Search results for: high accuracy

Authors: Mekha Mathew, Varun P Gopi

Abstract:

Wireless Capsule Endoscopy (WCE) has become a great device in Gastrointestinal (GI) tract diagnosis, which can examine the entire GI tract, especially the small intestine without invasiveness and sedation. Bleeding in the digestive tract is a symptom of a disease rather than a disease itself. Hence the detection of bleeding is important in diagnosing many diseases. In this paper we proposes a novel method for distinguishing bleeding regions from normal regions based on Contourlet transform and Local Binary Pattern (LBP). Experiments show that this method provides a high accuracy rate of 96.38% in CIE XYZ colour space for k-Nearest Neighbour (k-NN) classifier.

Keywords: Wireless Capsule Endoscopy, local binary pattern, k-NN classifier, contourlet transform

Procedia PDF Downloads 481

Authors: Serges Mendomo Meye, Li Guowei, Shen Zhenzhong

Abstract:

Earthquake is one of the main loads threatening dam safety. Once the dam is damaged, it will bring huge losses of life and property to the country and people. Therefore, it is very important to research the seismic safety of the dam. Due to the complex foundation conditions, high fortification intensity, and high scientific and technological content, it is necessary to adopt reasonable methods to evaluate the seismic safety performance of concrete arch dams built and under construction in strong earthquake areas. Structural seismic vulnerability analysis can predict the probability of structural failure at all levels under different intensity earthquakes, which can provide a scientific basis for reasonable seismic safety evaluation and decision-making. In this paper, the response surface method (RSM) is applied to the seismic vulnerability analysis of arch dams, which improves the efficiency of vulnerability analysis. Based on the central composite test design method, the material-seismic intensity samples are established. The response surface model (RSM) with arch crown displacement as performance index is obtained by finite element (FE) calculation of the samples, and then the accuracy of the response surface model (RSM) is verified. To obtain the seismic vulnerability curves, the seismic intensity measure ??(?1) is chosen to be 0.1~1.2g, with an interval of 0.1g and a total of 12 intensity levels. For each seismic intensity level, the arch crown displacement corresponding to 100 sets of different material samples can be calculated by algebraic operation of the response surface model (RSM), which avoids 1200 times of nonlinear dynamic calculation of arch dam; thus, the efficiency of vulnerability analysis is improved greatly.

Keywords: high concrete arch dam, performance index, response surface method, seismic vulnerability analysis, vector-valued intensity measure

Procedia PDF Downloads 236

Authors: W. H. Wan Zakiyatussariroh, A. A. Nasuhar, W. Y. Wan Fairos, Z. A. Nazatul Shahreen

Abstract:

Forecasting dengue incidence in a population can provide useful information to facilitate the planning of the public health intervention. Many studies on dengue cases in Malaysia were conducted but are limited in modeling the outbreak and forecasting incidence. This article attempts to propose the most appropriate time series model to explain the behavior of dengue incidence in Malaysia for the purpose of forecasting future dengue outbreaks. Several seasonal auto-regressive integrated moving average (SARIMA) models were developed to model Malaysia’s number of dengue incidence on weekly data collected from January 2001 to December 2011. SARIMA (2,1,1)(1,1,1)52 model was found to be the most suitable model for Malaysia’s dengue incidence with the least value of Akaike information criteria (AIC) and Bayesian information criteria (BIC) for in-sample fitting. The models further evaluate out-sample forecast accuracy using four different accuracy measures. The results indicate that SARIMA (2,1,1)(1,1,1)52 performed well for both in-sample fitting and out-sample evaluation.

Keywords: time series modeling, Box-Jenkins, SARIMA, forecasting

Procedia PDF Downloads 475

Authors: Ghodhbani Salah, Jemili Farah

Abstract:

With the growth of cyber attacks, information safety has become an important issue all over the world. Many firms rely on security technologies such as intrusion detection systems (IDSs) to manage information technology security risks. IDSs are considered to be the last line of defense to secure a network and play a very important role in detecting large number of attacks. However the main problem with today’s most popular commercial IDSs is generating high volume of alerts and huge number of false positives. This drawback has become the main motivation for many research papers in IDS area. Hence, in this paper we present a data mining technique to assist network administrators to analyze and reduce false positive alarms that are produced by an IDS and increase detection accuracy. Our data mining technique is unsupervised clustering method based on hybrid ANT algorithm. This algorithm discovers clusters of intruders’ behavior without prior knowledge of a possible number of classes, then we apply K-means algorithm to improve the convergence of the ANT clustering. Experimental results on real dataset show that our proposed approach is efficient with high detection rate and low false alarm rate.

