Search results for: dynamic neural networks

Authors: John Lachapelle

Abstract:

Introduction: Neural stimulation is increasingly targeted toward treatment of back pain, PTSD, Parkinson’s disease, and for sensory perception. Sensory recording during stimulation is important in order to examine neural response to stimulation. Most neural amplifiers (headstages) focus on noise efficiency factor (NEF). Conversely, neural headstages need to handle artifacts from several sources including power lines, movement (EMG), and neural stimulation itself. In this work a layered approach to artifact rejection is used to reduce corruption of the neural ENG signal by 60dBv, resulting in recovery of sensory signals in rats and primates that would previously not be possible. Methods: The approach combines analog techniques to reduce and handle unwanted signal amplitudes. The methods include optimized (1) sensory electrode placement, (2) amplifier configuration, and (3) artifact blanking when necessary. The techniques together are like concentric moats protecting a castle; only the wanted neural signal can penetrate. There are two conditions in which the headstage operates: unwanted artifact < 50mV, linear operation, and artifact > 50mV, fast-settle gain reduction signal limiting (covered in more detail in a separate paper). Unwanted Signals at the headstage input: Consider: (a) EMG signals are by nature < 10mV. (b) 60 Hz power line signals may be > 50mV with poor electrode cable conditions; with careful routing much of the signal is common to both reference and active electrode and rejected in the differential amplifier with <50mV remaining. (c) An unwanted (to the neural recorder) stimulation signal is attenuated from stimulation to sensory electrode. The voltage seen at the sensory electrode can be modeled Φ_m=I_o/4πσr. For a 1 mA stimulation signal, with 1 cm spacing between electrodes, the signal is <20mV at the headstage. Headstage ASIC design: The front end ASIC design is designed to produce < 1% THD at 50mV input; 50 times higher than typical headstage ASICs, with no increase in noise floor. This requires careful balance of amplifier stages in the headstage ASIC, as well as consideration of the electrodes effect on noise. The ASIC is designed to allow extremely small signal extraction on low impedance (< 10kohm) electrodes with configuration of the headstage ASIC noise floor to < 700nV/rt-Hz. Smaller high impedance electrodes (> 100kohm) are typically located closer to neural sources and transduce higher amplitude signals (> 10uV); the ASIC low-power mode conserves power with 2uV/rt-Hz noise. Findings: The enhanced neural processing ASIC has been compared with a commercial neural recording amplifier IC. Chronically implanted primates at MGH demonstrated the presence of commercial neural amplifier saturation as a result of large environmental artifacts. The enhanced artifact suppression headstage ASIC, in the same setup, was able to recover and process the wanted neural signal separately from the suppressed unwanted artifacts. Separately, the enhanced artifact suppression headstage ASIC was able to separate sensory neural signals from unwanted artifacts in mouse-implanted peripheral intrafascicular electrodes. Conclusion: Optimizing headstage ASICs allow observation of neural signals in the presence of large artifacts that will be present in real-life implanted applications, and are targeted toward human implantation in the DARPA HAPTIX program.

Keywords: ASIC, biosensors, biomedical signal processing, biomedical sensors

Procedia PDF Downloads 328

Authors: J. Gochermann

Abstract:

Due to complex markets and products, and increasing need to innovate, cooperation between small and medium size enterprises arose during the last decades, which are not prior driven by process optimization or sales enhancement. Especially small and medium sized enterprises (SME) collaborate increasingly in innovation and knowledge networks to enhance their knowledge and innovation potential, and to find strategic partners for product and market development. These networks are characterized by dual objectives, the superordinate goal of the total network, and the specific objectives of the network members, which can cause target conflicts. Moreover, most SMEs do not have structured innovation processes and they are not accustomed to collaborate in complex innovation projects in an open network structure. On the other hand, SMEs have suitable characteristics for promising networking. They are flexible and spontaneous, they have flat hierarchies, and the acting people are not anonymous. These characteristics indeed distinguish them from bigger concerns. Investigation of German SME networks have been done to identify success factors for SME innovation networks. The fundamental network principles, donation-return and confidence, could be confirmed and identified as basic success factors. Further factors are voluntariness, adequate number of network members, quality of communication, neutrality and competence of the network management, as well as reliability and obligingness of the network services. Innovation and knowledge networks with an appreciable number of members from science and technology institutions need also active sense-making to bring different disciplines into successful collaboration. It has also been investigated, whether and how the involvement in an innovation network impacts the innovation structure and culture inside the member companies. The degree of reaction grows with time and intensity of commitment.

