Search results for: graph convolutional network

Authors: Jaiden Xuan Schraut, Leon Liu, Yiqiao Yin

Abstract:

Computer vision in medical diagnosis has achieved a high level of success in diagnosing diseases with high accuracy. However, conventional classifiers that produce an image to-label result provides insufficient information for medical professionals to judge and raise concerns over the trust and reliability of a model with results that cannot be explained. In order to gain local insight into cancerous regions, separate tasks such as imaging segmentation need to be implemented to aid the doctors in treating patients, which doubles the training time and costs which renders the diagnosis system inefficient and difficult to be accepted by the public. To tackle this issue and drive AI-first medical solutions further, this paper proposes a multi-output network that follows a U-Net architecture for image segmentation output and features an additional convolutional neural networks (CNN) module for auxiliary classification output. Class activation maps are a method of providing insight into a convolutional neural network’s feature maps that leads to its classification but in the case of lung diseases, the region of interest is enhanced by U-net-assisted Class Activation Map (CAM) visualization. Therefore, our proposed model combines image segmentation models and classifiers to crop out only the lung region of a chest X-ray’s class activation map to provide a visualization that improves the explainability and is able to generate classification results simultaneously which builds trust for AI-led diagnosis systems. The proposed U-Net model achieves 97.61% accuracy and a dice coefficient of 0.97 on testing data from the COVID-QU-Ex Dataset which includes both diseased and healthy lungs.

Keywords: multi-output network model, U-net, class activation map, image classification, medical imaging analysis

Procedia PDF Downloads 203

Authors: Divvela Vishnu Sai Kumar, Deepak Arora, Sheenu Rizvi

Abstract:

Forecasting a cyclone through satellite images consists of the estimation of the intensity of the cyclone and predicting it before a cyclone comes. This research work can help people to take safety measures before the cyclone comes. The prediction of the intensity of a cyclone is very important to save lives and minimize the damage caused by cyclones. These cyclones are very costliest natural disasters that cause a lot of damage globally due to a lot of hazards. Authors have proposed five different CNN (Convolutional Neural Network) models that estimate the intensity of cyclones through INSAT-3D IR images. There are a lot of techniques that are used to estimate the intensity; the best model proposed by authors estimates intensity with a root mean squared error (RMSE) of 10.02 kts.

Keywords: estimating cyclone intensity, deep learning, convolution neural network, prediction models

Procedia PDF Downloads 127

Authors: Rujia Chen, Ajit Narayanan

Abstract:

Convolutional neural networks (CNN), as typically applied in deep learning, use layer-wise backpropagation (BP) to construct filters and kernels for feature extraction. Such filters are 2D or 3D groups of weights for constructing feature maps at subsequent layers of the CNN and are shared across the entire input. BP as a gradient descent algorithm has well-known problems of getting stuck at local optima. The use of genetic algorithms (GAs) for evolving weights between layers of standard artificial neural networks (ANNs) is a well-established area of neuroevolution. In particular, the use of crossover techniques when optimizing weights can help to overcome problems of local optima. However, the application of GAs for evolving the weights of filters and kernels in CNNs is not yet an established area of neuroevolution. In this paper, a GA-based filter development algorithm is proposed. The results of the proof-of-concept experiments described in this paper show the proposed GA algorithm can find filter weights through evolutionary techniques rather than BP learning. For some simple classification tasks like geometric shape recognition, the proposed algorithm can achieve 100% accuracy. The results for MNIST classification, while not as good as possible through standard filter learning through BP, show that filter and kernel evolution warrants further investigation as a new subarea of neuroevolution for deep architectures.