Keywords: intrusion detection system, alarm filtering, ANT class, ant clustering, intruders’ behaviors, false alarms

Procedia PDF Downloads 400

Authors: Sina Fatolahzadeh, Sergio A. Sepúlveda

Abstract:

This paper presents advanced developments in close-range, terrestrial remote sensing techniques to enhance the characterization of rock masses. The study integrates two state-of-the-art laser-scanning technologies, the HandySCAN and GeoSLAM laser scanners, to extract high-resolution geospatial data for rock mass analysis. These instruments offer high accuracy, precision, low acquisition time, and high efficiency in capturing intricate geological features in small to medium size outcrops and slope cuts. Using the HandySCAN and GeoSLAM laser scanners facilitates real-time, three-dimensional mapping of rock surfaces, enabling comprehensive assessments of rock mass characteristics. The collected data provide valuable insights into structural complexities, surface roughness, and discontinuity patterns, which are essential for geological and geotechnical analyses. The synergy of these advanced remote sensing technologies contributes to a more precise and straightforward understanding of rock mass behavior. In this case, the main parameters of RQD, joint spacing, persistence, aperture, roughness, infill, weathering, water condition, and joint orientation in a slope cut along the Sea-to-Sky Highway, BC, were remotely analyzed to calculate and evaluate the Rock Mass Rating (RMR) and Geological Strength Index (GSI) classification systems. Automatic and manual analyses of the acquired data are then compared with field measurements. The results show the usefulness of the proposed remote sensing methods and their appropriate conformity with the actual field data.

Keywords: remote sensing, rock mechanics, rock engineering, slope stability, discontinuity properties

Procedia PDF Downloads 57

Authors: Doyin Afolabi, Phillip Adewole, Oladipupo Sennaike

Abstract:

Most well-known classifiers, including the decision tree algorithm, can make predictions on balanced datasets efficiently. However, the decision tree algorithm tends to be biased towards imbalanced datasets because of the skewness of the distribution of such datasets. To overcome this problem, this study proposes a weighted decision tree algorithm that aims to remove the bias toward the majority class and prevents the reduction of majority observations in imbalance datasets classification. The proposed weighted decision tree algorithm was tested on three imbalanced datasets- cancer dataset, german credit dataset, and banknote dataset. The specificity, sensitivity, and accuracy metrics were used to evaluate the performance of the proposed decision tree algorithm on the datasets. The evaluation results show that for some of the weights of our proposed decision tree, the specificity, sensitivity, and accuracy metrics gave better results compared to that of the ID3 decision tree and decision tree induced with minority entropy for all three datasets.

Keywords: data mining, decision tree, classification, imbalance dataset

Procedia PDF Downloads 118

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 331

Authors: Andrew Lock, Alastair Allen

Abstract:

Fragile watermarking has been proposed as a means of adding additional security or functionality to biometric systems, particularly for authentication and tamper detection. In this paper we describe an experimental study on the effect of watermarking iris images with a particular class of fragile algorithm, reversible algorithms, and the ability to correctly perform iris recognition. We investigate two scenarios, matching watermarked images to unmodified images, and matching watermarked images to watermarked images. We show that different watermarking schemes give very different results for a given capacity, highlighting the importance of investigation. At high embedding rates most algorithms cause significant reduction in recognition performance. However, in many cases, for low embedding rates, recognition accuracy is improved by the watermarking process.

