Search results for: feed forward neural network
6851 Hyperspectral Band Selection for Oil Spill Detection Using Deep Neural Network
Authors: Asmau Mukhtar Ahmed, Olga Duran
Abstract:
Hydrocarbon (HC) spills constitute a significant problem that causes great concern to the environment. With the latest technology (hyperspectral images) and state of the earth techniques (image processing tools), hydrocarbon spills can easily be detected at an early stage to mitigate the effects caused by such menace. In this study; a controlled laboratory experiment was used, and clay soil was mixed and homogenized with different hydrocarbon types (diesel, bio-diesel, and petrol). The different mixtures were scanned with HYSPEX hyperspectral camera under constant illumination to generate the hypersectral datasets used for this experiment. So far, the Short Wave Infrared Region (SWIR) has been exploited in detecting HC spills with excellent accuracy. However, the Near-Infrared Region (NIR) is somewhat unexplored with regards to HC contamination and how it affects the spectrum of soils. In this study, Deep Neural Network (DNN) was applied to the controlled datasets to detect and quantify the amount of HC spills in soils in the Near-Infrared Region. The initial results are extremely encouraging because it indicates that the DNN was able to identify features of HC in the Near-Infrared Region with a good level of accuracy.Keywords: hydrocarbon, Deep Neural Network, short wave infrared region, near-infrared region, hyperspectral image
Procedia PDF Downloads 1066850 Optimal Tracking Control of a Hydroelectric Power Plant Incorporating Neural Forecasting for Uncertain Input Disturbances
Authors: Marlene Perez Villalpando, Kelly Joel Gurubel Tun
Abstract:
In this paper, we propose an optimal control strategy for a hydroelectric power plant subject to input disturbances like meteorological phenomena. The engineering characteristics of the system are described by a nonlinear model. The random availability of renewable sources is predicted by a high-order neural network trained with an extended Kalman filter, whereas the power generation is regulated by the optimal control law. The main advantage of the system is the stabilization of the amount of power generated in the plant. A control supervisor maintains stability and availability in hydropower reservoirs water levels for power generation. The proposed approach demonstrated a good performance to stabilize the reservoir level and the power generation along their desired trajectories in the presence of disturbances.Keywords: hydropower, high order neural network, Kalman filter, optimal control
Procedia PDF Downloads 2926849 Design of a Cooperative Neural Network, Particle Swarm Optimization (PSO) and Fuzzy Based Tracking Control for a Tilt Rotor Unmanned Aerial Vehicle
Authors: Mostafa Mjahed
Abstract:
Tilt Rotor UAVs (Unmanned Aerial Vehicles) are naturally unstable and difficult to maneuver. The purpose of this paper is to design controllers for the stabilization and trajectory tracking of this type of UAV. To this end, artificial intelligence methods have been exploited. First, the dynamics of this UAV was modeled using the Lagrange-Euler method. The conventional method based on Proportional, Integral and Derivative (PID) control was applied by decoupling the different flight modes. To improve stability and trajectory tracking of the Tilt Rotor, the fuzzy approach and the technique of multilayer neural networks (NN) has been used. Thus, Fuzzy Proportional Integral and Derivative (FPID) and Neural Network-based Proportional Integral and Derivative controllers (NNPID) have been developed. The meta-heuristic approach based on Particle Swarm Optimization (PSO) method allowed adjusting the setting parameters of NNPID controller, giving us an improved NNPID-PSO controller. Simulation results under the Matlab environment show the efficiency of the approaches adopted. Besides, the Tilt Rotor UAV has become stable and follows different types of trajectories with acceptable precision. The Fuzzy, NN and NN-PSO-based approaches demonstrated their robustness because the presence of the disturbances did not alter the stability or the trajectory tracking of the Tilt Rotor UAV.Keywords: neural network, fuzzy logic, PSO, PID, trajectory tracking, tilt-rotor UAV
Procedia PDF Downloads 1136848 Massively-Parallel Bit-Serial Neural Networks for Fast Epilepsy Diagnosis: A Feasibility Study
Authors: Si Mon Kueh, Tom J. Kazmierski
Abstract:
There are about 1% of the world population suffering from the hidden disability known as epilepsy and major developing countries are not fully equipped to counter this problem. In order to reduce the inconvenience and danger of epilepsy, different methods have been researched by using a artificial neural network (ANN) classification to distinguish epileptic waveforms from normal brain waveforms. This paper outlines the aim of achieving massive ANN parallelization through a dedicated hardware using bit-serial processing. The design of this bit-serial Neural Processing Element (NPE) is presented which implements the functionality of a complete neuron using variable accuracy. The proposed design has been tested taking into consideration non-idealities of a hardware ANN. The NPE consists of a bit-serial multiplier which uses only 16 logic elements on an Altera Cyclone IV FPGA and a bit-serial ALU as well as a look-up table. Arrays of NPEs can be driven by a single controller which executes the neural processing algorithm. In conclusion, the proposed compact NPE design allows the construction of complex hardware ANNs that can be implemented in a portable equipment that suits the needs of a single epileptic patient in his or her daily activities to predict the occurrences of impending tonic conic seizures.Keywords: Artificial Neural Networks (ANN), bit-serial neural processor, FPGA, Neural Processing Element (NPE)