Keywords: neuroevolution, convolutional neural network, genetic algorithm, filters, kernels

Procedia PDF Downloads 186

Authors: Pengfei Meng, Shuangcheng Jia, Qian Li

Abstract:

We proposed a real-time high-precision semantic segmentation network based on a multi-resolution feature fusion module, the auxiliary feature extracting module, upsampling module, and atrous spatial pyramid pooling (ASPP) module. We designed a feature fusion structure, which is integrated with sufficient features of different resolutions. We also studied the effect of side-branch structure on the network and made discoveries. Based on the discoveries about the side-branch of the network structure, we used a side-branch auxiliary feature extraction layer in the network to improve the effectiveness of the network. We also designed upsampling module, which has better results than the original upsampling module. In addition, we also re-considered the locations and number of atrous spatial pyramid pooling (ASPP) modules and modified the network structure according to the experimental results to further improve the effectiveness of the network. The network presented in this paper takes the backbone network of Bisenetv2 as a basic network, based on which we constructed a network structure on which we made improvements. We named this network deep multiple-resolution bilateral networks for real-time, referred to as DMBR-Net. After experimental testing, our proposed DMBR-Net network achieved 81.2% mIoU at 119FPS on the Cityscapes validation dataset, 80.7% mIoU at 109FPS on the CamVid test dataset, 29.9% mIoU at 78FPS on the COCOStuff test dataset. Compared with all lightweight real-time semantic segmentation networks, our network achieves the highest accuracy at an appropriate speed.

Keywords: multi-resolution feature fusion, atrous convolutional, bilateral networks, pyramid pooling

Procedia PDF Downloads 150

Authors: Yihao Kuang, Bowen Ding

Abstract:

With the increasing scale and complexity of knowledge graph, modern knowledge graph contains more and more types of entity, relationship, and attribute information. Therefore, in recent years, it has been a trend for knowledge graph inference to use reinforcement learning to deal with large-scale, incomplete, and noisy knowledge graph and improve the inference effect and interpretability. The Proximal Policy Optimization (PPO) algorithm utilizes a near-end strategy optimization approach. This allows for more extensive updates of policy parameters while constraining the update extent to maintain training stability. This characteristic enables PPOs to converge to improve strategies more rapidly, often demonstrating enhanced performance early in the training process. Furthermore, PPO has the advantage of offline learning, effectively utilizing historical experience data for training and enhancing sample utilization. This means that even with limited resources, PPOs can efficiently train for reinforcement learning tasks. Based on these characteristics, this paper aims to obtain better and more efficient inference effect by introducing PPO into knowledge inference technology.

Keywords: reinforcement learning, PPO, knowledge inference, supervised learning

Procedia PDF Downloads 67

Authors: Youhang Zhou, Weimin Zeng, Qi Xie

Abstract:

Abstract: In order to solve the wear recognition problem of the machine tool guide surface, a new machine tool guide surface recognition method based on the radar-graph barycentre feature is presented in this paper. Firstly, the gray mean value, skewness, projection variance, flat degrees and kurtosis features of the guide surface image data are defined as primary characteristics. Secondly, data Visualization technology based on radar graph is used. The visual barycentre graphical feature is demonstrated based on the radar plot of multi-dimensional data. Thirdly, a classifier based on the support vector machine technology is used, the radar-graph barycentre feature and wear original feature are put into the classifier separately for classification and comparative analysis of classification and experiment results. The calculation and experimental results show that the method based on the radar-graph barycentre feature can detect the guide surface effectively.

Keywords: guide surface, wear defects, feature extraction, data visualization

Procedia PDF Downloads 519

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 73

Authors: Anthony D. Rhodes, Manan Goel

Abstract:

We provide a high fidelity deep learning algorithm (HyperSeg) for interactive video segmentation tasks using a dense convolutional network with context-aware skip connections and compressed, 'hypercolumn' image features combined with a convolutional tessellation procedure. In order to maintain high output fidelity, our model crucially processes and renders all image features in high resolution, without utilizing downsampling or pooling procedures. We maintain this consistent, high grade fidelity efficiently in our model chiefly through two means: (1) we use a statistically-principled, tensor decomposition procedure to modulate the number of hypercolumn features and (2) we render these features in their native resolution using a convolutional tessellation technique. For improved pixel-level segmentation results, we introduce a boundary loss function; for improved temporal coherence in video data, we include temporal image information in our model. Through experiments, we demonstrate the improved accuracy of our model against baseline models for interactive segmentation tasks using high resolution video data. We also introduce a benchmark video segmentation dataset, the VFX Segmentation Dataset, which contains over 27,046 high resolution video frames, including green screen and various composited scenes with corresponding, hand-crafted, pixel-level segmentations. Our work presents a improves state of the art segmentation fidelity with high resolution data and can be used across a broad range of application domains, including VFX pipelines and medical imaging disciplines.

