Search results for: infinite feature selection

Authors: Thanakrit Taweesoontorn, Sarucha Yanyong, Poom Konghuayrob

Abstract:

Robotic arms have gained popularity in various industries due to their accuracy and efficiency. This research proposes a method for bin-picking tasks using the Cobot, combining the YOLOv5 CNNs model for object detection and pose estimation with traditional feature detection (FAST), feature description (BRISK), and matching algorithms. By integrating these algorithms and utilizing a small-scale depth sensor camera for capturing depth and color images, the system achieves real-time object detection and accurate pose estimation, enabling the robotic arm to pick objects correctly in both position and orientation. Furthermore, the proposed method is implemented within the ROS framework to provide a seamless platform for robotic control and integration. This integration of robotics, cameras, and AI technology contributes to the development of industrial robotics, opening up new possibilities for automating challenging tasks and improving overall operational efficiency.

Keywords: robotic vision, image processing, applications of robotics, artificial intelligent

Procedia PDF Downloads 97

Authors: Danielle Shackley, Yetunde Folajimi

Abstract:

As more people turn to the internet seeking health-related information, there is more risk of finding false, inaccurate, or dangerous information. Sentiment analysis is a natural language processing technique that assigns polarity scores to text, ranging from positive, neutral, and negative. In this research, we evaluate the weight of a sentiment analysis feature added to fake health news classification models. The dataset consists of existing reliably labeled health article headlines that were supplemented with health information collected about COVID-19 from social media sources. We started with data preprocessing and tested out various vectorization methods such as Count and TFIDF vectorization. We implemented 3 Naive Bayes classifier models, including Bernoulli, Multinomial, and Complement. To test the weight of the sentiment analysis feature on the dataset, we created benchmark Naive Bayes classification models without sentiment analysis, and those same models were reproduced, and the feature was added. We evaluated using the precision and accuracy scores. The Bernoulli initial model performed with 90% precision and 75.2% accuracy, while the model supplemented with sentiment labels performed with 90.4% precision and stayed constant at 75.2% accuracy. Our results show that the addition of sentiment analysis did not improve model precision by a wide margin; while there was no evidence of improvement in accuracy, we had a 1.9% improvement margin of the precision score with the Complement model. Future expansion of this work could include replicating the experiment process and substituting the Naive Bayes for a deep learning neural network model.

Keywords: sentiment analysis, Naive Bayes model, natural language processing, topic analysis, fake health news classification model

Procedia PDF Downloads 97

Authors: Omar Boutkhoum, Mohamed Hanine, Abdessadek Bendarag

Abstract:

Sustainable economic growth is nowadays driving firms to extend toward the adoption of many green supply chain management (GSCM) solutions. However, the evaluation and selection of these solutions is a matter of concern that needs very serious decisions, involving complexity owing to the presence of various associated factors. To resolve this problem, a comparative analysis approach based on multi-criteria decision-making methods is proposed for adequate evaluation of sustainable supply chain management solutions. In the present paper, we propose an integrated decision-making model based on FAHP (Fuzzy Analytic Hierarchy Process), TOPSIS (Technique for Order of Preference by Similarity to Ideal Solution) and PROMETHEE (Preference Ranking Organisation METHod for Enrichment Evaluations) to contribute to a better understanding and development of new sustainable strategies for industrial organizations. Due to the varied importance of the selected criteria, FAHP is used to identify the evaluation criteria and assign the importance weights for each criterion, while TOPSIS and PROMETHEE methods employ these weighted criteria as inputs to evaluate and rank the alternatives. The main objective is to provide a comparative analysis based on TOPSIS and PROMETHEE processes to help make sound and reasoned decisions related to the selection problem of GSCM solution.

