Search results for: Radial Basis Functions (RBF) neural networks

Authors: Shadrack Mambo, Karim Djouani, Yskandar Hamam, Barend van Wyk, Patrick Siarry

Abstract:

This paper discusses the current trends in medical image registration techniques and addresses the need to provide a solid theoretical foundation for research endeavours. Methodological analysis and synthesis of quality literature was done, providing a platform for developing a good foundation for research study in this field which is crucial in understanding the existing levels of knowledge. Research on medical image registration techniques assists clinical and medical practitioners in diagnosis of tumours and lesion in anatomical organs, thereby enhancing fast and accurate curative treatment of patients. Literature review aims to provide a solid theoretical foundation for research endeavours in image registration techniques. Developing a solid foundation for a research study is possible through a methodological analysis and synthesis of existing contributions. Out of these considerations, the aim of this paper is to enhance the scientific community’s understanding of the current status of research in medical image registration techniques and also communicate to them, the contribution of this research in the field of image processing. The gaps identified in current techniques can be closed by use of artificial neural networks that form learning systems designed to minimise error function. The paper also suggests several areas of future research in the image registration.

Keywords: image registration techniques, medical images, neural networks, optimisaztion, transformation

Procedia PDF Downloads 159

Authors: K. Bresilla, L. Manfrini, B. Morandi, A. Boini, G. Perulli, L. C. Grappadelli

Abstract:

Image/video processing for fruit in the tree using hard-coded feature extraction algorithms have shown high accuracy during recent years. While accurate, these approaches even with high-end hardware are computationally intensive and too slow for real-time systems. This paper details the use of deep convolution neural networks (CNNs), specifically an algorithm (YOLO - You Only Look Once) with 24+2 convolution layers. Using deep-learning techniques eliminated the need for hard-code specific features for specific fruit shapes, color and/or other attributes. This CNN is trained on more than 5000 images of apple and pear fruits on 960 cores GPU (Graphical Processing Unit). Testing set showed an accuracy of 90%. After this, trained data were transferred to an embedded device (Raspberry Pi gen.3) with camera for more portability. Based on correlation between number of visible fruits or detected fruits on one frame and the real number of fruits on one tree, a model was created to accommodate this error rate. Speed of processing and detection of the whole platform was higher than 40 frames per second. This speed is fast enough for any grasping/harvesting robotic arm or other real-time applications.

Keywords: artificial intelligence, computer vision, deep learning, fruit recognition, harvesting robot, precision agriculture

Procedia PDF Downloads 392

Authors: Syed Atif Hassan, Luv Mehta, Syed Asif Hassan

Abstract:

Hit song science is a field of investigation wherein machine learning techniques are applied to music tracks in order to extract such features from audio signals which can capture information that could explain the popularity of respective tracks. Record companies invest huge amounts of money into recruiting fresh talents and churning out new music each year. Gaining insight into the basis of why a song becomes popular will result in tremendous benefits for the music industry. This paper aims to extract basic musical and more advanced, acoustic features from songs while also taking into account external factors that play a role in making a particular song popular. We use a dataset derived from popular Spotify playlists divided by genre. We use ten genres (blues, classical, country, disco, hip-hop, jazz, metal, pop, reggae, rock), chosen on the basis of clear to ambiguous delineation in the typical sound of their genres. We feed these features into three different classifiers, namely, SVM with RBF kernel, a deep neural network, and a recurring neural network, to build separate predictive models and choosing the best performing model at the end. Predicting song popularity is particularly important for the music industry as it would allow record companies to produce better content for the masses resulting in a more competitive market.

Keywords: classifier, machine learning, music tracks, popularity, prediction

Procedia PDF Downloads 627

Authors: Hau-Wei Lee, Yu-Chi Liu, Chien-Hung Liu

Abstract:

A mathematical model is presented for a system that measures rotational errors in a shaft using a ball lens. The geometric optical characteristics of the ball lens mounted on the shaft allows the measurement of rotation axis errors in both the radial and axial directions. The equipment used includes two quadrant detectors (QD), two laser diodes and a ball lens that is mounted on the rotating shaft to be evaluated. Rotational errors in the shaft cause changes in the optical geometry of the ball lens. The resulting deflection of the laser beams is detected by the QDs and their output signals are used to determine rotational errors. The radial and the axial rotational errors can be calculated as explained by the mathematical model. Results from system calibration show that the measurement error is within ±1 m and resolution is about 20 nm. Using a direct drive motor (DD motor) as an example, experimental results show a rotational error of less than 20 m. The most important features of this system are that it does not require the use of expensive optical components, it is small, very easy to set up, and measurements are highly accurate.

