Search results for: neural nets
405 Computer-Aided Diagnosis of Polycystic Kidney Disease Using ANN
Authors: G. Anjan Babu, G. Sumana, M. Rajasekhar
Abstract:
Many inherited diseases and non-hereditary disorders are common in the development of renal cystic diseases. Polycystic kidney disease (PKD) is a disorder developed within the kidneys in which grouping of cysts filled with water like fluid. PKD is responsible for 5-10% of end-stage renal failure treated by dialysis or transplantation. New experimental models, application of molecular biology techniques have provided new insights into the pathogenesis of PKD. Researchers are showing keen interest for developing an automated system by applying computer aided techniques for the diagnosis of diseases. In this paper a multi-layered feed forward neural network with one hidden layer is constructed, trained and tested by applying back propagation learning rule for the diagnosis of PKD based on physical symptoms and test results of urinanalysis collected from the individual patients. The data collected from 50 patients are used to train and test the network. Among these samples, 75% of the data used for training and remaining 25% of the data are used for testing purpose. Furthermore, this trained network is used to implement for new samples. The output results in normality and abnormality of the patient.Keywords: dialysis, hereditary, transplantation, polycystic, pathogenesis
Procedia PDF Downloads 373404 Online Yoga Asana Trainer Using Deep Learning
Authors: Venkata Narayana Chejarla, Nafisa Parvez Shaik, Gopi Vara Prasad Marabathula, Deva Kumar Bejjam
Abstract:
Yoga is an advanced, well-recognized method with roots in Indian philosophy. Yoga benefits both the body and the psyche. Yoga is a regular exercise that helps people relax and sleep better while also enhancing their balance, endurance, and concentration. Yoga can be learned in a variety of settings, including at home with the aid of books and the internet as well as in yoga studios with the guidance of an instructor. Self-learning does not teach the proper yoga poses, and doing them without the right instruction could result in significant injuries. We developed "Online Yoga Asana Trainer using Deep Learning" so that people could practice yoga without a teacher. Our project is developed using Tensorflow, Movenet, and Keras models. The system makes use of data from Kaggle that includes 25 different yoga poses. The first part of the process involves applying the movement model for extracting the 17 key points of the body from the dataset, and the next part involves preprocessing, which includes building a pose classification model using neural networks. The system scores a 98.3% accuracy rate. The system is developed to work with live videos.Keywords: yoga, deep learning, movenet, tensorflow, keras, CNN
Procedia PDF Downloads 235403 Influence Analysis of Macroeconomic Parameters on Real Estate Price Variation in Taipei, Taiwan
Authors: Li Li, Kai-Hsuan Chu
Abstract:
It is well known that the real estate price depends on a lot of factors. Each house current value is dependent on the location, room number, transportation, living convenience, year and surrounding environments. Although, there are different experienced models for housing agent to estimate the price, it is a case by case study without overall dynamic variation investigation. However, many economic parameters may more or less influence the real estate price variation. Here, the influences of most macroeconomic parameters on real estate price are investigated individually based on least-square scheme and grey correlation strategy. Then those parameters are classified into leading indices, simultaneous indices and laggard indices. In addition, the leading time period is evaluated based on least square method. The important leading and simultaneous indices can be used to establish an artificial intelligent neural network model for real estate price variation prediction. The real estate price variation of Taipei, Taiwan during 2005 ~ 2017 are chosen for this research data analysis and validation. The results show that the proposed method has reasonable prediction function for real estate business reference.Keywords: real estate price, least-square, grey correlation, macroeconomics
Procedia PDF Downloads 192402 Preliminary Results on Marine Debris Classification in The Island of Mykonos (Greece) via Coastal and Underwater Clean up over 2016-20: A Successful Case of Recycling Plastics into Useful Daily Items
Authors: Eleni Akritopoulou, Katerina Topouzoglou
Abstract:
The last 20 years marine debris has been identified as one of the main marine pollution sources caused by anthropogenic activities. Plastics has reached the farthest marine areas of the planet affecting all marine trophic levels including the, recently discovered, amphipoda Eurythenes plasticus inhabiting Mariana Trench to large cetaceans, marine reptiles and sea birds causing immunodeficiency disorders, deteriorating health and death overtime. For the time period 2016-20, in the framework of the national initiative ‘Keep Aegean Blue”, All for Blue team has been collecting marine debris (coastline and underwater) following a modified in situ MEDSEALITTER monitoring protocol from eight Greek islands. After collection, marine debris was weighted, sorted and categorised according to material; plastic (PL), glass (G), metal (M), wood (W), rubber (R), cloth (CL), paper (P), mixed (MX). The goal of the project included the documentation of marine debris sources, human trends, waste management and public marine environmental awareness. Waste management was focused on plastics recycling and utilisation into daily useful products. This research is focused on the island of Mykonos due to its continuous touristic activity and lack of scientific information. In overall, a field work area of 1.832.856 m2 was cleaned up yielding 5092 kg of marine debris. The preliminary results indicated PL as main source of marine debris (62,8%) followed by M (15,5%), GL (13,2%) and MX (2,8%). Main items found were fishing tools (lines, nets), disposable cutlery, cups and straws, cigarette butts, flip flops and other items like plastic boat compartments. In collaboration with a local company for plastic management and the Circular Economy and Eco Innovation Institute (Sweden), all plastic debris was recycled. Granulation process was applied transforming plastic into building materials used for refugees’ houses, litter bins bought by municipalities and schools and, other items like shower components. In terms of volunteering and attendance in public awareness seminars, there was a raise of interest by 63% from different age ranges and professions. Regardless, the research being fairly new for Mykonos island and logistics issues potentially affected systemic sampling, it appeared that plastic debris is the main littering source attributed, possibly to the intense touristic activity of the island all year around. However, marine environmental awareness activities were pointed out to be an effective tool in forming public perception against marine debris and, alter the daily habits of local society. Since the beginning of this project, three new local environmental teams were formed against marine pollution supported by the local authorities and stakeholders. The continuous need and request for the production of items made by recycled marine debris appeared to be beneficial socio-economically to the local community and actions are taken to expand the project nationally. Finally, as an ongoing project and whilst, new scientific information is collected, further funding and research is needed.Keywords: Greece, marine debris, marine environmental awareness, Mykonos island, plastics debris, plastic granulation, recycled plastic, tourism, waste management
Procedia PDF Downloads 106401 Human Action Recognition Using Wavelets of Derived Beta Distributions
Authors: Neziha Jaouedi, Noureddine Boujnah, Mohamed Salim Bouhlel
Abstract:
In the framework of human machine interaction systems enhancement, we focus throw this paper on human behavior analysis and action recognition. Human behavior is characterized by actions and reactions duality (movements, psychological modification, verbal and emotional expression). It’s worth noting that many information is hidden behind gesture, sudden motion points trajectories and speeds, many research works reconstructed an information retrieval issues. In our work we will focus on motion extraction, tracking and action recognition using wavelet network approaches. Our contribution uses an analysis of human subtraction by Gaussian Mixture Model (GMM) and body movement through trajectory models of motion constructed from kalman filter. These models allow to remove the noise using the extraction of the main motion features and constitute a stable base to identify the evolutions of human activity. Each modality is used to recognize a human action using wavelets of derived beta distributions approach. The proposed approach has been validated successfully on a subset of KTH and UCF sports database.Keywords: feautures extraction, human action classifier, wavelet neural network, beta wavelet
Procedia PDF Downloads 406400 Subjective Time as a Marker of the Present Consciousness
Authors: Anastasiya Paltarzhitskaya
Abstract:
Subjective time plays an important role in consciousness processes and self-awareness at the moment. The concept of intrinsic neural timescales (INT) explains the difference in perceiving various time intervals. The capacity to experience the present builds on the fundamental properties of temporal cognition. The challenge that both philosophy and neuroscience try to answer is how the brain differentiates the present from the past and future. In our work, we analyze papers which describe mechanisms involved in the perception of ‘present’ and ‘non-present’, i.e., future and past moments. Taking into account that we perceive time intervals even during rest or relaxation, we suppose that the default-mode network activity can code time features, including the present moment. We can compare some results of time perceptual studies, where brain activity was shown in states with different flows of time, including resting states and during “mental time travel”. According to the concept of mental traveling, we employ a range of scenarios which demand episodic memory. However, some papers show that the hippocampal region does not activate during time traveling. It is a controversial result that is further complicated by the phenomenological aspect that includes a holistic set of information about the individual’s past and future.Keywords: temporal consciousness, time perception, memory, present
Procedia PDF Downloads 68399 A Multi-Model Approach to Assess Atlantic Bonito (Sarda Sarda, Bloch 1793) in the Eastern Atlantic Ocean: A Case Study of the Senegalese Exclusive Economic Zone
Authors: Ousmane Sarr
Abstract:
The Senegalese coasts have high productivity of fishery resources due to the frequency of intense up-welling system that occurs along its coast, caused by the maritime trade winds making its waters nutrients rich. Fishing plays a primordial role in Senegal's socioeconomic plans and food security. However, a global diagnosis of the Senegalese maritime fishing sector has highlighted the challenges this sector encounters. Among these concerns, some significant stocks, a priority target for artisanal fishing, need further assessment. If no efforts are made in this direction, most stock will be overexploited or even in decline. It is in this context that this research was initiated. This investigation aimed to apply a multi-modal approach (LBB, Catch-only-based CMSY model and its most recent version (CMSY++); JABBA, and JABBA-Select) to assess the stock of Atlantic bonito, Sarda sarda (Bloch, 1793) in the Senegalese Exclusive Economic Zone (SEEZ). Available catch, effort, and size data from Atlantic bonito over 15 years (2004-2018) were used to calculate the nominal and standardized CPUE, size-frequency distribution, and length at retentions (50 % and 95 % selectivity) of the species. These relevant results were employed as input parameters