Search results for: hardy cross networks accuracy

Authors: Mohammad Yahaghifar

Abstract:

Nowadays Wireless system designers have been facing the continuously increasing demand for high data rates and mobility required by new wireless applications. Evolving future communication network generation cellular wireless networks are envisioned to overcome the fundamental challenges of existing cellular networks, for example, higher data rates, excellent end-to-end performance, and user coverage in hot-spots and crowded areas with lower latency,energy consumption and cost per information transfer. In this paper we propose a potential cellular architecture that separates indoor and outdoor scenarios and discuss various promising technologies for future wireless communication systemssystems, such as massive MIMO, energy-efficient communications,cognitive radio networks, and visible light communications and we disscuse about 5G that is next generation of wireless networks.

Keywords: future challenges in networks, cellur architecture, visible light communication, 5G wireless technologies, spatial modulation, massiva mimo, cognitive radio network, green communications

Procedia PDF Downloads 456

Authors: Michael Hast

Abstract:

Surprisingly little is known from a research perspective about children’s understanding of rainbows and rainbow formation, and how this understanding changes with increasing age. Yet this kind of research is useful when conceptualizing pedagogy, lesson plans, or more general curricula. The present study aims to rectify this shortcoming. In a cross-sectional approach, children of three different age groups (4-5, 7-8 and 10-11 years) were asked to draw pictures that included rainbows. The pictures will be evaluated according to their scientific representation of rainbows, such as the order of colors, as well as according to any non-scientific conceptions, such as solidity. In addition to the drawings, the children took part in small focus groups where they had to discuss various questions about rainbows and rainbow formation. Similar to the drawings, these conversations will be evaluated around the degree of scientific accuracy of the children’s explanations. Gaining a complete developmental picture of children’s understanding of the rainbow may have important implications for pedagogy in early science education. Many other concepts in science, while not explicitly linked to rainbows and rainbow formation, can benefit from the use of rainbows as illustrations – such as understanding light and color, or the use of prisms. Even in non-science domains, such as art and even storytelling, recognizing the differentiation between fact and myth in relation to rainbows could be of value. In addition, research has pointed out that teachers tend to overestimate the proportion of students’ correct answers, so clarifying the actual level of conceptual understanding is crucial in this respect.

Keywords: conceptual development, cross-sectional research, primary science education, rainbows

Procedia PDF Downloads 186

Authors: Erick C. Valverde, Wansu Lim

Abstract:

Facial emotion recognition (FER) system has been recently developed for more advanced computer vision applications. The ability to identify human emotions would enable smart healthcare facility to diagnose mental health illnesses (e.g., depression and stress) as well as better human social interactions with smart technologies. The FER system involves two steps: 1) face detection task and 2) facial emotion recognition task. It classifies the human expression in various categories such as angry, disgust, fear, happy, sad, surprise, and neutral. This system requires intensive research to address issues with human diversity, various unique human expressions, and variety of human facial features due to age differences. These issues generally affect the ability of the FER system to detect human emotions with high accuracy. Early stage of FER systems used simple supervised classification task algorithms like K-nearest neighbors (KNN) and artificial neural networks (ANN). These conventional FER systems have issues with low accuracy due to its inefficiency to extract significant features of several human emotions. To increase the accuracy of FER systems, deep learning (DL)-based methods, like convolutional neural networks (CNN), are proposed. These methods can find more complex features in the human face by means of the deeper connections within its architectures. However, the inference speed and computational costs of a DL-based FER system is often disregarded in exchange for higher accuracy results. To cope with this drawback, an optimized DL-based FER system is proposed in this study.An extreme version of Inception V3, known as Xception model, is leveraged by applying different network optimization methods. Specifically, network pruning and quantization are used to enable lower computational costs and reduce memory usage, respectively. To support low resource requirements, a 68-landmark face detector from Dlib is used in the early step of the FER system.Furthermore, a DL compiler is utilized to incorporate advanced optimization techniques to the Xception model to improve the inference speed of the FER system. In comparison to VGG-Net and ResNet50, the proposed optimized DL-based FER system experimentally demonstrates the objectives of the network optimization methods used. As a result, the proposed approach can be used to create an efficient and real-time FER system.