Keywords: ball lens, quadrant detector, axial error, radial error

Procedia PDF Downloads 450

Authors: Haohao Wang

Abstract:

The purpose of this paper is to find elimination ideals via Grobner basis. We first introduce the concept of Grobner bases, and then, we provide computational algorithms to applications for curves and surfaces.

Keywords: curves, surfaces, Grobner basis, elimination

Procedia PDF Downloads 284

Authors: P. Karthick, K. Mahesh

Abstract:

Video has become an increasingly significant component of our digital everyday contact. With the advancement of greater contents and shows of the resolution, its significant volume poses serious obstacles to the objective of receiving, distributing, compressing, and revealing video content of high quality. In this paper, we propose the primary beginning to complete a deep video compression model that jointly upgrades all video compression components. The video compression method involves splitting the video into frames, comparing the images using convolutional neural networks (CNN) to remove duplicates, repeating the single image instead of the duplicate images by recognizing and detecting minute changes using generative adversarial network (GAN) and recorded with long short-term memory (LSTM). Instead of the complete image, the small changes generated using GAN are substituted, which helps in frame level compression. Pixel wise comparison is performed using K-nearest neighbours (KNN) over the frame, clustered with K-means, and singular value decomposition (SVD) is applied for each and every frame in the video for all three color channels [Red, Green, Blue] to decrease the dimension of the utility matrix [R, G, B] by extracting its latent factors. Video frames are packed with parameters with the aid of a codec and converted to video format, and the results are compared with the original video. Repeated experiments on several videos with different sizes, duration, frames per second (FPS), and quality results demonstrate a significant resampling rate. On average, the result produced had approximately a 10% deviation in quality and more than 50% in size when compared with the original video.

Keywords: video compression, K-means clustering, convolutional neural network, generative adversarial network, singular value decomposition, pixel visualization, stochastic gradient descent, frame per second extraction, RGB channel extraction, self-detection and deciding system

Procedia PDF Downloads 165

Authors: Li Kewen, Su Zhaoxin, Wang Xingmou, Zhu Jian Bing

Abstract:

Conventional reservoir prediction methods ar not sufficient to explore the implicit relation between seismic attributes, and thus data utilization is low. In order to improve the predictive classification accuracy of reservoir lithology, this paper proposes a deep learning lithology prediction method based on ResNet (Residual Neural Network) and SENet (Squeeze-and-Excitation Neural Network). The neural network model is built and trained by using seismic attribute data and lithology data of Shengli oilfield, and the nonlinear mapping relationship between seismic attribute and lithology marker is established. The experimental results show that this method can significantly improve the classification effect of reservoir lithology, and the classification accuracy is close to 70%. This study can effectively predict the lithology of undrilled area and provide support for exploration and development.

Keywords: convolutional neural network, lithology, prediction of reservoir, seismic attributes

Procedia PDF Downloads 158

Authors: Derjew Ayele Ejigu, Houde Song, Xiaojing Liu

Abstract:

This work presents the particle swarm optimization trained neural network (PSO-NN) supervisory proportional integral derivative (PID) control method to monitor the pressurized water reactor (PWR) core power for safe operation. The proposed control approach is implemented on the transfer function of the PWR core, which is computed from the state-space model. The PWR core state-space model is designed from the neutronics, thermal-hydraulics, and reactivity models using perturbation around the equilibrium value. The proposed control approach computes the control rod speed to maneuver the core power to track the reference in a closed-loop scheme. The particle swarm optimization (PSO) algorithm is used to train the neural network (NN) and to tune the PID simultaneously. The controller performance is examined using integral absolute error, integral time absolute error, integral square error, and integral time square error functions, and the stability of the system is analyzed by using the Bode diagram. The simulation results indicated that the controller shows satisfactory performance to control and track the load power effectively and smoothly as compared to the PSO-PID control technique. This study will give benefit to design a supervisory controller for nuclear engineering research fields for control application.