Keywords: innovation and knowledge networks, SME, success factors, innovation structure and culture

Procedia PDF Downloads 282

Authors: Ole-Christian Galbo Engstrøm, Erik Schou Dreier, Birthe Møller Jespersen, Kim Steenstrup Pedersen

Abstract:

Grain quality analysis is a multi-parameterized problem that includes a variety of qualitative and quantitative parameters such as grain type classification, damage type classification, and nutrient regression. Currently, these parameters require human inspection, a multitude of instruments employing a variety of sensor technologies, and predictive model types or destructive and slow chemical analysis. This paper investigates the feasibility of applying near-infrared hyperspectral imaging (NIR-HSI) to grain quality analysis. For this study two datasets of NIR hyperspectral images in the wavelength range of 900 nm - 1700 nm have been used. Both datasets contain images of sparsely and densely packed grain kernels. The first dataset contains ~87,000 image crops of bulk wheat samples from 63 harvests where protein value has been determined by the FOSS Infratec NOVA which is the golden industry standard for protein content estimation in bulk samples of cereal grain. The second dataset consists of ~28,000 image crops of bulk grain kernels from seven different wheat varieties and a single rye variety. In the first dataset, protein regression analysis is the problem to solve while variety classification analysis is the problem to solve in the second dataset. Deep convolutional neural networks (CNNs) have the potential to utilize spatio-spectral correlations within a hyperspectral image to simultaneously estimate the qualitative and quantitative parameters. CNNs can autonomously derive meaningful representations of the input data reducing the need for advanced preprocessing techniques required for classical chemometric model types such as artificial neural networks (ANNs) and partial least-squares regression (PLS-R). A comparison between different CNN architectures utilizing 2D and 3D convolution is conducted. These results are compared to the performance of ANNs and PLS-R. Additionally, a variety of preprocessing techniques from image analysis and chemometrics are tested. These include centering, scaling, standard normal variate (SNV), Savitzky-Golay (SG) filtering, and detrending. The results indicate that the combination of NIR-HSI and CNNs has the potential to be the foundation for an automatic system unifying qualitative and quantitative grain quality analysis within a single sensor technology and predictive model type.

Keywords: deep learning, grain analysis, hyperspectral imaging, preprocessing techniques

Procedia PDF Downloads 98

Authors: Le Zhao, Alain Nogaret

Abstract:

We have built universal Central Pattern Generator (CPG) hardware by interconnecting Hodgkin-Huxley neurons with reciprocally inhibitory synapses. We investigate the dynamics of neuron oscillations as a function of the time delay between current steps applied to individual neurons. We demonstrate stimulus dependent switching between spiking polyrhythms and map the phase portraits of the neuron oscillations to reveal the basins of attraction of the system. We experimentally study the dependence of the attraction basins on the network parameters: the neuron response time and the strength of inhibitory connections.

Keywords: central pattern generator, winnerless competition principle, artificial neural networks, synapses

Procedia PDF Downloads 472

Authors: Aishrith Rao

Abstract:

COVID 19 is a pandemic which has resulted in thousands of deaths around the world and a huge impact on the global economy. Testing is a huge issue as the test kits have limited availability and are expensive to manufacture. Using deep learning methods on radiology images in the detection of the coronavirus as these images contain information about the spread of the virus in the lungs is extremely economical and time-saving as it can be used in areas with a lack of testing facilities. This paper focuses on binary classification and multi-class classification of COVID 19 and other diseases such as pneumonia, tuberculosis, etc. Different deep learning methods such as VGG-19, COVID-Net, ResNET+ SVM, Deep CNN, DarkCovidnet, etc., have been used, and their accuracy has been compared using the Chest X-Ray dataset.

Keywords: deep learning, computer vision, radiology, COVID-19, ResNet, VGG-19, deep neural networks

Procedia PDF Downloads 159

Authors: X. S. Wu, H. Jia, P. H. Qian, Z. Zhang, H. L. Cai, F. M. Zhang

Abstract:

A bipolar resistance switching behaviour is detected for a Ti/TiO2-x/Au memristor device, which is fabricated by a masked designed magnetic sputtering. The current dependence of voltage indicates the curve changes slowly and continuously. When voltage pulses are applied to the device, the set and reset processes maintains linearity, which is used to simulate the synapses. We argue that the conduction mechanism of the device is from the oxygen vacancy channel model, and the resistance of the device change slowly due to the reaction between the titanium electrode and the intermediate layer and the existence of a large number of oxygen vacancies in the intermediate layer. Then, Hopfield neural network is constructed to simulate the behaviour of neural network in image processing, and the accuracy rate is more than 98%. This shows that titanium dioxide memristor has a broad application prospect in high performance neural network simulation.