Keywords: computer vision, object segmentation, interactive segmentation, model compression

Procedia PDF Downloads 120

Authors: Zhihan Li

Abstract:

Nowadays, most universities use the course enrollment system considering students’ registration orders. However, the students’ preference level to certain courses is also one important factor to consider. In this research, the possibility of applying a preference-first system has been discussed and analyzed compared to the order-first system. A bipartite graph is applied to resemble the relationship between students and courses they tend to register. With the graph set up, we apply Ford-Fulkerson (F.F.) Algorithm to maximize parings between two sets of nodes, in our case, students and courses. Two models are proposed in this paper: the one considered students’ order first, and the one considered students’ preference first. By comparing and contrasting the two models, we highlight the usability of models which potentially leads to better designs for school course registration systems.

Keywords: bipartite graph, Ford-Fulkerson (F.F.) algorithm, graph theory, maximum matching

Procedia PDF Downloads 111

Authors: Arya Prakash Padhi, Anupam Chakrabarti, Rajib Chowdhury

Abstract:

Topology or layout optimization often gives better performing economic structures and is very helpful in the conceptual design phase. But traditionally it is being done in finite element-based optimization schemes which, although gives a good result, is very time-consuming especially in 3D structures. Among other alternatives machine learning, especially deep learning-based methods, have a very good potential in resolving this computational issue. Here convolutional neural network (3D-CNN) based variational auto encoder (VAE) is trained using a dataset generated from commercially available topology optimization code ABAQUS Tosca using solid isotropic material with penalization (SIMP) method for compliance minimization. The encoded data in latent space is then fed to a 3D generative adversarial network (3D-GAN) to generate the outcome in 64x64x64 size. Here the network consists of 3D volumetric CNN with rectified linear unit (ReLU) activation in between and sigmoid activation in the end. The proposed network is seen to provide almost optimal results with significantly reduced computational time, as there is no iteration involved.

Keywords: 3D generative adversarial network, deep learning, structural topology optimization, variational auto encoder

Procedia PDF Downloads 174

Authors: Hamsini Pulugurtha, P. V. S. L. Jagadamba

Abstract:

Programmed Speech to Text and Text Summarization Using Graph-based Algorithms can be utilized in gatherings to get the short depiction of the gathering for future reference. This gives signature check utilizing Siamese neural organization to confirm the personality of the client and convert the client gave sound record which is in English into English text utilizing the discourse acknowledgment bundle given in python. At times just the outline of the gathering is required, the answer for this text rundown. Thus, the record is then summed up utilizing the regular language preparing approaches, for example, solo extractive text outline calculations

Keywords: Siamese neural network, English speech, English text, natural language processing, unsupervised extractive text summarization

Procedia PDF Downloads 218

Authors: Nishank Raisinghani

Abstract:

Efficiently predicting drug response remains a challenge in the realm of drug discovery. To address this issue, we propose four model architectures that combine graphical representation with varying positions of multiheaded self-attention mechanisms. By leveraging two types of multi-omics data, transcriptomics and genomics, we create a comprehensive representation of target cells and enable drug response prediction in precision medicine. A majority of our architectures utilize multiple transformer models, one with a graph attention mechanism and the other with a multiheaded self-attention mechanism, to generate latent representations of both drug and omics data, respectively. Our model architectures apply an attention mechanism to both drug and multiomics data, with the goal of procuring more comprehensive latent representations. The latent representations are then concatenated and input into a fully connected network to predict the IC-50 score, a measure of cell drug response. We experiment with all four of these architectures and extract results from all of them. Our study greatly contributes to the future of drug discovery and precision medicine by looking to optimize the time and accuracy of drug response prediction.