Keywords: machine learning, neural network, pressurized water reactor, supervisory controller

Procedia PDF Downloads 133

Authors: Khadija Refouh

Abstract:

Culture bound-expressions have been a bottleneck for Natural Language Processing (NLP) and comprehension, especially in the case of machine translation (MT). In the last decade, the field of machine translation has greatly advanced. Neural machine translation NMT has recently achieved considerable development in the quality of translation that outperformed previous traditional translation systems in many language pairs. Neural machine translation NMT is an Artificial Intelligence AI and deep neural networks applied to language processing. Despite this development, there remain some serious challenges that face neural machine translation NMT when translating culture bounded-expressions, especially for low resources language pairs such as Arabic-English and Arabic-French, which is not the case with well-established language pairs such as English-French. Machine translation of opaque idioms from English into French are likely to be more accurate than translating them from English into Arabic. For example, Google Translate Application translated the sentence “What a bad weather! It runs cats and dogs.” to “يا له من طقس سيء! تمطر القطط والكلاب” into the target language Arabic which is an inaccurate literal translation. The translation of the same sentence into the target language French was “Quel mauvais temps! Il pleut des cordes.” where Google Translate Application used the accurate French corresponding idioms. This paper aims to perform NMT experiments towards better translation of opaque idioms using high quality clean multilingual corpus. This Corpus will be collected analytically from human generated idiom translation. AutoML translation, a Google Neural Machine Translation Platform, is used as a custom translation model to improve the translation of opaque idioms. The automatic evaluation of the custom model will be compared to the Google NMT using Bilingual Evaluation Understudy Score BLEU. BLEU is an algorithm for evaluating the quality of text which has been machine-translated from one natural language to another. Human evaluation is integrated to test the reliability of the Blue Score. The researcher will examine syntactical, lexical, and semantic features using Halliday's functional theory.

Keywords: multilingual corpora, natural language processing (NLP), neural machine translation (NMT), opaque idioms

Procedia PDF Downloads 117

Authors: Pablo Martin, Jorge Olivares, Fernando Maass

Abstract:

The use of fractional derivatives to different problems in Engineering and Physics has been increasing in the last decade. For this reason, we have here considered partial derivatives when the integral is a spherical Bessel function of the first kind in both regular and modified ones simple initial conditions have been also considered. In this way, the solution has been found as a combination of hypergeometric functions. The case of a general rational value for α of the fractional derivative α has been solved in a general way for alpha between zero and two. The modified spherical Bessel functions of the first kind have been also considered and how to go from the regular case to the modified one will be also shown.

Keywords: caputo fractional derivatives, hypergeometric functions, linear differential equations, spherical Bessel functions

Procedia PDF Downloads 300

Authors: Ramin Karimi

Abstract:

One of common highly mobile wireless ad hoc networks is Vehicular Ad Hoc Networks. Hence routing in vehicular ad hoc network (VANET) has attracted much attention during the last few years. VANET is characterized by its high mobility of nodes and specific topology patterns. Moreover these networks encounter a significant loss rate and a very short duration of communication. In vehicular ad hoc networks, one of challenging is routing of data due to high speed mobility and changing topology of vehicles. Geographic routing protocols are becoming popular due to advancement and availability of GPS devices. Delay Tolerant Networks (DTNs) are a class of networks that enable communication where connectivity issues like sparse connectivity, intermittent connectivity; high latency, long delay, high error rates, asymmetric data rate, and even no end-to-end connectivity exist. In this paper, we review the existing Geographic Routing Protocols for VANETs and also provide a qualitative comparison of them.

Keywords: vehicular ad hoc networks, mobility, geographic routing, delay tolerant networks

Procedia PDF Downloads 493

Authors: Wafa Benaatou, Adnane Latif

Abstract:

In this document we studied more in detail the Performances of the vertical handover in the networks WLAN, WiMAX, UMTS before studying of it the Procedure of Handoff Vertical, the whole buckled by simulations putting forward the performances of the handover in the heterogeneous networks. The goal of Vertical Handover is to carry out several accesses in real-time in the heterogeneous networks. This makes it possible a user to use several networks (such as WLAN UMTS and WiMAX) in parallel, and the system to commutate automatically at another basic station, without disconnecting itself, as if there were no cut and with little loss of data as possible.

