Search results for: neural interface

Authors: A. Shoiynbek, K. Kozhakhmet, P. Menezes, D. Kuanyshbay, D. Bayazitov

Abstract:

Speech emotion recognition has received increasing research interest all through current years. There was used emotional speech that was collected under controlled conditions in most research work. Actors imitating and artificially producing emotions in front of a microphone noted those records. There are four issues related to that approach, namely, (1) emotions are not natural, and it means that machines are learning to recognize fake emotions. (2) Emotions are very limited by quantity and poor in their variety of speaking. (3) There is language dependency on SER. (4) Consequently, each time when researchers want to start work with SER, they need to find a good emotional database on their language. In this paper, we propose the approach to create an automatic tool for speech emotion extraction based on facial emotion recognition and describe the sequence of actions of the proposed approach. One of the first objectives of the sequence of actions is a speech detection issue. The paper gives a detailed description of the speech detection model based on a fully connected deep neural network for Kazakh and Russian languages. Despite the high results in speech detection for Kazakh and Russian, the described process is suitable for any language. To illustrate the working capacity of the developed model, we have performed an analysis of speech detection and extraction from real tasks.

Keywords: deep neural networks, speech detection, speech emotion recognition, Mel-frequency cepstrum coefficients, collecting speech emotion corpus, collecting speech emotion dataset, Kazakh speech dataset

Procedia PDF Downloads 102

Authors: Chen Xi, Lao Xuerui, Li Junjie, Jiang Yike, Wang Hanwei, Zeng Zihao

Abstract:

To further promote the development of smart cities, the microscopic "nerve endings" of the City Intelligent Model (CIM) are extended to be more sensitive. In this paper, we develop a pedestrian trajectory twin terminal based on the CIM and CNN technology. It also uses 5G networks, architectural and geoinformatics technologies, convolutional neural networks, combined with deep learning networks for human behaviour recognition models, to provide empirical data such as 'pedestrian flow data and human behavioural characteristics data', and ultimately form spatial performance evaluation criteria and spatial performance warning systems, to make the empirical data accurate and intelligent for prediction and decision making.

Keywords: urban planning, urban governance, CIM, artificial intelligence, convolutional neural network

Procedia PDF Downloads 154

Authors: Marziyeh Khavari

Abstract:

In recent decades, climate change, global warming, and the growing population worldwide face some challenges, such as increasing food consumption and shortage of resources. Assessing how climate change could disturb crops, especially hazelnut production, seems crucial for sustainable agriculture production. For hazelnut cultivation in the mid-warm condition, such as in Iran, here we present an investigation of climate parameters and how much they are effective on fertility and nut production of hazelnut trees. Therefore, the climate change of the northern zones in Iran has investigated (1960-2017) and was reached an uptrend in temperature. Furthermore, the descriptive analysis performed on six cultivars during seven years shows how this small-scale survey could demonstrate the effects of climate change on hazelnut production and stability. Results showed that some climate parameters are more significant on nut production, such as solar radiation, soil temperature, relative humidity, and precipitation. Moreover, some cultivars have produced more stable production, for instance, Negret and Segorbe, while the Mervill de Boliver recorded the most variation during the study. Another aspect that needs to be met is training and predicting an actual model to simulate nut production through a neural network and linear regression simulation. The study developed and estimated the ANN model's generalization capability with different criteria such as RMSE, SSE, and accuracy factors for dependent and independent variables (environmental and yield traits). The models were trained and tested while the accuracy of the model is proper to predict hazelnut production under fluctuations in weather parameters.

Keywords: climate change, neural network, hazelnut, global warming

Procedia PDF Downloads 132

Authors: Abdolhamid Anazadehsayed, Jamal Naser

Abstract:

An integrated computational fluid dynamics model is developed for a combined simulation of Plateau borders, films, and transitional areas between the film and the Plateau borders to reduce the simplifications and shortcomings of available models for foam drainage in micro-scale. Additionally, the counter-flow related to the Marangoni effect in the transitional area is investigated. The results of this combined model show the contribution of the films, the exterior Plateau borders, and Marangoni flow in the drainage process more accurately since the inter-influence of foam's elements is included in this study. The exterior Plateau borders flow rate can be four times larger than the interior ones. The exterior bubbles can be more prominent in the drainage process in cases where the number of the exterior Plateau borders increases due to the geometry of container. The ratio of the Marangoni counter-flow to the Plateau border flow increases drastically with an increase in the mobility of air-liquid interface. However, the exterior bubbles follow the same trend with much less intensity since typically, the flow is less dependent on the interface of air-liquid in the exterior bubbles. Moreover, the Marangoni counter-flow in a near-wall transition area is less important than an internal one. The influence of air-liquid interface mobility on the average velocity of interior foams is attained with more accuracy with more realistic boundary condition. Then it has been compared with other numerical and analytical results. The contribution of films in the drainage is significant for the mobile foams as the velocity of flow in the film has the same order of magnitude as the velocity in the Plateau border. Nevertheless, for foams with rigid interfaces, film's contribution in foam drainage is insignificant, particularly for the films near the wall of the container.