Keywords: biometrics, iris recognition, reversible watermarking, vision engineering

Procedia PDF Downloads 449

Authors: Zehai Yu, Hui Zhu, Linglong Lin, Huawei Liang, Biao Yu, Weixin Huang

Abstract:

With the development of intelligent vehicle systems, a high-precision road map is increasingly needed in many aspects. The automatic lane lines extraction and modeling are the most essential steps for the generation of a precise lane-level road map. In this paper, an automatic lane-level road map generation system is proposed. To extract the road markings on the ground, the multi-region Otsu thresholding method is applied, which calculates the intensity value of laser data that maximizes the variance between background and road markings. The extracted road marking points are then projected to the raster image and clustered using a two-stage clustering algorithm. Lane lines are subsequently recognized from these clusters by the shape features of their minimum bounding rectangle. To ensure the storage efficiency of the map, the lane lines are approximated to cubic polynomial curves using a Bayesian estimation approach. The proposed lane-level road map generation system has been tested on urban and expressway conditions in Hefei, China. The experimental results on the datasets show that our method can achieve excellent extraction and clustering effect, and the fitted lines can reach a high position accuracy with an error of less than 10 cm.

Keywords: curve fitting, lane-level road map, line recognition, multi-thresholding, two-stage clustering

Procedia PDF Downloads 125

Authors: Vaishnavi Patil, K. M. Kurundkar

Abstract:

Electrical Drives play a vital role in industry development and applications. Drives have an inevitable part in the needs of various fields such as industry, commercial, and domestic applications. The development of material technology, Power Electronics devices, and accompanying applications led to the focus of industry and researchers on high-speed electrical drives. Numerous articles charted the applications of electrical machines and various converters for high-speed applications. The choice depends on the application under study. This paper goals to highlight high-speed applications, main challenges, and some applications of electrical drives in the field.

Keywords: high-speed, electrical machines, drives, applications

Procedia PDF Downloads 59

Authors: Noha Al Majid, Said Mazer, Moulhime El Bekkali, Catherine Algani, Mahmoud Mehdi

Abstract:

A low noise figure (NF) and high linearity V-band Low Noise Amplifier (LNA) is reported in this article. The LNA compromises a three-stage cascode configuration. This LNA will be used as a part of a WPAN (Wireless Personal Area Network) receiver in the millimeter-wave band at 60 GHz. It is designed according to the MMIC technology (Monolithic Microwave Integrated Circuit) in PH 15 process from UMS foundry and uses a 0.15 μm GaAs PHEMT (Pseudomorphic High Electron Mobility Transistor). The particularity of this LNA compared to other LNAs in literature is its very low noise figure which is equal to 1 dB and its high linearity (IIP3 is about 22 dB). The LNA consumes 0.24 Watts, achieving a high gain which is about 23 dB, an input return loss better than -10 dB and an output return loss better than -8 dB.

Keywords: low noise amplifier, V-band, MMIC technology, LNA, amplifier, cascode, pseudomorphic high electron mobility transistor (PHEMT), high linearity

Procedia PDF Downloads 503

Authors: Rose Shayeghi, Pejman Hosseinioun

Abstract:

The Multiple Intelligences theory characterizes human intelligence as a multifaceted entity that exists in all human beings with varying degrees. The most important contribution of this theory to the field of English Language Teaching (ELT) is its role in identifying individual differences and designing more learner-centered programs. The present study aims at investigating the relationship between different elements of multiple intelligence and grammar scores. To this end, 63 female Iranian EFL learner selected from among intermediate students participated in the study. The instruments employed were a Nelson English language test, Michigan Grammar Test, and Teele Inventory for Multiple Intelligences (TIMI). The results of Pearson Product-Moment Correlation revealed a significant positive correlation between grammatical accuracy and linguistic as well as interpersonal intelligence. The results of Stepwise Multiple Regression indicated that linguistic intelligence contributed to the prediction of grammatical accuracy.

Keywords: multiple intelligence, grammar, ELT, EFL, TIMI

Procedia PDF Downloads 483

Authors: Degale Desta, Cheng Jian

Abstract:

The most important factor in identifying a person is their face. Even identical twins have their own distinct faces. As a result, identification and face recognition are needed to tell one person from another. A face recognition system is a verification tool used to establish a person's identity using biometrics. Nowadays, face recognition is a common technique used in a variety of applications, including home security systems, criminal identification, and phone unlock systems. This system is more secure because it only requires a facial image instead of other dependencies like a key or card. Face detection and face identification are the two phases that typically make up a human recognition system.The idea behind designing and creating a face recognition system using deep learning with Azure ML Python's OpenCV is explained in this paper. Face recognition is a task that can be accomplished using deep learning, and given the accuracy of this method, it appears to be a suitable approach. To show how accurate the suggested face recognition system is, experimental results are given in 98.46% accuracy using Fast-RCNN Performance of algorithms under different training conditions.

