Search results for: depth-wise separable convolutional neural network for light-weight GAN architecture for EDGE devices

Authors: Arian Hosseini, Mahmudul Hasan

Abstract:

To address the increasing need for efficient and accurate content moderation, we propose an efficient and lightweight deep classification ensemble structure. Our approach is based on a combination of simple visual features, designed for high-accuracy classification of violent content with low false positives. Our ensemble architecture utilizes a set of lightweight models with narrowed-down color features, and we apply it to both images and videos. We evaluated our approach using a large dataset of explosion and blast contents and compared its performance to popular deep learning models such as ResNet-50. Our evaluation results demonstrate significant improvements in prediction accuracy, while benefiting from 7.64x faster inference and lower computation cost. While our approach is tailored to explosion detection, it can be applied to other similar content moderation and violence detection use cases as well. Based on our experiments, we propose a "think small, think many" philosophy in classification scenarios. We argue that transforming a single, large, monolithic deep model into a verification-based step model ensemble of multiple small, simple, and lightweight models with narrowed-down visual features can possibly lead to predictions with higher accuracy.

Keywords: deep classification, content moderation, ensemble learning, explosion detection, video processing

Procedia PDF Downloads 31

Authors: Mahdieh Khalilinezhad, Silvana Dellepiane, Gianni Vernazza

Abstract:

The aim of the present work is to build a model based on tissue characterization that is able to discriminate pathological and non-pathological regions from three-phasic CT images. Based on feature selection in different phases, in this research, we design a neural network system that has optimal neuron number in a hidden layer. Our approach consists of three steps: feature selection, feature reduction, and classification. For each ROI, 6 distinct set of texture features are extracted such as first order histogram parameters, absolute gradient, run-length matrix, co-occurrence matrix, autoregressive model, and wavelet, for a total of 270 texture features. We show that with the injection of liquid and the analysis of more phases the high relevant features in each region changed. Our results show that for detecting HCC tumor phase3 is the best one in most of the features that we apply to the classification algorithm. The percentage of detection between these two classes according to our method, relates to first order histogram parameters with the accuracy of 85% in phase 1, 95% phase 2, and 95% in phase 3.

Keywords: multi-phasic liver images, texture analysis, neural network, hidden layer

Procedia PDF Downloads 249

Authors: Masood Varshosaz, Kamyar Hasanpour

Abstract:

In recent years, we have seen growing interest in recognizing humans in drone images for post-disaster search and rescue operations. Deep learning algorithms have shown great promise in this area, but they often require large amounts of labeled data to train the models. To keep the data acquisition cost low, augmentation techniques can be used to create additional data from existing images. There are many techniques of such that can help generate variations of an original image to improve the performance of deep learning algorithms. While data augmentation is potentially assumed to improve the accuracy and robustness of the models, it is important to ensure that the performance gains are not outweighed by the additional computational cost or complexity of implementing the techniques. To this end, it is important to evaluate the impact of data augmentation on the performance of the deep learning models. In this paper, we evaluated the most currently available 2D data augmentation techniques on a standard convolutional network which was trained for recognizing humans in drone images. The techniques include rotation, scaling, random cropping, flipping, shifting, and their combination. The results showed that the augmented models perform 1-3% better compared to a base network. However, as the augmented images only contain the human parts already visible in the original images, a new data augmentation approach is needed to include the invisible parts of the human body. Thus, we suggest a new method that employs simulated 3D human models to generate new data for training the network.

Keywords: human recognition, deep learning, drones, disaster mitigation

Procedia PDF Downloads 77

Authors: Edward Holupka, John Rossman, Tye Morancy, Joseph Aronovitz, Irving Kaplan

Abstract:

A common modality for the treatment of early stage prostate cancer is the implantation of radioactive seeds directly into the prostate. The radioactive seeds are positioned inside the prostate to achieve optimal radiation dose coverage to the prostate. These radioactive seeds are positioned inside the prostate using Transrectal ultrasound imaging. Once all of the planned seeds have been implanted, two dimensional transaxial transrectal ultrasound images separated by 2 mm are obtained through out the prostate, beginning at the base of the prostate up to and including the apex. A common deep neural network, called DetectNet was trained to automatically determine the position of the implanted radioactive seeds within the prostate under ultrasound imaging. The results of the training using 950 training ultrasound images and 90 validation ultrasound images. The commonly used metrics for successful training were used to evaluate the efficacy and accuracy of the trained deep neural network and resulted in an loss_bbox (train) = 0.00, loss_coverage (train) = 1.89e-8, loss_bbox (validation) = 11.84, loss_coverage (validation) = 9.70, mAP (validation) = 66.87%, precision (validation) = 81.07%, and a recall (validation) = 82.29%, where train and validation refers to the training image set and validation refers to the validation training set. On the hardware platform used, the training expended 12.8 seconds per epoch. The network was trained for over 10,000 epochs. In addition, the seed locations as determined by the Deep Neural Network were compared to the seed locations as determined by a commercial software based on a one to three months after implant CT. The Deep Learning approach was within \strikeout off\uuline off\uwave off2.29\uuline default\uwave default mm of the seed locations determined by the commercial software. The Deep Learning approach to the determination of radioactive seed locations is robust, accurate, and fast and well within spatial agreement with the gold standard of CT determined seed coordinates.

Keywords: prostate, deep neural network, seed implant, ultrasound

Procedia PDF Downloads 180

Authors: Serap Durmus

Abstract:

The aim of this paper is to exemplify the relation of architecture and philosophy over the Japanese architect Toyo Ito’s conceptual architecture. The study is practiced in ‘Architecture and Philosophy Readings’ elective course with 22 sophomore architecture students in Karadeniz Technical University Department of Architecture. It is planned as a workshop, which discusses the design philosophy of Toyo Ito’s buildings and the reflections of concept in his intellectual architecture. So, the paper contains Toyo Ito’s philosophy, his discourses and buildings and also thinking similarities with philosopher Gilles Deleuze. Thus, the workshop of course is about architecture and philosophy relationship. With this aspect, a holistic graphic representation is aimed for Toyo Ito who thinks that everything composes a whole. As a result, it can be said that architect and philosopher interaction in architecture and philosophy relation supports creative thinking. Conceptual architecture of Toyo Ito has philosophical roots and his philosophy can be read over his buildings and can be represent totally via a holistic pattern.

Keywords: architecture, conceptual architecture, Gilles Deleuze, philosophy, Toyo Ito

Procedia PDF Downloads 556

Authors: Sushish Baral, Pratibha Joshi, Yaman Maharjan

Abstract:

Glaucoma is a chronic eye condition that causes vision loss that is irreversible. Early detection and treatment are critical to prevent vision loss because it can be asymptomatic. For the identification of glaucoma, multiple deep learning algorithms are used. Transformer-based architectures, which use the self-attention mechanism to encode long-range dependencies and acquire extremely expressive representations, have recently become popular. Convolutional architectures, on the other hand, lack knowledge of long-range dependencies in the image due to their intrinsic inductive biases. The aforementioned statements inspire this thesis to look at transformer-based solutions and investigate the viability of adopting transformer-based network designs for glaucoma detection. Using retinal fundus images of the optic nerve head to develop a viable algorithm to assess the severity of glaucoma necessitates a large number of well-curated images. Initially, data is generated by augmenting ocular pictures. After that, the ocular images are pre-processed to make them ready for further processing. The system is trained using pre-processed images, and it classifies the input images as normal or glaucoma based on the features retrieved during training. The Vision Transformer (ViT) architecture is well suited to this situation, as it allows the self-attention mechanism to utilise structural modeling. Extensive experiments are run on the common dataset, and the results are thoroughly validated and visualized.