Keywords: vertical handoff, WLAN, UMTS, WIMAX, heterogeneous

Procedia PDF Downloads 365

Authors: Majid Rashidi, Shahrbanoo Farkhondeh Biabnavi

Abstract:

The hydrodynamic instability phenomenon in a journal bearing may occur by either a reduction in the load carried by journal bearing, by an increase in the journal speed, by change in the lubricant viscosity, or a combination of these factors. The previous research and development work done to overcome the instability issue of journal bearings, operating in hydrodynamic lubricate regime, can be categorized as follows: A) Actively controlling the bearing sleeve by using piezo actuator, b) Inclusion of strategically located and shaped internal grooves within inner surface of the bearing sleeve, c) Actively controlling the bearing sleeve using an electromagnetic actuator, d)Actively and externally pressurizing the lubricant within a journal bearing set, and e)Incorporating tilting pads within the inner surface of the bearing sleeve that assume different equilibrium angular position in response to changes in the bearing design parameter such as speed and load. This work presents an innovative design concept for a 'smart journal bearing' set to operate in a stable hydrodynamic lubrication regime, despite variations in bearing speed, load, and its lubricant viscosity. The proposed bearing design allows adjusting its radial clearance for an attempt to maintain a stable bearing operation under those conditions that may cause instability for a bearing with a fixed radial clearance. The design concept allows adjusting the radial clearance at small increments in the order of 0.00254 mm. This is achieved by axially moving two symmetric conical rigid cavities that are in close contact with the conically shaped outer shell of a sleeve bearing. The proposed work includes a 3D model of the bearing that depicts the structural interactions of the bearing components. The 3D model is employed to conduct finite element Analyses to simulate the mechanical behavior of the bearing from a structural point of view. The concept of controlling of the radial clearance, as presented in this work, is original and has not been proposed and discuss in previous research. A typical journal bearing was analyzed under a set of design parameters, namely r =1.27 cm (journal radius), c = 0.0254 mm (radial clearance), L=1.27 cm (bearing length), w = 445N (bearing load), μ = 0.028 Pascale (lubricant viscosity). A shaft speed as 3600 r.p.m was considered, and the mass supported by the bearing, m, is set to be 4.38kg. The Summerfield Number associated with the above bearing design parameters turn to be, S=0.3. These combinations resulted in stable bearing operation. Subsequently, the speed was postulated to increase from 3600 r.p.mto 7200 r.p.m; the bearing was found to be unstable under the new increased speed. In order to regain stability, the radial clearance was increased from c = 0.0254 mm to0.0358mm. The change in the radial clearance was shown to bring the bearing back to stable an operating condition.

Keywords: adjustable clearance, bearing, hydrodynamic, instability, journal

Procedia PDF Downloads 261

Authors: Haoshu Li, Shaolong Wan

Abstract:

The recent focus has been on directional signal amplification of a signal input at one end of a one-dimensional chain and measured at the other end. The amplification rate is given by the end-to-end Green’s functions of the system. In this work, we derive the exact formulas for the end-to-end Green's functions of non-Hermitian single-band systems. While in the bulk region, it is found that the Green's functions are displaced from the prior established integral formula by O(e⁻ᵇᴸ). The results confirm the correspondence between the signal amplification and the non-Hermitian skin effect.

Keywords: non-Hermitian, Green's function, non-Hermitian skin effect, signal amplification

Procedia PDF Downloads 119

Authors: A. M. Khourshid, A. M. El-Kassas, I. Sabry

Abstract:

The objective of this work was to investigate the mechanical properties in order to demonstrate the feasibility of friction stir welding for joining Al 6061 aluminium alloys. Welding was performed on pipe with different thickness (2, 3 and 4 mm), five rotational speeds (485, 710, 910, 1120 and 1400 rpm) and a traverse speed of 4mm/min. This work focuses on two methods which are artificial neural networks using software and Response Surface Methodology (RSM) to predict the tensile strength, the percentage of elongation and hardness of friction stir welded 6061 aluminium alloy. An Artificial Neural Network (ANN) model was developed for the analysis of the friction stir welding parameters of 6061 pipe. Tensile strength, the percentage of elongation and hardness of weld joints were predicted by taking the parameters tool rotation speed, material thickness and axial force as a function. A comparison was made between measured and predicted data. Response Surface Methodology (RSM) was also developed and the values obtained for the response tensile strength, the percentage of elongation and hardness are compared with measured values. The effect of FSW process parameters on mechanical properties of 6061 aluminium alloy has been analysed in detail.

