. Conclusions: As compared to the clinical ECG device, this AI ECG model promotes the precision of AF detection from 0.77 to 0.94, and can generate impacts on clinical applications.

Keywords: 12-lead ECG, atrial fibrillation, deep learning, convolutional neural network

Procedia PDF Downloads 97
7929 OSEME: A Smart Learning Environment for Music Education

Authors: Konstantinos Sofianos, Michael Stefanidakis

Abstract:

Nowadays, advances in information and communication technologies offer a range of opportunities for new approaches, methods, and tools in the field of education and training. Teacher-centered learning has changed to student-centered learning. E-learning has now matured and enables the design and construction of intelligent learning systems. A smart learning system fully adapts to a student's needs and provides them with an education based on their preferences, learning styles, and learning backgrounds. It is a wise friend and available at any time, in any place, and with any digital device. In this paper, we propose an intelligent learning system, which includes an ontology with all elements of the learning process (learning objects, learning activities) and a massive open online course (MOOC) system. This intelligent learning system can be used in music education.

Keywords: intelligent learning systems, e-learning, music education, ontology, semantic web

Procedia PDF Downloads 292
7928 Effect of Deep Mixing Columns and Geogrid on Embankment Settlement on the Soft Soil

Authors: Seyed Abolhasan Naeini, Saeideh Mohammadi

Abstract:

Embankment settlement on soft clays has always been problematic due to the high compaction and low shear strength of the soil. Deep soil mixing and geosynthetics are two soil improvement methods in such fields. Here, a numerical study is conducted on the embankment performance on the soft ground improved by deep soil mixing columns and geosynthetics based on the data of a real project. For this purpose, the finite element method is used in the Plaxis 2D software. The Soft Soil Creep model considers the creep phenomenon in the soft clay layer while the Mohr-Columb model simulates other soil layers. Results are verified using the data of an experimental embankment built on deep mixing columns. The effect of depth and diameter of deep mixing columns and the stiffness of geogrid on the vertical and horizontal movements of embankment on clay subsoil will be investigated in the following.

Keywords: PLAXIS 2D, embankment settlement, horizontal movement, deep soil mixing column, geogrid

Procedia PDF Downloads 151
7927 Identification of Biological Pathways Causative for Breast Cancer Using Unsupervised Machine Learning

Authors: Karthik Mittal

Abstract:

This study performs an unsupervised machine learning analysis to find clusters of related SNPs which highlight biological pathways that are important for the biological mechanisms of breast cancer. Studying genetic variations in isolation is illogical because these genetic variations are known to modulate protein production and function; the downstream effects of these modifications on biological outcomes are highly interconnected. After extracting the SNPs and their effect on different types of breast cancer using the MRBase library, two unsupervised machine learning clustering algorithms were implemented on the genetic variants: a k-means clustering algorithm and a hierarchical clustering algorithm; furthermore, principal component analysis was executed to visually represent the data. These algorithms specifically used the SNP’s beta value on the three different types of breast cancer tested in this project (estrogen-receptor positive breast cancer, estrogen-receptor negative breast cancer, and breast cancer in general) to perform this clustering. Two significant genetic pathways validated the clustering produced by this project: the MAPK signaling pathway and the connection between the BRCA2 gene and the ESR1 gene. This study provides the first proof of concept showing the importance of unsupervised machine learning in interpreting GWAS summary statistics.

Keywords: breast cancer, computational biology, unsupervised machine learning, k-means, PCA

Procedia PDF Downloads 122
7926 Deep Learning-Based Approach to Automatic Abstractive Summarization of Patent Documents

Authors: Sakshi V. Tantak, Vishap K. Malik, Neelanjney Pilarisetty

Abstract:

A patent is an exclusive right granted for an invention. It can be a product or a process that provides an innovative method of doing something, or offers a new technical perspective or solution to a problem. A patent can be obtained by making the technical information and details about the invention publicly available. The patent owner has exclusive rights to prevent or stop anyone from using the patented invention for commercial uses. Any commercial usage, distribution, import or export of a patented invention or product requires the patent owner’s consent. It has been observed that the central and important parts of patents are scripted in idiosyncratic and complex linguistic structures that can be difficult to read, comprehend or interpret for the masses. The abstracts of these patents tend to obfuscate the precise nature of the patent instead of clarifying it via direct and simple linguistic constructs. This makes it necessary to have an efficient access to this knowledge via concise and transparent summaries. However, as mentioned above, due to complex and repetitive linguistic constructs and extremely long sentences, common extraction-oriented automatic text summarization methods should not be expected to show a remarkable performance when applied to patent documents. Other, more content-oriented or abstractive summarization techniques are able to perform much better and generate more concise summaries. This paper proposes an efficient summarization system for patents using artificial intelligence, natural language processing and deep learning techniques to condense the knowledge and essential information from a patent document into a single summary that is easier to understand without any redundant formatting and difficult jargon.

Keywords: abstractive summarization, deep learning, natural language Processing, patent document

Procedia PDF Downloads 105