Keywords: foam, plateau border, film, Marangoni, CFD, bubble

Procedia PDF Downloads 345

Authors: Rakkrit Duangsoithong, Jermphiphut Jaruenpunyasak, Alba Garcia

Abstract:

The use of foot recognition can be applied in many medical fields such as the gait pattern analysis and the knee exercises of patients in rehabilitation. Generally, a camera-based foot recognition system is intended to capture a patient image in a controlled room and background to recognize the foot in the limited views. However, this system can be inconvenient to monitor the knee exercises at home. In order to overcome these problems, this paper proposes to use the deep learning method using Convolutional Neural Networks (CNNs) for foot recognition. The results are compared with the traditional classification method using LBP and HOG features with kNN and SVM classifiers. According to the results, deep learning method provides better accuracy but with higher complexity to recognize the foot images from online databases than the traditional classification method.

Keywords: foot recognition, deep learning, knee rehabilitation, convolutional neural network

Procedia PDF Downloads 163

Authors: Camellia Al-Ibrahim, Jenny Yiend, Sukhwinder S. Shergill

Abstract:

Background: Attention bias to threat play a role in the development, maintenance, and exacerbation of delusional beliefs in schizophrenia in which patients emphasize the threatening characteristics of stimuli and prioritise them for processing. Cognitive control deficits arise when task-irrelevant emotional information elicits attentional bias and obstruct optimal performance. This study is investigating neural correlates of interference effect of linguistic threat and whether these effects are independent of delusional severity. Methods: Using an event-related functional magnetic resonance imaging (fMRI), neural correlates of interference effect of linguistic threat during the emotional Stroop task were investigated and compared patients with schizophrenia with high (N=17) and low (N=16) paranoid symptoms and healthy controls (N=20). Participants were instructed to identify the font colour of each word presented on the screen as quickly and accurately as possible. Stimuli types vary between threat-relevant, positive and neutral words. Results: Group differences in whole brain effects indicate decreased amygdala activity in patients with high paranoid symptoms compared with low paranoid patients and healthy controls. Regions of interest analysis (ROI) validated our results within the amygdala and investigated changes within the striatum showing a pattern of reduced activation within the clinical group compared to healthy controls. Delusional severity was associated with significant decreased neural activity in the striatum within the clinical group. Conclusion: Our findings suggest that the emotional interference mediated by the amygdala and striatum may reduce responsiveness to threat-related stimuli in schizophrenia and that attenuation of fMRI Blood-oxygen-level dependent (BOLD) signal within these areas might be influenced by the severity of delusional symptoms.

Keywords: attention bias, fMRI, Schizophrenia, Stroop

Procedia PDF Downloads 201

Authors: Rama Shanker, Anil Kumar Sachan

Abstract:

Basic ingredients of concrete are cement, fine aggregate, coarse aggregate and water. To produce a concrete of certain specific properties, optimum proportion of these ingredients are mixed. The important factors which govern the mix design are grade of concrete, type of cement and size, shape and grading of aggregates. Concrete mix design method is based on experimentally evolved empirical relationship between the factors in the choice of mix design. Basic draw backs of this method are that it does not produce desired strength, calculations are cumbersome and a number of tables are to be referred for arriving at trial mix proportion moreover, the variation in attainment of desired strength is uncertain below the target strength and may even fail. To solve this problem, a lot of cubes of standard grades were prepared and attained 28 days strength determined for different combination of cement, fine aggregate, coarse aggregate and water. An artificial neural network (ANN) was prepared using these data. The input of ANN were grade of concrete, type of cement, size, shape and grading of aggregates and output were proportions of various ingredients. With the help of these inputs and outputs, ANN was trained using feed forward back proportion model. Finally trained ANN was validated, it was seen that it gave the result with/ error of maximum 4 to 5%. Hence, specific type of concrete can be prepared from given material properties and proportions of these materials can be quickly evaluated using the proposed ANN.

Keywords: aggregate proportions, artificial neural network, concrete grade, concrete mix design

Procedia PDF Downloads 390

Authors: Zhaojun Wang, Zongdi Sun, Zhiyuan Liu

Abstract:

First of all, the carbon trading price and trading volume in Shanghai are transformed by Fourier transform, and the frequency response diagram is obtained. Then, the frequency response diagram is analyzed and the Blackman filter is designed. The Blackman filter is used to filter, and the carbon trading time domain and frequency response diagram are obtained. After wavelet analysis, the carbon trading data were processed; respectively, we got the average value for each 5 days, 10 days, 20 days, 30 days, and 60 days. Finally, the data are used as input of the Back Propagation Neural Network model for prediction.

