Search results for: reduction data set and recognition

Authors: Jérémie Ochin

Abstract:

Soccer analytics are built on two data sources: the frame-by-frame position of each player on the terrain and the sequences of events, such as ball drive, pass, cross, shot, throw-in... With more than 2000 ball-events per soccer game, their precise and exhaustive annotation, based on a monocular video stream such as a TV broadcast, remains a tedious and costly manual task. State-of-the-art methods for spatio-temporal action detection from a monocular video stream, often based on 3D convolutional neural networks, are close to reach levels of performances in mean Average Precision (mAP) compatibles with the automation of such task. Nevertheless, to meet their expectation of exhaustiveness in the context of data analytics, such methods must be applied in a regime of high recall – low precision, using low confidence score thresholds. This setting unavoidably leads to the detection of false positives that are the product of the well documented overconfidence behaviour of neural networks and, in this case, their limited access to contextual information and understanding of the game: their predictions are highly unstructured. Based on the assumption that professional soccer players’ behaviour, pose, positions and velocity are highly interrelated and locally driven by the player performing a ball-action, it is hypothesized that the addition of information regarding surrounding player’s appearance, positions and velocity in the prediction methods can improve their metrics. Several methods are compared to build a proper representation of the game surrounding a player, from handcrafted features of the local graph, based on domain knowledge, to the use of Graph Neural Networks trained in an end-to-end fashion with existing state-of-the-art 3D convolutional neural networks. It is shown that the inclusion of information regarding surrounding players helps reaching higher metrics.

Keywords: fine-grained action recognition, human action recognition, convolutional neural networks, graph neural networks, spatio-temporal action recognition

Procedia PDF Downloads 15

Authors: Ja-Keoung Koo, Kensuke Nakamura, Hyohun Kim, Dongwha Shin, Yeonseok Kim, Ji-Su Ahn, Byung-Woo Hong

Abstract:

The machine learning techniques based on a convolutional neural network (CNN) have been actively developed and successfully applied to a variety of image analysis tasks including reconstruction, noise reduction, resolution enhancement, segmentation, motion estimation, object recognition. The classical visual information processing that ranges from low level tasks to high level ones has been widely developed in the deep learning framework. It is generally considered as a challenging problem to derive visual interpretation from high dimensional imagery data. A CNN is a class of feed-forward artificial neural network that usually consists of deep layers the connections of which are established by a series of non-linear operations. The CNN architecture is known to be shift invariant due to its shared weights and translation invariance characteristics. However, it is often computationally intractable to optimize the network in particular with a large number of convolution layers due to a large number of unknowns to be optimized with respect to the training set that is generally required to be large enough to effectively generalize the model under consideration. It is also necessary to limit the size of convolution kernels due to the computational expense despite of the recent development of effective parallel processing machinery, which leads to the use of the constantly small size of the convolution kernels throughout the deep CNN architecture. However, it is often desired to consider different scales in the analysis of visual features at different layers in the network. Thus, we propose a CNN model where different sizes of the convolution kernels are applied at each layer based on the random projection. We apply random filters with varying sizes and associate the filter responses with scalar weights that correspond to the standard deviation of the random filters. We are allowed to use large number of random filters with the cost of one scalar unknown for each filter. The computational cost in the back-propagation procedure does not increase with the larger size of the filters even though the additional computational cost is required in the computation of convolution in the feed-forward procedure. The use of random kernels with varying sizes allows to effectively analyze image features at multiple scales leading to a better generalization. The robustness and effectiveness of the proposed CNN based on random kernels are demonstrated by numerical experiments where the quantitative comparison of the well-known CNN architectures and our models that simply replace the convolution kernels with the random filters is performed. The experimental results indicate that our model achieves better performance with less number of unknown weights. The proposed algorithm has a high potential in the application of a variety of visual tasks based on the CNN framework. Acknowledgement—This work was supported by the MISP (Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by IITP, and NRF-2014R1A2A1A11051941, NRF2017R1A2B4006023.

Keywords: deep learning, convolutional neural network, random kernel, random projection, dimensionality reduction, object recognition

Procedia PDF Downloads 284

Authors: Kailas S. Jagtap, Karthik Sundarraj, Nirmal Kumar, S. Rajnarasimha, Prakash S. Kulkarni

Abstract:

The issue of turbulence base streams and the drag related to it have been of important attention for rockets, missiles, and aircraft. Different techniques are used for base drag reduction. This paper presents the numerical study of numerous drag reduction technique. The base drag or afterbody drag of bluff bodies can be reduced easily using locked vortex drag reduction technique. For bluff bodies having a cylindrical shape, the base drag is much larger compared to streamlined bodies. For such bodies using splitter plates, the vortex can be trapped between the base and the plate, which results in smooth flow. Splitter plate with round and curved corner shapes has influence in drag reduction. In this paper, the comparison is done between single splitter plate as different positions and with the bluff body. Base drag for the speed of 30m/s can be reduced about 20% to 30% by using single splitter plate as compared to the bluff body.