Keywords: memristor fabrication, neuromorphic computing, bionic synaptic application, TiO₂-based

Procedia PDF Downloads 87

Authors: A. Al-Rifaie, Z. W. Guan, S. W. Jones

Abstract:

This paper presents a method for modelling and analysing end plate beam-to-column connections to obtain the quasi-static behaviour using non-linear dynamic explicit integration. In addition to its importance to study the static behaviour of a structural member, quasi-static behaviour is largely needed to be compared with the dynamic behaviour of such members in order to investigate the dynamic effect by proposing dynamic increase factors (DIFs). The beam-to-column bolted connections contain various contact surfaces at which the implicit procedure may have difficulties converging, resulting in a large number of iterations. Contrary, explicit procedure could deal effectively with complex contacts without converging problems. Hence, finite element modelling using ABAQUS/explicit is used in this study to address the dynamic effect may be produced using explicit procedure. Also, the effect of loading rate and mass scaling are discussed to investigate their effect on the time of analysis. The results show that the explicit procedure is valuable to model the end plate beam-to-column connections in terms of failure mode, load-displacement relationships. Also, it is concluded that loading rate and mass scaling should be carefully selected to avoid the dynamic effect in the solution.

Keywords: quasi-static, end plate, finite elements, connections

Procedia PDF Downloads 305

Authors: Kaleem Kashif, Tayyaba Anam, Yizhi Wu

Abstract:

This paper introduces a methodology for advancing Italian speech vowels landmark detection within the distinctive feature-based speech recognition domain. Leveraging the legacy tool 'xkl' by integrating combined convolutional neural networks (CNNs) and recurrent neural networks (RNNs), the study presents a comprehensive enhancement to the 'xkl' legacy software. This integration incorporates re-assigned spectrogram methodologies, enabling meticulous acoustic analysis. Simultaneously, our proposed model, integrating combined CNNs and RNNs, demonstrates unprecedented precision and robustness in landmark detection. The augmentation of re-assigned spectrogram fusion within the 'xkl' software signifies a meticulous advancement, particularly enhancing precision related to vowel formant estimation. This augmentation catalyzes unparalleled accuracy in landmark detection, resulting in a substantial performance leap compared to conventional methods. The proposed model emerges as a state-of-the-art solution in the distinctive feature-based speech recognition systems domain. In the realm of deep learning, a synergistic integration of combined CNNs and RNNs is introduced, endowed with specialized temporal embeddings, harnessing self-attention mechanisms, and positional embeddings. The proposed model allows it to excel in capturing intricate dependencies within Italian speech vowels, rendering it highly adaptable and sophisticated in the distinctive feature domain. Furthermore, our advanced temporal modeling approach employs Bayesian temporal encoding, refining the measurement of inter-landmark intervals. Comparative analysis against state-of-the-art models reveals a substantial improvement in accuracy, highlighting the robustness and efficacy of the proposed methodology. Upon rigorous testing on a database (LaMIT) speech recorded in a silent room by four Italian native speakers, the landmark detector demonstrates exceptional performance, achieving a 95% true detection rate and a 10% false detection rate. A majority of missed landmarks were observed in proximity to reduced vowels. These promising results underscore the robust identifiability of landmarks within the speech waveform, establishing the feasibility of employing a landmark detector as a front end in a speech recognition system. The synergistic integration of re-assigned spectrogram fusion, CNNs, RNNs, and Bayesian temporal encoding not only signifies a significant advancement in Italian speech vowels landmark detection but also positions the proposed model as a leader in the field. The model offers distinct advantages, including unparalleled accuracy, adaptability, and sophistication, marking a milestone in the intersection of deep learning and distinctive feature-based speech recognition. This work contributes to the broader scientific community by presenting a methodologically rigorous framework for enhancing landmark detection accuracy in Italian speech vowels. The integration of cutting-edge techniques establishes a foundation for future advancements in speech signal processing, emphasizing the potential of the proposed model in practical applications across various domains requiring robust speech recognition systems.