Keywords: glaucoma, vision transformer, convolutional architectures, retinal fundus images, self-attention, deep learning

Procedia PDF Downloads 180

Authors: Diego Luján Villarreal

Abstract:

Retinal prosthetic devices aim to repair some vision in visual impairment patients by stimulating electrically neural cells in the visual system. In this study, the 3D linear electrode carrier is presented. A simulation framework was developed by placing the 3D carrier 1 mm away from the fovea center at the highest-density cell. Cell stimulation is verified in COMSOL Multiphysics by developing a 3D computational model which includes the relevant retinal interface elements and dynamics of the voltage-gated ionic channels. Current distribution resulting from low threshold amplitudes produces a small volume equivalent to the volume confined by individual cells at the highest-density cell using small-sized electrodes. Delicate retinal tissue is protected by excessive charge density

Keywords: retinal prosthetic devices, visual devices, retinal implants., visual prosthetic devices

Procedia PDF Downloads 90

Authors: Mustafa Kamoona, Mohamed El-Sharkawy

Abstract:

Although the latest Wireless Local Area Network technology Wi-Fi 802.11i standard addresses many of the security weaknesses of the antecedent Wired Equivalent Privacy (WEP) protocol, there are still scenarios where the network security are still vulnerable. The first security model that 802.11i offers is the Personal model which is very cheap and simple to install and maintain, yet it uses a Pre Shared Key (PSK) and thus has a low to medium security level. The second model that 802.11i provide is the Enterprise model which is highly secured but much more expensive and difficult to install/maintain and requires the installation and maintenance of an authentication server that will handle the authentication and key management for the wireless network. A central issue with the personal model is that the PSK needs to be shared with all the devices that are connected to the specific Wi-Fi network. This pre-shared key, unless changed regularly, can be cracked using offline dictionary attacks within a matter of hours. The key is burdensome to change in all the connected devices manually unless there is some kind of algorithm that coordinate this PSK update. The key idea of this paper is to propose a new algorithm that proactively and effectively coordinates the pre-shared key generation, management, and distribution in the cheap WPA/WPA2 personal security model using only a DD-WRT router.

Keywords: Wi-Fi, WPS, TLS, DD-WRT

Procedia PDF Downloads 218

Authors: Chia-Hao Chang, Geng-Gui Wang, Jee-Cheng Wu

Abstract:

The prediction of a landslide is a difficult task because it requires a detailed study of past activities using a complete range of investigative methods to determine the changing condition. In this research, first step, LiDAR 1-meter by 1-meter resolution of digital elevation model (DEM) was used to generate six environmental factors of landslide. Then, back-propagation neural networks (BPNN) was adopted to identify scarp, landslide areas and non-landslide areas. The BPNN uses 6 environmental factors in input layer and 1 output layer. Moreover, 6 landslide areas are used as training areas and 4 landslide areas as test areas in the BPNN. The hidden layer is set to be 1 and 2; the hidden layer neurons are set to be 4, 5, 6, 7 and 8; the learning rates are set to be 0.01, 0.1 and 0.5. When using 1 hidden layer with 7 neurons and the learning rate sets to be 0.5, the result of Network training root mean square error is 0.001388. Finally, evaluation of BPNN classification accuracy by the confusion matrix shows that the overall accuracy can reach 94.4%, and the Kappa value is 0.7464.

Keywords: digital elevation model, DEM, environmental factors, back-propagation neural network, BPNN, LiDAR

Procedia PDF Downloads 122

Authors: Abanoub Rady Shaker Saleb

Abstract:

Nowadays, design and architecture are being affected and underwent change with the rapid advancements in technology, economics, politics, society and culture. Architecture has been transforming with the latest developments after the inclusion of computers into design. Integration of design into the computational environment has revolutionized the architecture and new perspectives in architecture have been gained. The history of architecture shows the various technological developments and changes in which the architecture has transformed with time. Therefore, the analysis of integration between technology and the history of the architectural process makes it possible to build a consensus on the idea of how architecture is to proceed. In this study, each period that occurs with the integration of technology into architecture is addressed within historical process. At the same time, changes in architecture via technology are identified as important milestones and predictions with regards to the future of architecture have been determined. Developments and changes in technology and the use of technology in architecture within years are analyzed in charts and graphs comparatively. The historical process of architecture and its transformation via technology are supported with detailed literature review and they are consolidated with the examination of focal points of 20th-century architecture under the titles; parametric design, genetic architecture, simulation, and biomimicry. It is concluded that with the historical research between past and present; the developments in architecture cannot keep up with the advancements in technology and recent developments in technology overshadow the architecture, even the technology decides the direction of architecture. As a result, a scenario is presented with regards to the reach of technology in the future of architecture and the role of the architect.