Procedia PDF Downloads 3166847 A Neural Network System for Predicting the Hardness of Titanium Aluminum Nitrite (TiAlN) Coatings
Authors: Omar M. Elmabrouk
Abstract:
The cutting tool, in the high-speed machining process, is consistently dealing with high localized stress at the tool tip, tip temperature exceeds 800°C and the chip slides along the rake face. These conditions are affecting the tool wear, the cutting tool performances, the quality of the produced parts and the tool life. Therefore, a thin film coating on the cutting tool should be considered to improve the tool surface properties while maintaining its bulks properties. One of the general coating processes in applying thin film for hard coating purpose is PVD magnetron sputtering. In this paper, the prediction of the effects of PVD magnetron sputtering coating process parameters, sputter power in the range of (4.81-7.19 kW), bias voltage in the range of (50.00-300.00 Volts) and substrate temperature in the range of (281.08-600.00 °C), were studied using artificial neural network (ANN). The results were compared with previously published results using RSM model. It was found that the ANN is more accurate in prediction of tool hardness, and hence, it will not only improve the tool life of the tool but also significantly enhances the efficiency of the machining processes.Keywords: artificial neural network, hardness, prediction, titanium aluminium nitrate coating
Procedia PDF Downloads 5506846 A Survey of Field Programmable Gate Array-Based Convolutional Neural Network Accelerators
Authors: Wei Zhang
Abstract:
With the rapid development of deep learning, neural network and deep learning algorithms play a significant role in various practical applications. Due to the high accuracy and good performance, Convolutional Neural Networks (CNNs) especially have become a research hot spot in the past few years. However, the size of the networks becomes increasingly large scale due to the demands of the practical applications, which poses a significant challenge to construct a high-performance implementation of deep learning neural networks. Meanwhile, many of these application scenarios also have strict requirements on the performance and low-power consumption of hardware devices. Therefore, it is particularly critical to choose a moderate computing platform for hardware acceleration of CNNs. This article aimed to survey the recent advance in Field Programmable Gate Array (FPGA)-based acceleration of CNNs. Various designs and implementations of the accelerator based on FPGA under different devices and network models are overviewed, and the versions of Graphic Processing Units (GPUs), Application Specific Integrated Circuits (ASICs) and Digital Signal Processors (DSPs) are compared to present our own critical analysis and comments. Finally, we give a discussion on different perspectives of these acceleration and optimization methods on FPGA platforms to further explore the opportunities and challenges for future research. More helpfully, we give a prospect for future development of the FPGA-based accelerator.Keywords: deep learning, field programmable gate array, FPGA, hardware accelerator, convolutional neural networks, CNN
Procedia PDF Downloads 1196845 Nonlinear Modeling of the PEMFC Based on NNARX Approach
Authors: Shan-Jen Cheng, Te-Jen Chang, Kuang-Hsiung Tan, Shou-Ling Kuo
Abstract:
Polymer Electrolyte Membrane Fuel Cell (PEMFC) is such a time-vary nonlinear dynamic system. The traditional linear modeling approach is hard to estimate structure correctly of PEMFC system. From this reason, this paper presents a nonlinear modeling of the PEMFC using Neural Network Auto-regressive model with eXogenous inputs (NNARX) approach. The multilayer perception (MLP) network is applied to evaluate the structure of the NNARX model of PEMFC. The validity and accuracy of NNARX model are tested by one step ahead relating output voltage to input current from measured experimental of PEMFC. The results show that the obtained nonlinear NNARX model can efficiently approximate the dynamic mode of the PEMFC and model output and system measured output consistently.Keywords: PEMFC, neural network, nonlinear modeling, NNARX
Procedia PDF Downloads 3726844 Artificial Neural Network Based Approach for Estimation of Individual Vehicle Speed under Mixed Traffic Condition
Authors: Subhadip Biswas, Shivendra Maurya, Satish Chandra, Indrajit Ghosh
Abstract:
Developing speed model is a challenging task particularly under mixed traffic condition where the traffic composition plays a significant role in determining vehicular speed. The present research has been conducted to model individual vehicular speed in the context of mixed traffic on an urban arterial. Traffic speed and volume data have been collected from three midblock arterial road sections in New Delhi. Using the field data, a volume based speed prediction model has been developed adopting the methodology of Artificial Neural Network (ANN). The model developed in this work is capable of estimating speed for individual vehicle category. Validation results show a great deal of agreement between the observed speeds and the predicted values by the model developed. Also, it has been observed that the ANN based model performs better compared to other existing models in terms of accuracy. Finally, the sensitivity analysis has been performed utilizing the model in order to examine the effects of traffic volume and its composition on individual speeds.Keywords: speed model, artificial neural network, arterial, mixed traffic