Keywords: base drag, bluff body, splitter plate, vortex flow, ANSYS, fluent

Procedia PDF Downloads 173

Authors: Peng Wang, Tigang Jiang

Abstract:

The computer based lip reading method of different languages cannot be universal. At present, for the research of Chinese lip reading, whether the work on data sets or recognition algorithms, is far from mature. In this paper, we study the Chinese lipreading method based on machine learning, and propose a Chinese Sentence-level lip-reading network (CNLipNet) model which consists of spatio-temporal convolutional neural network(CNN), recurrent neural network(RNN) and Connectionist Temporal Classification (CTC) loss function. This model can map variable-length sequence of video frames to Chinese Pinyin sequence and is trained end-to-end. More over, We create CNLRS, a Chinese Lipreading Dataset, which contains 5948 samples and can be shared through github. The evaluation of CNLipNet on this dataset yielded a 41% word correct rate and a 70.6% character correct rate. This evaluation result is far superior to the professional human lip readers, indicating that CNLipNet performs well in lipreading.

Keywords: lipreading, machine learning, spatio-temporal, convolutional neural network, recurrent neural network

Procedia PDF Downloads 123

Authors: Ankita Wadhawan, Parteek Kumar, Umesh Kumar

Abstract:

Gesture is any body movement that expresses some attitude or any sentiment. Gestures as a sign language are used by deaf people for conveying messages which helps in eliminating the communication barrier between deaf people and normal persons. Nowadays, everybody is using mobile phone and computer as a very important gadget in their life. But there are some physically challenged people who are blind/deaf and the use of mobile phone or computer like device is very difficult for them. So, there is an immense need of a system which works on body gesture or sign language as input. In this research, Microsoft Kinect Sensor, SDK V2 and Hidden Markov Toolkit (HTK) are used to recognize the object, motion of object and human body joints through Touch less NUI (Natural User Interface) in real-time. The depth data collected from Microsoft Kinect has been used to recognize gestures of Indian Sign Language (ISL). The recorded clips are analyzed using depth, IR and skeletal data at different angles and positions. The proposed system has an average accuracy of 85%. The developed Touch less NUI provides an interface to recognize gestures and controls the cursor and click operation in computer just by waving hand gesture. This research will help deaf people to make use of mobile phones, computers and socialize among other persons in the society.

Keywords: gesture recognition, Indian sign language, Microsoft Kinect, natural user interface, sign language

Procedia PDF Downloads 302

Authors: Sean W. T. Bayly, Daniel Glover, Don Horrell, Simon Horrocks, Barnes Callum, Stuart Gibson, Mac Misuira

Abstract:

We assess suitability of recent, ∼7B parameter, instruction-tuned Language Models Mistral-v0.3, Llama-3, and Phi-3, for Generative Named Entity Recognition (GNER). Our proposed Multi-Level Information Retrieval method achieves notable improvements over finetuned entity-level and sentence-level methods. We consider recent developments at the cross roads of prompt engineering and Retrieval Augmented Generation (RAG), such as EmotionPrompt. We conclude that language models directed toward this task are highly capable when distinguishing between positive classes (precision). However, smaller models seem to struggle to find all entities (recall). Poorly defined classes such as ”Miscellaneous” exhibit substantial declines in performance, likely due to the ambiguity it introduces to the prompt. This is partially resolved through a self verification method using engineered prompts containing knowledge of the stricter class definitions, particularly in areas where their boundaries are in danger of overlapping, such as the conflation between the location ”Britain” and the nationality ”British”. Finally, we explore correlations between model performance on the GNER task with performance on relevant academic benchmarks.

Keywords: generative named entity recognition, information retrieval, lightweight artificial intelligence, prompt engineering, personal information identification, retrieval augmented generation, self verification

Procedia PDF Downloads 31

Authors: Gabriel Sunday Ayayia

Abstract:

Food waste has reached alarming levels worldwide, contributing to food insecurity, resource depletion, and environmental degradation. While numerous strategies exist to mitigate this issue, the role of traditional practices and indigenous knowledge remains underexplored. There is a need to investigate how these age-old practices can contribute to sustainable food waste reduction, particularly in the African context. This study explores the potential of traditional practices and indigenous knowledge in Africa to address this challenge sustainably. The study examines traditional African food management practices and indigenous knowledge related to food preservation and utilization; assess the impact of traditional practices on reducing food waste and its broader implications for sustainable development, and identify key factors influencing the continued use and effectiveness of traditional practices in contemporary African societies. Thus, the study argues that traditional practices and indigenous knowledge in Africa offer valuable insights and strategies for sustainable food waste reduction that can be adapted and integrated into global initiatives This research will employ a mixed-methods approach, combining qualitative and quantitative research techniques. Data collection will involve in-depth interviews, surveys, and participant observations in selected African communities. Moreover, a comprehensive review of literature on traditional food management practices and their impact on food waste reduction will be conducted. The significance of this study lies in its potential to bridge the gap between traditional knowledge and modern sustainability efforts. By uncovering the value of traditional practices in reducing food waste, this research can inform policies, interventions, and awareness campaigns aimed at achieving sustainable food systems worldwide.