Keywords: design and development the information technology architecture, enterprise architecture, enterprise architecture design result, TOGAF architecture development method (ADM)

Procedia PDF Downloads 48

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 98

Authors: Reham Al-Zahrani, Noura Aleisa

Abstract:

The proliferation of Radio Frequency Identification (RFID) technology has raised concerns about system security, particularly regarding tag impersonation attacks. Regarding RFID systems, an appropriate authentication protocol must resist active and passive attacks. A tag impersonation occurs when an adversary's tag is used to fool an authenticating reader into believing it is a legitimate tag. This paper analyzed the security of the efficient, secure, and practical ultra-lightweight RFID Authentication Scheme (ESRAS). Then, the paper presents a comprehensive analysis of the Efficient, Secure, and Practical Ultra-Lightweight RFID Authentication Scheme (ESRAS) in the context of radio frequency identification (RFID) systems that employed the Scyther tool to examine the protocol's security against a tag impersonation attack.

Keywords: RFID, impersonation attack, authentication, ultra-lightweight protocols

Procedia PDF Downloads 47

Authors: Mohammad Torabiyan, Kazem Mosawi Nejad

Abstract:

Today architecture has become as a powerful media for introducing cultures to the world, which in turn brings about a change in the global insight, power gaining, investment and development. Islamic architecture is based on the language of Koran and shows the depth and richness of Islam through spiritual soul. This is in a way that belief in monotheism and faith in Islamic teachings are manifested as Islam's aesthetic thought in Islamic architecture. Unfortunately, Islamic architecture has been damaged a lot due to lack of necessary information and also successive wars which have overtaken the Muslims as well as the dominance of colonizing counties. Islamic architecture is rooted in the history, culture and civilization of Muslims but its deficiencies and shortcomings should be removed through systematizing the Islamic architecture researchers. Islamic countries should act in a way that the art of Islamic architecture shows its true place in different architecture eras and makes everybody aware that Islamic architecture has a historical root and is connected eternally to the genuineness, religious art and culture of Muslims and civilization.

Keywords: art, culture, civilization, Islamic architecture, Muslims

Procedia PDF Downloads 516

Authors: Soner Guler, Fuat Korkut

Abstract:

Recently, the using of lightweights concretes in construction sector is rapidly increasing all over the world. Faster construction, low density and thermal transmitting coefficient and high fire resistance are the remarkable characteristics of the lightweight concretes. Lightweight concrete can be described as a type of concrete which enhance the volume of the mixture while giving additional advantages such as to reduce the dead weight of the structures. It is lighter than the conventional concrete. The use of lightweight concrete has been widely spread across countries such as USA, United Kingdom, and Sweden. In this study, the necessity of the using of lightweights concretes in the construction sector is emphasized and evaluated briefly for the architectures and civil engineers.

Keywords: lightweights concretes, low density, low thermal coefficient, construction sector

Procedia PDF Downloads 499

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 286

Authors: Petr Šimek

Abstract:

This work deals with the problem of synchronization of bus frames during transmission using USB (Universal Serial Bus). The principles for synchronization between USB and the non-deterministic CAN (Controller Area Network) bus will be described here. Furthermore, the work deals with ensuring the time sequence of communication frames when receiving from multiple communication bus channels. The structure of a general object for storing frames from different types of communication buses, such as CAN and LIN (Local Interconnect Network), will be described here. Finally, an evaluation of the communication throughput of bus frames for USB High speed will be performed. The creation of this architecture was based on the analysis of the communication of control units with a large number of communication buses. For the design of the architecture, a test HW with a USB-HS interface was used, which received previously known messages, which were compared with the received result. The result of this investigation is the block architecture of the control program for test HW ensuring correct data transmission via the USB bus.