Keywords: deep learning, face detection, facial emotion recognition, network optimization methods

Procedia PDF Downloads 78

Authors: Mouhammd Alkasassbeh, Alaa Lasasmeh

Abstract:

We live in an era of rapid development as a result of significant scientific growth. Like other technologies, wireless sensor networks (WSNs) are playing one of the main roles. Based on WSNs, ZigBee adds many features to devices, such as minimum cost and power consumption, and increasing the range and connect ability of sensor nodes. ZigBee technology has come to be used in various fields, including science, engineering, and networks, and even in medicinal aspects of intelligence building. In this work, we generated two main datasets, the first being based on tree topology and the second on star topology. The datasets were evaluated by three machine learning (ML) algorithms: J48, meta.j48 and multilayer perceptron (MLP). Each topology was classified into normal and abnormal (attack) network traffic. The dataset used in our work contained simulated data from network simulation 2 (NS2). In each database, the Bayesian network meta.j48 classifier achieved the highest accuracy level among other classifiers, of 99.7% and 99.2% respectively.

Keywords: IDS, Machine learning, WSN, ZigBee technology

Procedia PDF Downloads 515

Authors: Mahdi Pirmoradian, Olayinka Adigun, Christos Politis

Abstract:

Cooperative spectrum sensing is a crucial challenge in cognitive radio networks. Cooperative sensing can increase the reliability of spectrum hole detection, optimize sensing time and reduce delay in cooperative networks. In this paper, an efficient central capacity optimization algorithm is proposed to minimize cooperative sensing time in a homogenous sensor network using OR decision rule subject to the detection and false alarm probabilities constraints. The evaluation results reveal significant improvement in the sensing time and normalized capacity of the cognitive sensors.

Keywords: cooperative networks, normalized capacity, sensing time

Procedia PDF Downloads 596

Authors: M. C. Paliwal, A. K. Jain, S. K. Katiyar

Abstract:

Classification of satellite imagery is very important for the assessment of its accuracy. In order to determine the accuracy of the classified image, usually the assumed-true data are derived from ground truth data using Global Positioning System. The data collected from satellite imagery and ground truth data is then compared to find out the accuracy of data and error matrices are prepared. Overall and individual accuracies are calculated using different methods. The study illustrates advanced classification and accuracy assessment of land use/land cover mapping using satellite imagery. IRS-1C-LISS IV data were used for classification of satellite imagery. The satellite image was classified using the software in fourteen classes namely water bodies, agricultural fields, forest land, urban settlement, barren land and unclassified area etc. Classification of satellite imagery and calculation of accuracy was done by using ERDAS-Imagine software to find out the best method. This study is based on the data collected for Bhopal city boundaries of Madhya Pradesh State of India.

Keywords: resolution, accuracy assessment, land use mapping, satellite imagery, ground truth data, error matrices

Procedia PDF Downloads 472

Authors: Jeremy Jenrette, Z. Y. C. Liu, Pranav Chimote, Edward Fox, Trevor Hastie, Francesco Ferretti

Abstract:

Suitable shark conservation depends on well-informed population assessments. Direct methods such as scientific surveys and fisheries monitoring are adequate for defining population statuses, but species-specific indices of abundance and distribution coming from these sources are rare for most shark species. We can rapidly fill these information gaps by boosting media-based remote monitoring efforts with machine learning and automation. We created a database of shark images by sourcing 24,546 images covering 219 species of sharks from the web application spark pulse and the social network Instagram. We used object detection to extract shark features and inflate this database to 53,345 images. We packaged object-detection and image classification models into a Shark Detector bundle. We developed the Shark Detector to recognize and classify sharks from videos and images using transfer learning and convolutional neural networks (CNNs). We applied these models to common data-generation approaches of sharks: boosting training datasets, processing baited remote camera footage and online videos, and data-mining Instagram. We examined the accuracy of each model and tested genus and species prediction correctness as a result of training data quantity. The Shark Detector located sharks in baited remote footage and YouTube videos with an average accuracy of 89\%, and classified located subjects to the species level with 69\% accuracy (n =\ eight species). The Shark Detector sorted heterogeneous datasets of images sourced from Instagram with 91\% accuracy and classified species with 70\% accuracy (n =\ 17 species). Data-mining Instagram can inflate training datasets and increase the Shark Detector’s accuracy as well as facilitate archiving of historical and novel shark observations. Base accuracy of genus prediction was 68\% across 25 genera. The average base accuracy of species prediction within each genus class was 85\%. The Shark Detector can classify 45 species. All data-generation methods were processed without manual interaction. As media-based remote monitoring strives to dominate methods for observing sharks in nature, we developed an open-source Shark Detector to facilitate common identification applications. Prediction accuracy of the software pipeline increases as more images are added to the training dataset. We provide public access to the software on our GitHub page.