Keywords: traditional practices, indigenous knowledge, food waste reduction, sustainability

Procedia PDF Downloads 72

Authors: Umair Rashid

Abstract:

Normally softmax loss is used as the supervision signal in face recognition (FR) system, and it boosts the separability of features. In the last two years, a number of techniques have been proposed by reformulating the original softmax loss to enhance the discriminating power of Deep Convolutional Neural Networks (DCNNs) for FR system. To learn angularly discriminative features Cosine-Margin based softmax has been adjusted as monotonically decreasing angular function, that is the main challenge for angular based softmax. On that issue, we propose monotonically decreasing element for Cosine-Margin based softmax and also, we discussed the effect of different monotonically decreasing parameters on angular Margin softmax for FR system. We train the model on publicly available dataset CASIA- WebFace via our proposed monotonically decreasing parameters for cosine function and the tests on YouTube Faces (YTF, Labeled Face in the Wild (LFW), VGGFace1 and VGGFace2 attain the state-of-the-art performance.

Keywords: deep convolutional neural networks, cosine margin face recognition, softmax loss, monotonically decreasing parameter

Procedia PDF Downloads 96

Authors: Iyad Muslih, Azzah Alkhalailah, Ali Merdji

Abstract:

Photovoltaic efficiency is highly affected by dust accumulation; the dust particles prevent direct solar radiation from reaching the panel surface; therefore a reduction in output power will occur. A study of dust and soiling accumulation effect on the output power of PV panels was conducted for different periods of time from May to October in three countries of the MENA region, Jordan, Egypt, and Algeria, under local weather conditions. This study leads to build a more realistic equation to estimate the power reduction as a function of time. This logarithmic function shows the high reduction in power in the first days with 10% reduction in output power compared to the reference system, where it reaches a steady state value after 60 days to reach a maximum value of 30%.

Keywords: solar energy, PV system, soiling, MENA

Procedia PDF Downloads 216

Authors: Milagros Jaén-Vargas, Javier García Martínez, Karla Miriam Reyes Leiva, María Fernanda Trujillo-Guerrero, Francisco Fernandes, Sérgio Barroso Gonçalves, Miguel Tavares Silva, Daniel Simões Lopes, José Javier Serrano Olmedo

Abstract:

Human Activity Recognition (HAR) is having a growing impact in creating new applications and is responsible for emerging new technologies. Also, the use of wearable sensors is an important key to exploring the human body's behavior when performing activities. Hence, the use of these dispositive is less invasive and the person is more comfortable. In this study, a database that includes three activities is used. The activities were acquired from inertial measurement unit sensors (IMU) and motion capture systems (MOCAP). The main objective is differentiating the performance from four Deep Learning (DL) models: Deep Neural Network (DNN), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN) and hybrid model Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM), when considering acceleration, velocity and position and evaluate if integrating the IMU acceleration to obtain velocity and position represent an increment in performance when it works as input to the DL models. Moreover, compared with the same type of data provided by the MOCAP system. Despite the acceleration data is cleaned when integrating, results show a minimal increase in accuracy for the integrated signals.

Keywords: HAR, IMU, MOCAP, acceleration, velocity, position, feature maps

Procedia PDF Downloads 92

Authors: Alwyn John Lim

Abstract:

Philippines is one of the most vulnerable areas to natural disasters in the world. Almost every year different types of natural disasters occur in Philippines and destroy many lives and resources of people. Although it is not possible to prevent the occurrence of disasters influenced by natural causes, proper plan and management such as disaster risk reduction may minimize the damage cause by natural disasters. Based on literature review this paper will analyze literatures on public/community awareness and education in disaster risk reduction that would help promote a country wide public disaster awareness and education program in the Philippines. This will include best practices and importance of community disaster awareness and education. The paper will also tackle ICT tools that will help boost the process and effectiveness of community/public disaster awareness and education.