for stock assessment models mentioned above to define the stock status of this species in this region of the Atlantic Ocean. The LBB model indicated an Atlantic bonito healthy stock status with B/BMSY values ranging from 1.3 to 1.6 and B/B0 values varying from 0.47 to 0.61 of the main scenarios performed (BON_AFG_CL, BON_GN_Length, and BON_PS_Length). The results estimated by LBB are consistent with those obtained by CMSY. The CMSY model results demonstrate that the SEEZ Atlantic bonito stock is in a sound condition in the final year of the main scenarios analyzed (BON, BON-bt, BON-GN-bt, and BON-PS-bt) with sustainable relative stock biomass (B2018/BMSY = 1.13 to 1.3) and fishing pressure levels (F2018/FMSY= 0.52 to 1.43). The B/BMSY and F/FMSY results for the JABBA model ranged between 2.01 to 2.14 and 0.47 to 0.33, respectively. In contrast, The estimated B/BMSY and F/FMSY for JABBA-Select ranged from 1.91 to 1.92 and 0.52 to 0.54. The Kobe plots results of the base case scenarios ranged from 75% to 89% probability in the green area, indicating sustainable fishing pressure and an Atlantic bonito healthy stock size capable of producing high yields close to the MSY. Based on the stock assessment results, this study highlighted scientific advice for temporary management measures. This study suggests an improvement of the selectivity parameters of longlines and purse seines and a temporary prohibition of the use of sleeping nets in the fishery for the Atlantic bonito stock in the SEEZ based on the results of the length-base models. Although these actions are temporary, they can be essential to reduce or avoid intense pressure on the Atlantic bonito stock in the SEEZ. However, it is necessary to establish harvest control rules to provide coherent and solid scientific information that leads to appropriate decision-making for rational and sustainable exploitation of Atlantic bonito in the SEEZ and the Eastern Atlantic Ocean.Keywords: multi-model approach, stock assessment, atlantic bonito, healthy stock, sustainable, SEEZ, temporary management measures
Procedia PDF Downloads 55398 A Brain Controlled Robotic Gait Trainer for Neurorehabilitation
Authors: Qazi Umer Jamil, Abubakr Siddique, Mubeen Ur Rehman, Nida Aziz, Mohsin I. Tiwana
Abstract:
This paper discusses a brain controlled robotic gait trainer for neurorehabilitation of Spinal Cord Injury (SCI) patients. Patients suffering from Spinal Cord Injuries (SCI) become unable to execute motion control of their lower proximities due to degeneration of spinal cord neurons. The presented approach can help SCI patients in neuro-rehabilitation training by directly translating patient motor imagery into walkers motion commands and thus bypassing spinal cord neurons completely. A non-invasive EEG based brain-computer interface is used for capturing patient neural activity. For signal processing and classification, an open source software (OpenVibe) is used. Classifiers categorize the patient motor imagery (MI) into a specific set of commands that are further translated into walker motion commands. The robotic walker also employs fall detection for ensuring safety of patient during gait training and can act as a support for SCI patients. The gait trainer is tested with subjects, and satisfactory results were achieved.Keywords: brain computer interface (BCI), gait trainer, spinal cord injury (SCI), neurorehabilitation
Procedia PDF Downloads 153397 Satellite Imagery Classification Based on Deep Convolution Network
Authors: Zhong Ma, Zhuping Wang, Congxin Liu, Xiangzeng Liu
Abstract:
Satellite imagery classification is a challenging problem with many practical applications. In this paper, we designed a deep convolution neural network (DCNN) to classify the satellite imagery. The contributions of this paper are twofold — First, to cope with the large-scale variance in the satellite image, we introduced the inception module, which has multiple filters with different size at the same level, as the building block to build our DCNN model. Second, we proposed a genetic algorithm based method to efficiently search the best hyper-parameters of the DCNN in a large search space. The proposed method is evaluated on the benchmark database. The results of the proposed hyper-parameters search method show it will guide the search towards better regions of the parameter space. Based on the found hyper-parameters, we built our DCNN models, and evaluated its performance on satellite imagery classification, the results show the classification accuracy of proposed models outperform the state of the art method.Keywords: satellite imagery classification, deep convolution network, genetic algorithm, hyper-parameter optimization
Procedia PDF Downloads 292396 The Neurofunctional Dissociation between Animal and Tool Concepts: A Network-Based Model
Authors: Skiker Kaoutar, Mounir Maouene
Abstract:
Neuroimaging studies have shown that animal and tool concepts rely on distinct networks of brain areas. Animal concepts depend predominantly on temporal areas while tool concepts rely on fronto-temporo-parietal areas. However, the origin of this neurofunctional distinction for processing animal and tool concepts remains still unclear. Here, we address this question from a network perspective suggesting that the neural distinction between animals and tools might reflect the differences in their structural semantic networks. We build semantic networks for animal and tool concepts derived from McRae and colleagues’s behavioral study conducted on a large number of participants. These two networks are thus analyzed through a large number of graph theoretical measures for small-worldness: centrality, clustering coefficient, average shortest path length, as well as resistance to random and targeted attacks. The results indicate that both animal and tool networks have small-world properties. More importantly, the animal network is more vulnerable to targeted attacks compared to the tool network a result that correlates with brain lesions studies.Keywords: animals, tools, network, semantics, small-worls, resilience to damage