Keywords: deep learning, face recognition, identification, fast-RCNN

Procedia PDF Downloads 134

Authors: Muhammet Baldan, Emel Timuçin

Abstract:

Molecular solubility prediction plays a crucial role in various fields, such as drug discovery, environmental science, and material science. In this study, we compare the performance of five machine learning algorithms—linear regression, support vector machines (SVM), random forests, gradient boosting machines (GBM), and neural networks—for predicting molecular solubility using the AqSolDB dataset. The dataset consists of 9981 data points with their corresponding solubility values. MACCS keys (166 bits), RDKit properties (20 properties), and structural properties(3) features are extracted for every smile representation in the dataset. A total of 189 features were used for training and testing for every molecule. Each algorithm is trained on a subset of the dataset and evaluated using metrics accuracy scores. Additionally, computational time for training and testing is recorded to assess the efficiency of each algorithm. Our results demonstrate that random forest model outperformed other algorithms in terms of predictive accuracy, achieving an 0.93 accuracy score. Gradient boosting machines and neural networks also exhibit strong performance, closely followed by support vector machines. Linear regression, while simpler in nature, demonstrates competitive performance but with slightly higher errors compared to ensemble methods. Overall, this study provides valuable insights into the performance of machine learning algorithms for molecular solubility prediction, highlighting the importance of algorithm selection in achieving accurate and efficient predictions in practical applications.

Keywords: random forest, machine learning, comparison, feature extraction

Procedia PDF Downloads 33

Authors: Gilbert Makanda, Roelf Sypkens

Abstract:

In this study we investigated the relevance of high school mathematics in university education. The paper particularly focused on whether the concepts taught in high school are enough for engineering courses at diploma level. The study identified particular concepts that are required in engineering courses whether they were adequately covered in high school. A questionnaire was used to investigate whether relevant topics were covered in high school. The respondents were 228 first year students at the Central University of Technology in the Faculty of Engineering and Information Technology. The study indicates that there are some topics such as integration, complex numbers and matrices that are not done at high schools and are required in engineering courses at university. It is further observed that some students did not cover the topics that are in the current syllabus. Female students enter the university less prepared than their male counterparts. More than 30% of the respondents in this study felt that high school mathematics was not useful for them to be able to do engineering courses.

Keywords: high school mathematics, university education, SPSS package, students' perceptions

Procedia PDF Downloads 280

Authors: Kaveh Shahi, Helmi Z. M. Shafri, Ebrahim Taherzadeh

Abstract:

In remote sensing, shadow causes problems in many applications such as change detection and classification. It is caused by objects which are elevated, thus can directly affect the accuracy of information. For these reasons, it is very important to detect shadows particularly in urban high spatial resolution imagery which created a significant problem. This paper focuses on automatic shadow detection based on a new spectral index for multispectral imagery known as Shadow Detection Index (SDI). The new spectral index was tested on different areas of World-View 2 images and the results demonstrated that the new spectral index has a massive potential to extract shadows effectively and automatically.

Keywords: spectral index, shadow detection, remote sensing images, World-View 2

Procedia PDF Downloads 524

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 378

Authors: Dua Hişam, Serhat İkizoğlu

Abstract:

Identifying the problem behind balance disorder is one of the most interesting topics in the medical literature. This study has considerably enhanced the development of artificial intelligence (AI) algorithms applying multiple machine learning (ML) models to sensory data on gait collected from humans to classify between normal people and those suffering from Vestibular System (VS) problems. Although AI is widely utilized as a diagnostic tool in medicine, AI models have not been used to perform feature extraction and identify VS disorders through training on raw data. In this study, three machine learning (ML) models, the Random Forest Classifier (RF), Extreme Gradient Boosting (XGB), and K-Nearest Neighbor (KNN), have been trained to detect VS disorder, and the performance comparison of the algorithms has been made using accuracy, recall, precision, and f1-score. With an accuracy of 95.28 %, Random Forest Classifier (RF) was the most accurate model.