Keywords: Shanghai carbon trading, carbon trading price, carbon trading volume, wavelet analysis, BP neural network model

Procedia PDF Downloads 391

Authors: T. Praveenkumar, Kulpreet Singh, Divy Bhanpuriya, M. Saimurugan

Abstract:

This study analysed the classification accuracy for gearbox faults using Machine Learning Techniques. Gearboxes are widely used for mechanical power transmission in rotating machines. Its rotating components such as bearings, gears, and shafts tend to wear due to prolonged usage, causing fluctuating vibrations. Increasing the dependability of mechanical components like a gearbox is hampered by their sealed design, which makes visual inspection difficult. One way of detecting impending failure is to detect a change in the vibration signature. The current study proposes various machine learning algorithms, with aid of these vibration signals for obtaining the fault classification accuracy of an automotive 4-Speed synchromesh gearbox. Experimental data in the form of vibration signals were acquired from a 4-Speed synchromesh gearbox using Data Acquisition System (DAQs). Statistical features were extracted from the acquired vibration signal under various operating conditions. Then the extracted features were given as input to the algorithms for fault classification. Supervised Machine Learning algorithms such as Support Vector Machines (SVM) and unsupervised algorithms such as Deep Feed Forward Neural Network (DFFNN), Deep Belief Networks (DBN) algorithms are used for fault classification. The fusion of DBN & DFFNN classifiers were architected to further enhance the classification accuracy and to reduce the computational complexity. The fault classification accuracy for each algorithm was thoroughly studied, tabulated, and graphically analysed for fused and individual algorithms. In conclusion, the fusion of DBN and DFFNN algorithm yielded the better classification accuracy and was selected for fault detection due to its faster computational processing and greater efficiency.

Keywords: deep belief networks, DBN, deep feed forward neural network, DFFNN, fault diagnosis, fusion of algorithm, vibration signal

Procedia PDF Downloads 116

Authors: David Oluigbo, Erik Hemberg, Nathan Shwatal, Wenqi Ding, Yin Yuan, Susanna Mierau

Abstract:

Introduction: Calcium imaging is an established technique in neuroscience research for detecting activity in neural networks. Bursts of action potentials in neurons lead to transient increases in intracellular calcium visualized with fluorescent indicators. Manual identification of cell bodies and their contours by experts typically takes 10-20 minutes per calcium imaging recording. Our aim, therefore, was to design an automated pipeline to facilitate and optimize calcium imaging data analysis. Our pipeline aims to accelerate cell body and contour identification and production of graphical representations reflecting changes in neuronal calcium-based fluorescence. Methods: We created a Python-based pipeline that uses OpenCV (a computer vision Python package) to accurately (1) detect neuron contours, (2) extract the mean fluorescence within the contour, and (3) identify transient changes in the fluorescence due to neuronal activity. The pipeline consisted of 3 Python scripts that could both be easily accessed through a Python Jupyter notebook. In total, we tested this pipeline on ten separate calcium imaging datasets from murine dissociate cortical cultures. We next compared our automated pipeline outputs with the outputs of manually labeled data for neuronal cell location and corresponding fluorescent times series generated by an expert neuroscientist. Results: Our results show that our automated pipeline efficiently pinpoints neuronal cell body location and neuronal contours and provides a graphical representation of neural network metrics accurately reflecting changes in neuronal calcium-based fluorescence. The pipeline detected the shape, area, and location of most neuronal cell body contours by using binary thresholding and grayscale image conversion to allow computer vision to better distinguish between cells and non-cells. Its results were also comparable to manually analyzed results but with significantly reduced result acquisition times of 2-5 minutes per recording versus 10-20 minutes per recording. Based on these findings, our next step is to precisely measure the specificity and sensitivity of the automated pipeline’s cell body and contour detection to extract more robust neural network metrics and dynamics. Conclusion: Our Python-based pipeline performed automated computer vision-based analysis of calcium image recordings from neuronal cell bodies in neuronal cell cultures. Our new goal is to improve cell body and contour detection to produce more robust, accurate neural network metrics and dynamic graphs.