Procedia PDF Downloads 536395 Using Machine-Learning Methods for Allergen Amino Acid Sequence's Permutations
Authors: Kuei-Ling Sun, Emily Chia-Yu Su
Abstract:
Allergy is a hypersensitive overreaction of the immune system to environmental stimuli, and a major health problem. These overreactions include rashes, sneezing, fever, food allergies, anaphylaxis, asthmatic, shock, or other abnormal conditions. Allergies can be caused by food, insect stings, pollen, animal wool, and other allergens. Their development of allergies is due to both genetic and environmental factors. Allergies involve immunoglobulin E antibodies, a part of the body’s immune system. Immunoglobulin E antibodies will bind to an allergen and then transfer to a receptor on mast cells or basophils triggering the release of inflammatory chemicals such as histamine. Based on the increasingly serious problem of environmental change, changes in lifestyle, air pollution problem, and other factors, in this study, we both collect allergens and non-allergens from several databases and use several machine learning methods for classification, including logistic regression (LR), stepwise regression, decision tree (DT) and neural networks (NN) to do the model comparison and determine the permutations of allergen amino acid’s sequence.Keywords: allergy, classification, decision tree, logistic regression, machine learning
Procedia PDF Downloads 297394 Ensemble of Deep CNN Architecture for Classifying the Source and Quality of Teff Cereal
Authors: Belayneh Matebie, Michael Melese
Abstract:
The study focuses on addressing the challenges in classifying and ensuring the quality of Eragrostis Teff, a small and round grain that is the smallest cereal grain. Employing a traditional classification method is challenging because of its small size and the similarity of its environmental characteristics. To overcome this, this study employs a machine learning approach to develop a source and quality classification system for Teff cereal. Data is collected from various production areas in the Amhara regions, considering two types of cereal (high and low quality) across eight classes. A total of 5,920 images are collected, with 740 images for each class. Image enhancement techniques, including scaling, data augmentation, histogram equalization, and noise removal, are applied to preprocess the data. Convolutional Neural Network (CNN) is then used to extract relevant features and reduce dimensionality. The dataset is split into 80% for training and 20% for testing. Different classifiers, including FVGG16, FINCV3, QSCTC, EMQSCTC, SVM, and RF, are employed for classification, achieving accuracy rates ranging from 86.91% to 97.72%. The ensemble of FVGG16, FINCV3, and QSCTC using the Max-Voting approach outperforms individual algorithms.Keywords: Teff, ensemble learning, max-voting, CNN, SVM, RF
Procedia PDF Downloads 40393 Application of Data Mining Techniques for Tourism Knowledge Discovery
Authors: Teklu Urgessa, Wookjae Maeng, Joong Seek Lee
Abstract:
Application of five implementations of three data mining classification techniques was experimented for extracting important insights from tourism data. The aim was to find out the best performing algorithm among the compared ones for tourism knowledge discovery. Knowledge discovery process from data was used as a process model. 10-fold cross validation method is used for testing purpose. Various data preprocessing activities were performed to get the final dataset for model building. Classification models of the selected algorithms were built with different scenarios on the preprocessed dataset. The outperformed algorithm tourism dataset was Random Forest (76%) before applying information gain based attribute selection and J48 (C4.5) (75%) after selection of top relevant attributes to the class (target) attribute. In terms of time for model building, attribute selection improves the efficiency of all algorithms. Artificial Neural Network (multilayer perceptron) showed the highest improvement (90%). The rules extracted from the decision tree model are presented, which showed intricate, non-trivial knowledge/insight that would otherwise not be discovered by simple statistical analysis with mediocre accuracy of the machine using classification algorithms.Keywords: classification algorithms, data mining, knowledge discovery, tourism
Procedia PDF Downloads 286392 Use of Computer and Machine Learning in Facial Recognition
Authors: Neha Singh, Ananya Arora
Abstract:
Facial expression measurement plays a crucial role in the identification of emotion. Facial expression plays a key role in psychophysiology, neural bases, and emotional disorder, to name a few. The Facial Action Coding System (FACS) has proven to be the most efficient and widely used of the various systems used to describe facial expressions. Coders can manually code facial expressions with FACS and, by viewing video-recorded facial behaviour at a specified frame rate and slow motion, can decompose into action units (AUs). Action units are the most minor visually discriminable facial movements. FACS explicitly differentiates between facial actions and inferences about what the actions mean. Action units are the fundamental unit of FACS methodology. It is regarded as the standard measure for facial behaviour and finds its application in various fields of study beyond emotion science. These include facial neuromuscular disorders, neuroscience, computer vision, computer graphics and animation, and face encoding for digital processing. This paper discusses the conceptual basis for FACS, a numerical listing of discrete facial movements identified by the system, the system's psychometric evaluation, and the software's recommended training requirements.Keywords: facial action, action units, coding, machine learning
Procedia PDF Downloads 100391 Aspect-Level Sentiment Analysis with Multi-Channel and Graph Convolutional Networks
Authors: Jiajun Wang, Xiaoge Li
Abstract:
The purpose of the aspect-level sentiment analysis task is to identify the sentiment polarity of aspects in a sentence. Currently, most methods mainly focus on using neural networks and attention mechanisms to model the relationship between aspects and context, but they ignore the dependence of words in different ranges in the sentence, resulting in deviation when assigning relationship weight to other words other than aspect words. To solve these problems, we propose a new aspect-level sentiment analysis model that combines a multi-channel convolutional network and graph convolutional network (GCN). Firstly, the context and the degree of association between words are characterized by Long Short-Term Memory (LSTM) and self-attention mechanism. Besides, a multi-channel convolutional network is used to extract the features of words in different ranges. Finally, a convolutional graph network is used to associate the node information of the dependency tree structure. We conduct experiments on four benchmark datasets. The experimental results are compared with those of other models, which shows that our model is better and more effective.Keywords: aspect-level sentiment analysis, attention, multi-channel convolution network, graph convolution network, dependency tree
Procedia PDF Downloads 206390 Operator Optimization Based on Hardware Architecture Alignment Requirements
Authors: Qingqing Gai, Junxing Shen, Yu Luo
Abstract:
Due to the hardware architecture characteristics, some operators tend to acquire better performance if the input/output tensor dimensions are aligned to a certain minimum granularity, such as convolution and deconvolution commonly used in deep learning. Furthermore, if the requirements are not met, the general strategy is to pad with 0 to satisfy the requirements, potentially leading to the under-utilization of the hardware resources. Therefore, for the convolution and deconvolution whose input and output channels do not meet the minimum granularity alignment, we propose to transfer the W-dimensional data to the C-dimension for computation (W2C) to enable the C-dimension to meet the hardware requirements. This scheme also reduces the number of computations in the W-dimension. Although this scheme substantially increases computation, the operator’s speed can improve significantly. It achieves remarkable speedups on multiple hardware accelerators, including Nvidia Tensor cores, Qualcomm digital signal processors (DSPs), and Huawei neural processing units (NPUs). All you need to do is modify the network structure and rearrange the operator weights offline without retraining. At the same time, for some operators, such as the Reducemax, we observe that transferring the Cdimensional data to the W-dimension(C2W) and replacing the Reducemax with the Maxpool can accomplish acceleration under certain circumstances.Keywords: convolution, deconvolution, W2C, C2W, alignment, hardware accelerator
Procedia PDF Downloads 98389 Using Bidirectional Encoder Representations from Transformers to Extract Topic-Independent Sentiment Features for Social Media Bot Detection
Authors: Maryam Heidari, James H. Jones Jr.
Abstract:
Millions of online posts about different topics and products are shared on popular social media platforms. One use of this content is to provide crowd-sourced information about a specific topic, event or product. However, this use raises an important question: what percentage of information available through these services is trustworthy? In particular, might some of this information be generated by a machine, i.e., a bot, instead of a human? Bots can be, and often are, purposely designed to generate enough volume to skew an apparent trend or position on a topic, yet the consumer of such content cannot easily distinguish a bot post from a human post. In this paper, we introduce a model for social media bot detection which uses Bidirectional Encoder Representations from Transformers (Google Bert) for sentiment classification of tweets to identify topic-independent features. Our use of a Natural Language Processing approach to derive topic-independent features for our new bot detection model distinguishes this work from previous bot detection models. We achieve 94\% accuracy classifying the contents of data as generated by a bot or a human, where the most accurate prior work achieved accuracy of 92\%.Keywords: bot detection, natural language processing, neural network, social media
Procedia PDF Downloads 110388 Artificial Intelligence Methods for Returns Expectations in Financial Markets
Authors: Yosra Mefteh Rekik, Younes Boujelbene
Abstract:
We introduce in this paper a new conceptual model representing the stock market dynamics. This model is essentially based on cognitive behavior of the intelligence investors. In order to validate our model, we build an artificial stock market simulation based on agent-oriented methodologies. The proposed simulator is composed of market supervisor agent essentially responsible for executing transactions via an order book and various kinds of investor agents depending to their profile. The purpose of this simulation is to understand the influence of psychological character of an investor and its neighborhood on its decision-making and their impact on the market in terms of price fluctuations. Therefore, the difficulty of the prediction is due to several features: the complexity, the non-linearity and the dynamism of the financial market system, as well as the investor psychology. The Artificial Neural Networks learning mechanism take on the role of traders, who from their futures return expectations and place orders based on their expectations. The results of intensive analysis indicate that the existence of agents having heterogeneous beliefs and preferences has provided a better understanding of price dynamics in the financial market.Keywords: artificial intelligence methods, artificial stock market, behavioral modeling, multi-agent based simulation
Procedia PDF Downloads 440387 Cellulose Acetate Nanofiber Modification for Regulating Astrocyte Activity via Simple Heat Treatment
Authors: Sang-Myung Jung, Jeong Hyun Ju, Gwang Heum Yoon, Hwa Sung Shin
Abstract:
Central nervous system (CNS) consists of neuronal cell and supporting cells. Astrocytes are the most common supporting cells and play roles in metabolism between neurons and blood vessel. For this function, engineered astrocytes have been studied as a therapeutic source for CNS injury. In neural tissue engineering, nanofiber has been suggested as an effective scaffold for providing structure and mechanical properties influencing physiology. Cellulose acetate (CA) has been investigated for material to fabricate scaffold because of its biocompatibility, biodegradability and fine thermal stability. In this research, CA nanofiber was modified via heat treatment and its effect on astrocyte activity was evaluated. Adhesion and viability of astrocyte were increased in proportion to stiffness. Additionally, expression of GFAP, a marker of astrocyte activation, was increased via stiffness of scaffold. This research suggests a simple modification method to change stiffness of CA nanofiber and shows cellular behavior affecting stiffness of three-dimensional scaffold independently. For the results, we highlight that the stiffness is a factor to regulate astrocyte activity.Keywords: astrocyte, cellulose acetate, cell therapy, stiffness of scaffold
Procedia PDF Downloads 473386 Proposing an Architecture for Drug Response Prediction by Integrating Multiomics Data and Utilizing Graph Transformers
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 142385 Automatic Product Identification Based on Deep-Learning Theory in an Assembly Line
Authors: Fidel Lòpez Saca, Carlos Avilés-Cruz, Miguel Magos-Rivera, José Antonio Lara-Chávez
Abstract:
Automated object recognition and identification systems are widely used throughout the world, particularly in assembly lines, where they perform quality control and automatic part selection tasks. This article presents the design and implementation of an object recognition system in an assembly line. The proposed shapes-color recognition system is based on deep learning theory in a specially designed convolutional network architecture. The used methodology involve stages such as: image capturing, color filtering, location of object mass centers, horizontal and vertical object boundaries, and object clipping. Once the objects are cut out, they are sent to a convolutional neural network, which automatically identifies the type of figure. The identification system works in real-time. The implementation was done on a Raspberry Pi 3 system and on a Jetson-Nano device. The proposal is used in an assembly course of bachelor’s degree in industrial engineering. The results presented include studying the efficiency of the recognition and processing time.Keywords: deep-learning, image classification, image identification, industrial engineering.
Procedia PDF Downloads 155384 Quasi-Photon Monte Carlo on Radiative Heat Transfer: An Importance Sampling and Learning Approach
Authors: Utkarsh A. Mishra, Ankit Bansal
Abstract:
At high temperature, radiative heat transfer is the dominant mode of heat transfer. It is governed by various phenomena such as photon emission, absorption, and scattering. The solution of the governing integrodifferential equation of radiative transfer is a complex process, more when the effect of participating medium and wavelength properties are taken into consideration. Although a generic formulation of such radiative transport problem can be modeled for a wide variety of problems with non-gray, non-diffusive surfaces, there is always a trade-off between simplicity and accuracy of the problem. Recently, solutions of complicated mathematical problems with statistical methods based on randomization of naturally occurring phenomena have gained significant importance. Photon bundles with discrete energy can be replicated with random numbers describing the emission, absorption, and scattering processes. Photon Monte Carlo (PMC) is a simple, yet powerful technique, to solve radiative transfer problems in complicated geometries with arbitrary participating medium. The method, on the one hand, increases the accuracy of estimation, and on the other hand, increases the computational cost. The participating media -generally a gas, such as CO₂, CO, and H₂O- present complex emission and absorption spectra. To model the emission/absorption accurately with random numbers requires a weighted sampling as different sections of the spectrum carries different importance. Importance sampling (IS) was implemented to sample random photon of arbitrary wavelength, and the sampled data provided unbiased training of MC estimators for better results. A better replacement to uniform random numbers is using deterministic, quasi-random sequences. Halton, Sobol, and Faure Low-Discrepancy Sequences are used in this study. They possess better space-filling performance than the uniform random number generator and gives rise to a low variance, stable Quasi-Monte Carlo (QMC) estimators with faster convergence. An optimal supervised learning scheme was further considered to reduce the computation costs of the PMC simulation. A one-dimensional plane-parallel slab problem with participating media was formulated. The history of some randomly sampled photon bundles is recorded to train an Artificial Neural Network (ANN), back-propagation model. The flux was calculated using the standard quasi PMC and was considered to be the training target. Results obtained with the proposed model for the one-dimensional problem are compared with the exact analytical and PMC model with the Line by Line (LBL) spectral model. The approximate variance obtained was around 3.14%. Results were analyzed with respect to time and the total flux in both cases. A significant reduction in variance as well a faster rate of convergence was observed in the case of the QMC method over the standard PMC method. However, the results obtained with the ANN method resulted in greater variance (around 25-28%) as compared to the other cases. There is a great scope of machine learning models to help in further reduction of computation cost once trained successfully. Multiple ways of selecting the input data as well as various architectures will be tried such that the concerned environment can be fully addressed to the ANN model. Better results can be achieved in this unexplored domain.Keywords: radiative heat transfer, Monte Carlo Method, pseudo-random numbers, low discrepancy sequences, artificial neural networks