Keywords: community awareness, disaster education, disaster risk reduction, Philippines

Procedia PDF Downloads 498

Authors: Amita Barik, Ranjit Prasad Bahadur

Abstract:

We investigate the role of water molecules in 89 protein-RNA complexes taken from the Protein Data Bank. Those with tRNA and single-stranded RNA are less hydrated than with duplex or ribosomal proteins. Protein-RNA interfaces are hydrated less than protein-DNA interfaces, but more than protein-protein interfaces. Majority of the waters at protein-RNA interfaces makes multiple H-bonds; however, a fraction does not make any. Those making Hbonds have preferences for the polar groups of RNA than its partner protein. The spatial distribution of waters makes interfaces with ribosomal proteins and single-stranded RNA relatively ‘dry’ than interfaces with tRNA and duplex RNA. In contrast to protein-DNA interfaces, mainly due to the presence of the 2’OH, the ribose in protein-RNA interfaces is hydrated more than the phosphate or the bases. The minor groove in protein-RNA interfaces is hydrated more than the major groove, while in protein-DNA interfaces it is reverse. The strands make the highest number of water-mediated H-bonds per unit interface area followed by the helices and the non-regular structures. The preserved waters at protein-RNA interfaces make higher number of H-bonds than the other waters. Preserved waters contribute toward the affinity in protein-RNA recognition and should be carefully treated while engineering protein-RNA interfaces.

Keywords: h-bonds, minor-major grooves, preserved water, protein-RNA interfaces

Procedia PDF Downloads 298

Authors: Chen Xi, Liu Xuebing, Lao Xueru, Kuan Sinman, Jiang Yike, Wang Hanwei, Yang Xiaolang, Zhou Junjie, Xie Jinpeng

Abstract:

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

Keywords: urban planning, urban governance, CIM, artificial intelligence, sustainable development

Procedia PDF Downloads 410

Authors: Khaled Salah

Abstract:

Model order reduction has been one of the most challenging topics in the past years. In this paper, a hybrid solution of genetic algorithm (GA) and simulated annealing algorithm (SA) are used to approximate high-order transfer functions (TFs) to lower-order TFs. In this approach, hybrid algorithm is applied to model order reduction putting in consideration improving accuracy and preserving the properties of the original model which are two important issues for improving the performance of simulation and computation and maintaining the behavior of the original complex models being reduced. Compared to conventional mathematical methods that have been used to obtain a reduced order model of high order complex models, our proposed method provides better results in terms of reducing run-time. Thus, the proposed technique could be used in electronic design automation (EDA) tools.

Keywords: genetic algorithm, simulated annealing, model reduction, transfer function

Procedia PDF Downloads 141

Authors: Teodora Vukovic, Christoph Hottiger, Noah Bubenhofer

Abstract:

The development of VIAN-DH aims at bridging two linguistic approaches: conversation analysis/interactional linguistics (IL), so far a dominantly qualitative field, and computational/corpus linguistics and its quantitative and automated methods. Contemporary IL investigates the systematic organization of conversations and interactions composed of speech, gaze, gestures, and body positioning, among others. These highly integrated multimodal behaviour is analysed based on video data aimed at uncovering so called “multimodal gestalts”, patterns of linguistic and embodied conduct that reoccur in specific sequential positions employed for specific purposes. Multimodal analyses (and other disciplines using videos) are so far dependent on time and resource intensive processes of manual transcription of each component from video materials. Automating these tasks requires advanced programming skills, which is often not in the scope of IL. Moreover, the use of different tools makes the integration and analysis of different formats challenging. Consequently, IL research often deals with relatively small samples of annotated data which are suitable for qualitative analysis but not enough for making generalized empirical claims derived quantitatively. VIAN-DH aims to create a workspace where many annotation layers required for the multimodal analysis of videos can be created, processed, and correlated in one platform. VIAN-DH will provide a graphical interface that operates state-of-the-art tools for automating parts of the data processing. The integration of tools that already exist in computational linguistics and computer vision, facilitates data processing for researchers lacking programming skills, speeds up the overall research process, and enables the processing of large amounts of data. The main features to be introduced are automatic speech recognition for the transcription of language, automatic image recognition for extraction of gestures and other visual cues, as well as grammatical annotation for adding morphological and syntactic information to the verbal content. In the ongoing instance of VIAN-DH, we focus on gesture extraction (pointing gestures, in particular), making use of existing models created for sign language and adapting them for this specific purpose. In order to view and search the data, VIAN-DH will provide a unified format and enable the import of the main existing formats of annotated video data and the export to other formats used in the field, while integrating different data source formats in a way that they can be combined in research. VIAN-DH will adapt querying methods from corpus linguistics to enable parallel search of many annotation levels, combining token-level and chronological search for various types of data. VIAN-DH strives to bring crucial and potentially revolutionary innovation to the field of IL, (that can also extend to other fields using video materials). It will allow the processing of large amounts of data automatically and, the implementation of quantitative analyses, combining it with the qualitative approach. It will facilitate the investigation of correlations between linguistic patterns (lexical or grammatical) with conversational aspects (turn-taking or gestures). Users will be able to automatically transcribe and annotate visual, spoken and grammatical information from videos, and to correlate those different levels and perform queries and analyses.