Keywords: calcium imaging, computer vision, neural activity, neural networks

Procedia PDF Downloads 83

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 382

Authors: Su Yin Chiam, Zhipeng Ding, Guang Yang, Danny Jian Hang Tng, Peiyi Song, Geok Ing Ng, Ken-Tye Yong, Qing Xin Zhang

Abstract:

Brain-machine interfaces (BMI) is a ground rich of exploration opportunities where manipulation of neural activity are used for interconnect with myriad form of external devices. These research and intensive development were evolved into various areas from medical field, gaming and entertainment industry till safety and security field. The technology were extended for neurological disorders therapy such as obsessive compulsive disorder and Parkinson’s disease by introducing current pulses to specific region of the brain. Nonetheless, the work to develop a real-time observing, recording and altering of neural signal brain-machine interfaces system will require a significant amount of effort to overcome the obstacles in improving this system without delay in response. To date, feature size of interface devices and the density of the electrode population remain as a limitation in achieving seamless performance on BMI. Currently, the size of the BMI devices is ranging from 10 to 100 microns in terms of electrodes’ diameters. Henceforth, to accommodate the single cell level precise monitoring, smaller and denser Nano-scaled nanowire electrode arrays are vital in fabrication. In this paper, we would like to showcase the fabrication of high aspect ratio of vertical silicon nanowire electrodes arrays using microelectromechanical system (MEMS) method. Nanofabrication of the nanowire electrodes involves in deep reactive ion etching, thermal oxide thinning, electron-beam lithography patterning, sputtering of metal targets and bottom anti-reflection coating (BARC) etch. Metallization on the nanowire electrode tip is a prominent process to optimize the nanowire electrical conductivity and this step remains a challenge during fabrication. Metal electrodes were lithographically defined and yet these metal contacts outline a size scale that is larger than nanometer-scale building blocks hence further limiting potential advantages. Therefore, we present an integrated contact solution that overcomes this size constraint through self-aligned Nickel silicidation process on the tip of vertical silicon nanowire electrodes. A 4 x 4 array of vertical silicon nanowires electrodes with the diameter of 290nm and height of 3µm has been successfully fabricated.

Keywords: brain-machine interfaces, microelectromechanical systems (MEMS), nanowire, nickel silicide

Procedia PDF Downloads 435

Authors: Charles Kwaku Oppong

Abstract:

The research linked urban expansion resulting from urbanization with changing morphology processes happening in peri-urban communities. Two villages of Kumasi City peri-urban were used as a case study. Appropriate analytical framework and methodology (literature review and empirical evidence) were employed to ensure that all pertinent issues of peri-urban interface are brought to light. It was discovered from the study that since peri-urban livelihood is linked with assets base; it has been found that stock of asset, as well as transformation processes, were major factors in the shaping of livelihoods strategies. For that reason, success or failure of household livelihoods was seen to relate to the kind of livelihood strategy employed. With efforts to mitigate for livelihoods failure due to peri-urban development, households' recourse to remittances, land disposal, and other means as an alternative livelihood approach. The study calls for local government policy interventions in regulating peri-urban transformation process and providing safety nets for the vulnerable.

Keywords: urban expansion, peri-urban interface, livelihoods, asset

Procedia PDF Downloads 268

Authors: Ng Liang Shen, Ngahzaifa Abdul Ghani

Abstract:

This research aimed at developing an early warning system for pre-diabetic and diabetics by analyzing simple and easily determinable signs and symptoms of diabetes among the people living in Malaysia using Particle Swarm Optimized Artificial. With the skyrocketing prevalence of Type 2 diabetes in Malaysia, the system can be used to encourage affected people to seek further medical attention to prevent the onset of diabetes or start managing it early enough to avoid the associated complications. The study sought to find out the best predictive variables of Type 2 Diabetes Mellitus, developed a system to diagnose diabetes from the variables using Artificial Neural Networks and tested the system on accuracy to find out the patent generated from diabetes diagnosis result in machine learning algorithms even at primary or advanced stages.

Keywords: diabetes diagnosis, Artificial Neural Networks, artificial intelligence, soft computing, medical diagnosis

Procedia PDF Downloads 337

Authors: K. Senthil Kumar, A. Vasumalaikannan

Abstract:

In this paper, teleoperation of the quadrotor using Internet with Force feedback is addressed. Teleoperation with Force feedback is the ability to remotely control a robot, where contact (obstacle) or environment (wind gust etc) information (force feedback) is communicated from the quadrotor to the master joystick and thus giving the operator a sense of telepresence. The stability and performance of such a teleoperator is highly dependent on the amount of time delay present in the control loop. This problem is further complicated given the fact that for network based communication the time delay is itself time varying and highly non deterministic. In this paper, a novel method using Neural based Smith Predictor at the master side the stability is achieved. The performance of the system even during worst case scenario is within acceptable.