Keywords: classification, data mining, Instagram, remote monitoring, sharks

Procedia PDF Downloads 89

Authors: Sorin Valcan, Mihail Gaianu

Abstract:

Labeling is a very costly and time consuming process which aims to generate datasets for training neural networks in several functionalities and projects. For driver monitoring system projects, the need for labeled images has a significant impact on the budget and distribution of effort. This paper presents the modifications done to an algorithm used for the generation of ground truth data for 2D eyes location on infrared images with drivers in order to improve the quality of the data and performance of the trained neural networks. The algorithm restrictions become tougher, which makes it more accurate but also less constant. The resulting dataset becomes smaller and shall not be altered by any kind of manual label adjustment before being used in the neural networks training process. These changes resulted in a much better performance of the trained neural networks.

Keywords: labeling automation, infrared camera, driver monitoring, eye detection, convolutional neural networks

Procedia PDF Downloads 80

Authors: Afnan Al-Romi, Iman Al-Momani

Abstract:

The urge of applying the Software Engineering (SE) processes is both of vital importance and a key feature in critical, complex large-scale systems, for example, safety systems, security service systems, and network systems. Inevitably, associated with this are risks, such as system vulnerabilities and security threats. The probability of those risks increases in unsecured environments, such as wireless networks in general and in Wireless Sensor Networks (WSNs) in particular. WSN is a self-organizing network of sensor nodes connected by wireless links. WSNs consist of hundreds to thousands of low-power, low-cost, multi-function sensor nodes that are small in size and communicate over short-ranges. The distribution of sensor nodes in an open environment that could be unattended in addition to the resource constraints in terms of processing, storage and power, make such networks in stringent limitations such as lifetime (i.e. period of operation) and security. The importance of WSN applications that could be found in many militaries and civilian aspects has drawn the attention of many researchers to consider its security. To address this important issue and overcome one of the main challenges of WSNs, security solution systems have been developed by researchers. Those solutions are software-based network Intrusion Detection Systems (IDSs). However, it has been witnessed, that those developed IDSs are neither secure enough nor accurate to detect all malicious behaviours of attacks. Thus, the problem is the lack of coverage of all malicious behaviours in proposed IDSs, leading to unpleasant results, such as delays in the detection process, low detection accuracy, or even worse, leading to detection failure, as illustrated in the previous studies. Also, another problem is energy consumption in WSNs caused by IDS. So, in other words, not all requirements are implemented then traced. Moreover, neither all requirements are identified nor satisfied, as for some requirements have been compromised. The drawbacks in the current IDS are due to not following structured software development processes by researches and developers when developing IDS. Consequently, they resulted in inadequate requirement management, process, validation, and verification of requirements quality. Unfortunately, WSN and SE research communities have been mostly impermeable to each other. Integrating SE and WSNs is a real subject that will be expanded as technology evolves and spreads in industrial applications. Therefore, this paper will study the importance of Requirement Engineering when developing IDSs. Also, it will study a set of existed IDSs and illustrate the absence of Requirement Engineering and its effect. Then conclusions are drawn in regard of applying requirement engineering to systems to deliver the required functionalities, with respect to operational constraints, within an acceptable level of performance, accuracy and reliability.

Keywords: software engineering, requirement engineering, Intrusion Detection System, IDS, Wireless Sensor Networks, WSN

Procedia PDF Downloads 292

Authors: Natarajan Ramasamy, Gurulingamurthy Haralur, Ramesh Nivarthu, Nikhil Kumar Singha

Abstract:

Elastomers are polymeric materials with varied backbone architectures ranging from linear to dendrimeric structures and wide varieties of monomeric repeat units. These elastomers show strongly viscous and weakly elastic when it is not cross-linked. But when crosslinked, based on the extent the properties of these elastomers can range from highly flexible to highly stiff nature. Lightly cross-linked systems are well studied and reported. Understanding the nature of highly cross-linked rubber based upon chemical structure and architecture is critical for varieties of applications. One of the critical parameters is cross-link density. In the current work, we have studied the highly cross-linked state of linear, lightly branched to star-shaped branched elastomers and determined the cross-linked density by using different models. Change in hardness, shift in Tg, change in modulus and swelling behavior were measured experimentally as a function of the extent of curing. These properties were analyzed using varied models to determine cross-link density. We used hardness measurements to examine cure time. Hardness to the extent of curing relationship is determined. It is well known that micromechanical transitions like Tg and storage modulus are related to the extent of crosslinking. The Tg of the elastomer in different crosslinked state was determined by DMA, and based on plateau modulus the crosslink density is estimated by using Nielsen’s model. Usually for lightly crosslinked systems, based on equilibrium swelling ratio in solvent the cross link density is estimated by using Flory–Rhener model. When it comes to highly crosslinked system, Flory-Rhener model is not valid because of smaller chain length. So models based on the assumption of polymer as a Non-Gaussian chain like 1) Helmis–Heinrich–Straube (HHS) model, 2) Gloria M.gusler and Yoram Cohen Model, 3) Barbara D. Barr-Howell and Nikolaos A. Peppas model is used for estimating crosslink density. In this work, correction factors are determined to the existing models and based upon it structure-property relationship of highly crosslinked elastomers was studied.