Keywords: multimodal analysis, corpus linguistics, computational linguistics, image recognition, speech recognition

Procedia PDF Downloads 105

Authors: Djamila Meghraoui, Bachir Boudraa, Thouraya Meksen, M.Boudraa

Abstract:

Parkinson's disease is a pathology that involves characteristic perturbations in patients’ voices. This paper describes a proposed method that aims to diagnose persons with Parkinson (PWP) by analyzing on line their voices signals. First, Thresholds signals alterations are determined by the Multi-Dimensional Voice Program (MDVP). Principal Analysis (PCA) is exploited to select the main voice principal componentsthat are significantly affected in a patient. The decision phase is realized by a Mul-tinomial Bayes (MNB) Classifier that categorizes an analyzed voice in one of the two resulting classes: healthy or PWP. The prediction accuracy achieved reaching 98.8% is very promising.

Keywords: Parkinson’s disease recognition, PCA, MDVP, multinomial Naive Bayes

Procedia PDF Downloads 275

Authors: Changyeop Lee, Sewon Kim, Jongho Lee

Abstract:

Reburning technology has been developed to adopt various commercial combustion systems. Fuel lean reburning is an advanced reburning method to reduce NOx economically without using burnout air, however it is not easy to get high NOx reduction efficiency. In the fuel lean reburning system, the localized fuel rich eddies are used to establish partial fuel rich regions so that the NOx can react with hydrocarbon radical restrictively. In this paper, a new advanced reburning method which supplies reburn fuel with oscillatory motion is introduced to increase NOx reduction rate effectively. To clarify whether forced oscillating injection of reburn fuel can effectively reduce NOx emission, experimental tests were conducted in vertical combustion furnace. Experiments were performed in flames stabilized by a gas burner, which was mounted at the bottom of the furnace. The natural gas is used as both main and reburn fuel and total thermal input is about 40kW. The forced oscillating injection of reburn fuel is realized by electronic solenoid valve, so that fuel rich region and fuel lean region is established alternately. In the fuel rich region, NOx is converted to N2 by reburning reaction, however unburned hydrocarbon and CO is oxidized in fuel lean zone and mixing zone at downstream where slightly fuel lean region is formed by mixing of two regions. This paper reports data on flue gas emissions and temperature distribution in the furnace for a wide range of experimental conditions. All experimental data has been measured at steady state. The NOx reduction rate increases up to 41% by forced oscillating reburn motion. The CO emissions were shown to be kept at very low level. And this paper makes clear that in order to decrease NOx concentration in the exhaust when oscillating reburn fuel injection system is adopted, the control of factors such as frequency and duty ratio is very important.

Keywords: NOx, CO, reburning, pollutant

Procedia PDF Downloads 287

Authors: J. H. Park, R. H. Hwang, K. B. Yi

Abstract:

Carbon Capture and Storage (CCS) is one of the important technology to reduce the CO₂ emission from large stationary sources such as a power plant. Among the carbon technologies for power plants, chemical looping combustion (CLC) has attracted much attention due to a higher thermal efficiency and a lower cost of electricity. A CLC process is consists of a fuel reactor and an air reactor which are interconnected fluidized bed reactor. In the fuel reactor, an oxygen carrier (OC) is reduced by fuel gas such as CH₄, H₂, CO. And the OC is send to air reactor and oxidized by air or O₂ gas. The oxidation and reduction reaction of OC occurs between the two reactors repeatedly. In the CLC system, high concentration of CO₂ can be easily obtained by steam condensation only from the fuel reactor. It is very important to understand the oxidation and reduction characteristics of oxygen carrier in the CLC system to determine the solids circulation rate between the air and fuel reactors, and the amount of solid bed materials. In this study, we have conducted the experiment and interpreted oxidation and reduction reaction characteristics via observing weight change of Ni-based oxygen carrier using the TGA with varying as concentration and temperature. Characterizations of the oxygen carrier were carried out with BET, SEM. The reaction rate increased with increasing the temperature and increasing the inlet gas concentration. We also compared experimental results and adapted basic reaction kinetic model (JMA model). JAM model is one of the nucleation and nuclei growth models, and this model can explain the delay time at the early part of reaction. As a result, the model data and experimental data agree over the arranged conversion and time with overall variance (R²) greater than 98%. Also, we calculated activation energy, pre-exponential factor, and reaction order through the Arrhenius plot and compared with previous Ni-based oxygen carriers.