Keywords: teleoperation, quadrotor, neural smith predictor, time delay

Procedia PDF Downloads 616

Authors: Harkishen Singh, Gavin Mangeni

Abstract:

This project aims at building an efficient and automatic power monitoring SCADA system, which is capable of monitoring the electrical parameters of high voltage powered devices in real time for example RMS voltage and current, frequency, energy consumed, power factor etc. The system uses RS-485 serial communication interface to transfer data over longer distances. Embedded C programming is the platform used to develop two hardware modules namely: RTU and Master Station modules, which both use the CC2540 BLE 4.0 microcontroller configured in slave / master mode. The Si8900 galvanic ally isolated microchip is used to perform ADC externally. The hardware communicates via UART port and sends data to the user PC using the USB port. Labview software is used to design a user interface to display current state of the power loads being monitored as well as logs data to excel spreadsheet file. An understanding of the Si8900’s auto baud rate process is key to successful implementation of this project.

Keywords: SCADA, RS485, CC2540, labview, Si8900

Procedia PDF Downloads 302

Authors: Felipe A. Guth, Shane Ward, Kevin McDonnell

Abstract:

The assessment of disease levels in crop fields is an important and time-consuming task that generally relies on expert knowledge of trained individuals. Image classification in agriculture problems historically has been based on classical machine learning strategies that make use of hand-engineered features in the top of a classification algorithm. This approach tends to not produce results with high accuracy and generalization to the classes classified by the system when the nature of the elements has a significant variability. The advent of deep convolutional neural networks has revolutionized the field of machine learning, especially in computer vision tasks. These networks have great resourcefulness of learning and have been applied successfully to image classification and object detection tasks in the last years. The objective of this work was to propose a new method based on deep learning convolutional neural networks towards the task of disease level monitoring. Common RGB images of winter wheat were obtained during a growing season. Five categories of disease levels presence were produced, in collaboration with agronomists, for the algorithm classification. Disease level tasks performed by experts provided ground truth data for the disease score of the same winter wheat plots were RGB images were acquired. The system had an overall accuracy of 84% on the discrimination of the disease level classes.

Keywords: crop disease assessment, deep learning, precision agriculture, residual neural networks

Procedia PDF Downloads 333

Authors: Christos Theoharatos, Dimitris Tsourounis, Spiros Oikonomou, Andreas Makedonas

Abstract:

This paper focuses on the problem of visually inspecting and recognizing the road conditions in front of moving vehicles, targeting automotive scenarios. The goal of road inspection is to identify whether the road is slippery or not, as well as to detect possible anomalies on the road surface like potholes or body bumps/humps. Our work is based on an artificial intelligence methodology for real-time monitoring of road conditions in autonomous driving scenarios, using state-of-the-art deep convolutional neural network (CNN) techniques. Initially, the road and ego lane are segmented within the field of view of the camera that is integrated into the front part of the vehicle. A novel classification CNN is utilized to identify among plain and slippery road textures (e.g., wet, snow, etc.). Simultaneously, a robust detection CNN identifies severe surface anomalies within the ego lane, such as potholes and speed bumps/humps, within a distance of 5 to 25 meters. The overall methodology is illustrated under the scope of an integrated application (or system), which can be integrated into complete Advanced Driver-Assistance Systems (ADAS) systems that provide a full range of functionalities. The outcome of the proposed techniques present state-of-the-art detection and classification results and real-time performance running on AI accelerator devices like Intel’s Myriad 2/X Vision Processing Unit (VPU).

Keywords: deep learning, convolutional neural networks, road condition classification, embedded systems

Procedia PDF Downloads 135

Authors: Wang Yichen, Haruka Yamashita

Abstract:

In recent years, in the field of sports, decision making such as member in the game and strategy of the game based on then analysis of the accumulated sports data are widely attempted. In fact, in the NBA basketball league where the world's highest level players gather, to win the games, teams analyze the data using various statistical techniques. However, it is difficult to analyze the game data for each play such as the ball tracking or motion of the players in the game, because the situation of the game changes rapidly, and the structure of the data should be complicated. Therefore, it is considered that the analysis method for real time game play data is proposed. In this research, we propose an analytical model for "determining the optimal lineup composition" using the real time play data, which is considered to be difficult for all coaches. In this study, because replacing the entire lineup is too complicated, and the actual question for the replacement of players is "whether or not the lineup should be changed", and “whether or not Small Ball lineup is adopted”. Therefore, we propose an analytical model for the optimal player selection problem based on Small Ball lineups. In basketball, we can accumulate scoring data for each play, which indicates a player's contribution to the game, and the scoring data can be considered as a time series data. In order to compare the importance of players in different situations and lineups, we combine RNN (Recurrent Neural Network) model, which can analyze time series data, and NN (Neural Network) model, which can analyze the situation on the field, to build the prediction model of score. This model is capable to identify the current optimal lineup for different situations. In this research, we collected all the data of accumulated data of NBA from 2019-2020. Then we apply the method to the actual basketball play data to verify the reliability of the proposed model.