Keywords: friction stir welding, aluminium alloy, response surface methodology, artificial neural network

Procedia PDF Downloads 269

Authors: H. Gorine, M. Ramadan Elmezughi

Abstract:

In this paper, we investigate security issues and challenges facing researchers in wireless sensor networks and countermeasures to resolve them. The broadcast nature of wireless communication makes Wireless Sensor Networks prone to various attacks. Due to resources limitation constraint in terms of limited energy, computation power and memory, security in wireless sensor networks creates different challenges than wired network security. We will discuss several attempts at addressing the issues of security in wireless sensor networks in an attempt to encourage more research into this area.

Keywords: wireless sensor networks, network security, light weight encryption, threats

Procedia PDF Downloads 494

Authors: Yin Yuanling

Abstract:

A Deep Feedback Recurrent Neural Network (DFRNN) and Bidirectional Long Short-Term Memory (BiLSTM) are designed to address the problem of low accuracy of traditional relationship extraction models. This method combines a deep feedback-based recurrent neural network (DFRNN) with a bi-directional long short-term memory (BiLSTM) approach. The method combines DFRNN, which extracts local features of text based on deep feedback recurrent mechanism, BiLSTM, which better extracts global features of text, and Self-Attention, which extracts semantic information. Experiments show that the method achieves an F1 value of 76.69% on the CEC dataset, which is 0.0652 better than the BiLSTM+Self-ATT model, thus optimizing the performance of the deep learning method in the event relationship extraction task.

Keywords: event relations, deep learning, DFRNN models, bi-directional long and short-term memory networks

Procedia PDF Downloads 112

Authors: Muazzam Ali Khan Khattak

Abstract:

Next Generation Network is combination of different networks having different technologies. Due to mobile nature of nodes the movement of nodes occurs from one network to another network. Multicasting in such networks is still a hot issue of research because the user in today's world wants reliable communication wherever it lies. Due to heterogeneity of NGN it is very difficult to handle reliable multicast communication. In this paper we proposed an improved scheme for reliable multicast communication in next generation networks. Because multicast communication is very important to deliver same data packets to multiple receivers and minimize the network traffic. This new scheme will make the multicast communication in NGN more reliable and efficient.

Keywords: next generation networks, route request, IPT, NACK, ARQ, DTN

Procedia PDF Downloads 477

Authors: Pau Rodriguez, Jordi Gonzalez, Josep M. Gonfaus, Xavier Roca

Abstract:

Image sharing in social networks has increased exponentially in the past years. Officially, there are 600 million Instagrammers uploading around 100 million photos and videos per day. Consequently, there is a need for developing new tools to understand the content expressed in shared images, which will greatly benefit social media communication and will enable broad and promising applications in education, advertisement, entertainment, and also psychology. Following these trends, our work aims to take advantage of the existing relationship between text and personality, already demonstrated by multiple researchers, so that we can prove that there exists a relationship between images and personality as well. To achieve this goal, we consider that images posted on social networks are typically conditioned on specific words, or hashtags, therefore any relationship between text and personality can also be observed with those posted images. Our proposal makes use of the most recent image understanding models based on neural networks to process the vast amount of data generated by social users to determine those images most correlated with personality traits. The final aim is to train a weakly-supervised image-based model for personality assessment that can be used even when textual data is not available, which is an increasing trend. The procedure is described next: we explore the images directly publicly shared by users based on those accompanying texts or hashtags most strongly related to personality traits as described by the OCEAN model. These images will be used for personality prediction since they have the potential to convey more complex ideas, concepts, and emotions. As a result, the use of images in personality questionnaires will provide a deeper understanding of respondents than through words alone. In other words, from the images posted with specific tags, we train a deep learning model based on neural networks, that learns to extract a personality representation from a picture and use it to automatically find the personality that best explains such a picture. Subsequently, a deep neural network model is learned from thousands of images associated with hashtags correlated to OCEAN traits. We then analyze the network activations to identify those pictures that maximally activate the neurons: the most characteristic visual features per personality trait will thus emerge since the filters of the convolutional layers of the neural model are learned to be optimally activated depending on each personality trait. For example, among the pictures that maximally activate the high Openness trait, we can see pictures of books, the moon, and the sky. For high Conscientiousness, most of the images are photographs of food, especially healthy food. The high Extraversion output is mostly activated by pictures of a lot of people. In high Agreeableness images, we mostly see flower pictures. Lastly, in the Neuroticism trait, we observe that the high score is maximally activated by animal pets like cats or dogs. In summary, despite the huge intra-class and inter-class variabilities of the images associated to each OCEAN traits, we found that there are consistencies between visual patterns of those images whose hashtags are most correlated to each trait.