Procedia PDF Downloads 217383 Hydro-Gravimetric Ann Model for Prediction of Groundwater Level
Authors: Jayanta Kumar Ghosh, Swastik Sunil Goriwale, Himangshu Sarkar
Abstract:
Groundwater is one of the most valuable natural resources that society consumes for its domestic, industrial, and agricultural water supply. Its bulk and indiscriminate consumption affects the groundwater resource. Often, it has been found that the groundwater recharge rate is much lower than its demand. Thus, to maintain water and food security, it is necessary to monitor and management of groundwater storage. However, it is challenging to estimate groundwater storage (GWS) by making use of existing hydrological models. To overcome the difficulties, machine learning (ML) models are being introduced for the evaluation of groundwater level (GWL). Thus, the objective of this research work is to develop an ML-based model for the prediction of GWL. This objective has been realized through the development of an artificial neural network (ANN) model based on hydro-gravimetry. The model has been developed using training samples from field observations spread over 8 months. The developed model has been tested for the prediction of GWL in an observation well. The root means square error (RMSE) for the test samples has been found to be 0.390 meters. Thus, it can be concluded that the hydro-gravimetric-based ANN model can be used for the prediction of GWL. However, to improve the accuracy, more hydro-gravimetric parameter/s may be considered and tested in future.Keywords: machine learning, hydro-gravimetry, ground water level, predictive model
Procedia PDF Downloads 120382 An Accurate Brain Tumor Segmentation for High Graded Glioma Using Deep Learning
Authors: Sajeeha Ansar, Asad Ali Safi, Sheikh Ziauddin, Ahmad R. Shahid, Faraz Ahsan
Abstract:
Gliomas are most challenging and aggressive type of tumors which appear in different sizes, locations, and scattered boundaries. CNN is most efficient deep learning approach with outstanding capability of solving image analysis problems. A fully automatic deep learning based 2D-CNN model for brain tumor segmentation is presented in this paper. We used small convolution filters (3 x 3) to make architecture deeper. We increased convolutional layers for efficient learning of complex features from large dataset. We achieved better results by pushing convolutional layers up to 16 layers for HGG model. We achieved reliable and accurate results through fine-tuning among dataset and hyper-parameters. Pre-processing of this model includes generation of brain pipeline, intensity normalization, bias correction and data augmentation. We used the BRATS-2015, and Dice Similarity Coefficient (DSC) is used as performance measure for the evaluation of the proposed method. Our method achieved DSC score of 0.81 for complete, 0.79 for core, 0.80 for enhanced tumor regions. However, these results are comparable with methods already implemented 2D CNN architecture.Keywords: brain tumor segmentation, convolutional neural networks, deep learning, HGG
Procedia PDF Downloads 247381 Tracking Filtering Algorithm Based on ConvLSTM
Authors: Ailing Yang, Penghan Song, Aihua Cai
Abstract:
The nonlinear maneuvering target tracking problem is mainly a state estimation problem when the target motion model is uncertain. Traditional solutions include Kalman filtering based on Bayesian filtering framework and extended Kalman filtering. However, these methods need prior knowledge such as kinematics model and state system distribution, and their performance is poor in state estimation of nonprior complex dynamic systems. Therefore, in view of the problems existing in traditional algorithms, a convolution LSTM target state estimation (SAConvLSTM-SE) algorithm based on Self-Attention memory (SAM) is proposed to learn the historical motion state of the target and the error distribution information measured at the current time. The measured track point data of airborne radar are processed into data sets. After supervised training, the data-driven deep neural network based on SAConvLSTM can directly obtain the target state at the next moment. Through experiments on two different maneuvering targets, we find that the network has stronger robustness and better tracking accuracy than the existing tracking methods.Keywords: maneuvering target, state estimation, Kalman filter, LSTM, self-attention
Procedia PDF Downloads 158380 [Keynote Talk]: Analysis of Intelligent Based Fault Tolerant Capability System for Solar Photovoltaic Energy Conversion
Authors: Albert Alexander Stonier
Abstract:
Due to the fossil fuel exhaustion and environmental pollution, renewable energy sources especially solar photovoltaic system plays a predominant role in providing energy to the consumers. It has been estimated that by 2050 the renewable energy sources will satisfy 50% of the total energy requirement of the world. In this context, the faults in the conversion process require a special attention which is considered as a major problem. A fault which remains even for a few seconds will cause undesirable effects to the system. The presentation comprises of the analysis, causes, effects and mitigation methods of various faults occurring in the entire solar photovoltaic energy conversion process. In order to overcome the faults in the system, an intelligent based artificial neural networks and fuzzy logic are proposed which can significantly mitigate the faults. Hence the presentation intends to find the problem in renewable energy and provides the possible solution to overcome it with simulation and experimental results. The work performed in a 3kWp solar photovoltaic plant whose results cites the improvement in reliability, availability, power quality and fault tolerant ability.Keywords: solar photovoltaic, power electronics, power quality, PWM