Keywords: recurrent neural network, players lineup, basketball data, decision making model

Procedia PDF Downloads 134

Authors: Raida Zouari, Iness Ahriz, Rafik Zayani, Ali Dziri, Ridha Bouallegue

Abstract:

This paper proposes a room level indoor localization algorithm based on the use Multi-Layer Neural Network (MLNN) classifiers and one versus one strategy. Seven parameters of the Channel Impulse Response (CIR) were used and Gram-Shmidt Orthogonalization was performed to study the relevance of the extracted parameters. Simulation results show that when relevant CIR parameters are used as position fingerprint and when optimal MLNN architecture is selected good room level localization score can be achieved. The current study showed also that some of the CIR parameters are not correlated to the location and can decrease the localization performance of the system.

Keywords: mobile indoor localization, multi-layer neural network (MLNN), channel impulse response (CIR), Gram-Shmidt orthogonalization

Procedia PDF Downloads 361

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 85

Authors: Soheila Sadeghi

Abstract:

Construction projects are complex and often subject to significant cost overruns due to the multifaceted nature of the activities involved. Accurate cost estimation is crucial for effective budget planning and resource allocation. Traditional methods for predicting overruns often rely on expert judgment or analysis of historical data, which can be time-consuming, subjective, and may fail to consider important factors. However, with the increasing availability of data from construction projects, machine learning techniques can be leveraged to improve the accuracy of overrun predictions. This study applied machine learning algorithms to enhance the prediction of cost overruns in a case study of a construction project. The methodology involved the development and evaluation of two machine learning models: Random Forest and Neural Networks. Random Forest can handle high-dimensional data, capture complex relationships, and provide feature importance estimates. Neural Networks, particularly Deep Neural Networks (DNNs), are capable of automatically learning and modeling complex, non-linear relationships between input features and the target variable. These models can adapt to new data, reduce human bias, and uncover hidden patterns in the dataset. The findings of this study demonstrate that both Random Forest and Neural Networks can significantly improve the accuracy of cost overrun predictions compared to traditional methods. The Random Forest model also identified key cost drivers and risk factors, such as changes in the scope of work and delays in material delivery, which can inform better project risk management. However, the study acknowledges several limitations. First, the findings are based on a single construction project, which may limit the generalizability of the results to other projects or contexts. Second, the dataset, although comprehensive, may not capture all relevant factors influencing cost overruns, such as external economic conditions or political factors. Third, the study focuses primarily on cost overruns, while schedule overruns are not explicitly addressed. Future research should explore the application of machine learning techniques to a broader range of projects, incorporate additional data sources, and investigate the prediction of both cost and schedule overruns simultaneously.

Keywords: cost prediction, machine learning, project management, random forest, neural networks

Procedia PDF Downloads 60

Authors: David Edgar

Abstract:

To understand how the brain’s subconscious and conscious functions, we must conquer the physics of Unity, which leads to duality’s algorithm. Where the subconscious (bottom-up) and conscious (top-down) processes function together to produce and consume intelligence, we use terms like ‘time is relative,’ but we really do understand the meaning. In the brain, there are different processes and, therefore, different observers. These different processes experience time at different rates. A sensory system such as the eyes cycles measurement around 33 milliseconds, the conscious process of the frontal lobe cycles at 300 milliseconds, and the subconscious process of the thalamus cycle at 5 milliseconds. Three different observers experience time differently. To bridge observers, the thalamus, which is the fastest of the processes, maintains a synchronous state and entangles the different components of the brain’s physical process. The entanglements form a synchronous cohesion between the brain components allowing them to share the same state and execute in the same measurement cycle. The thalamus uses the shared state to control the firing sequence of the brain’s linear subconscious process. Sharing state also allows the brain to cheat on the amount of sensory data that must be exchanged between components. Only unpredictable motion is transferred through the synchronous state because predictable motion already exists in the shared framework. The brain’s synchronous subconscious process is entirely based on energy conservation, where prediction regulates energy usage. So, the eyes every 33 milliseconds dump their sensory data into the thalamus every day. The thalamus is going to perform a motion measurement to identify the unpredictable motion in the sensory data. Here is the trick. The thalamus conducts its measurement based on the original observation time of the sensory system (33 ms), not its own process time (5 ms). This creates a data payload of synchronous motion that preserves the original sensory observation. Basically, a frozen moment in time (Flat 4D). The single moment in time can then be processed through the single state maintained by the synchronous process. Other processes, such as consciousness (300 ms), can interface with the synchronous state to generate awareness of that moment. Now, synchronous data traveling through a separate faster synchronous process creates a theoretical time tunnel where observation time is tunneled through the synchronous process and is reproduced on the other side in the original time-relativity. The synchronous process eliminates time dilation by simply removing itself from the equation so that its own process time does not alter the experience. To the original observer, the measurement appears to be instantaneous, but in the thalamus, a linear subconscious process generating sensory perception and thought production is being executed. It is all just occurring in the time available because other observation times are slower than thalamic measurement time. For life to exist in the physical universe requires a linear measurement process, it just hides by operating at a faster time relativity. What’s interesting is time dilation is not the problem; it’s the solution. Einstein said there was no universal time.