Procedia PDF Downloads 3806843 The Use of Layered Neural Networks for Classifying Hierarchical Scientific Fields of Study
Authors: Colin Smith, Linsey S Passarella
Abstract:
Due to the proliferation and decentralized nature of academic publication, no widely accepted scheme exists for organizing papers by their scientific field of study (FoS) to the author’s best knowledge. While many academic journals require author provided keywords for papers, these keywords range wildly in scope and are not consistent across papers, journals, or field domains, necessitating alternative approaches to paper classification. Past attempts to perform field-of-study (FoS) classification on scientific texts have largely used a-hierarchical FoS schemas or ignored the schema’s inherently hierarchical structure, e.g. by compressing the structure into a single layer for multi-label classification. In this paper, we introduce an application of a Layered Neural Network (LNN) to the problem of performing supervised hierarchical classification of scientific fields of study (FoS) on research papers. In this approach, paper embeddings from a pretrained language model are fed into a top-down LNN. Beginning with a single neural network (NN) for the highest layer of the class hierarchy, each node uses a separate local NN to classify the subsequent subfield child node(s) for an input embedding of concatenated paper titles and abstracts. We compare our LNN-FOS method to other recent machine learning methods using the Microsoft Academic Graph (MAG) FoS hierarchy and find that the LNN-FOS offers increased classification accuracy at each FoS hierarchical level.Keywords: hierarchical classification, layer neural network, scientific field of study, scientific taxonomy
Procedia PDF Downloads 1256842 A New Approach to Predicting Physical Biometrics from Behavioural Biometrics
Authors: Raid R. O. Al-Nima, S. S. Dlay, W. L. Woo
Abstract:
A relationship between face and signature biometrics is established in this paper. A new approach is developed to predict faces from signatures by using artificial intelligence. A multilayer perceptron (MLP) neural network is used to generate face details from features extracted from signatures, here face is the physical biometric and signatures is the behavioural biometric. The new method establishes a relationship between the two biometrics and regenerates a visible face image from the signature features. Furthermore, the performance efficiencies of our new technique are demonstrated in terms of minimum error rates compared to published work.Keywords: behavioural biometric, face biometric, neural network, physical biometric, signature biometric
Procedia PDF Downloads 4696841 Emotion Classification Using Recurrent Neural Network and Scalable Pattern Mining
Authors: Jaishree Ranganathan, MuthuPriya Shanmugakani Velsamy, Shamika Kulkarni, Angelina Tzacheva
Abstract:
Emotions play an important role in everyday life. An-alyzing these emotions or feelings from social media platforms like Twitter, Facebook, blogs, and forums based on user comments and reviews plays an important role in various factors. Some of them include brand monitoring, marketing strategies, reputation, and competitor analysis. The opinions or sentiments mined from such data helps understand the current state of the user. It does not directly provide intuitive insights on what actions to be taken to benefit the end user or business. Actionable Pattern Mining method provides suggestions or actionable recommendations on what changes or actions need to be taken in order to benefit the end user. In this paper, we propose automatic classification of emotions in Twitter data using Recurrent Neural Network - Gated Recurrent Unit. We achieve training accuracy of 87.58% and validation accuracy of 86.16%. Also, we extract action rules with respect to the user emotion that helps to provide actionable suggestion.Keywords: emotion mining, twitter, recurrent neural network, gated recurrent unit, actionable pattern mining
Procedia PDF Downloads 1596840 An Ensemble-based Method for Vehicle Color Recognition
Authors: Saeedeh Barzegar Khalilsaraei, Manoocheher Kelarestaghi, Farshad Eshghi
Abstract:
The vehicle color, as a prominent and stable feature, helps to identify a vehicle more accurately. As a result, vehicle color recognition is of great importance in intelligent transportation systems. Unlike conventional methods which use only a single Convolutional Neural Network (CNN) for feature extraction or classification, in this paper, four CNNs, with different architectures well-performing in different classes, are trained to extract various features from the input image. To take advantage of the distinct capability of each network, the multiple outputs are combined using a stack generalization algorithm as an ensemble technique. As a result, the final model performs better than each CNN individually in vehicle color identification. The evaluation results in terms of overall average accuracy and accuracy variance show the proposed method’s outperformance compared to the state-of-the-art rivals.Keywords: Vehicle Color Recognition, Ensemble Algorithm, Stack Generalization, Convolutional Neural Network
Procedia PDF Downloads 756839 Cost Effective and Efficient Feeding: A Way Forward for Sustainable and Profitable Aquaculture
Authors: Pawan Kumar Sharma, J. Stephan Sampath Kumar, S. Anand, Chandana B. L.