Keywords: landmark detection, acoustic analysis, convolutional neural network, recurrent neural network

Procedia PDF Downloads 62

Authors: Rao Fu, Jie Chen, Shutian Zeng, Yiping Zhuang, Agus Sudjianto

Abstract:

Generative Adversarial Net (GAN) has proved to be a powerful machine learning tool in image data analysis and generation. In this paper, we propose to use Conditional Generative Adversarial Net (CGAN) to learn and simulate time series data. The conditions include both categorical and continuous variables with different auxiliary information. Our simulation studies show that CGAN has the capability to learn different types of normal and heavy-tailed distributions, as well as dependent structures of different time series. It also has the capability to generate conditional predictive distributions consistent with training data distributions. We also provide an in-depth discussion on the rationale behind GAN and the neural networks as hierarchical splines to establish a clear connection with existing statistical methods of distribution generation. In practice, CGAN has a wide range of applications in market risk and counterparty risk analysis: it can be applied to learn historical data and generate scenarios for the calculation of Value-at-Risk (VaR) and Expected Shortfall (ES), and it can also predict the movement of the market risk factors. We present a real data analysis including a backtesting to demonstrate that CGAN can outperform Historical Simulation (HS), a popular method in market risk analysis to calculate VaR. CGAN can also be applied in economic time series modeling and forecasting. In this regard, we have included an example of hypothetical shock analysis for economic models and the generation of potential CCAR scenarios by CGAN at the end of the paper.

Keywords: conditional generative adversarial net, market and credit risk management, neural network, time series

Procedia PDF Downloads 143

Authors: Ivan Belik

Abstract:

In terms of social networks split graphs correspond to the variety of interpersonal and intergroup relations. In this paper we analyse the interaction between the cliques (socially strong and trusty groups) and the independent sets (fragmented and non-connected groups of people) as the basic components of any split graph. Based on the Semi-Lagrangean relaxation for the k-cardinality assignment problem we show the way of how to minimize the socially risky interactions between the cliques and the independent sets within the social network.

Keywords: cliques, independent sets, k-cardinality assignment, social networks, split graphs

Procedia PDF Downloads 319

Authors: C. Jameke

Abstract:

During the cognitivist era in cognitive psychology, a theory of internal rules and symbolic representations was posited as an account of human cognition. This type of cognitive architecture had its heyday during the 1970s and 80s, but it has now been largely abandoned in favour of subsymbolic architectures (e.g. connectionism), non-representational frameworks (e.g. dynamical systems theory), and statistical approaches such as Bayesian theory. In this presentation I describe this changing landscape of research, and comment on the increasing influence of neuroscience on cognitive psychology. I then briefly review a few recent developments in connectionism, and neurocomputation relevant to cognitive psychology, and critically discuss the assumption made by some researchers in these frameworks that higher-level aspects of human cognition are simply emergent properties of massively large distributed neural networks

Keywords: connectionism, emergentism, postocgnitivist, representations, subsymbolic archiitecture

Procedia PDF Downloads 575

Authors: Rui Wu

Abstract:

In the volatile modern manufacturing environment, new orders randomly occur at any time, while the pre-emptive methods are infeasible. This leads to a real-time scheduling method that can produce a reasonably good schedule quickly. The dynamic Flexible Job Shop problem is an NP-hard scheduling problem that hybrid the dynamic Job Shop problem with the Parallel Machine problem. A Flexible Job Shop contains different work centres. Each work centre contains parallel machines that can process certain operations. Many algorithms, such as genetic algorithms or simulated annealing, have been proposed to solve the static Flexible Job Shop problems. However, the time efficiency of these methods is low, and these methods are not feasible in a dynamic scheduling problem. Therefore, a dynamic rule selection scheduling system based on the reinforcement learning method is proposed in this research, in which the dynamic Flexible Job Shop problem is divided into several parallel machine problems to decrease the complexity of the dynamic Flexible Job Shop problem. Firstly, the features of jobs, machines, work centres, and flexible job shops are selected to describe the status of the dynamic Flexible Job Shop problem at each decision point in each work centre. Secondly, a framework of reinforcement learning algorithm using a double-layer deep Q-learning network is applied to select proper composite dispatching rules based on the status of each work centre. Then, based on the selected composite dispatching rule, an available operation is selected from the waiting buffer and assigned to an available machine in each work centre. Finally, the proposed algorithm will be compared with well-known dispatching rules on objectives of mean tardiness, mean flow time, mean waiting time, or mean percentage of waiting time in the real-time Flexible Job Shop problem. The result of the simulations proved that the proposed framework has reasonable performance and time efficiency.