Keywords: neural synchronization, natural intelligence, 99.95% IoT data transmission savings, artificial subconscious intelligence (ASI)

Procedia PDF Downloads 127

Authors: E. A. Mlybari, M. S. Elbisy, A. H. Alshahri, O. M. Albarakati

Abstract:

Sea level rise threatens to increase the impact of future storms and hurricanes on coastal communities. Accurate sea level change prediction and supplement is an important task in determining constructions and human activities in coastal and oceanic areas. In this study, support vector machines (SVM) is proposed to predict daily tidal levels along the Jeddah Coast, Saudi Arabia. The optimal parameter values of kernel function are determined using a genetic algorithm. The SVM results are compared with the field data and with back propagation (BP). Among the models, the SVM is superior to BPNN and has better generalization performance.

Keywords: tides, prediction, support vector machines, genetic algorithm, back-propagation neural network, risk, hazards

Procedia PDF Downloads 468

Authors: Ayyaz Hussain, Tariq Sadad

Abstract:

Breast cancer (BC) is one of the widespread ailments among females globally. The early prognosis of BC can decrease the mortality rate. Exact findings of benign tumors can avoid unnecessary biopsies and further treatments of patients under investigation. However, due to variations in images, it is a tough job to isolate cancerous cases from normal and benign ones. The machine learning technique is widely employed in the classification of BC pattern and prognosis. In this research, a deep convolution neural network (DCNN) called AlexNet architecture is employed to get more discriminative features from breast tissues. To achieve higher accuracy, K-nearest neighbor (KNN) classifiers are employed as a substitute for the softmax layer in deep learning. The proposed model is tested on a widely used breast image database called MIAS dataset for experimental purposes and achieved 99% accuracy.

Keywords: breast cancer, DCNN, KNN, mammography

Procedia PDF Downloads 137

Authors: Chithra A. V., Somoshree Datta, Sandeep Nithyanandan

Abstract:

Sign Language Recognition (SLR) is the process of interpreting and translating sign language into spoken or written language using technological systems. It involves recognizing hand gestures, facial expressions, and body movements that makeup sign language communication. The primary goal of SLR is to facilitate communication between hearing- and speech-impaired communities and those who do not understand sign language. Due to the increased awareness and greater recognition of the rights and needs of the hearing- and speech-impaired community, sign language recognition has gained significant importance over the past 10 years. Technological advancements in the fields of Artificial Intelligence and Machine Learning have made it more practical and feasible to create accurate SLR systems. This paper presents a distinct approach to SLR by framing it as a video classification problem using Deep Learning (DL), whereby a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) has been used. This research targets the integration of sign language recognition into healthcare settings, aiming to improve communication between medical professionals and patients with hearing impairments. The spatial features from each video frame are extracted using a CNN, which captures essential elements such as hand shapes, movements, and facial expressions. These features are then fed into an RNN network that learns the temporal dependencies and patterns inherent in sign language sequences. The INCLUDE dataset has been enhanced with more videos from the healthcare domain and the model is evaluated on the same. Our model achieves 91% accuracy, representing state-of-the-art performance in this domain. The results highlight the effectiveness of treating SLR as a video classification task with the CNN-RNN architecture. This approach not only improves recognition accuracy but also offers a scalable solution for real-time SLR applications, significantly advancing the field of accessible communication technologies.

Keywords: sign language recognition, deep learning, convolution neural network, recurrent neural network

Procedia PDF Downloads 30

Authors: Shahrzad Zolfagharnassab, Abdul Rashid Mohamed Shariff, Reza Ehsani, Hawa Ze Jaffar, Ishak Aris

Abstract:

Ripeness estimation of oil palm fresh fruit is important processes that affect the profitableness and salability of oil palm fruits. The adulthood or ripeness of the oil palm fruits influences the quality of oil palm. Conventional procedure includes physical grading of Fresh Fruit Bunches (FFB) maturity by calculating the number of loose fruits per bunch. This physical classification of oil palm FFB is costly, time consuming and the results may have human error. Hence, many researchers try to develop the methods for ascertaining the maturity of oil palm fruits and thereby, deviously the oil content of distinct palm fruits without the need for exhausting oil extraction and analysis. This research investigates the potential of infrared images (Thermal Images) as a predictor to classify the oil palm FFB ripeness. A total of 270 oil palm fresh fruit bunches from most common cultivar of oil palm bunches Nigresens according to three maturity categories: under ripe, ripe and over ripe were collected. Each sample was scanned by the thermal imaging cameras FLIR E60 and FLIR T440. The average temperature of each bunches were calculated by using image processing in FLIR Tools and FLIR ThermaCAM researcher pro 2.10 environment software. The results show that temperature content decreased from immature to over mature oil palm FFBs. An overall analysis-of-variance (ANOVA) test was proved that this predictor gave significant difference between underripe, ripe and overripe maturity categories. This shows that the temperature as predictors can be good indicators to classify oil palm FFB. Classification analysis was performed by using the temperature of the FFB as predictors through Linear Discriminant Analysis (LDA), Mahalanobis Discriminant Analysis (MDA), Artificial Neural Network (ANN) and K- Nearest Neighbor (KNN) methods. The highest overall classification accuracy was 88.2% by using Artificial Neural Network. This research proves that thermal imaging and neural network method can be used as predictors of oil palm maturity classification.

Keywords: artificial neural network, maturity classification, oil palm FFB, thermal imaging

Procedia PDF Downloads 363

Authors: Hassan Masoumi, Ahad Salimi, Nazanin Barhemmat, Babak Gholami

Abstract:

Artificial neural networks have gained a lot of interest as empirical models for their powerful representational capacity, multi input and output mapping characteristics. In fact, most feed-forward networks with nonlinear nodal functions have been proved to be universal approximates. In this paper, we propose a new supervised method for color image classification based on self organizing feature maps (SOFM). This algorithm is based on competitive learning. The method partitions the input space using self-organizing feature maps to introduce the concept of local neighborhoods. Our image classification system entered into RGB image. Experiments with simulated data showed that separability of classes increased when increasing training time. In additional, the result shows proposed algorithms are effective for color image classification.

Keywords: classification, SOFM algorithm, neural network, neighborhood, RGB image

Procedia PDF Downloads 480

Authors: Kewei Fan, Sihong Liu, Yi Pik Cheng

Abstract:

This paper aims to analyse the failure behaviour of the retaining wall constructed with soil bags that are formed by filling river sand into woven bags (geosynthetics). Model tests were conducted to obtain the failure mode of the wall, and shear tests on two-layers and five-layers of soil bags were designed to investigate the mechanical characteristics of the interface of soil bags. The test results show that the slip surface in the soil bags-constructed retaining wall is ladder-like due to the inter-layer insertion of soil bags, and the wall above the ladder-like surface undergoes a rigid body translation. The insertion strengthens the shear strength of two-layer staggered-stacked soil bags. Meanwhile, it affects the shape of the slip surface of the five-layer staggered-stacked soil bags. Finally, the interlayer resisting friction of soil bags is found to be related to the shape of the slip surface.

Keywords: geosynthetics, retaining wall, soil bag, failure mode, interface, shear strength

Procedia PDF Downloads 131

Authors: D. Miroud, H. Mokaddem, M. Tata, N. Foucha

Abstract:

The body of PDC (polycrystalline diamond compact) drill bit can be manufactured from two different materials, steel and tungsten carbide matrix. Commonly the steel body is produced by machining, thermal spraying a bonding layer and hardfacing of Ni-based matrix reinforced with fused eutectic tungsten carbide (WC/W2C). The matrix body bit is manufactured by infiltrating tungsten carbide particles, with a Copper binary or ternary alloy. By erosion-corrosion mechanisms, the PDC drill bits matrix undergoes severe damage, occurring particularly around the PDC inserts and near injection nozzles. In this study, we investigated the possibility to repair the damaged matrix regions by hardfacing technic. Ni-based hardfacing alloy reinforced with fused eutectic tungsten carbide is deposited on infiltrated WC-W-Ni substrate by oxyacetylene welding (OAW). The microstructure at the hardfacing / matrix interface is characterized by SEM- EDS, XRD and micro hardness Hv0.1. The hardfacing conditions greatly affect the dilution phenomenon and the distribution of carbides at the interface, without formation of transition zone. During OAW welding deposition, interdiffusion of atoms occurs: Cu and Sn diffuse from infiltrated matrix substrate into hardfacing and simultaneously Cr and Si alloy elements from hardfacing diffuse towards the substrate. The dilution zone consists of a nickel-rich phase with a heterogeneous distribution of eutectic spherical (Ni-based hardfacing alloy) and irregular (matrix) WC/W2C carbides and a secondary phase rich in Cr-W-Si. Hardfacing conditions cause the dissolution of banding around both spherical and irregular carbides. The micro-hardness of interface is significantly improved by the presence of secondary phase in the inter-dendritic structure.

Keywords: dilution, dissolution, hardfacing, infiltrated matrix, PDC drill bits

Procedia PDF Downloads 341