Abstract:
Protein is the major component for the success in culture of shrimp and fishes. Apparently, excess dietary protein is undesirable, as it not only enhances the production cost but also leads to water quality deterioration. A field survey was conducted with aqua farmers of Kerala, India, a leading state in coastal aquaculture, to assess the role of protein component in feed that can be efficiently and effectively managed for sustainable aquaculture. The study showed an average feed amount of 13.55 ± 2.16 tonnes per hectare was being used by the farmers of Kerala. The average feed cost percentage of Rs. 57.76 ± 13.46 /kg was invested for an average protein level of 36.26 % ± 0.082 in the feed and Rs.78.95 ± 3.086 per kilogram of feed was being paid by the farmers. Study revealed that replacement of fish meal and fish oil within shrimp aquafeeds with alternative protein, and lipid sources can only be achieved if changes are made in the basic shrimp culturing practices, such as closed farming system through water recycling or zero-water exchange, and by maximizing in-situ, floc and natural food production within the culture system. The upshot of such production systems is that imports of high-quality feed ingredients and aqua feeds can eventually be eliminated, and the utilization of locally available feed ingredients from agricultural by-products can be greatly improved and maximized. The promotion of closed shrimp production systems would also greatly reduce water use and increase shrimp production per unit area but would necessitate the continuous provision of electricity for aeration during production. Alternative energy sources such as solar power might be used, and resource poor farming communities should also explore wind energy for use. The study concluded that farm made feed and closed farming systems are essential for the sustainability and profitability of the aquaculture industry.Keywords: aqua feeds, floc, fish meal, protein, zero-water exchange
Procedia PDF Downloads 1386838 An Algorithm for Determining the Arrival Behavior of a Secondary User to a Base Station in Cognitive Radio Networks
Authors: Danilo López, Edwin Rivas, Leyla López
Abstract:
This paper presents the development of an algorithm that predicts the arrival of a secondary user (SU) to a base station (BS) in a cognitive network based on infrastructure, requesting a Best Effort (BE) or Real Time (RT) type of service with a determined bandwidth (BW) implementing neural networks. The algorithm dynamically uses a neural network construction technique using the geometric pyramid topology and trains a Multilayer Perceptron Neural Networks (MLPNN) based on the historical arrival of an SU to estimate future applications. This will allow efficiently managing the information in the BS, since it precedes the arrival of the SUs in the stage of selection of the best channel in CRN. As a result, the software application determines the probability of arrival at a future time point and calculates the performance metrics to measure the effectiveness of the predictions made.Keywords: cognitive radio, base station, best effort, MLPNN, prediction, real time
Procedia PDF Downloads 3226837 Leveraging the Power of Dual Spatial-Temporal Data Scheme for Traffic Prediction
Authors: Yang Zhou, Heli Sun, Jianbin Huang, Jizhong Zhao, Shaojie Qiao
Abstract:
Traffic prediction is a fundamental problem in urban environment, facilitating the smart management of various businesses, such as taxi dispatching, bike relocation, and stampede alert. Most earlier methods rely on identifying the intrinsic spatial-temporal correlation to forecast. However, the complex nature of this problem entails a more sophisticated solution that can simultaneously capture the mutual influence of both adjacent and far-flung areas, with the information of time-dimension also incorporated seamlessly. To tackle this difficulty, we propose a new multi-phase architecture, DSTDS (Dual Spatial-Temporal Data Scheme for traffic prediction), that aims to reveal the underlying relationship that determines future traffic trend. First, a graph-based neural network with an attention mechanism is devised to obtain the static features of the road network. Then, a multi-granularity recurrent neural network is built in conjunction with the knowledge from a grid-based model. Subsequently, the preceding output is fed into a spatial-temporal super-resolution module. With this 3-phase structure, we carry out extensive experiments on several real-world datasets to demonstrate the effectiveness of our approach, which surpasses several state-of-the-art methods.Keywords: traffic prediction, spatial-temporal, recurrent neural network, dual data scheme
Procedia PDF Downloads 1106836 Growth Performance, Survival Rate and Feed Efficacy of Climbing Perch, Anabas testudineus, Feed Experimental Diet with Several Dosages of Papain Enzyme
Authors: Zainal A. Muchlisin, Muhammad Iqbal, Abdullah A. Muhammadar
Abstract:
The objective of the present study was to determine the optimum dose of papain enzyme in the diet for growing, survival rate and feed efficacy of climbing perch (Anabas testudineus). The study was conducted at the Laboratory of Aquatic of Faculty of Veterinary, Syiah Kuala University from January to March 2016. The completely randomized design was used in this study. Six dosages level of papain enzyme were tested with 4 replications i.e. 0 g kg-1 of feed, 20.0 g kg-1 feed, 22.5 g kg-1 of feed, 25.0 g kg-1 of feed, 27.5 g kg-1 of feed, and 30.0 g kg-1 of feed. The experimental fish fed twice a day at feeding level of 5% for 60 days. The results showed that weight gain ranged from 2.41g to 7.37g, total length gain ranged from 0.67cm to 3.17cm, specific growth rate ranged from 1.46 % day to 3.41% day, daily growth rate ranged from 0.04 g day to 0.13 g day, feed conversion ratio ranged from 1.94 to 3.59, feed efficiency ranged from 27.99% to 51.37%, protein retention ranged from 3.38% to 28.28%, protein digestibility ranged from 50.63% to 90.38%, and survival rate ranged from 88.89% to 100%. The highest rate for all parameters was found in the dosage of 3.00% papain enzyme kg feed. The ANOVA test showed that enzyme papain gave a significant effect on the weight gain, total length gain, daily growth rate, specific growth rate, feed conversion ratio, feed efficiency, protein retention, protein digestibility, and survival rate of the climbing perch (Anabas testudieus). The best enzyme papain dosage was 3.0%.Keywords: betok, feed conversion ratio, freshwater fish, nutrition, feeding