Keywords: drug discovery, transformers, graph neural networks, multiomics

Procedia PDF Downloads 153

Authors: Elias Ogutu Azariah Tembe, Hussain Abdullah Habib Al-Salamin

Abstract:

There is decagram of strategic decisions of operations and production/service management (POSM) within operational research (OR) which must collate, namely: design, inventory, quality, location, process and capacity, layout, scheduling, maintain ace, and supply chain. This paper presents an architectural configuration conceptual framework of a decagram of sets decisions in a form of mathematical complete graph and abelian graph. Mathematically, a complete graph is undirected (UDG), and directed (DG) a relationship where every pair of vertices are connected, collated, confluent, and holomorphic. There has not been any study conducted which, however, prioritizes the holomorphic sets which of POMS within OR field of study. The study utilizes OR structured technique known as The Analytic Hierarchy Process (AHP) analysis for organizing, sorting and prioritizing (ranking) the sets within the decagram of POMS according to their attribution (propensity), and provides an analysis how the prioritization has real-world application within the 21st century.

Keywords: holomorphic, decagram, decagon, confluent, complete graph, AHP analysis, SCM, HRM, OR, OM, abelian graph

Procedia PDF Downloads 402

Authors: Hossein Pourali

Abstract:

In this paper, we extend the concepts of primal and weakly primal ideals for posets. Further, the diameter of the zero divisor graph of a poset with respect to a non-primal ideal is determined. The relation between primary and primal ideals in posets is also studied.

Keywords: ‎associated prime ideal, ‎‎ideal, ‎‎primary ideal, primal ideal‎, prime‎ ‎ideal, semiprime ideal, ‎weakly primal ideal, zero divisors graph

Procedia PDF Downloads 255

Authors: Analen Malnegro, Gina Malacas

Abstract:

Dominating sets and related topics have been studied extensively in the past few decades. A dominating set of a graph G is a subset D of V such that every vertex not in D is adjacent to at least one member of D. The domination number γ(G) is the number of vertices in a smallest dominating set for G. Some problems involving detection devices can be modeled with graphs. Finding the minimum number of devices needed according to the type of devices and the necessity of locating the object gives rise to locating-dominating sets. A subset S of vertices of a graph G is called locating-dominating set, LD-set for short, if it is a dominating set and if every vertex v not in S is uniquely determined by the set of neighbors of v belonging to S. The location-domination number λ(G) is the minimum cardinality of an LD-set for G. The complement of a graph G is a graph Ḡ on same vertices such that two distinct vertices of Ḡ are adjacent if and only if they are not adjacent in G. An LD-set of a graph G is global if it is an LD-set of both G and its complement Ḡ. The global location-domination number λg(G) is defined as the minimum cardinality of a global LD-set of G. In this paper, global LD-sets on the join of two graphs are characterized. Global location-domination numbers of these graphs are also determined.

Keywords: dominating set, global locating-dominating set, global location-domination number, locating-dominating set, location-domination number

Procedia PDF Downloads 184

Authors: Cheng Fang, Lingwei Quan, Cunyue Lu

Abstract:

Human pose estimation and tracking are to accurately identify and locate the positions of human joints in the video. It is a computer vision task which is of great significance for human motion recognition, behavior understanding and scene analysis. There has been remarkable progress on human pose estimation in recent years. However, more researches are needed for human pose tracking especially for online tracking. In this paper, a framework, called PoseSRPN, is proposed for online single-person pose estimation and tracking. We use Siamese network attaching a pose estimation branch to incorporate Single-person Pose Tracking (SPT) and Visual Object Tracking (VOT) into one framework. The pose estimation branch has a simple network structure that replaces the complex upsampling and convolution network structure with deconvolution. By augmenting the loss of fully convolutional Siamese network with the pose estimation task, pose estimation and tracking can be trained in one stage. Once trained, PoseSRPN only relies on a single bounding box initialization and producing human joints location. The experimental results show that while maintaining the good accuracy of pose estimation on COCO and PoseTrack datasets, the proposed method achieves a speed of 59 frame/s, which is superior to other pose tracking frameworks.