Keywords: emotions and effects of mood, social impact theory in social psychology, social influence, social structure and social networks

Procedia PDF Downloads 172

Authors: Osung Im, Neha Yadav, Eui Hoon Lee, Joong Hoon Kim

Abstract:

Artificial Neural Network (ANN) approach is commonly used in lots of fields for forecasting. In water resources engineering, forecast of water level or inflow of reservoir is useful for various kind of purposes. Due to advantages of ANN, many papers were written for inflow prediction in river networks, but in this study, ANN is used in urban sewer networks. The growth of severe rain storm in Korea has increased flood damage severely, and the precipitation distribution is getting more erratic. Therefore, effective pump operation in pump station is an essential task for the reduction in urban area. If real time inflow of pump station reservoir can be predicted, it is possible to operate pump effectively for reducing the flood damage. This study used ANN model for pump station reservoir inflow prediction using upstream sewer depth data. For this study, rainfall events, sewer depth, and inflow into Banpo pump station reservoir between years of 2013-2014 were considered. Feed – Forward Back Propagation (FFBF), Cascade – Forward Back Propagation (CFBP), Elman Back Propagation (EBP) and Nonlinear Autoregressive Exogenous (NARX) were used as ANN model for prediction. A comparison of results with ANN model suggests that ANN is a powerful tool for inflow prediction using the sewer depth data.

Keywords: artificial neural network, forecasting, reservoir inflow, sewer depth

Procedia PDF Downloads 291

Authors: Kassim A. Jassim

Abstract:

In the present paper, we introduce and discuss a new class Kp(λ,α) of meromorphic multivalent functions in the punctured unit disk U*={z∈¢:0<|z|<1} defined by Ruscheweyh derivative. We obtain some sufficient conditions for the functions belonging to the class Kp(λ,α).

Keywords: meromorphic multivalent function, Ruscheweyh derivative, hadamard product

Procedia PDF Downloads 316

Authors: S. Ghammamy, M. Mirzaabdollahiha

Abstract:

Quantum mechanical calculations of energies, geometries, and vibrational wavenumbers of fluorous 1,3-dion compounds are carried out using density functional theory (DFT/B3LYP) method with LANL2DZ basis sets. The calculated HOMO and LUMO energies show that charge transfer occurs in the molecules. The thermodynamic functions of fluorous 1,3-dion compounds have been performed at B3LYP/LANL2DZ basis sets. The theoretical spectrograms for F NMR spectra of fluorous 1,3-dion compounds have also been constructed. The F NMR nuclear shieldings of fluoride ligands in fluorous 1,3-dion compounds have been studied quantum chemical.

Keywords: density function theory, natural bond orbital, HOMO, LOMO, fluorous

Procedia PDF Downloads 367

Authors: Natasha Petrovska, Mirjana Pavlovic, Maria M. Larrondo-Petrie

Abstract:

Neural stem cells (NSCs) are multi-potent, self-renewing cells that generate new neurons. Three subtypes of NSCs can be separated regarding the stages of NSC lineage: quiescent neural stem cells (qNSCs), activated neural stem cells (aNSCs) and neural progenitor cells (NPCs), but their gene expression signatures are not utterly understood yet. Single-cell examinations have started to elucidate the complex structure of NSC populations. Nevertheless, there is a lack of thorough molecular interpretation of the NSC lineage heterogeneity and an increasing need for tools to analyze and improve the efficiency and correctness of single-cell sequencing data. Feature selection and ordering can identify and classify the gene expression signatures of these subtypes and can discover novel subpopulations during the NSCs activation and differentiation processes. The aim here is to review the implementation of the feature selection technique on NSC subtypes and the classification techniques that have been used for the identification of gene expression signatures.

Keywords: feature selection, feature similarity, neural stem cells, genes, feature selection methods

Procedia PDF Downloads 120

Authors: Aleksei Samarin, Artyom Nazarenko, Valentin Malykh

Abstract:

Image enhancement is becoming more and more popular, especially on mobile devices. Nowadays, it is a common approach to enhance an image using a convolutional neural network (CNN). Such a network should be of significant size; otherwise, a possibility for the artifacts to occur is overgrowing. The existing large CNNs are computationally expensive, which could be crucial for mobile devices. Another important flaw of such models is they are poorly interpretable. There is another approach to image enhancement, namely, the usage of predefined filters in combination with the prediction of their applicability. We present an approach following this paradigm, which outperforms both existing CNN-based and filter-based approaches in the image enhancement task. It is easily adaptable for mobile devices since it has only 47 thousand parameters. It shows the best SSIM 0.919 on RANDOM250 (MIT Adobe FiveK) among small models and is thrice faster than previous models.