Keywords: chemical looping combustion, kinetic, nickel-based, oxygen carrier, spray drying method

Procedia PDF Downloads 206

Authors: Anees K. Ahamed, Aakash Kumar R. G., Raj M. Mohan

Abstract:

The main objective is to apply lean tools to identify and eliminate waste in and among the work stations so as to improve the process speed and quality. From the top seven wastes in the lean concept, we consider the movement of materials, defects, and inventory for the improvement since these cause the major impact on the performance measures. The layout was improved to reduce the movement of materials. It also quantifies the reduction in movement among the work stations. Value stream mapping has been used for identification of waste. Cause and effect diagram and 5W analysis are used to identify the reasons for defects and to provide the counter measures. Some cycle time reduction techniques also proposed to improve the productivity. Lean Audit check sheet was also used to identify the current position of the industry and to identify the gap to make the industry Lean.

Keywords: cause and effect diagram, cycle time reduction, defects, lean, waste reduction

Procedia PDF Downloads 381

Authors: Albatool Al Abdulwahid, Bayan Shakally, Mariam Mohamed, Wed Almokri

Abstract:

Artificial intelligence has infiltrated every part of our life and every field we can think of. With technical developments, artificial intelligence applications are becoming more prevalent. We chose ELSA speak because it is a magnificent example of Artificial intelligent applications, ELSA speak is a smartphone application that is free to download on both IOS and Android smartphones. ELSA speak utilizes artificial intelligence to help non-native English speakers pronounce words and phrases similar to a native speaker, as well as enhance their English skills. It employs speech-recognition technology that aids the application to excel the pronunciation of its users. This remarkable feature distinguishes ELSA from other voice recognition algorithms and increase the efficiency of the application. This study focused on evaluating ELSA speak application, by testing the degree of effectiveness based on survey questions. The results of the questionnaire were variable. The generality of the participants strongly agreed that ELSA has helped them enhance their pronunciation skills. However, a few participants were unconfident about the application’s ability to assist them in their learning journey.

Keywords: ELSA speak application, artificial intelligence, speech-recognition technology, language learning, english pronunciation

Procedia PDF Downloads 103

Authors: J. K. Adedeji, M. O. Oyekanmi

Abstract:

This paper has critically examined the use of Machine Learning procedures in curbing unauthorized access into valuable areas of an organization. The use of passwords, pin codes, user’s identification in recent times has been partially successful in curbing crimes involving identities, hence the need for the design of a system which incorporates biometric characteristics such as DNA and pattern recognition of variations in facial expressions. The facial model used is the OpenCV library which is based on the use of certain physiological features, the Raspberry Pi 3 module is used to compile the OpenCV library, which extracts and stores the detected faces into the datasets directory through the use of camera. The model is trained with 50 epoch run in the database and recognized by the Local Binary Pattern Histogram (LBPH) recognizer contained in the OpenCV. The training algorithm used by the neural network is back propagation coded using python algorithmic language with 200 epoch runs to identify specific resemblance in the exclusive OR (XOR) output neurons. The research however confirmed that physiological parameters are better effective measures to curb crimes relating to identities.

Keywords: biometric characters, facial recognition, neural network, OpenCV

Procedia PDF Downloads 251

Authors: Ryoko Yoshida, Jyunpei Yoshida, Hua Fang Yu, Yasushi Sasaki, Tetsuya Nagasaka

Abstract:

Phosphorous is an important element for agriculture and industry and is a non-renewable resource. Especially, yellow phosphorus is an essential material in advanced industrial technology, but phosphorus resources were not produced in Japan at all, and all depend on imports. It has been suggested, however, that the remaining accessible reserves of phosphate ore will be depleted within 50 years. Therefore, alternative resources for phosphate ore must be found. In this research, we have developed a process that enables the production of high-purity yellow phosphorus from domestic unused phosphorus resources such as steelmaking slags. The process consists of two parts: (1) the production of crude phosphoric acid from wastes such as steelmaking slag; (2) producing high-purity yellow phosphorus by low-temperature carbothermic reduction of phosphoric acid (H₃PO₄). The details of the carbothermic reduction of phosphoric acid are presented in this paper. Yellow phosphorus is commercially produced by carbothermic reduction of phosphate ore in an electric arc furnace at more than 1673K. In the newly developed system, gaseous P₄O₁₀ evaporated from H₃PO₄ is successfully reduced to yellow phosphorus by using carbon packed bed at less than 1273K. To meet the depletion of phosphate ore, the proposed process in this study to produce yellow phosphorus by carbothermic reduction of H₃PO₄ that are extracted from dephosphorization slags will be one of the effective and economical solutions.