Keywords: vestibular disorder, machine learning, random forest classifier, k-nearest neighbor, extreme gradient boosting

Procedia PDF Downloads 63

Authors: Cristian P. Topa, Esteban A. Valencia, Victor H. Hidalgo, Marco A. Martinez

Abstract:

Wind tunnel experiments for aerodynamic profiles display numerous advantages, such as: clean steady laminar flow, controlled environmental conditions, streamlines visualization, and real data acquisition. However, the experiment instrumentation usually is expensive, and hence, each test implies a incremented in design cost. The aim of this work is to select and implement a low-cost static pressure data acquisition system for a NACA 2412 airfoil in an open cycle wind tunnel. This work compares wind tunnel experiment with Computational Fluid Dynamics (CFD) simulation and parametric analysis. The experiment was evaluated at Reynolds of 1.65 e⁵, with increasing angles from -5° to 15°. The comparison between the approaches show good enough accuracy, between the experiment and CFD, additional parametric analysis results differ widely from the other methods, which complies with the lack of accuracy of the lateral approach due its simplicity.

Keywords: wind tunnel, low cost instrumentation, experimental testing, CFD simulation

Procedia PDF Downloads 173

Authors: Jeries J. Abou-Hanna, Bradley Storm

Abstract:

This paper looks to reduce the complexity of determining stress intensity factors while maintaining high levels of accuracy by the use of a linearized layering approach. Many techniques for stress intensity factor determination exist, but they can be limited by conservative results, requiring too many user parameters, or by being too computationally intensive. Multiple notch geometries with various crack lengths were investigated in this study to better understand the effectiveness of the proposed method. By linearizing the average stresses in radial layers around the crack tip, stress intensity factors were found to have error ranging from -10.03% to 8.94% when compared to analytically exact solutions. This approach proved to be a robust and efficient method of accurately determining stress intensity factors.

Keywords: fracture mechanics, finite element method, stress intensity factor, stress linearization

Procedia PDF Downloads 137

Authors: Anchana Julsiri, Seree Chadcham

Abstract:

The present study determined the effects of listening to pleasant Thai classical music on increasing working memory in elderly. Thai classical music without lyrics that made participants feel fun and aroused was used in the experiment for 3.19-5.40 minutes. The accuracy scores of Counting Span Task (CST), upper alpha ERD%, and theta ERS% were used to assess working memory of participants both before and after listening to pleasant Thai classical music. The results showed that the accuracy scores of CST and upper alpha ERD% in the frontal area of participants after listening to Thai classical music were significantly higher than before listening to Thai classical music (p < .05). Theta ERS% in the fronto-parietal network of participants after listening to Thai classical music was significantly lower than before listening to Thai classical music (p < .05).

Keywords: brain wave, elderly, pleasant Thai classical music, working memory

Procedia PDF Downloads 453

Authors: Andrey V. Timofeev, Dmitry V. Egorov

Abstract:

The practical efficient approach is suggested for estimation of the seismoacoustic sources energy in C-OTDR monitoring systems. This approach represents the sequential plan for confidence estimation both the seismoacoustic sources energy, as well the absorption coefficient of the soil. The sequential plan delivers the non-asymptotic guaranteed accuracy of obtained estimates in the form of non-asymptotic confidence regions with prescribed sizes. These confidence regions are valid for a finite sample size when the distributions of the observations are unknown. Thus, suggested estimates are non-asymptotic and nonparametric, and also these estimates guarantee the prescribed estimation accuracy in the form of the prior prescribed size of confidence regions, and prescribed confidence coefficient value.

Keywords: nonparametric estimation, sequential confidence estimation, multichannel monitoring systems, C-OTDR-system, non-lineary regression

Procedia PDF Downloads 350

Authors: Bharatendra Rai

Abstract:

Predictive data analysis and modeling involving machine learning techniques become challenging in presence of too many explanatory variables or features. Presence of too many features in machine learning is known to not only cause algorithms to slow down, but they can also lead to decrease in model prediction accuracy. This study involves housing dataset with 79 quantitative and qualitative features that describe various aspects people consider while buying a new house. Boruta algorithm that supports feature selection using a wrapper approach build around random forest is used in this study. This feature selection process leads to 49 confirmed features which are then used for developing predictive random forest models. The study also explores five different data partitioning ratios and their impact on model accuracy are captured using coefficient of determination (r-square) and root mean square error (rsme).