Keywords: universal filter, image enhancement, neural networks, computer vision

Procedia PDF Downloads 82

Authors: Pranav Gunhal., Krish Jhurani

Abstract:

This study tackles the significant computational challenge of predicting excited state dynamics in organic photovoltaic (OPV) materials—a pivotal factor in the performance of solar energy solutions. Time-dependent density functional theory (TDDFT), though effective, is computationally prohibitive for larger and more complex molecules. As a solution, the research explores the application of transformer neural networks, a type of artificial intelligence (AI) model known for its superior performance in natural language processing, to predict excited state dynamics in OPV materials. The methodology involves a two-fold process. First, the transformer model is trained on an extensive dataset comprising over 10,000 TDDFT calculations of excited state dynamics from a diverse set of OPV materials. Each training example includes a molecular structure and the corresponding TDDFT-calculated excited state lifetimes and key electronic transitions. Second, the trained model is tested on a separate set of molecules, and its predictions are rigorously compared to independent TDDFT calculations. The results indicate a remarkable degree of predictive accuracy. Specifically, for a test set of 1,000 OPV materials, the transformer model predicted excited state lifetimes with a mean absolute error of 0.15 picoseconds, a negligible deviation from TDDFT-calculated values. The model also correctly identified key electronic transitions contributing to the excited state dynamics in 92% of the test cases, signifying a substantial concordance with the results obtained via conventional quantum chemistry calculations. The practical integration of the transformer model with existing quantum chemistry software was also realized, demonstrating its potential as a powerful tool in the arsenal of materials scientists and chemists. The implementation of this AI model is estimated to reduce the computational cost of predicting excited state dynamics by two orders of magnitude compared to conventional TDDFT calculations. The successful utilization of transformer neural networks to accurately predict excited state dynamics provides an efficient computational pathway for the accelerated discovery and design of new OPV materials, potentially catalyzing advancements in the realm of sustainable energy solutions.

Keywords: transformer neural networks, organic photovoltaic materials, excited state dynamics, time-dependent density functional theory, predictive modeling

Procedia PDF Downloads 84

Authors: Ian O'Loughlin

Abstract:

Memory networks aim to integrate some of the recent successes in machine learning with a dynamic memory base that can be updated and deployed in artificial reasoning tasks. These models involve training networks to identify, update, and operate over stored elements in a large memory array in order, for example, to ably perform question and answer tasks parsing real-world and simulated discourses. This family of approaches still faces numerous challenges: the performance of these network models in simulated domains remains considerably better than in open, real-world domains, wide-context cues remain elusive in parsing words and sentences, and even moderately complex sentence structures remain problematic. This innovation, employing an array of stored and updatable ‘memory’ elements over which the system operates as it parses text input and develops responses to questions, is a compelling one for at least two reasons: first, it addresses one of the difficulties that standard machine learning techniques face, by providing a way to store a large bank of facts, offering a way forward for the kinds of long-term reasoning that, for example, recurrent neural networks trained on a corpus have difficulty performing. Second, the addition of a stored long-term memory component in artificial reasoning seems psychologically plausible; human reasoning appears replete with invocations of long-term memory, and the stored but dynamic elements in the arrays of memory networks are deeply reminiscent of the way that human memory is readily and often characterized. However, this apparent psychological plausibility is belied by a recent turn in the study of human memory in cognitive science. In recent years, the very notion that there is a stored element which enables remembering, however dynamic or reconstructive it may be, has come under deep suspicion. In the wake of constructive memory studies, amnesia and impairment studies, and studies of implicit memory—as well as following considerations from the cognitive neuroscience of memory and conceptual analyses from the philosophy of mind and cognitive science—researchers are now rejecting storage and retrieval, even in principle, and instead seeking and developing models of human memory wherein plasticity and dynamics are the rule rather than the exception. In these models, storage is entirely avoided by modeling memory using a recurrent neural network designed to fit a preconceived energy function that attains zero values only for desired memory patterns, so that these patterns are the sole stable equilibrium points in the attractor network. So although the array of long-term memory elements in memory networks seem psychologically appropriate for reasoning systems, they may actually be incurring difficulties that are theoretically analogous to those that older, storage-based models of human memory have demonstrated. The kind of emergent stability found in the attractor network models more closely fits our best understanding of human long-term memory than do the memory network arrays, despite appearances to the contrary.