Keywords: analysis, CAN, interface, LIN, synchronization, USB

Procedia PDF Downloads 38

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 105

Authors: Rashima Mahajan, Dipali Bansal, Shweta Singh

Abstract:

Real time non-invasive Brain Computer Interfaces have a significant progressive role in restoring or maintaining a quality life for medically challenged people. This manuscript provides a comprehensive review of emerging research in the field of cognitive/affective computing in context of human neural responses. The perspectives of different emotion assessment modalities like face expressions, speech, text, gestures, and human physiological responses have also been discussed. Focus has been paid to explore the ability of EEG (Electroencephalogram) signals to portray thoughts, feelings, and unspoken words. An automated workflow-based protocol to design an EEG-based real time Brain Computer Interface system for analysis and classification of human emotions elicited by external audio/visual stimuli has been proposed. The front end hardware includes a cost effective and portable Emotive EEG Neuroheadset unit, a personal computer and a set of external stimulators. Primary signal analysis and processing of real time acquired EEG shall be performed using MATLAB based advanced brain mapping toolbox EEGLab/BCILab. This shall be followed by the development of MATLAB based self-defined algorithm to capture and characterize temporal and spectral variations in EEG under emotional stimulations. The extracted hybrid feature set shall be used to classify emotional states using artificial intelligence tools like Artificial Neural Network. The final system would result in an inexpensive, portable and more intuitive Brain Computer Interface in real time scenario to control prosthetic devices by translating different brain states into operative control signals.

Keywords: brain computer interface, electroencephalogram, EEGLab, BCILab, emotive, emotions, interval features, spectral features, artificial neural network, control applications

Procedia PDF Downloads 304

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 301

Authors: K. Kalaiarasan, B. Pandeeswari, A. Arockia John Francis

Abstract:

Wireless, Multi-hop networks consist of one or more intermediate nodes along the path that receive and forward packets via wireless links. The backpressure algorithm provides throughput optimal routing and scheduling decisions for multi-hop networks with dynamic traffic. Xpress, a cross-layer backpressure architecture was designed to reach the capacity of wireless multi-hop networks and it provides well coordination between layers of network by turning a mesh network into a wireless switch. Transmission over the network is scheduled using a throughput-optimal backpressure algorithm. But this architecture operates much below their capacity due to out-of-order packet delivery and variable packet size. In this paper, we present Xpress-T, a throughput optimal backpressure architecture with TCP support designed to reach maximum throughput of wireless multi-hop networks. Xpress-T operates at the IP layer, and therefore any transport protocol, including TCP, can run on top of Xpress-T. The proposed design not only avoids bottlenecks but also handles out-of-order packet delivery and variable packet size, optimally load-balances traffic across them when needed, improving fairness among competing flows. Our simulation results shows that Xpress-T gives 65% more throughput than Xpress.

Keywords: backpressure scheduling and routing, TCP, congestion control, wireless multihop network

Procedia PDF Downloads 507

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 542

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 365

Authors: Pawel Twardowski, Maciej Tabaszewski, Jakub Czyżycki

Abstract:

The main goal of the work was to use machine learning to predict cutting-edge wear. The research was carried out while milling hardened steel with sintered carbide cutters at various cutting speeds. During the tests, cutting-edge wear was measured, and vibration acceleration signals were also measured. Appropriate measures were determined from the vibration signals and served as input data in the machine-learning process. Two approaches were used in this work. The first one involved a two-state classification of the cutting edge - suitable and unfit for further work. In the second approach, prediction of the cutting-edge state based on vibration signals was used. The obtained research results show that the appropriate use of machine learning algorithms gives excellent results related to monitoring cutting edge during the process.