Keywords: carbothermic reduction, phosphoric acid, dephosphorization slags, yellow phosphorus

Procedia PDF Downloads 117

Authors: Kothuri Sriraman, Mattupalli Komal Teja

Abstract:

In this paper, a novel algorithm is proposed for the recognition of hulls in a hand written images that might be irregular or digit or character shape. Identification of objects and internal objects is quite difficult to extract, when the structure of the image is having bulk of clusters. The estimation results are easily obtained while going through identifying the sub-regional objects by using the SASK algorithm. Focusing mainly to recognize the number of internal objects exist in a given image, so as it is shadow-free and error-free. The hard clustering and density clustering process of obtained image rough set is used to recognize the differentiated internal objects, if any. In order to find out the internal hull regions it involves three steps pre-processing, Boundary Extraction and finally, apply the Hull Detection system. By detecting the sub-regional hulls it can increase the machine learning capability in detection of characters and it can also be extend in order to get the hull recognition even in irregular shape objects like wise black holes in the space exploration with their intensities. Layered hulls are those having the structured layers inside while it is useful in the Military Services and Traffic to identify the number of vehicles or persons. This proposed SASK algorithm is helpful in making of that kind of identifying the regions and can useful in undergo for the decision process (to clear the traffic, to identify the number of persons in the opponent’s in the war).

Keywords: chain code, Hull regions, Hough transform, Hull recognition, Layered Outline Extraction, SASK algorithm

Procedia PDF Downloads 343

Authors: Mohammed S. Al-Rawi, J. Bastos, J. Rodriguez

Abstract:

Object detection and object recognition are essential components of every computer vision system. Despite the high computational complexity and other problems related to numerical stability and accuracy, Zernike moments of 2D images (ZMs) have shown resilience when used in object recognition and have been used in various image analysis applications. In this work, we propose a novel method for computing ZMs via Fast Fourier Transform (FFT). Notably, this is the first algorithm that can generate ZMs up to extremely high orders accurately, e.g., it can be used to generate ZMs for orders up to 1000 or even higher. Furthermore, the proposed method is also simpler and faster than the other methods due to the availability of FFT software and/or hardware. The accuracies and numerical stability of ZMs computed via FFT have been confirmed using the orthogonality property. We also introduce normalizing ZMs with Neumann factor when the image is embedded in a larger grid, and color image reconstruction based on RGB normalization of the reconstructed images. Astonishingly, higher-order image reconstruction experiments show that the proposed methods are superior, both quantitatively and subjectively, compared to the q-recursive method.

Keywords: Chebyshev polynomial, fourier transform, fast algorithms, image recognition, pseudo Zernike moments, Zernike moments

Procedia PDF Downloads 261

Authors: B. Afsharipoor, E. Nazemi

Abstract:

Artificial neural networks (ANNs) are powerful tool for prediction which can be trained based on a set of examples and thus, it would be useful for nonlinear image processing. The present paper reviews several paper regarding applications of ANN in image processing to shed the light on advantage and disadvantage of ANNs in this field. Different steps in the image processing chain including pre-processing, enhancement, segmentation, object recognition, image understanding and optimization by using ANN are summarized. Furthermore, results on using multi artificial neural networks are presented.

Keywords: neural networks, image processing, segmentation, object recognition, image understanding, optimization, MANN

Procedia PDF Downloads 402

Authors: Shuo Mu, Guangzhi Jiang, Jinsa Chen

Abstract:

The analysis of Indel for RNA sequencing of clinical samples is easily affected by sequencing experiment errors and software selection. In order to improve the efficiency and accuracy of analysis, we developed an automatic reporting system for Indel recognition and annotation based on image snapshot of transcriptome reads alignment. This system includes sequence local-assembly and realignment, target point snapshot, and image-based recognition processes. We integrated high-confidence Indel dataset from several known databases as a training set to improve the accuracy of image processing and added a bioinformatical processing module to annotate and filter Indel artifacts. Subsequently, the system will automatically generate data, including data quality levels and images results report. Sanger sequencing verification of the reference Indel mutation of cell line NA12878 showed that the process can achieve 83% sensitivity and 96% specificity. Analysis of the collected clinical samples showed that the interpretation accuracy of the process was equivalent to that of manual inspection, and the processing efficiency showed a significant improvement. This work shows the feasibility of accurate Indel analysis of clinical next-generation sequencing (NGS) transcriptome. This result may be useful for RNA study for clinical samples with microsatellite instability in immunotherapy in the future.

Keywords: automatic reporting, indel, next-generation sequencing, NGS, transcriptome

Procedia PDF Downloads 187

Authors: Aisultan Shoiynbek, Darkhan Kuanyshbay, Paulo Menezes, Akbayan Bekarystankyzy, Assylbek Mukhametzhanov, Temirlan Shoiynbek

Abstract:

Speech emotion recognition (SER) has received increasing research interest in recent years. It is a common practice to utilize emotional speech collected under controlled conditions recorded by actors imitating and artificially producing emotions in front of a microphone. There are four issues related to that approach: emotions are not natural, meaning that machines are learning to recognize fake emotions; emotions are very limited in quantity and poor in variety of speaking; there is some language dependency in SER; consequently, each time researchers want to start work with SER, they need to find a good emotional database in their language. This paper proposes an approach to create an automatic tool for speech emotion extraction based on facial emotion recognition and describes the sequence of actions involved in the proposed approach. One of the first objectives in the sequence of actions is the speech detection issue. The paper provides a detailed description of the speech detection model based on a fully connected deep neural network for Kazakh and Russian. Despite the high results in speech detection for Kazakh and Russian, the described process is suitable for any language. To investigate the working capacity of the developed model, an analysis of speech detection and extraction from real tasks has been performed.