Keywords: artificial reasoning, human memory, machine learning, neural networks

Procedia PDF Downloads 250

Authors: B. S.Akhmetov, S. T. Akhmetova, D. N. Nadeyev, V. Yu. Yegorov, V. V. Smogoonov

Abstract:

Estimated probabilities of errors of the first and second kind for nonideal biometrics-neural transducers 256 outputs, the construction of nomograms based error probability of 'own' and 'alien' from the mathematical expectation and standard deviation of the normalized measures Hamming.

Keywords: modeling, errors, probability, biometrics, neural network, authentication

Procedia PDF Downloads 466

Authors: Feng Wang, Shencheng Ni, Shuying Han, Shanhong You

Abstract:

With the development of optical communication, optical performance monitoring (OPM) has received more and more attentions. Since optical signal-to-noise ratio (OSNR) is directly related to bit error rate (BER), it is one of the important parameters in optical networks. Recently, artificial neural network (ANN) has been greatly developed. ANN has strong learning and generalization ability. In this paper, a method of OSNR monitoring based on delay-tap sampling (DTS) and ANN has been proposed. DTS technique is used to extract the eigenvalues of the signal. Then, the eigenvalues are input into the ANN to realize the OSNR monitoring. The experiments of 10 Gb/s non-return-to-zero (NRZ) on–off keying (OOK), 20 Gb/s pulse amplitude modulation (PAM4) and 20 Gb/s return-to-zero (RZ) differential phase-shift keying (DPSK) systems are demonstrated for the OSNR monitoring based on the proposed method. The experimental results show that the range of OSNR monitoring is from 15 to 30 dB and the root-mean-square errors (RMSEs) for 10 Gb/s NRZ-OOK, 20 Gb/s PAM4 and 20 Gb/s RZ-DPSK systems are 0.36 dB, 0.45 dB and 0.48 dB respectively. The impact of chromatic dispersion (CD) on the accuracy of OSNR monitoring is also investigated in the three experimental systems mentioned above.

Keywords: artificial neural network (ANN), chromatic dispersion (CD), delay-tap sampling (DTS), optical signal-to-noise ratio (OSNR)

Procedia PDF Downloads 90

Authors: Fernando Maass, Pablo Martin, Jorge Olivares

Abstract:

Fractional derivatives have become very important in several areas of Engineering, however, the solutions of simple differential equations are not known. Here we are considering the simplest first order nonhomogeneous differential equations with Bessel regular functions of the first kind, in this way the solutions have been found which are hypergeometric solutions for any fractional derivative of order α, where α is rational number α=m/p, between zero and one. The way to find this result is by using Laplace transform and the Caputo definitions of fractional derivatives. This method is for values longer than one. However for α entire number the hypergeometric functions are Kumer type, no integer values of alpha, the hypergeometric function is more complicated is type ₂F₃(a,b,c, t2/2). The argument of the hypergeometric changes sign when we go from the regular Bessel functions to the modified Bessel functions of the first kind, however it integer seems that using precise values of α and considering no integers values of α, a solution can be obtained in terms of two hypergeometric functions. Further research is required for future papers in order to obtain the general solution for any rational value of α.

Keywords: Caputo, fractional calculation, hypergeometric, linear differential equations

Procedia PDF Downloads 176

Authors: Artion Kashuri, Rozana Liko

Abstract:

In this paper, the authors establish an integral identity using delta differentiable functions. By applying this identity, some new results via a general class of convex functions with respect to two nonnegative functions on a time scale are given. Also, for suitable choices of nonnegative functions, some special cases are deduced. Finally, in order to illustrate the efficiency of our main results, some applications to special means are obtained as well. We hope that current work using our idea and technique will attract the attention of researchers working in mathematical analysis, mathematical inequalities, numerical analysis, special functions, fractional calculus, quantum mechanics, quantum calculus, physics, probability and statistics, differential and difference equations, optimization theory, and other related fields in pure and applied sciences.

Keywords: convex functions, Hermite-Hadamard inequality, special means, time scale

Procedia PDF Downloads 131