Keywords: dynamic mechanical analysis, glass transition temperature, parts per hundred grams of rubber, crosslink density, number of networks per unit volume of elastomer

Procedia PDF Downloads 136

Authors: Mohammed Ali Hjaji, Magdi Mohareb

Abstract:

This paper develops the exact solutions for coupled flexural-lateral-torsional static response of thin-walled asymmetric open members subjected to general loading. Using the principle of stationary total potential energy, the governing differential equations of equilibrium are formulated as well as the associated boundary conditions. The formulation is based on a generalized Timoshenko-Vlasov beam theory and accounts for the effects of shear deformation due to bending and warping, and captures the effects of flexural–torsional coupling due to cross-section asymmetry. Closed-form solutions are developed for cantilever and simply supported beams under various forces. In order to demonstrate the validity and the accuracy of this solution, numerical examples are presented and compared with well-established ABAQUS finite element solutions and other numerical results available in the literature. In addition, the results are compared against non-shear deformable beam theories in order to demonstrate the shear deformation effects.

Keywords: asymmetric cross-section, flexural-lateral-torsional response, Vlasov-Timoshenko beam theory, closed form solution

Procedia PDF Downloads 444

Authors: Sirilak Areerachakul, Nat Ployong, Supayothin Na Songkla

Abstract:

This research’s objective is to select the model with most accurate value by using Neural Network Technique as a way to filter potential students who enroll in IT course by electronic learning at Suan Suanadha Rajabhat University. It is designed to help students selecting the appropriate courses by themselves. The result showed that the most accurate model was 100 Folds Cross-validation which had 73.58% points of accuracy.

Keywords: artificial neural network, classification, students, e-learning

Procedia PDF Downloads 393

Authors: Elena Kovalevich, Irina Tomasheva

Abstract:

The research relevance is caused by the importance of studying features of cross-cultural communication in the system of intensive language contacts, on the one hand, and on the other – by the need of control over the language situation as cross-cultural contacts often reflect emotionally intense reality, destructive for national culture and language and also for health and mentality of the individual. The objective consists in systematization of requirements imposed by the globalized society on ethics, aesthetics and emotive component of cross-cultural communication under conditions of language hybridization of modern Russian-speaking society. Problems connected with establishing the criteria differentiating eco-friendly and eco-unfriendly communication; identifying the specifics of the eco-unfriendly communication containing language hybrids; justifying the negative impact of language hybridization on ethics and esthetics of cross-cultural communication are considered, taking into account the category of emotivity. The study makes a contribution to the development of key problems of modern linguistics connected with exploration of basics in the theory of language personality, ecology of language, emotive linguistics. The results can be used by specialists in the fields of sociolinguistics, cross-cultural communication, the national language policy.

Keywords: cross-cultural communication, eco-linguistics, ethics and aesthetics, emotivity, language hybrids

Procedia PDF Downloads 148

Authors: Xiaolin Zeng, Lei Cheng, Zhirong Li, Xueping Liu

Abstract:

Aiming at the problem of low accuracy and susceptibility to cultural relic diseases in the generation of high-resolution archaeology drawings by current image generation algorithms, an archaeology drawings generation algorithm based on a conditional generative adversarial network is proposed. An attention mechanism is added into the high-resolution image generation network as the backbone network, which enhances the line feature extraction capability and improves the accuracy of line drawing generation. A dual-branch parallel architecture consisting of two backbone networks is implemented, where the semantic translation branch extracts semantic features from orthophotographs of cultural relics, and the gradient screening branch extracts effective gradient features. Finally, the fusion fine-tuning module combines these two types of features to achieve the generation of high-quality and high-resolution archaeology drawings. Experimental results on the self-constructed archaeology drawings dataset of grotto temple statues show that the proposed algorithm outperforms current mainstream image generation algorithms in terms of pixel accuracy (PA), structural similarity (SSIM), and peak signal-to-noise ratio (PSNR) and can be used to assist in drawing archaeology drawings.