Keywords: dynamic scheduling problem, flexible job shop, dispatching rules, deep reinforcement learning

Procedia PDF Downloads 106

Authors: Cesar Hernández, Diego Giral, Ingrid Páez

Abstract:

This article proposes a hybrid algorithm for spectrum allocation in cognitive radio networks based on the algorithms Analytical Hierarchical Process (AHP) and Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) to improve the performance of the spectrum mobility of secondary users in cognitive radio networks. To calculate the level of performance of the proposed algorithm a comparative analysis between the proposed AHP-TOPSIS, Grey Relational Analysis (GRA) and Multiplicative Exponent Weighting (MEW) algorithm is performed. Four evaluation metrics is used. These metrics are the accumulative average of failed handoffs, the accumulative average of handoffs performed, the accumulative average of transmission bandwidth, and the accumulative average of the transmission delay. The results of the comparison show that AHP-TOPSIS Algorithm provides 2.4 times better performance compared to a GRA Algorithm and, 1.5 times better than the MEW Algorithm.

Keywords: cognitive radio, decision making, hybrid algorithm, spectrum handoff, wireless networks

Procedia PDF Downloads 540

Authors: Priti Kumari, Tricha Anjali

Abstract:

Body Area Networks (BANs) have emerged as the most promising technology for pervasive health care applications. Since they facilitate communication of very sensitive health data, information leakage in such networks can put human life at risk, and hence security inside BANs is a critical issue. Safe distribution and periodic refreshment of cryptographic keys are needed to ensure the highest level of security. In this paper, we focus on the key distribution techniques and how they are categorized for BAN. The state-of-art pre-shared key distribution algorithms are surveyed. Possible attacks on algorithms are demonstrated with examples.

Keywords: attacks, body area network, key distribution, key refreshment, pre-shared keys

Procedia PDF Downloads 360

Authors: J. A. Ageeva, Z. S. Zavyalova

Abstract:

The article considers social media as a tool for business promotion. We analyze and compare the SMM experience in the western countries and Russia. A short review of Russian social networks are given including their peculiar features, and the main problems and perspectives of Russian SMM are described.

Keywords: social media, social networks, marketing, SMM

Procedia PDF Downloads 555

Authors: Ahmad M. Awwad, Jehad Al-Sadi

Abstract:

The star network is one of the promising interconnection networks for future high speed parallel computers, it is expected to be one of the future-generation networks. The star network is both edge and vertex symmetry, it was shown to have many gorgeous topological proprieties also it is owns hierarchical structure framework. Although much of the research work has been done on this promising network in literature, it still suffers from having enough algorithms for load balancing problem. In this paper we try to work on this issue by investigating and proposing an efficient algorithm for load balancing problem for the star network. The proposed algorithm is called Star Clustered Dimension Exchange Method SCDEM to be implemented on the star network. The proposed algorithm is based on the Clustered Dimension Exchange Method (CDEM). The SCDEM algorithm is shown to be efficient in redistributing the load balancing as evenly as possible among all nodes of different factor networks.

Keywords: load balancing, star network, interconnection networks, algorithm

Procedia PDF Downloads 319

Authors: Robert J. Thomas, Colton Bedke, Andrew Sorensen

Abstract:

The exemplary mechanical performance and durability of ultra-high performance concrete (UHPC) has led to its rapid emergence as an advanced cementitious material. The uncharacteristically high mechanical strength and ductility of UHPC makes it a promising potential material for defense structures which may be subject to highly dynamic loads like impact or blast. However, the mechanical response of UHPC under dynamic loading has not been fully characterized. In particular, there is a need to characterize the energy absorption of UHPC under high-frequency shear loading. This paper presents preliminary results from a parametric study of the dynamic shear energy absorption of UHPC using the Charpy impact test. UHPC mixtures with compressive strengths in the range of 100-150 MPa exhibited dynamic shear energy absorption in the range of 0.9-1.5 kJ/m. Energy absorption is shown to be sensitive to the water/cement ratio, silica fume content, and aggregate gradation. Energy absorption was weakly correlated to compressive strength. Results are highly sensitive to specimen preparation methods, and there is a demonstrated need for a standardized test method for high frequency shear in cementitious composites.

Keywords: Charpy impact test, dynamic shear, impact loading, ultra-high performance concrete

Procedia PDF Downloads 292

Authors: Ashok Kumar, Sarita Sahu, H. N. Bar

Abstract:

Low cycle fatigue behavior of a ferritic, martensitic pressure vessel steel at dynamic strain ageing regime of 250°C to 280°C has been investigated. Dynamic strain ageing is a mechanism that has attracted interests of researchers due to its fascinating inexplicable repetitive nature for quite a long time. The interaction of dynamic strain ageing and cyclic plasticity has been studied from the mechanistic point of view. Dynamic strain ageing gives rise to identical serrated flow behavior in tensile and compressive halves of hysteresis loops and this has been found to gives rise to initial cyclic hardening followed by softening behavior, where as in non-DSA regime continuous cyclic softening has been found to be the dominant mechanism. An appreciable sensitivity towards nature of serrations has been observed due to degree of hardening of stable loop. The increase in degree of hardening with strain amplitude in the regime where only A type serrations are present and it decreases with strain amplitude where A+B type of serrations are present. Masing type of locus has been found in the behavior of metal at 280°C. Cyclic Stress Strain curve and Master curve has been constructed to decipher among the fatigue strength and ductility coefficients. Fractographic examinations have also shown a competition between progression of striations and secondary cracking.