Keywords: computer vision, pose estimation, pose tracking, Siamese network

Procedia PDF Downloads 153

Authors: Mohammad Saleh Vahdatpour, Yanqing Zhang

Abstract:

Understanding the neural mechanisms underlying motion detection in the human visual system has long been a fascinating challenge in neuroscience and artificial intelligence. This paper presents a spiking neural network model inspired by the processing of motion information in the primate visual system, particularly focusing on the Middle Temporal (MT) area. In our study, we propose a multi-layer spiking neural network model to perform motion detection tasks, leveraging the idea that synaptic delays in neuronal communication are pivotal in motion perception. Synaptic delay, determined by factors like axon length and myelin insulation, affects the temporal order of input spikes, thereby encoding motion direction and speed. Overall, our spiking neural network model demonstrates the feasibility of capturing motion detection principles observed in the primate visual system. The combination of synaptic delays, learning mechanisms, and shared weights and delays in SMD provides a promising framework for motion perception in artificial systems, with potential applications in computer vision and robotics.

Keywords: neural network, motion detection, signature detection, convolutional neural network

Procedia PDF Downloads 88

Authors: Kirolos Gerges Yakoub Gerges

Abstract:

Self-sustaining agricultural machines act in stochastic surroundings and therefore, should be capable of perceive the surroundings in real time. This notion can be done using image sensors blended with superior device learning, mainly Deep mastering. Deep convolutional neural networks excel in labeling and perceiving colour pix and since the fee of RGB-cameras is low, the hardware cost of accurate notion relies upon heavily on memory and computation power. This paper investigates the opportunity of designing lightweight convolutional neural networks for semantic segmentation (pixel clever class) with reduced hardware requirements, to allow for embedded usage in self-reliant agricultural machines. The usage of compression techniques, a lightweight convolutional neural community is designed to carry out actual-time semantic segmentation on an embedded platform. The community is skilled on two big datasets, ImageNet and Pascal Context, to apprehend as much as four hundred man or woman instructions. The 400 training are remapped into agricultural superclasses (e.g. human, animal, sky, road, area, shelterbelt and impediment) and the capacity to provide correct actual-time perception of agricultural environment is studied. The network is carried out to the case of self-sufficient grass mowing the usage of the NVIDIA Tegra X1 embedded platform. Feeding case-unique pics to the community consequences in a fully segmented map of the superclasses within the picture. As the network remains being designed and optimized, handiest a qualitative analysis of the technique is entire on the abstract submission deadline. intending this cut-off date, the finalized layout is quantitatively evaluated on 20 annotated grass mowing pictures. Light-weight convolutional neural networks for semantic segmentation can be implemented on an embedded platform and show aggressive performance on the subject of accuracy and speed. It’s miles viable to offer value-efficient perceptive capabilities related to semantic segmentation for autonomous agricultural machines.

Keywords: centrifuge pump, hydraulic energy, agricultural applications, irrigationaxial flux machines, axial flux applications, coreless machines, PM machinesautonomous agricultural machines, deep learning, safety, visual perception

Procedia PDF Downloads 26

Authors: Amadou Fall Dia, Maurras Ulbricht Togbe, Aliou Boly, Zakia Kazi Aoul, Elisabeth Metais

Abstract:

Existing RDF (Resource Description Framework) Stream Processing (RSP) systems allow continuous processing of RDF data issued from different application domains such as weather station measuring phenomena, geolocation, IoT applications, drinking water distribution management, and so on. However, processing window phase often expires before finishing the entire session and RSP systems immediately delete data streams after each processed window. Such mechanism does not allow optimized exploitation of the RDF data streams as the most relevant and pertinent information of the data is often not used in a due time and almost impossible to be exploited for further analyzes. It should be better to keep the most informative part of data within streams while minimizing the memory storage space. In this work, we propose an RDF graph summarization system based on an explicit and implicit expressed needs through three main approaches: (1) an approach for user queries (SPARQL) in order to extract their needs and group them into a more global query, (2) an extension of the closeness centrality measure issued from Social Network Analysis (SNA) to determine the most informative parts of the graph and (3) an RDF graph summarization technique combining extracted user query needs and the extended centrality measure. Experiments and evaluations show efficient results in terms of memory space storage and the most expected approximate query results on summarized graphs compared to the source ones.