Keywords: archaeology drawings, digital heritage, image generation, deep learning

Procedia PDF Downloads 19

Authors: Mumtaz Begum Mustafa, Siti Salwah Salim, Feizal Dani Rahman

Abstract:

Recently, Automatic Speech Recognition (ASR) systems were used to assist children in language acquisition as it has the ability to detect human speech signal. Despite the benefits offered by the ASR system, there is a lack of ASR systems for Malay-speaking children. One of the contributing factors for this is the lack of continuous speech database for the target users. Though cross-lingual adaptation is a common solution for developing ASR systems for under-resourced language, it is not viable for children as there are very limited speech databases as a source model. In this research, we propose a two-stage adaptation for the development of ASR system for Malay-speaking children using a very limited database. The two stage adaptation comprises the cross-lingual adaptation (first stage) and cross-age adaptation. For the first stage, a well-known speech database that is phonetically rich and balanced, is adapted to the medium-sized Malay adults using supervised MLLR. The second stage adaptation uses the speech acoustic model generated from the first adaptation, and the target database is a small-sized database of the target users. We have measured the performance of the proposed technique using word error rate, and then compare them with the conventional benchmark adaptation. The two stage adaptation proposed in this research has better recognition accuracy as compared to the benchmark adaptation in recognizing children’s speech.

Keywords: Automatic Speech Recognition System, children speech, adaptation, Malay

Procedia PDF Downloads 366

Authors: Mohamed Adnan Landolsi, Ali F. Almutairi

Abstract:

The paper addresses the problem of line-of-sight (LOS) vs. non-line-of-sight (NLOS) propagation link identification in ultra-wideband (UWB) wireless networks, which is necessary for improving the accuracy of radiolocation and positioning applications. A LOS/NLOS likelihood hypothesis testing approach is applied based on exploiting distinctive statistical features of the channel impulse response (CIR) using parameters related to the “skewness” of the CIR and its root mean square (RMS) delay spread. A log-normal fit is presented for the probability densities of the CIR parameters. Simulation results show that different environments (residential, office, outdoor, etc.) have measurable differences in their CIR parameters’ statistics, which is then exploited in determining the nature of the propagation channels. Correct LOS/NLOS channel identification rates exceeding 90% are shown to be achievable for most types of environments. Additional improvement is also obtained by combining both CIR skewness and RMS delay statistics.

Keywords: UWB, propagation, LOS, NLOS, identification

Procedia PDF Downloads 208

Authors: Naim Karasekreter, Ugur Fidan, Fatih Basciftci

Abstract:

Wireless sensor networks are networks in which more than one sensor node is organized among themselves. The working principle is based on the transfer of the sensed data over the other nodes in the network to the central station. Wireless sensor networks concentrate on routing algorithms, energy efficiency and clustering algorithms. In the clustering method, the nodes in the network are divided into clusters using different parameters and the most suitable cluster head is selected from among them. The data to be sent to the center is sent per cluster, and the cluster head is transmitted to the center. With this method, the network traffic is reduced and the energy efficiency of the nodes is increased. In this study, clustering algorithms were examined in terms of clustering performances and cluster head selection characteristics to try to identify weak and strong sides. This work is supported by the Project 17.Kariyer.123 of Afyon Kocatepe University BAP Commission.

Keywords: wireless sensor networks (WSN), clustering algorithm, cluster head, clustering

Procedia PDF Downloads 473

Authors: Hong Lu, Wei Fan, Yongquan Zhang, Junbo Zhang

Abstract:

A cross coupling sliding synchronization control strategy is proposed for the dual-driving feed system. This technology will minimize the position error oscillation and achieve the precise synchronization performance in the high speed and high precision drive system, especially some high speed and high precision machine. Moreover, a cross coupling compensation matrix is provided to offset the mismatched disturbance and the disturbance observer is established to eliminate the chattering phenomenon. Performance comparisons of proposed dual-driving cross coupling sliding mode control (CCSMC), normal cross coupling control （CCC） strategy with PID control, and electronic virtual main shaft control (EVMSC) strategy with SMC control are investigated by simulation and a dual-driving control system; the results show the effectiveness of the proposed control scheme.