Keywords: housing data, feature selection, random forest, Boruta algorithm, root mean square error

Procedia PDF Downloads 315

Authors: Nur Nadhirah Rusyda Rosnan, Nursuhaili Najwa Masrol, Nurul Fatiha MD Nor, Mohammad Zafrullah Mohammad Salim, Sim Choon Cheak

Abstract:

Accurate inventories of oil palm planted areas are crucial for plantation management as this would impact the overall economy and production of oil. One of the technological advancements in the oil palm industry is semi-automated palm counting, which is replacing conventional manual palm counting via digitizing aerial imagery. Most of the semi-automated palm counting method that has been developed was limited to mature palms due to their ideal canopy size represented by satellite image. Therefore, immature palms were often left out since the size of the canopy is barely visible from satellite images. In this paper, an approach using a morphological filter and high-resolution satellite image is proposed to detect immature palm trees. This approach makes it possible to count the number of immature oil palm trees. The method begins with an erosion filter with an appropriate window size of 3m onto the high-resolution satellite image. The eroded image was further segmented using watershed segmentation to delineate immature palm tree regions. Then, local minimum detection was used because it is hypothesized that immature oil palm trees are located at the local minimum within an oil palm field setting in a grayscale image. The detection points generated from the local minimum are displaced to the center of the immature oil palm region and thinned. Only one detection point is left that represents a tree. The performance of the proposed method was evaluated on three subsets with slopes ranging from 0 to 20° and different planting designs, i.e., straight and terrace. The proposed method was able to achieve up to more than 90% accuracy when compared with the ground truth, with an overall F-measure score of up to 0.91.

Keywords: immature palm count, oil palm, precision agriculture, remote sensing

Procedia PDF Downloads 69

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

Abstract:

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

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

Procedia PDF Downloads 170

Authors: Shuo Liu, Dan Liu

Abstract:

In the field of named entity recognition, most of the research has been conducted around simple entities. However, for nested named entities, which still contain entities within entities, it has been difficult to identify them accurately due to their boundary ambiguity. In this paper, a hierarchical recognition model is constructed based on the grammatical structure and semantic features of Chinese text for boundary calculation based on lexical features. The analysis is carried out at different levels in terms of granularity, semantics, and lexicality, respectively, avoiding repetitive work to reduce computational effort and using the semantic features of words to calculate the boundaries of entities to improve the accuracy of the recognition work. The results of the experiments carried out on web-based microblogging data show that the model achieves an accuracy of 86.33% and an F1 value of 89.27% in recognizing nested named entities, making up for the shortcomings of some previous recognition models and improving the efficiency of recognition of nested named entities.

Keywords: coarse-grained, nested named entity, Chinese natural language processing, word embedding, T-SNE dimensionality reduction algorithm

Procedia PDF Downloads 121

Authors: Rishabh Nagpal, Riya Uchagaonkar, Venkata Naga Narasimha Ashish Mernedi, Ahmed Hambaba

Abstract:

The rapid evolution of technology in the communication sector continually seeks to bridge the gap between different communities, notably between the deaf community and the hearing world. This project develops a comprehensive American Sign Language (ASL) recognition system, leveraging the advanced capabilities of convolutional neural networks (CNNs) and vision transformers (ViTs) to interpret and translate ASL in real-time. The primary objective of this system is to provide an effective communication tool that enables seamless interaction through accurate sign language interpretation. The architecture of the proposed system integrates dual networks -VGG16 for precise spatial feature extraction and vision transformers for contextual understanding of the sign language gestures. The system processes live input, extracting critical features through these sophisticated neural network models, and combines them to enhance gesture recognition accuracy. This integration facilitates a robust understanding of ASL by capturing detailed nuances and broader gesture dynamics. The system is evaluated through a series of tests that measure its efficiency and accuracy in real-world scenarios. Results indicate a high level of precision in recognizing diverse ASL signs, substantiating the potential of this technology in practical applications. Challenges such as enhancing the system’s ability to operate in varied environmental conditions and further expanding the dataset for training were identified and discussed. Future work will refine the model’s adaptability and incorporate haptic feedback to enhance the interactivity and richness of the user experience. This project demonstrates the feasibility of an advanced ASL recognition system and lays the groundwork for future innovations in assistive communication technologies.