Keywords: dynamic strain ageing, hardening, low cycle fatigue, softening

Procedia PDF Downloads 299

Authors: Lamyaa Gamal El-Deen Taha, Ashraf Sharawi

Abstract:

Planet image is a new data source from planet lab. This research is concerned with the assessment of Planet image for land cover mapping. Two pixel based classifiers and one subpixel based classifier were compared. Firstly, rectification of Planet image was performed. Secondly, a comparison between minimum distance, maximum likelihood and neural network classifications for classification of Planet image was performed. Thirdly, the overall accuracy of classification and kappa coefficient were calculated. Results indicate that neural network classification is best followed by maximum likelihood classifier then minimum distance classification for land cover mapping.

Keywords: planet image, land cover mapping, rectification, neural network classification, multilayer perceptron, soft classifiers, hard classifiers

Procedia PDF Downloads 185

Authors: M. P. Nanda Kumar, K. Dheeraj

Abstract:

The design of a feedback controller, so as to minimize a given performance criterion, for a general non-linear dynamical system is difficult; if not impossible. But for a large class of non-linear dynamical systems, the open loop control that minimizes a performance criterion can be obtained using calculus of variations and Pontryagin’s minimum principle. In this paper, the open loop optimal trajectories, that minimizes a given performance measure, is used to train the neural network whose inputs are state variables of non-linear dynamical systems and the open loop optimal control as the desired output. This trained neural network is used as the feedback controller. In other words, attempts are made here to solve the “inverse optimal control problem” by using the state and control trajectories that are optimal in an open loop sense.

Keywords: inverse optimal control, radial basis function, neural network, controller design

Procedia PDF Downloads 550

Authors: Min Jindong, Wang Mingxia

Abstract:

With the widespread use of artificial intelligence in life, computer vision, especially deep convolutional neural network models, has developed rapidly. With the increase of the complexity of the real visual target detection task and the improvement of the recognition accuracy, the target detection network model is also very large. The huge deep neural network model is not conducive to deployment on edge devices with limited resources, and the timeliness of network model inference is poor. In this paper, knowledge distillation is used to compress the huge and complex deep neural network model, and the knowledge contained in the complex network model is comprehensively transferred to another lightweight network model. Different from traditional knowledge distillation methods, we propose a novel knowledge distillation that incorporates multi-faceted features, called M-KD. In this paper, when training and optimizing the deep neural network model for target detection, the knowledge of the soft target output of the teacher network in knowledge distillation, the relationship between the layers of the teacher network and the feature attention map of the hidden layer of the teacher network are transferred to the student network as all knowledge. in the model. At the same time, we also introduce an intermediate transition layer, that is, an intermediate guidance layer, between the teacher network and the student network to make up for the huge difference between the teacher network and the student network. Finally, this paper adds an exploration module to the traditional knowledge distillation teacher-student network model. The student network model not only inherits the knowledge of the teacher network but also explores some new knowledge and characteristics. Comprehensive experiments in this paper using different distillation parameter configurations across multiple datasets and convolutional neural network models demonstrate that our proposed new network model achieves substantial improvements in speed and accuracy performance.

Keywords: object detection, knowledge distillation, convolutional network, model compression

Procedia PDF Downloads 276

Authors: Chanyuan Gu, Shouming Zhong

Abstract:

Synchronization is a fundamental phenomenon that enables coherent behavior in networks as a result of interactions. The purpose of this research had been to investigate the problem of anti-phase synchronization for complex delayed dynamical networks with output coupling. The coupling configuration is general, with the coupling matrix not assumed to be symmetric or irreducible. The amount of the coupling variables between two connected nodes is flexible, the nodes in the drive and response systems need not to be identical and there is not any extra constraint on the coupling matrix. Some pinning controllers are designed to make the drive-response system achieve the anti-phase synchronization. For the convenience of description, we applied the matrix Kronecker product. Some new criteria are proposed based on the Lyapunov stability theory, linear matrix inequalities (LMI) and Schur complement. Lastly, some simulation examples are provided to illustrate the effectiveness of our proposed conditions.