Keywords: cross coupling matrix, dual motors, synchronization control, sliding mode control

Procedia PDF Downloads 340

Authors: Ella Sèdé Maforikan

Abstract:

Accurate land cover mapping is essential for effective environmental monitoring and natural resources management. This study focuses on assessing the classification performance of two satellite datasets and evaluating the impact of different input feature combinations on classification accuracy in the Beterou catchment, situated in the northern part of Benin. Landsat-8 and Sentinel-2 images from June 1, 2020, to March 31, 2021, were utilized. Employing the Random Forest (RF) algorithm on Google Earth Engine (GEE), a supervised classification categorized the land into five classes: forest, savannas, cropland, settlement, and water bodies. GEE was chosen due to its high-performance computing capabilities, mitigating computational burdens associated with traditional land cover classification methods. By eliminating the need for individual satellite image downloads and providing access to an extensive archive of remote sensing data, GEE facilitated efficient model training on remote sensing data. The study achieved commendable overall accuracy (OA), ranging from 84% to 85%, even without incorporating spectral indices and terrain metrics into the model. Notably, the inclusion of additional input sources, specifically terrain features like slope and elevation, enhanced classification accuracy. The highest accuracy was achieved with Sentinel-2 (OA = 91%, Kappa = 0.88), slightly surpassing Landsat-8 (OA = 90%, Kappa = 0.87). This underscores the significance of combining diverse input sources for optimal accuracy in land cover mapping. The methodology presented herein not only enables the creation of precise, expeditious land cover maps but also demonstrates the prowess of cloud computing through GEE for large-scale land cover mapping with remarkable accuracy. The study emphasizes the synergy of different input sources to achieve superior accuracy. As a future recommendation, the application of Light Detection and Ranging (LiDAR) technology is proposed to enhance vegetation type differentiation in the Beterou catchment. Additionally, a cross-comparison between Sentinel-2 and Landsat-8 for assessing long-term land cover changes is suggested.

Keywords: land cover mapping, Google Earth Engine, random forest, Beterou catchment

Procedia PDF Downloads 30

Authors: Chia-Feng Lu, Yuh-Jen Wang, Yu-Te Wu, Sui-Hing Yan

Abstract:

This study aimed at investigating whether the functional brain networks constructed using the initial EEG (obtained when patients first visited hospital) can be correlated with the progression of cognitive decline calculated as the changes of mini-mental state examination (MMSE) scores between the latest and initial examinations. We integrated the time–frequency cross mutual information (TFCMI) method to estimate the EEG functional connectivity between cortical regions, and the network analysis based on graph theory to investigate the organization of functional networks in aMCI. Our finding suggested that higher integrated functional network with sufficient connection strengths, dense connection between local regions, and high network efficiency in processing information at the initial stage may result in a better prognosis of the subsequent cognitive functions for aMCI. In conclusion, the functional connectivity can be a useful biomarker to assist in prediction of cognitive declines in aMCI.

Keywords: cognitive decline, functional connectivity, MCI, MMSE

Procedia PDF Downloads 344

Authors: Sergey Ermolin, Olga Ermolin

Abstract:

A Deep Convolution Neural Network with Triplet Loss is used to identify duplicate images in real-estate advertisements in the presence of image artifacts such as watermarking, cropping, hue/brightness adjustment, and others. The effects of batch normalization, spatial dropout, and various convergence methodologies on the resulting detection accuracy are discussed. For comparative Return-on-Investment study (per industry request), end-2-end performance is benchmarked on both Nvidia Titan GPUs and Intel’s Xeon CPUs. A new real-estate dataset from San Francisco Bay Area is used for this work. Sufficient duplicate detection accuracy is achieved to supplement other database-grounded methods of duplicate removal. The implemented method is used in a Proof-of-Concept project in the real-estate industry.

Keywords: visual recognition, convolutional neural networks, triplet loss, spatial batch normalization with dropout, duplicate removal, advertisement technologies, performance benchmarking

Procedia PDF Downloads 305

Authors: Shaode Yu, Jiajian Meng, Bing Zhu, Hang Yu, Qiurui Sun

Abstract:

Speech emotion recognition (SER) is for recognizing human subjective emotions through audio data in-depth analysis. From speech audios, how to comprehensively extract emotional information and how to effectively fuse extracted features remain challenging. This paper presents a dual-stream SER framework that embraces both full training and transfer learning of different networks for thorough feature encoding. Besides, a plug-and-play cross-attention fusion (CAF) module is implemented for the valid integration of the dual-stream encoder output. The effectiveness of the proposed CAF module is compared to the other three fusion modules (feature summation, feature concatenation, and feature-wise linear modulation) on two databases (RAVDESS and IEMO-CAP) using different dual-stream encoders (full training network, DPCNN or TextRCNN; transfer learning network, HuBERT or Wav2Vec2). Experimental results suggest that the CAF module can effectively reconcile conflicts between features from different encoders and outperform the other three feature fusion modules on the SER task. In the future, the plug-and-play CAF module can be extended for multi-branch feature fusion, and the dual-stream SER framework can be widened for multi-stream data representation to improve the recognition performance and generalization capacity.