Procedia PDF Downloads 2306835 An Event Relationship Extraction Method Incorporating Deep Feedback Recurrent Neural Network and Bidirectional Long Short-Term Memory
Authors: Yin Yuanling
Abstract:
A Deep Feedback Recurrent Neural Network (DFRNN) and Bidirectional Long Short-Term Memory (BiLSTM) are designed to address the problem of low accuracy of traditional relationship extraction models. This method combines a deep feedback-based recurrent neural network (DFRNN) with a bi-directional long short-term memory (BiLSTM) approach. The method combines DFRNN, which extracts local features of text based on deep feedback recurrent mechanism, BiLSTM, which better extracts global features of text, and Self-Attention, which extracts semantic information. Experiments show that the method achieves an F1 value of 76.69% on the CEC dataset, which is 0.0652 better than the BiLSTM+Self-ATT model, thus optimizing the performance of the deep learning method in the event relationship extraction task.Keywords: event relations, deep learning, DFRNN models, bi-directional long and short-term memory networks
Procedia PDF Downloads 1356834 Oil Reservoir Asphalting Precipitation Estimating during CO2 Injection
Authors: I. Alhajri, G. Zahedi, R. Alazmi, A. Akbari
Abstract:
In this paper, an Artificial Neural Network (ANN) was developed to predict Asphaltene Precipitation (AP) during the injection of carbon dioxide into crude oil reservoirs. In this study, the experimental data from six different oil fields were collected. Seventy percent of the data was used to develop the ANN model, and different ANN architectures were examined. A network with the Trainlm training algorithm was found to be the best network to estimate the AP. To check the validity of the proposed model, the model was used to predict the AP for the thirty percent of the data that was unevaluated. The Mean Square Error (MSE) of the prediction was 0.0018, which confirms the excellent prediction capability of the proposed model. In the second part of this study, the ANN model predictions were compared with modified Hirschberg model predictions. The ANN was found to provide more accurate estimates compared to the modified Hirschberg model. Finally, the proposed model was employed to examine the effect of different operating parameters during gas injection on the AP. It was found that the AP is mostly sensitive to the reservoir temperature. Furthermore, the carbon dioxide concentration in liquid phase increases the AP.Keywords: artificial neural network, asphaltene, CO2 injection, Hirschberg model, oil reservoirs
Procedia PDF Downloads 3626833 Can the Intervention of SCAMPER Bring about Changes of Neural Activation While Taking Creativity Tasks?
Authors: Yu-Chu Yeh, WeiChin Hsu, Chih-Yen Chang
Abstract:
Substitution, combination, modification, putting to other uses, elimination, and rearrangement (SCAMPER) has been regarded as an effective technique that provides a structured way to help people to produce creative ideas and solutions. Although some neuroscience studies regarding creativity training have been conducted, no study has focused on SCAMPER. This study therefore aimed at examining whether the learning of SCAMPER through video tutorials would result in alternations of neural activation. Thirty college students were randomly assigned to the experimental group or the control group. The experimental group was requested to watch SCAMPER videos, whereas the control group was asked to watch natural-scene videos which were regarded as neutral stimulating materials. Each participant was brain scanned in a Functional magnetic resonance imaging (fMRI) machine while undertaking a creativity test before and after watching the videos. Furthermore, a two-way ANOVA was used to analyze the interaction between groups (the experimental group; the control group) and tasks (C task; M task; X task). The results revealed that the left precuneus significantly activated in the interaction of groups and tasks, as well as in the main effect of group. Furthermore, compared with the control group, the experimental group had greater activation in the default mode network (left precuneus and left inferior parietal cortex) and the motor network (left postcentral gyrus and left supplementary area). The findings suggest that the SCAMPER training may facilitate creativity through the stimulation of the default mode network and the motor network.Keywords: creativity, default mode network, neural activation, SCAMPER
Procedia PDF Downloads 976832 The Effect of the Earthworm (Lumbricus rubellus) as the Source of Protein Feed and Pathogen Antibacterial for Broiler
Authors: Waode Nurmayani, Nikmatul Riswanda
Abstract:
Broilers are chickens which are kept with the most efficient time and hoped get a good body weight. All things are done, for example with the improvement of feed and use antibiotics. Feed cost is the most cost to be spent. Nearly 80% of the cost is spent just for buy feed. Earthworm (Lumbricus rubellus) is a good choice to reduce the cost of feed protein source. The Earthworm has a high crude protein content of about 48.5%-61.9%, rich with proline amino acid about 15% of the 62 amino acids. Not only about protein, this earthworm also has a role in disease prevention. Prevention of disease in livestock usual with use feed supplement. Earthworm (Lumbricus rubellus) is one of the natural materials used as feed. In addition, several types of earthworms that have been known to contain active substances about antibacterial pathogens namely Lumbricus rubellus. The earthworm could be used as an antibiotic because it contain the antibody of Lumbricine active substance. So that, this animal feed from Lumbricus rubellus could improve the performance of broilers. Bioactive of anti-bacterial is called Lumbricine able to inhibit the growth of pathogenic bacteria in the intestinal wall so that the population of pathogenic bacteria is reduced. The method of write in this scientific writing is divided into 3 techniques, namely data completion, data analysis, and thinking pan from various literature about earthworm (Lumbricus rubellus) as broiler feed. It is expected that innovation of feed material of earthworm (Lumbricus rubellus) could reduce the cost of protein feed and the use of chemical antibiotics.Keywords: earthworm, broiler, protein, antibiotic