Keywords: anti-phase synchronization, complex networks, output coupling, pinning control

Procedia PDF Downloads 394

Authors: Mu-Yen Chen, Min-Hsuan Fan, Chia-Chen Chen, Siang-Yu Jhong

Abstract:

In recent years, real estate prediction or valuation has been a topic of discussion in many developed countries. Improper hype created by investors leads to fluctuating prices of real estate, affecting many consumers to purchase their own homes. Therefore, scholars from various countries have conducted research in real estate valuation and prediction. With the back-propagation neural network that has been popular in recent years and the orthogonal array in the Taguchi method, this study aimed to find the optimal parameter combination at different levels of orthogonal array after the system presented different parameter combinations, so that the artificial neural network obtained the most accurate results. The experimental results also demonstrated that the method presented in the study had a better result than traditional machine learning. Finally, it also showed that the model proposed in this study had the optimal predictive effect, and could significantly reduce the cost of time in simulation operation. The best predictive results could be found with a fewer number of experiments more efficiently. Thus users could predict a real estate transaction price that is not far from the current actual prices.

Keywords: artificial neural network, Taguchi method, real estate valuation model, investors

Procedia PDF Downloads 485

Authors: Reza Dezvareh

Abstract:

The aim of this study is to investigate the amount of wind turbulence on the aero hydrodynamic behavior of offshore wind turbines with a monopile holder platform. Since in the sea, the wind turbine structures are under water and structures interactions, the dynamic analysis has been conducted under combined wind and wave loading. The offshore wind turbines have been investigated undertow models of normal and severe wind turbulence, and the results of this study show that the amplitude of fluctuation of dynamic response of structures including thrust force and base shear force of structures is increased with increasing the amount of wind turbulence, and this increase is not necessarily observed in the mean values of responses. Therefore, conducting the dynamic analysis is inevitable in order to observe the effect of wind turbulence on the structures' response.

Keywords: offshore wind turbine, wind turbulence, structural vibration, aero-hydro dynamic

Procedia PDF Downloads 206

Authors: Robson C. Santos, Christian N. Barreto, Gerson G. Cunha, Severino J. C. Neto

Abstract:

This paper aims to project the construction of a prototype azimuthal thruster, mounted with materials of low cost and easy access, testing in a controlled environment to measure their performance, characteristics and feasibility of future projects. The construction of the simulation of dynamic positioning software, responsible for simulating a vessel and reposition it when necessary . Tests for partial and full validation of the model were conducted, operates independently of the control system and executes the commands and commands of the helix of rotation azimuth. The system provides an interface to the user and simulates the conditions unfavorable positioning of a vessel, accurately calculates the azimuth angle, the direction of rotation of the helix and the time that this should be turned on so that the vessel back to position original. There is a serial communication that connects the Simulation Dynamic Positioning System with Embedded System causing the user-generated data to simulate the DP system arrives in the form of control signals to the motors of the propellant. This article addresses issues in the marine industry employees.

Keywords: azimuthal thruster, dynamic positioning, embedded system, simulator dynamic positioning

Procedia PDF Downloads 463

Authors: Sungkyung Kim, Jee-Hyeon Na, Dong-Seung Kwon

Abstract:

Future mobile networks following 5th generation will be characterized by one thousand times higher gains in capacity; connections for at least one hundred billion devices; user experience capable of extremely low latency and response times. To be close to the capacity requirements and higher reliability, advanced technologies have been studied, such as multiple connectivity, small cell enhancement, heterogeneous networking, and advanced interference and mobility management. This paper is focused on the multiple connectivity in heterogeneous cellular networks. We investigate the performance of coverage and user throughput in several deployment scenarios. Using the stochastic geometry approach, the SINR distributions and the coverage probabilities are derived in case of dual connection. Also, to compare the user throughput enhancement among the deployment scenarios, we calculate the spectral efficiency and discuss our results.

Keywords: heterogeneous networks, multiple connectivity, small cell enhancement, stochastic geometry

Procedia PDF Downloads 330

Authors: Joo-Hyung Oh

Abstract:

The number of service users of 4G VoLTE (voice over LTE) using LTE data networks is rapidly growing. VoLTE based on all-IP network enables clearer and higher-quality voice calls than 3G. It does, however, pose new challenges; a voice call through IP networks makes it vulnerable to security threats such as wiretapping and forged or falsified information. And in particular, stealing other users’ phone numbers and forging or falsifying call request messages from outgoing voice calls within VoLTE result in considerable losses that include user billing and voice phishing to acquaintances. This paper focuses on the threats of caller phone number spoofing in the VoLTE and countermeasure technology as safety measures for mobile communication networks.