Keywords: speech emotion recognition, cross-attention fusion, dual-stream, pre-trained

Procedia PDF Downloads 41

Authors: Gadiri Sabiha

Abstract:

Introduction: Current allergy diagnostic tools using Multiplex technology have made it possible to increase the efficiency of the search for specific IgE. This opportunity is provided by the newly developed “Alex Biochip”, consisting of a panel of 282 allergens in native and molecular form, a CCD inhibitor, and the potential for detecting cross-reactive allergens. We evaluated the performance of this technology in detecting cross-reactivity in previously explored patients. Material/Method: The sera of 39 patients presenting sensitization and polysensitization profiles were explored. The search for specific IgE is carried out by the Alex ® IgE Biochip, and the results are analyzed by nature and by molecular family of allergens using specific software. Results/Discussion: The analysis gave a particular profile of cross-reactivity allergens: 33% for the Ole e1 family, 31% for NPC2, 26% for storage proteins, 20% for Tropomyosin, 10% for LTPs, 10% for Arginine Kinase and 10% for Uteroglobin CCDs were absent in all patients. The “Ole e1” allergen is responsible for a pollen-pollen cross allergy. The storage proteins found and LTP are not species-specific, causing cross-pollen-food allergy. The nDer p2 of the NPC2 family is responsible for cross-reactivity between mite species. Conclusion: The cross-reactivities responsible for mixed syndromes at diagnosis in our patients were dominated by pollen-pollen and pollen-food syndromes. They allow the identification of severity factors linked to the prognosis and the best-adapted immunotherapy.

Keywords: specific IgE, allergy, cross reactivity, molecular allergens

Procedia PDF Downloads 38

Authors: Andrey V. Timofeev

Abstract:

This paper introduces an original method for guaranteed estimation of the accuracy of an ensemble of Lipschitz classifiers. The solution was obtained as a finite closed set of alternative hypotheses, which contains an object of classification with a probability of not less than the specified value. Thus, the classification is represented by a set of hypothetical classes. In this case, the smaller the cardinality of the discrete set of hypothetical classes is, the higher is the classification accuracy. Experiments have shown that if the cardinality of the classifiers ensemble is increased then the cardinality of this set of hypothetical classes is reduced. The problem of the guaranteed estimation of the accuracy of an ensemble of Lipschitz classifiers is relevant in the multichannel classification of target events in C-OTDR monitoring systems. Results of suggested approach practical usage to accuracy control in C-OTDR monitoring systems are present.

Keywords: Lipschitz classifiers, confidence set, C-OTDR monitoring, classifiers accuracy, classifiers ensemble

Procedia PDF Downloads 461

Authors: M. Heydari Vini

Abstract:

There is a complicated relation between effective input parameters of cold rolling and output rolling force and exit thickness of strips.in many mathematical models, the effect of some rolling parameters have been ignored and the outputs have not a desirable accuracy. In the other hand, there is a special relation among input thickness of strips,the width of the strips,rolling speeds,mandrill tensions and the required exit thickness of strips with rolling force and the real exit thickness of the rolled strip. First of all, in this paper the effective parameters of cold rolling process modeled using an artificial neural network according to the optimum network achieved by using a written program in MATLAB,it has been shown that the prediction of rolling stand parameters with different properties and new dimensions attained from prior rolled strips by an artificial neural network is applicable.

Keywords: cold rolling, artificial neural networks, rolling force, real rolled thickness of strips

Procedia PDF Downloads 469

Authors: Redouane Tlemsani, Redouane, Belkacem Kouninef, Abdelkader Benyettou

Abstract:

In this paper, our system is a Markovien system which we can see it like a Dynamic Bayesian Networks. One of the major interests of these systems resides in the complete training of the models (topology and parameters) starting from training data. The Bayesian Networks are representing models of dubious knowledge on complex phenomena. They are a union between the theory of probability and the graph theory in order to give effective tools to represent a joined probability distribution on a set of random variables. The representation of knowledge bases on description, by graphs, relations of causality existing between the variables defining the field of study. The theory of Dynamic Bayesian Networks is a generalization of the Bayesians networks to the dynamic processes. Our objective amounts finding the better structure which represents the relationships (dependencies) between the variables of a dynamic bayesian network. In applications in pattern recognition, one will carry out the fixing of the structure which obliges us to admit some strong assumptions (for example independence between some variables).