Procedia PDF Downloads 273379 Spontaneous and Posed Smile Detection: Deep Learning, Traditional Machine Learning, and Human Performance
Authors: Liang Wang, Beste F. Yuksel, David Guy Brizan
Abstract:
A computational model of affect that can distinguish between spontaneous and posed smiles with no errors on a large, popular data set using deep learning techniques is presented in this paper. A Long Short-Term Memory (LSTM) classifier, a type of Recurrent Neural Network, is utilized and compared to human classification. Results showed that while human classification (mean of 0.7133) was above chance, the LSTM model was more accurate than human classification and other comparable state-of-the-art systems. Additionally, a high accuracy rate was maintained with small amounts of training videos (70 instances). The derivation of important features to further understand the success of our computational model were analyzed, and it was inferred that thousands of pairs of points within the eyes and mouth are important throughout all time segments in a smile. This suggests that distinguishing between a posed and spontaneous smile is a complex task, one which may account for the difficulty and lower accuracy of human classification compared to machine learning models.Keywords: affective computing, affect detection, computer vision, deep learning, human-computer interaction, machine learning, posed smile detection, spontaneous smile detection
Procedia PDF Downloads 120378 A Different Approach to Smart Phone-Based Wheat Disease Detection System Using Deep Learning for Ethiopia
Authors: Nathenal Thomas Lambamo
Abstract:
Based on the fact that more than 85% of the labor force and 90% of the export earnings are taken by agriculture in Ethiopia and it can be said that it is the backbone of the overall socio-economic activities in the country. Among the cereal crops that the agriculture sector provides for the country, wheat is the third-ranking one preceding teff and maize. In the present day, wheat is in higher demand related to the expansion of industries that use them as the main ingredient for their products. The local supply of wheat for these companies covers only 35 to 40% and the rest 60 to 65% percent is imported on behalf of potential customers that exhaust the country’s foreign currency reserves. The above facts show that the need for this crop in the country is too high and in reverse, the productivity of the crop is very less because of these reasons. Wheat disease is the most devastating disease that contributes a lot to this unbalance in the demand and supply status of the crop. It reduces both the yield and quality of the crop by 27% on average and up to 37% when it is severe. This study aims to detect the most frequent and degrading wheat diseases, Septoria and Leaf rust, using the most efficiently used subset of machine learning technology, deep learning. As a state of the art, a deep learning class classification technique called Convolutional Neural Network (CNN) has been used to detect diseases and has an accuracy of 99.01% is achieved.Keywords: septoria, leaf rust, deep learning, CNN
Procedia PDF Downloads 70377 Comparing the Detection of Autism Spectrum Disorder within Males and Females Using Machine Learning Techniques
Authors: Joseph Wolff, Jeffrey Eilbott
Abstract:
Autism Spectrum Disorders (ASD) are a spectrum of social disorders characterized by deficits in social communication, verbal ability, and interaction that can vary in severity. In recent years, researchers have used magnetic resonance imaging (MRI) to help detect how neural patterns in individuals with ASD differ from those of neurotypical (NT) controls for classification purposes. This study analyzed the classification of ASD within males and females using functional MRI data. Functional connectivity (FC) correlations among brain regions were used as feature inputs for machine learning algorithms. Analysis was performed on 558 cases from the Autism Brain Imaging Data Exchange (ABIDE) I dataset. When trained specifically on females, the algorithm underperformed in classifying the ASD subset of our testing population. Although the subject size was relatively smaller in the female group, the manual matching of both male and female training groups helps explain the algorithm’s bias, indicating the altered sex abnormalities in functional brain networks compared to typically developing peers. These results highlight the importance of taking sex into account when considering how generalizations of findings on males with ASD apply to females.Keywords: autism spectrum disorder, machine learning, neuroimaging, sex differences
Procedia PDF Downloads 204376 Toward an Understanding of the Neurofunctional Dissociation between Animal and Tool Concepts: A Graph Theoretical Analysis
Authors: Skiker Kaoutar, Mounir Maouene
Abstract:
Neuroimaging studies have shown that animal and tool concepts rely on distinct networks of brain areas. Animal concepts depend predominantly on temporal areas while tool concepts rely on fronto-temporo-parietal areas. However, the origin of this neurofunctional distinction for processing animal and tool concepts remains still unclear. Here, we address this question from a network perspective suggesting that the neural distinction between animals and tools might reflect the differences in their structural semantic networks. We build semantic networks for animal and tool concepts derived from Mc Rae and colleagues’s behavioral study conducted on a large number of participants. These two networks are thus analyzed through a large number of graph theoretical measures for small-worldness: centrality, clustering coefficient, average shortest path length, as well as resistance to random and targeted attacks. The results indicate that both animal and tool networks have small-world properties. More importantly, the animal network is more vulnerable to targeted attacks compared to the tool network a result that correlates with brain lesions studies.Keywords: animals, tools, network, semantics, small-world, resilience to damage
Procedia PDF Downloads 538