Keywords: GSCM solutions, multi-criteria analysis, decision support system, TOPSIS, FAHP, PROMETHEE

Procedia PDF Downloads 163

Authors: Nivedita Paul

Abstract:

Marriages in India are part and parcel of kinship and cultural practices. Marriage practices differ in India because of cross-regional diversities in social relations which itself has evolved as a result of causal relationship between space and culture. As the place is important for the formation of culture and other social structures, therefore there is regional differentiation in cultural practices and marital customs. Based on the cultural practices some scholars have divided India into North and South kinship regions where women in the North get married early and have lesser autonomy compared to women in the South where marriages are mostly consanguineous. But, the emergence of new modes and alternative strategies such as matrimonial advertisements becoming popular, as well as the increase in women’s literacy and work force participation, matchmaking process in India has changed to some extent. The present study uses data from Indian Human Development Survey II (2011-12) which is a nationally representative multitopic survey that covers 41,554 households. Currently married women of age group 15-49 in their first marriage; whose year of marriage is from the 1970s to 2000s have been taken for the study. Based on spouse selection experiences, the sample of women has been divided into three marriage categories-self, semi and family arranged. Women in self-arranged or love marriage is the sole decision maker in choosing the partner, in semi-arranged marriage or arranged marriage with consent both parents and women together take the decision, whereas in family arranged or arranged marriage without consent only parents take the decision. The main aim of the study is to show the spatial and regional variations in spouse selection decision making. The basis for regionalization has been taken from Irawati Karve’s pioneering work on kinship studies in India called Kinship Organization in India. India is divided into four kinship regions-North, Central, South and East. Since this work was formulated in 1953, some of the states have experienced changes due to modernization; hence these have been regrouped. After mapping spouse selection patterns using GIS software, it is found that the northern region has mostly family arranged marriages (around 64.6%), the central zone shows a mixed pattern since family arranged marriages are less than north but more than south and semi-arranged marriages are more than north but less than south. The southern zone has the dominance of semi-arranged marriages (around 55%) whereas the eastern zone has more of semi-arranged marriage (around 53%) but there is also a high percentage of self-arranged marriage (around 42%). Thus, arranged marriage is the dominant form of marriage in all four regions, but with a difference in the degree of the involvement of the female and her parents and relatives.

Keywords: spouse selection, consent, kinship, regional pattern

Procedia PDF Downloads 168

Authors: Ma Lei-Lei, Zhou You

Abstract:

Aiming at the problems of low detection accuracy of deep learning algorithm in traffic sign detection, this paper proposes improved EfficientDet based traffic sign detection algorithm. Multi-head self-attention is introduced in the minimum resolution layer of the backbone of EfficientDet to achieve effective aggregation of local and global depth information, and this study proposes an improved feature fusion pyramid with increased vertical cross-layer connections, which improves the performance of the model while introducing a small amount of complexity, the Balanced L1 Loss is introduced to replace the original regression loss function Smooth L1 Loss, which solves the problem of balance in the loss function. Experimental results show, the algorithm proposed in this study is suitable for the task of traffic sign detection. Compared with other models, the improved EfficientDet has the best detection accuracy. Although the test speed is not completely dominant, it still meets the real-time requirement.

Keywords: convolutional neural network, transformer, feature pyramid networks, loss function

Procedia PDF Downloads 98

Authors: Y. Kourd, D. Lefebvre

Abstract:

The monitoring of industrial processes is required to ensure operating conditions of industrial systems through automatic detection and isolation of faults. This paper proposes a method of fault diagnosis based on a neuro-fuzzy hybrid structure. This hybrid structure combines the selection of threshold and decision tree. The validation of this method is obtained with the DAMADICS benchmark. In the first phase of the method, a model will be constructed that represents the normal state of the system to fault detection. Signatures of the faults are obtained with residuals analysis and selection of appropriate thresholds. These signatures provide groups of non-separable faults. In the second phase, we build faulty models to see the flaws in the system that cannot be isolated in the first phase. In the latest phase we construct the tree that isolates these faults.