Keywords: centrality measures, RDF graphs summary, RDF graphs stream, SPARQL query

Procedia PDF Downloads 203

Authors: Robert Gold

Abstract:

Control flow graphs are a well-known representation of the sequential control flow structure of programs with a multitude of applications. Not only single functions but also sets of functions or complete programs can be modelled by control flow graphs. In this case the size of the graphs can grow considerably and thus makes it difficult for software engineers to analyse the control flow. Graph reductions are helpful in this situation. In this paper we define reductions to subsets of nodes. Since executions of programs are represented by paths through the control flow graphs, paths should be preserved. Furthermore, the composition of reductions makes a stepwise analysis approach possible.

Keywords: control flow graph, graph reduction, software engineering, software applications

Procedia PDF Downloads 552

Authors: Aicha Majda, Abdelhamid El Hassani

Abstract:

Lung CT image segmentation is a prerequisite in lung CT image analysis. Most of the conventional methods need a post-processing to deal with the abnormal lung CT scans such as lung nodules or other lesions. The simplest similarity measure in the standard Graph Cuts Algorithm consists of directly comparing the pixel values of the two neighboring regions, which is not accurate because this kind of metrics is extremely sensitive to minor transformations such as noise or other artifacts problems. In this work, we propose an improved version of the standard graph cuts algorithm based on the Patch-Based similarity metric. The boundary penalty term in the graph cut algorithm is defined Based on Patch-Based similarity measurement instead of the simple intensity measurement in the standard method. The weights between each pixel and its neighboring pixels are Based on the obtained new term. The graph is then created using theses weights between its nodes. Finally, the segmentation is completed with the minimum cut/Max-Flow algorithm. Experimental results show that the proposed method is very accurate and efficient, and can directly provide explicit lung regions without any post-processing operations compared to the standard method.

Keywords: graph cuts, lung CT scan, lung parenchyma segmentation, patch-based similarity metric

Procedia PDF Downloads 169

Authors: Rahma Abed, Sahbi Bahroun, Ezzeddine Zagrouba

Abstract:

Due to the huge amount of data in videos, extracting the relevant frames became a necessity and an essential step prior to performing face recognition. In this context, we propose a method for extracting keyframes from videos based on face quality and deep learning for a face recognition task. This method has two steps. We start by generating face quality scores for each face image based on the use of three face feature extractors, including Gabor, LBP, and HOG. The second step consists in training a Deep Convolutional Neural Network in a supervised manner in order to select the frames that have the best face quality. The obtained results show the effectiveness of the proposed method compared to the methods of the state of the art.

Keywords: keyframe extraction, face quality assessment, face in video recognition, convolution neural network

Procedia PDF Downloads 233

Authors: Yasmeen A. S. Essawy, Khaled Nassar

Abstract:

With the rapid increase of complexity in the building industry, professionals in the A/E/C industry were forced to adopt Building Information Modeling (BIM) in order to enhance the communication between the different project stakeholders throughout the project life cycle and create a semantic object-oriented building model that can support geometric-topological analysis of building elements during design and construction. This paper presents a model that extracts topological relationships and geometrical properties of building elements from an existing fully designed BIM, and maps this information into a directed acyclic Elemental Graph Data Model (EGDM). The model incorporates BIM-based search algorithms for automatic deduction of geometrical data and topological relationships for each building element type. Using graph search algorithms, such as Depth First Search (DFS) and topological sortings, all possible construction sequences can be generated and compared against production and construction rules to generate an optimized construction sequence and its associated schedule. The model is implemented in a C# platform.

Keywords: building information modeling (BIM), elemental graph data model (EGDM), geometric and topological data models, graph theory

Procedia PDF Downloads 382

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 114

Authors: Shankaran Sitarama

Abstract:

New Product Development (NPD) is invariably a team effort and involves effective teamwork. NPD team has members from different disciplines coming together and working through the different phases all the way from conceptual design phase till the production and product roll out. Creativity and Innovation are some of the key factors of successful NPD. Team members going through the different phases of NPD interact and work closely yet challenge each other during the design phases to brainstorm on ideas and later converge to work together. These two traits require the teams to have a divergent and a convergent thinking simultaneously. There needs to be a good balance. The team dynamics invariably result in conflicts among team members. While some amount of conflict (ideational conflict) is desirable in NPD teams to be creative as a group, relational conflicts (or discords among members) could be detrimental to teamwork. Team communication truly reflect these tensions and team dynamics. In this research, team communication (emails) between the members of the NPD teams is considered for analysis. The email communication is processed through a semantic analysis algorithm (LSA) to analyze the content of communication and a semantic similarity analysis to arrive at a social network graph that depicts the communication amongst team members based on the content of communication. The amount of communication (content and not frequency of communication) defines the interaction strength between the members. Social network adjacency matrix is thus obtained for the team. Standard social network analysis techniques based on the Adjacency Matrix (AM) and Dichotomized Adjacency Matrix (DAM) based on network density yield network graphs and network metrics like centrality. The social network graphs are then rendered for visual representation using a Metric Multi-Dimensional Scaling (MMDS) algorithm for node placements and arcs connecting the nodes (representing team members) are drawn. The distance of the nodes in the placement represents the tie-strength between the members. Stronger tie-strengths render nodes closer. Overall visual representation of the social network graph provides a clear picture of the team’s interactions. This research reveals four distinct patterns of team interaction that are clearly identifiable in the visual representation of the social network graph and have a clearly defined computational scheme. The four computational patterns of team interaction defined are Central Member Pattern (CMP), Subgroup and Aloof member Pattern (SAP), Isolate Member Pattern (IMP), and Pendant Member Pattern (PMP). Each of these patterns has a team dynamics implication in terms of the conflict level in the team. For instance, Isolate member pattern, clearly points to a near break-down in communication with the member and hence a possible high conflict level, whereas the subgroup or aloof member pattern points to a non-uniform information flow in the team and some moderate level of conflict. These pattern classifications of teams are then compared and correlated to the real level of conflict in the teams as indicated by the team members through an elaborate self-evaluation, team reflection, feedback form and results show a good correlation.

Keywords: team dynamics, team communication, team interactions, social network analysis, sna, new product development, latent semantic analysis, LSA, NPD teams

Procedia PDF Downloads 70

Authors: Leyla Noroozbabaee, David Nickerson

Abstract:

We introduce a modular, consistent, reusable bond graph model of the renal nephron’s proximal convoluted tubule (PCT), which can reproduce biological behaviour. In this work, we focus on ion and volume transport in the proximal convoluted tubule of the renal nephron. Modelling complex systems requires complex modelling problems to be broken down into manageable pieces. This can be enabled by developing models of subsystems that are subsequently coupled hierarchically. Because they are based on a graph structure. In the current work, we define two modular subsystems: the resistive module representing the membrane and the capacitive module representing solution compartments. Each module is analyzed based on thermodynamic processes, and all the subsystems are reintegrated into circuit theory in network thermodynamics. The epithelial transport system we introduce in the current study consists of five transport membranes and four solution compartments. Coupled dissipations in the system occur in the membrane subsystems and coupled free-energy increasing, or decreasing processes appear in solution compartment subsystems. These structural subsystems also consist of elementary thermodynamic processes: dissipations, free-energy change, and power conversions. We provide free and open access to the Python implementation to ensure our model is accessible, enabling the reader to explore the model through setting their simulations and reproducibility tests.

Keywords: Bond Graph, Epithelial Transport, Water Transport, Mathematical Modeling

Procedia PDF Downloads 87

Authors: Tesfaye Fenta Boka, Niu Zhendong

Abstract:

Recommender systems play a crucial role in connecting individuals with the items they require, as is particularly evident in the rapid growth of online grocery shopping platforms. These systems predominantly rely on user-centered recommendations, where items are suggested based on individual preferences, garnering considerable attention and adoption. However, our focus lies on the item-centered recommendation task within the grocery shopping context. In the reverse next item period recommendation (RNPR) task, we are presented with a specific item and challenged to identify potential users who are likely to consume it in the upcoming period. Despite the ever-expanding inventory of products on online grocery platforms, the cold start item problem persists, posing a substantial hurdle in delivering personalized and accurate recommendations for new or niche grocery items. To address this challenge, we propose a Graph Neural Network (GNN)-based approach. By capitalizing on the inherent relationships among grocery items and leveraging users' historical interactions, our model aims to provide reliable and context-aware recommendations for cold-start items. This integration of GNN technology holds the promise of enhancing recommendation accuracy and catering to users' individual preferences. This research contributes to the advancement of personalized recommendations in the online grocery shopping domain. By harnessing the potential of GNNs and exploring item-centered recommendation strategies, we aim to improve the overall shopping experience and satisfaction of users on these platforms.