Keywords: milling of hardened steel, tool wear, vibrations, machine learning

Procedia PDF Downloads 33

Authors: Adel Gurel, Ozge Ceylin Yildirim

Abstract:

Nowadays, design and architecture are being affected and underwent change with the rapid advancements in technology, economics, politics, society and culture. Architecture has been transforming with the latest developments after the inclusion of computers into design. Integration of design into the computational environment has revolutionized the architecture and new perspectives in architecture have been gained. The history of architecture shows the various technological developments and changes in which the architecture has transformed with time. Therefore, the analysis of integration between technology and the history of the architectural process makes it possible to build a consensus on the idea of how architecture is to proceed. In this study, each period that occurs with the integration of technology into architecture is addressed within historical process. At the same time, changes in architecture via technology are identified as important milestones and predictions with regards to the future of architecture have been determined. Developments and changes in technology and the use of technology in architecture within years are analyzed in charts and graphs comparatively. The historical process of architecture and its transformation via technology are supported with detailed literature review and they are consolidated with the examination of focal points of 20th-century architecture under the titles; parametric design, genetic architecture, simulation, and biomimicry. It is concluded that with the historical research between past and present; the developments in architecture cannot keep up with the advancements in technology and recent developments in technology overshadow the architecture, even the technology decides the direction of architecture. As a result, a scenario is presented with regards to the reach of technology in the future of architecture and the role of the architect.

Keywords: computer technologies, future architecture, scientific developments, transformation

Procedia PDF Downloads 175

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 374

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 118

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 465

Authors: Emhimed Saffor

Abstract:

In this paper, the problem of edge detection in digital images is considered. Three methods of edge detection based on mathematical morphology algorithm were applied on two sets (Brain and Chest) CT images. 3x3 filter for first method, 5x5 filter for second method and 7x7 filter for third method under MATLAB programming environment. The results of the above-mentioned methods are subjectively evaluated. The results show these methods are more efficient and satiable for medical images, and they can be used for different other applications.

Keywords: CT images, Matlab, medical images, edge detection

Procedia PDF Downloads 315

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 152

Authors: Jia Li, Xing Wei, Yuchen Hong, Yang Lu

Abstract:

Detecting vehicle behavior has always been the focus of intelligent transportation, but with the explosive growth of the number of vehicles and the complexity of the road environment, the vehicle behavior videos captured by traditional surveillance have been unable to satisfy the study of vehicle behavior. The traditional method of manually labeling vehicle behavior is too time-consuming and labor-intensive, but the existing object detection and tracking algorithms have poor practicability and low behavioral location detection rate. This paper proposes a vehicle behavior detection algorithm based on the dual-stream convolution network and the multi-dimensional video dynamic detection network. In the videos, the straight-line behavior of the vehicle will default to the background behavior. The Changing lanes, turning and turning around are set as target behaviors. The purpose of this model is to automatically mark the target behavior of the vehicle from the untrimmed videos. First, the target behavior proposals in the long video are extracted through the dual-stream convolution network. The model uses a dual-stream convolutional network to generate a one-dimensional action score waveform, and then extract segments with scores above a given threshold M into preliminary vehicle behavior proposals. Second, the preliminary proposals are pruned and identified using the multi-dimensional video dynamic detection network. Referring to the hierarchical reinforcement learning, the multi-dimensional network includes a Timer module and a Spacer module, where the Timer module mines time information in the video stream and the Spacer module extracts spatial information in the video frame. The Timer and Spacer module are implemented by Long Short-Term Memory (LSTM) and start from an all-zero hidden state. The Timer module uses the Transformer mechanism to extract timing information from the video stream and extract features by linear mapping and other methods. Finally, the model fuses time information and spatial information and obtains the location and category of the behavior through the softmax layer. This paper uses recall and precision to measure the performance of the model. Extensive experiments show that based on the dataset of this paper, the proposed model has obvious advantages compared with the existing state-of-the-art behavior detection algorithms. When the Time Intersection over Union (TIoU) threshold is 0.5, the Average-Precision (MP) reaches 36.3% (the MP of baselines is 21.5%). In summary, this paper proposes a vehicle behavior detection model based on multi-dimensional dynamic detection network. This paper introduces spatial information and temporal information to extract vehicle behaviors in long videos. Experiments show that the proposed algorithm is advanced and accurate in-vehicle timing behavior detection. In the future, the focus will be on simultaneously detecting the timing behavior of multiple vehicles in complex traffic scenes (such as a busy street) while ensuring accuracy.

Keywords: vehicle behavior detection, convolutional neural network, long short-term memory, deep learning

Procedia PDF Downloads 114