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

Procedia PDF Downloads 20

Authors: Reza Shakoori

Abstract:

This paper presents a structural correction of Arabic and Persian strokes using manipulation of their chain codes in order to improve the rate and performance of Persian and Arabic handwritten word recognition systems. It collects pure and effective features to represent a character with one consolidated feature vector and reduces variations in order to decrease the number of training samples and increase the chance of successful classification. Our results also show that how the proposed approaches can simplify classification and consequently recognition by reducing variations and possible noises on the chain code by keeping orientation of characters and their backbone structures.

Keywords: Arabic, chain code normalization, OCR systems, image processing

Procedia PDF Downloads 399

Authors: Z. Gharaee

Abstract:

Recognizing actions performed by others is important in our daily lives since it is necessary for communicating with others in a proper way. We perceive an action by observing the kinematics of motions involved in the performance. We use our experience and concepts to make a correct recognition of the actions. Although building the action concepts is a life-long process, which is repeated throughout life, we are very efficient in applying our learned concepts in analyzing motions and recognizing actions. Experiments on the subjects observing the actions performed by an actor show that an action is recognized after only about two hundred milliseconds of observation. In this study, hierarchical action recognition architecture is proposed by using growing grid layers. The first-layer growing grid receives the pre-processed data of consecutive 3D postures of joint positions and applies some heuristics during the growth phase to allocate areas of the map by inserting new neurons. As a result of training the first-layer growing grid, action pattern vectors are generated by connecting the elicited activations of the learned map. The ordered vector representation layer receives action pattern vectors to create time-invariant vectors of key elicited activations. Time-invariant vectors are sent to second-layer growing grid for categorization. This grid creates the clusters representing the actions. Finally, one-layer neural network developed by a delta rule labels the action categories in the last layer. System performance has been evaluated in an experiment with the publicly available MSR-Action3D dataset. There are actions performed by using different parts of human body: Hand Clap, Two Hands Wave, Side Boxing, Bend, Forward Kick, Side Kick, Jogging, Tennis Serve, Golf Swing, Pick Up and Throw. The growing grid architecture was trained by applying several random selections of generalization test data fed to the system during on average 100 epochs for each training of the first-layer growing grid and around 75 epochs for each training of the second-layer growing grid. The average generalization test accuracy is 92.6%. A comparison analysis between the performance of growing grid architecture and self-organizing map (SOM) architecture in terms of accuracy and learning speed show that the growing grid architecture is superior to the SOM architecture in action recognition task. The SOM architecture completes learning the same dataset of actions in around 150 epochs for each training of the first-layer SOM while it takes 1200 epochs for each training of the second-layer SOM and it achieves the average recognition accuracy of 90% for generalization test data. In summary, using the growing grid network preserves the fundamental features of SOMs, such as topographic organization of neurons, lateral interactions, the abilities of unsupervised learning and representing high dimensional input space in the lower dimensional maps. The architecture also benefits from an automatic size setting mechanism resulting in higher flexibility and robustness. Moreover, by utilizing growing grids the system automatically obtains a prior knowledge of input space during the growth phase and applies this information to expand the map by inserting new neurons wherever there is high representational demand.

Keywords: action recognition, growing grid, hierarchical architecture, neural networks, system performance

Procedia PDF Downloads 155

Authors: Jamshaid ul Rahman, Akhter Ali, Adnan Manzoor

Abstract:

Learning-based systems have received increasing interest in recent years; recognition structures, including end-to-end speak recognition, are one of the hot topics in this area. A famous work on end-to-end speaker verification by using Angular Softmax Loss gained significant importance and is considered useful to directly trains a discriminative model instead of the traditional adopted i-vector approach. The margin-based strategy in angular softmax is beneficial to learn discriminative speaker embeddings where the random selection of margin values is a big issue in additive angular margin and multiplicative angular margin. As a better solution in this matter, we present an alternative approach by introducing a bit similar form of an additive parameter that was originally introduced for face recognition, and it has a capacity to adjust automatically with the corresponding margin values and is applicable to learn more discriminative features than the Softmax. Experiments are conducted on the part of Fisher dataset, where it observed that the additive parameter with angular softmax to train the front-end and probabilistic linear discriminant analysis (PLDA) in the back-end boosts the performance of the structure.

Keywords: additive parameter, angular softmax, speaker verification, PLDA

Procedia PDF Downloads 95