Keywords: recommender systems, cold start item recommendations, online grocery shopping platforms, graph neural networks

Procedia PDF Downloads 90

Authors: A. Boulanoir, B. Ould Bouamama, A. Debiane, N. Achour

Abstract:

The paper deals with robust Fault Detection and isolation with respect to parameter uncertainties based on linear fractional transformation form (LFT) Bond graph. The innovative interest of the proposed methodology is the use only one representation for systematic generation of robust analytical redundancy relations and adaptive residual thresholds for sensibility analysis. Furthermore, the parameter uncertainties are introduced graphically in the bond graph model. The methodology applied to the nonlinear industrial Electro-Mechanical Actuators (EMA) used in avionic systems, has determined first the structural monitorability analysis (which component can be monitored) with given instrumentation architecture with any need of complex calculation and secondly robust fault indicators for online supervision.

Keywords: bond graph (BG), electro mechanical actuators (EMA), fault detection and isolation (FDI), linear fractional transformation (LFT), mechatronic systems, parameter uncertainties, avionic system

Procedia PDF Downloads 350

Authors: Xiaoheng Tan, Xianfang Li, Tan Guo, Yuchuan Liu, Zhijun Yang, Hongye Li, Kai Fu, Yufang Wu, Heling Gong

Abstract:

The image data collected in reality often have high dimensions, and it contains noise and redundant information. Therefore, it is necessary to extract the compact feature expression of the original perceived image. In this process, effective use of prior knowledge such as data structure distribution and sample label is the key to enhance image feature discrimination and robustness. Based on the above considerations, this paper proposes a local preserving discriminant feature learning model based on graph optimization. The model has the following characteristics: (1) Locality preserving constraint can effectively excavate and preserve the local structural relationship between data. (2) The flexibility of graph learning can be improved by constructing a new local geometric structure graph using label information and the nearest neighbor threshold. (3) The L₂,₁ norm is used to redefine LDA, and the diagonal matrix is introduced as the scale factor of LDA, and the samples are selected, which improves the robustness of feature learning. The validity and robustness of the proposed algorithm are verified by experiments in two public image datasets.

Keywords: feature extraction, graph optimization local preserving projection, linear discriminant analysis, L₂, ₁ norm

Procedia PDF Downloads 149

Authors: Dongju Kim, Youngjoo Suh, Hyojin Kim, Gyeongyeong Kim

Abstract:

Acoustic Emission Testing (AET) is widely used to test the structural integrity of an operational hydrogen storage container, and clustering algorithms are frequently used in pattern recognition methods to interpret AET results. However, the interpretation of AET results can vary from user to user as the tuning of the relevant parameters relies on the user's experience and knowledge of AET. Therefore, it is necessary to use a deep learning model to identify patterns in acoustic emission (AE) signal data that can be used to classify defects instead. In this paper, a deep learning-based model for classifying the types of defects in hydrogen storage tanks, using AE sensor waveforms, is proposed. As hydrogen storage tanks are commonly constructed using carbon fiber reinforced polymer composite (CFRP), a defect classification dataset is collected through a tensile test on a specimen of CFRP with an AE sensor attached. The performance of the classification model, using one-dimensional convolutional neural network (1-D CNN) and synthetic minority oversampling technique (SMOTE) data augmentation, achieved 91.09% accuracy for each defect. It is expected that the deep learning classification model in this paper, used with AET, will help in evaluating the operational safety of hydrogen storage containers.

Keywords: acoustic emission testing, carbon fiber reinforced polymer composite, one-dimensional convolutional neural network, smote data augmentation

Procedia PDF Downloads 93