Keywords: sign language, computer vision, vision transformer, VGG16, CNN

Procedia PDF Downloads 31

Authors: Rahul Patel

Abstract:

Ahmedabad, a city located in western India, is experiencing rapid growth due to urbanization and industrialization. It is projected to become a metropolitan city in the near future, resulting in various construction activities. Soil testing is necessary before construction can commence, requiring construction companies and contractors to periodically conduct soil testing. The focus of this study is on the process of creating a spatial database that is digitally formatted and integrated with geotechnical data and a Geographic Information System (GIS). Building a comprehensive geotechnical (Geo)-database involves three steps: collecting borehole data from reputable sources, verifying the accuracy and redundancy of the data, and standardizing and organizing the geotechnical information for integration into the database. Once the database is complete, it is integrated with GIS, allowing users to visualize, analyze, and interpret geotechnical information spatially. Using a Topographic to Raster interpolation process in GIS, estimated values are assigned to all locations based on sampled geotechnical data values. The study area was contoured for SPT N-Values, Soil Classification, Φ-Values, and Bearing Capacity (T/m2). Various interpolation techniques were cross-validated to ensure information accuracy. This GIS map enables the calculation of SPT N-Values, Φ-Values, and bearing capacities for different footing widths and various depths. This study highlights the potential of GIS in providing an efficient solution to complex phenomena that would otherwise be tedious to achieve through other means. Not only does GIS offer greater accuracy, but it also generates valuable information that can be used as input for correlation analysis. Furthermore, this system serves as a decision support tool for geotechnical engineers.

Keywords: ArcGIS, borehole data, geographic information system, geo-database, interpolation, SPT N-value, soil classification, Φ-Value, bearing capacity

Procedia PDF Downloads 71

Authors: Belkacem Laimouche

Abstract:

With the field of artificial intelligence (AI) experiencing exponential growth, fueled by technological advancements that pave the way for increasingly innovative and promising applications, there is an escalating need to develop rigorous methods for assessing their performance in pursuit of transparency and equity. This article proposes a metrology-inspired statistical framework for evaluating bias and explainability in AI systems. Drawing from the principles of metrology, we propose a pioneering approach, using a concrete example, to evaluate the accuracy and precision of AI models, as well as to quantify the sources of measurement uncertainty that can lead to bias in their predictions. Furthermore, we explore a statistical approach for evaluating the explainability of AI systems based on their ability to provide interpretable and transparent explanations of their predictions.

Keywords: artificial intelligence, metrology, measurement uncertainty, prediction error, bias, machine learning algorithms, probabilistic models, interlaboratory comparison, data analysis, data reliability, measurement of bias impact on predictions, improvement of model accuracy and reliability

Procedia PDF Downloads 101

Authors: Rohini Hariharan, Yazhini R, Bhamidipati Naga Shrikarti

Abstract:

In the realm of cricket, particularly within the context of the Indian Premier League (IPL), the ability to predict team scores accurately holds significant importance for both cricket enthusiasts and stakeholders alike. This paper presents a comprehensive study on IPL score prediction utilizing various machine learning algorithms, including Support Vector Machines (SVM), XGBoost, Multiple Regression, Linear Regression, K-nearest neighbors (KNN), and Random Forest. Through meticulous data preprocessing, feature engineering, and model selection, we aimed to develop a robust predictive framework capable of forecasting team scores with high precision. Our experimentation involved the analysis of historical IPL match data encompassing diverse match and player statistics. Leveraging this data, we employed state-of-the-art machine learning techniques to train and evaluate the performance of each model. Notably, Multiple Regression emerged as the top-performing algorithm, achieving an impressive accuracy of 77.19% and a precision of 54.05% (within a threshold of +/- 10 runs). This research contributes to the advancement of sports analytics by demonstrating the efficacy of machine learning in predicting IPL team scores. The findings underscore the potential of advanced predictive modeling techniques to provide valuable insights for cricket enthusiasts, team management, and betting agencies. Additionally, this study serves as a benchmark for future research endeavors aimed at enhancing the accuracy and interpretability of IPL score prediction models.

Keywords: indian premier league (IPL), cricket, score prediction, machine learning, support vector machines (SVM), xgboost, multiple regression, linear regression, k-nearest neighbors (KNN), random forest, sports analytics

Procedia PDF Downloads 36