Keywords: LTE, 4G, VoLTE, phone number spoofing

Procedia PDF Downloads 431

Authors: Tesfaye Mengistu

Abstract:

Power cables play a crucial role in the transmission and distribution of electrical energy. As the electricity generation, transmission, distribution, and storage systems become smarter, there is a growing emphasis on incorporating intelligent approaches to ensure the reliability of power cables. Various types of electrical cables are employed for transmitting and distributing electrical energy, with cross-linked polyethylene (XLPE) cables being widely utilized due to their exceptional electrical and mechanical properties. However, insulation defects can occur in XLPE cables due to subpar manufacturing techniques during production and cable joint installation. To address this issue, experts have proposed different methods for monitoring XLPE cables. Some suggest the use of interdigital capacitive (IDC) technology for online monitoring, while others propose employing continuous wave (CW) terahertz (THz) imaging systems to detect internal defects in XLPE plates used for power cable insulation. In this study, we have developed models that employ a custom dataset collected locally to classify the physical safety status of individual power cables. Our models aim to replace physical inspections with computer vision and image processing techniques to classify defective power cables from non-defective ones. The implementation of our project utilized the Python programming language along with the TensorFlow package and a convolutional neural network (CNN). The CNN-based algorithm was specifically chosen for power cable defect classification. The results of our project demonstrate the effectiveness of CNNs in accurately classifying power cable defects. We recommend the utilization of similar or additional datasets to further enhance and refine our models. Additionally, we believe that our models could be used to develop methodologies for detecting power cable defects from live video feeds. We firmly believe that our work makes a significant contribution to the field of power cable inspection and maintenance. Our models offer a more efficient and cost-effective approach to detecting power cable defects, thereby improving the reliability and safety of power grids.

Keywords: artificial intelligence, computer vision, defect detection, convolutional neural net

Procedia PDF Downloads 111

Authors: Bojan Najdenov, Danco Davcev

Abstract:

Reduction of traffic congestions and the effects of pollution and waste of resources that come with them has been a big challenge in the past decades. Having reliable systems to facilitate the process of modeling and prediction of traffic conditions would not only reduce the environmental pollution, but will also save people time and money. Social networks play big role of people’s lives nowadays providing them means of communicating and sharing thoughts and ideas, that way generating huge knowledge bases by crowdsourcing. In addition to that, crowdsourcing as a concept provides mechanisms for fast and relatively reliable data generation and also many services are being used on regular basis because they are mainly powered by the public as main content providers. In this paper we present the Social-NETS-Traffic-Control System (SNTCS) that should serve as a facilitator in the process of modeling and prediction of traffic congestions. The main contribution of our system is to integrate data from social networks as Twitter and also implements a custom created crowdsourcing subsystem with which users report traffic conditions using an android application. Our first experience of the usage of the system confirms that the integrated approach allows easy extension of the system with other social networks and represents a very useful tool for traffic control.

Keywords: traffic, congestion reduction, crowdsource, social networks, twitter, android

Procedia PDF Downloads 480

Authors: Sophia Shi

Abstract:

Acute kidney injury (AKI) is the sudden onset of kidney damage in which the kidneys cannot filter waste from the blood, requiring emergency hospitalization. AKI patient mortality rate is high in the ICU and is virtually impossible for doctors to predict because it is so unexpected. Currently, there is no hybrid model predicting AKI that takes advantage of two types of data. De-identified patient data from the MIMIC-III database and de-identified kidney images and corresponding patient records from the Beijing Hospital of the Ministry of Health were collected. Using data features including serum creatinine among others, two numeric models using MIMIC and Beijing Hospital data were built, and with the hospital ultrasounds, an image-only model was built. Convolutional neural networks (CNN) were used, VGG and Resnet for numeric data and Resnet for image data, and they were combined into a hybrid model by concatenating feature maps of both types of models to create a new input. This input enters another CNN block and then two fully connected layers, ending in a binary output after running through Softmax and additional code. The hybrid model successfully predicted AKI and the highest AUROC of the model was 0.953, achieving an accuracy of 90% and F1-score of 0.91. This model can be implemented into urgent clinical settings such as the ICU and aid doctors by assessing the risk of AKI shortly after the patient’s admission to the ICU, so that doctors can take preventative measures and diminish mortality risks and severe kidney damage.

Keywords: Acute kidney injury, Convolutional neural network, Hybrid deep learning, Patient record data, ResNet, Ultrasound kidney images, VGG

Procedia PDF Downloads 131