Procedia PDF Downloads 1496831 A Research About to Determination the Quality of Feed Oils Used as Mixedfeed Raw Material from Some Feed Factories in Konya-Turkey
Authors: Gülşah Kanbur, Veysel Ayhan
Abstract:
Feed oil samples which are used as mixed feed raw material were taken from six different feed factories in March, May and July. All factories make production in Konya, Turkey and all of the samples were which taken are crude soybean oil. Some physical and chemical analysis, free radical scavenger effect and total phenol content were determined on these oil samples. Moisture content was found between 0.10-22.23 %, saponification number was determined 143.13 to 167.93 KOH/kg, free fatty acidity was varied 0.73 to 35.00 % , peroxide value was found between 1.53 and 28.43 meq/kg , unsaponifiable matter was determined from 0.40 to 17.10 % , viscosity was found between 34.30 and 625.67 mPas, sediment amount was determined between 0.60-18.16 % , free radical scavenger effect was varied 20.7 to 43.04 % inhibition of the extract and total phenol content was found between 1.20 and 2.69 mg/L extract. Different results were found between months and factories.Keywords: crude soybean oil, feed oils, mixed feed, Konya
Procedia PDF Downloads 3066830 A Survey of Skin Cancer Detection and Classification from Skin Lesion Images Using Deep Learning
Authors: Joseph George, Anne Kotteswara Roa
Abstract:
Skin disease is one of the most common and popular kinds of health issues faced by people nowadays. Skin cancer (SC) is one among them, and its detection relies on the skin biopsy outputs and the expertise of the doctors, but it consumes more time and some inaccurate results. At the early stage, skin cancer detection is a challenging task, and it easily spreads to the whole body and leads to an increase in the mortality rate. Skin cancer is curable when it is detected at an early stage. In order to classify correct and accurate skin cancer, the critical task is skin cancer identification and classification, and it is more based on the cancer disease features such as shape, size, color, symmetry and etc. More similar characteristics are present in many skin diseases; hence it makes it a challenging issue to select important features from a skin cancer dataset images. Hence, the skin cancer diagnostic accuracy is improved by requiring an automated skin cancer detection and classification framework; thereby, the human expert’s scarcity is handled. Recently, the deep learning techniques like Convolutional neural network (CNN), Deep belief neural network (DBN), Artificial neural network (ANN), Recurrent neural network (RNN), and Long and short term memory (LSTM) have been widely used for the identification and classification of skin cancers. This survey reviews different DL techniques for skin cancer identification and classification. The performance metrics such as precision, recall, accuracy, sensitivity, specificity, and F-measures are used to evaluate the effectiveness of SC identification using DL techniques. By using these DL techniques, the classification accuracy increases along with the mitigation of computational complexities and time consumption.Keywords: skin cancer, deep learning, performance measures, accuracy, datasets
Procedia PDF Downloads 1226829 Multi-Stream Graph Attention Network for Recommendation with Knowledge Graph
Abstract:
In recent years, Graph neural network has been widely used in knowledge graph recommendation. The existing recommendation methods based on graph neural network extract information from knowledge graph through entity and relation, which may not be efficient in the way of information extraction. In order to better propose useful entity information for the current recommendation task in the knowledge graph, we propose an end-to-end Neural network Model based on multi-stream graph attentional Mechanism (MSGAT), which can effectively integrate the knowledge graph into the recommendation system by evaluating the importance of entities from both users and items. Specifically, we use the attention mechanism from the user's perspective to distil the domain nodes information of the predicted item in the knowledge graph, to enhance the user's information on items, and generate the feature representation of the predicted item. Due to user history, click items can reflect the user's interest distribution, we propose a multi-stream attention mechanism, based on the user's preference for entities and relationships, and the similarity between items to be predicted and entities, aggregate user history click item's neighborhood entity information in the knowledge graph and generate the user's feature representation. We evaluate our model on three real recommendation datasets: Movielens-1M (ML-1M), LFM-1B 2015 (LFM-1B), and Amazon-Book (AZ-book). Experimental results show that compared with the most advanced models, our proposed model can better capture the entity information in the knowledge graph, which proves the validity and accuracy of the model.Keywords: graph attention network, knowledge graph, recommendation, information propagation
Procedia PDF Downloads 1096828 A Neural Network Model to Simulate Urban Air Temperatures in Toulouse, France
Authors: Hiba Hamdi, Thomas Corpetti, Laure Roupioz, Xavier Briottet
Abstract:
Air temperatures are generally higher in cities than in their rural surroundings. The overheating of cities is a direct consequence of increasing urbanization, characterized by the artificial filling of soils, the release of anthropogenic heat, and the complexity of urban geometry. This phenomenon, referred to as urban heat island (UHI), is more prevalent during heat waves, which have increased in frequency and intensity in recent years. In the context of global warming and urban population growth, helping urban planners implement UHI mitigation and adaptation strategies is critical. In practice, the study of UHI requires air temperature information at the street canyon level, which is difficult to obtain. Many urban air temperature simulation models have been proposed (mostly based on physics or statistics), all of which require a variety of input parameters related to urban morphology, land use, material properties, or meteorological conditions. In this paper, we build and evaluate a neural network model based on Urban Weather Generator (UWG) model simulations and data from meteorological stations that simulate air temperature over Toulouse, France, on days favourable to UHI.Keywords: air temperature, neural network model, urban heat island, urban weather generator