Keywords: Arabic on line character recognition, dynamic Bayesian network, pattern recognition, networks

Procedia PDF Downloads 583

Authors: Yuqing Chen, Ying Xu, Renfa Li

Abstract:

The development of matrix completion theory provides new approaches for data gathering in Wireless Sensor Networks (WSN). The existing matrix completion algorithms for WSN mainly consider how to reduce the sampling number without considering the real-time performance when recovering the data matrix. In order to guarantee the recovery accuracy and reduce the recovery time consumed simultaneously, we propose a new ALM algorithm to recover the weather monitoring data. A lot of experiments have been carried out to investigate the performance of the proposed ALM algorithm by using different parameter settings, different sampling rates and sampling models. In addition, we compare the proposed ALM algorithm with some existing algorithms in the literature. Experimental results show that the ALM algorithm can obtain better overall recovery accuracy with less computing time, which demonstrate that the ALM algorithm is an effective and efficient approach for recovering the real world weather monitoring data in WSN.

Keywords: wireless sensor network, matrix completion, singular value thresholding, augmented Lagrange multiplier

Procedia PDF Downloads 355

Authors: Márcia Aparecida Teixeira

Abstract:

Sports, in particular football, boosts considerably the financial market of a certain locality, be it city or even a country. The financial transactions involving this medium stand out from other existing businesses, such as small industries. Strategically, social networks are inserted in this sporting environment, in order to promote and attract new fans of this modality. The present study analyzes the use of social networks in Sports Marketing with a focus on football. For the object of this study, it was chosen a specific club, the Club Atlético Mineiro, a Brazilian club of great national notoriety. The social networks on focus will be: Facebook, Twitter, and Instagram. It will be analyzed the content and frequency of the posts, reception of the target public in relation to the content made available and its feedback.

Keywords: social network, sport, strategy, marketing

Procedia PDF Downloads 357

Authors: Marwane Ben Hcine, Ridha Bouallegue

Abstract:

The aim of this work is to provide an original analytical framework for downlink effective SINR evaluation in LTE networks. The classical single carrier SINR performance evaluation is extended to multi-carrier systems operating over frequency selective channels. Extension is achieved by expressing the link outage probability in terms of the statistics of the effective SINR. For effective SINR computation, the exponential effective SINR mapping (EESM) method is used on this work. Closed-form expression for the link outage probability is achieved assuming a log skew normal approximation for single carrier case. Then we rely on the lognormal approximation to express the exponential effective SINR distribution as a function of the mean and standard deviation of the SINR of a generic subcarrier. Achieved formulas is easily computable and can be obtained for a user equipment (UE) located at any distance from its serving eNodeB. Simulations show that the proposed framework provides results with accuracy within 0.5 dB.

Keywords: LTE, OFDMA, effective SINR, log skew normal approximation

Procedia PDF Downloads 332

Authors: Somayeh Sadat Hashemi Kamangar, Fatemeh Bakouie, Shahriar Gharibzadeh

Abstract:

In this study, we target to exploit Maximum Spanning Trees (MST) of children's semantic networks to investigate their language development. To do so, we examine the graph-theoretic properties of word-embedding networks. The networks are made of words children learn prior to the age of 30 months as the nodes and the links which are built from the cosine vector similarity of words normatively acquired by children prior to two and a half years of age. These networks are weighted graphs and the strength of each link is determined by the numerical similarities of the two words (nodes) on the sides of the link. To avoid changing the weighted networks to the binaries by setting a threshold, constructing MSTs might present a solution. MST is a unique sub-graph that connects all the nodes in such a way that the sum of all the link weights is maximized without forming cycles. MSTs as the backbone of the semantic networks are suitable to examine developmental changes in semantic network topology in children. From these trees, several parameters were calculated to characterize the developmental change in network organization. We showed that MSTs provides an elegant method sensitive to capture subtle developmental changes in semantic network organization.

Keywords: maximum spanning trees, word-embedding, semantic networks, language development

Procedia PDF Downloads 107