Procedia PDF Downloads 796827 A Prediction Model for Dynamic Responses of Building from Earthquake Based on Evolutionary Learning
Authors: Kyu Jin Kim, Byung Kwan Oh, Hyo Seon Park
Abstract:
The seismic responses-based structural health monitoring system has been performed to prevent seismic damage. Structural seismic damage of building is caused by the instantaneous stress concentration which is related with dynamic characteristic of earthquake. Meanwhile, seismic response analysis to estimate the dynamic responses of building demands significantly high computational cost. To prevent the failure of structural members from the characteristic of the earthquake and the significantly high computational cost for seismic response analysis, this paper presents an artificial neural network (ANN) based prediction model for dynamic responses of building considering specific time length. Through the measured dynamic responses, input and output node of the ANN are formed by the length of specific time, and adopted for the training. In the model, evolutionary radial basis function neural network (ERBFNN), that radial basis function network (RBFN) is integrated with evolutionary optimization algorithm to find variables in RBF, is implemented. The effectiveness of the proposed model is verified through an analytical study applying responses from dynamic analysis for multi-degree of freedom system to training data in ERBFNN.Keywords: structural health monitoring, dynamic response, artificial neural network, radial basis function network, genetic algorithm
Procedia PDF Downloads 2976826 Monitor Student Concentration Levels on Online Education Sessions
Authors: M. K. Wijayarathna, S. M. Buddika Harshanath
Abstract:
Monitoring student engagement has become a crucial part of the educational process and a reliable indicator of the capacity to retain information. As online learning classrooms are now more common these days, students' attention levels have become increasingly important, making it more difficult to check each student's concentration level in an online classroom setting. To profile student attention to various gradients of engagement, a study is a plan to conduct using machine learning models. Using a convolutional neural network, the findings and confidence score of the high accuracy model are obtained. In this research, convolutional neural networks are using to help discover essential emotions that are critical in defining various levels of participation. Students' attention levels were shown to be influenced by emotions such as calm, enjoyment, surprise, and fear. An improved virtual learning system was created as a result of these data, which allowed teachers to focus their support and advise on those students who needed it. Student participation has formed as a crucial component of the learning technique and a consistent predictor of a student's capacity to retain material in the classroom. Convolutional neural networks have a plan to implement the platform. As a preliminary step, a video of the pupil would be taken. In the end, researchers used a convolutional neural network utilizing the Keras toolkit to take pictures of the recordings. Two convolutional neural network methods are planned to use to determine the pupils' attention level. Finally, those predicted student attention level results plan to display on the graphical user interface of the System.Keywords: HTML5, JavaScript, Python flask framework, AI, graphical user
Procedia PDF Downloads 916825 Optical Signal-To-Noise Ratio Monitoring Based on Delay Tap Sampling Using Artificial Neural Network
Authors: Feng Wang, Shencheng Ni, Shuying Han, Shanhong You
Abstract:
With the development of optical communication, optical performance monitoring (OPM) has received more and more attentions. Since optical signal-to-noise ratio (OSNR) is directly related to bit error rate (BER), it is one of the important parameters in optical networks. Recently, artificial neural network (ANN) has been greatly developed. ANN has strong learning and generalization ability. In this paper, a method of OSNR monitoring based on delay-tap sampling (DTS) and ANN has been proposed. DTS technique is used to extract the eigenvalues of the signal. Then, the eigenvalues are input into the ANN to realize the OSNR monitoring. The experiments of 10 Gb/s non-return-to-zero (NRZ) on–off keying (OOK), 20 Gb/s pulse amplitude modulation (PAM4) and 20 Gb/s return-to-zero (RZ) differential phase-shift keying (DPSK) systems are demonstrated for the OSNR monitoring based on the proposed method. The experimental results show that the range of OSNR monitoring is from 15 to 30 dB and the root-mean-square errors (RMSEs) for 10 Gb/s NRZ-OOK, 20 Gb/s PAM4 and 20 Gb/s RZ-DPSK systems are 0.36 dB, 0.45 dB and 0.48 dB respectively. The impact of chromatic dispersion (CD) on the accuracy of OSNR monitoring is also investigated in the three experimental systems mentioned above.Keywords: artificial neural network (ANN), chromatic dispersion (CD), delay-tap sampling (DTS), optical signal-to-noise ratio (OSNR)
Procedia PDF Downloads 1086824 Semi-Supervised Learning for Spanish Speech Recognition Using Deep Neural Networks
Authors: B. R. Campomanes-Alvarez, P. Quiros, B. Fernandez
Abstract:
Automatic Speech Recognition (ASR) is a machine-based process of decoding and transcribing oral speech. A typical ASR system receives acoustic input from a speaker or an audio file, analyzes it using algorithms, and produces an output in the form of a text. Some speech recognition systems use Hidden Markov Models (HMMs) to deal with the temporal variability of speech and Gaussian Mixture Models (GMMs) to determine how well each state of each HMM fits a short window of frames of coefficients that represents the acoustic input. Another way to evaluate the fit is to use a feed-forward neural network that takes several frames of coefficients as input and produces posterior probabilities over HMM states as output. Deep neural networks (DNNs) that have many hidden layers and are trained using new methods have been shown to outperform GMMs on a variety of speech recognition systems. Acoustic models for state-of-the-art ASR systems are usually training on massive amounts of data. However, audio files with their corresponding transcriptions can be difficult to obtain, especially in the Spanish language. Hence, in the case of these low-resource scenarios, building an ASR model is considered as a complex task due to the lack of labeled data, resulting in an under-trained system. Semi-supervised learning approaches arise as necessary tasks given the high cost of transcribing audio data. The main goal of this proposal is to develop a procedure based on acoustic semi-supervised learning for Spanish ASR systems by using DNNs. This semi-supervised learning approach consists of: (a) Training a seed ASR model with a DNN using a set of audios and their respective transcriptions. A DNN with a one-hidden-layer network was initialized; increasing the number of hidden layers in training, to a five. A refinement, which consisted of the weight matrix plus bias term and a Stochastic Gradient Descent (SGD) training were also performed. The objective function was the cross-entropy criterion. (b) Decoding/testing a set of unlabeled data with the obtained seed model. (c) Selecting a suitable subset of the validated data to retrain the seed model, thereby improving its performance on the target test set. To choose the most precise transcriptions, three confidence scores or metrics, regarding the lattice concept (based on the graph cost, the acoustic cost and a combination of both), was performed as selection technique. The performance of the ASR system will be calculated by means of the Word Error Rate (WER). The test dataset was renewed in order to extract the new transcriptions added to the training dataset. Some experiments were carried out in order to select the best ASR results. A comparison between a GMM-based model without retraining and the DNN proposed system was also made under the same conditions. Results showed that the semi-supervised ASR-model based on DNNs outperformed the GMM-model, in terms of WER, in all tested cases. The best result obtained an improvement of 6% relative WER. Hence, these promising results suggest that the proposed technique could be suitable for building ASR models in low-resource environments.Keywords: automatic speech recognition, deep neural networks, machine learning, semi-supervised learning
Procedia PDF Downloads 3356823 A Neural Network Classifier for Identifying Duplicate Image Entries in Real-Estate Databases
Authors: Sergey Ermolin, Olga Ermolin
Abstract:
A Deep Convolution Neural Network with Triplet Loss is used to identify duplicate images in real-estate advertisements in the presence of image artifacts such as watermarking, cropping, hue/brightness adjustment, and others. The effects of batch normalization, spatial dropout, and various convergence methodologies on the resulting detection accuracy are discussed. For comparative Return-on-Investment study (per industry request), end-2-end performance is benchmarked on both Nvidia Titan GPUs and Intel’s Xeon CPUs. A new real-estate dataset from San Francisco Bay Area is used for this work. Sufficient duplicate detection accuracy is achieved to supplement other database-grounded methods of duplicate removal. The implemented method is used in a Proof-of-Concept project in the real-estate industry.Keywords: visual recognition, convolutional neural networks, triplet loss, spatial batch normalization with dropout, duplicate removal, advertisement technologies, performance benchmarking
Procedia PDF Downloads 3316822 Implications of Optimisation Algorithm on the Forecast Performance of Artificial Neural Network for Streamflow Modelling
Authors: Martins Y. Otache, John J. Musa, Abayomi I. Kuti, Mustapha Mohammed
Abstract:
The performance of an artificial neural network (ANN) is contingent on a host of factors, for instance, the network optimisation scheme. In view of this, the study examined the general implications of the ANN training optimisation algorithm on its forecast performance. To this end, the Bayesian regularisation (Br), Levenberg-Marquardt (LM), and the adaptive learning gradient descent: GDM (with momentum) algorithms were employed under different ANN structural configurations: (1) single-hidden layer, and (2) double-hidden layer feedforward back propagation network. Results obtained revealed generally that the gradient descent with momentum (GDM) optimisation algorithm, with its adaptive learning capability, used a relatively shorter time in both training and validation phases as compared to the Levenberg- Marquardt (LM) and Bayesian Regularisation (Br) algorithms though learning may not be consummated; i.e., in all instances considering also the prediction of extreme flow conditions for 1-day and 5-day ahead, respectively especially using the ANN model. In specific statistical terms on the average, model performance efficiency using the coefficient of efficiency (CE) statistic were Br: 98%, 94%; LM: 98 %, 95 %, and GDM: 96 %, 96% respectively for training and validation phases. However, on the basis of relative error distribution statistics (MAE, MAPE, and MSRE), GDM performed better than the others overall. Based on the findings, it is imperative to state that the adoption of ANN for real-time forecasting should employ training algorithms that do not have computational overhead like the case of LM that requires the computation of the Hessian matrix, protracted time, and sensitivity to initial conditions; to this end, Br and other forms of the gradient descent with momentum should be adopted considering overall time expenditure and quality of the forecast as well as mitigation of network overfitting. On the whole, it is recommended that evaluation should consider implications of (i) data quality and quantity and (ii) transfer functions on the overall network forecast performance.Keywords: streamflow, neural network, optimisation, algorithm
Procedia PDF Downloads 148