Keywords: decision tree, residuals analysis, ANFIS, fault diagnosis

Procedia PDF Downloads 626

Authors: Xiaoqing Wang, Junfeng Wang, Xiaolan Zhu

Abstract:

Android operating system has been recognized by most application developers because of its good open-source and compatibility, which enriches the categories of applications greatly. However, it has become the target of malware attackers due to the lack of strict security supervision mechanisms, which leads to the rapid growth of malware, thus bringing serious safety hazards to users. Therefore, it is critical to detect Android malware effectively. Generally, the permissions declared in the AndroidManifest.xml can reflect the function and behavior of the application to a large extent. Since current Android system has not any restrictions to the number of permissions that an application can request, developers tend to apply more than actually needed permissions in order to ensure the successful running of the application, which results in the abuse of permissions. However, some traditional detection methods only consider the requested permissions and ignore whether it is actually used, which leads to incorrect identification of some malwares. Therefore, a machine learning detection method based on the actually used permissions combination and API calls was put forward in this paper. Meanwhile, several experiments are conducted to evaluate our methodology. The result shows that it can detect unknown malware effectively with higher true positive rate and accuracy while maintaining a low false positive rate. Consequently, the AdaboostM1 (J48) classification algorithm based on information gain feature selection algorithm has the best detection result, which can achieve an accuracy of 99.8%, a true positive rate of 99.6% and a lowest false positive rate of 0.

Keywords: android, API Calls, machine learning, permissions combination

Procedia PDF Downloads 329

Authors: Uma Maheshwari V., Rajanikanth Aluvalu, Kumar Gautam

Abstract:

The COVID-19 disease is a highly contagious viral infection with major worldwide health implications. The global economy suffers as a result of COVID. The spread of this pandemic disease can be slowed if positive patients are found early. COVID-19 disease prediction is beneficial for identifying patients' health problems that are at risk for COVID. Deep learning and machine learning algorithms for COVID prediction using X-rays have the potential to be extremely useful in solving the scarcity of doctors and clinicians in remote places. In this paper, a convolutional neural network (CNN) with deep layers is presented for recognizing COVID-19 patients using real-world datasets. We gathered around 6000 X-ray scan images from various sources and split them into two categories: normal and COVID-impacted. Our model examines chest X-ray images to recognize such patients. Because X-rays are commonly available and affordable, our findings show that X-ray analysis is effective in COVID diagnosis. The predictions performed well, with an average accuracy of 99% on training photographs and 88% on X-ray test images.

Keywords: deep CNN, COVID–19 analysis, feature extraction, feature map, accuracy

Procedia PDF Downloads 80

Authors: L. Yu, W. K. Li, S. K. Ong, A. Y. C. Nee

Abstract:

In this paper, a scalable augmented reality framework for handheld devices is presented. The presented framework is enabled by using a server-client data communication structure, in which the search for tracking targets among a database of images is performed on the server-side while pixel-wise 3D tracking is performed on the client-side, which, in this case, is a handheld mobile device. Image search on the server-side adopts a residual-enhanced image descriptors representation that gives the framework a scalability property. The tracking algorithm on the client-side is based on a gravity-aligned feature descriptor which takes the advantage of a sensor-equipped mobile device and an optimized intensity-based image alignment approach that ensures the accuracy of 3D tracking. Automatic content streaming is achieved by using a key-frame selection algorithm, client working phase monitoring and standardized rules for content communication between the server and client. The recognition accuracy test performed on a standard dataset shows that the method adopted in the presented framework outperforms the Bag-of-Words (BoW) method that has been used in some of the previous systems. Experimental test conducted on a set of video sequences indicated the real-time performance of the tracking system with a frame rate at 15-30 frames per second. The presented framework is exposed to be functional in practical situations with a demonstration application on a campus walk-around.

Keywords: augmented reality framework, server-client model, vision-based tracking, image search

Procedia PDF Downloads 275

Authors: Adelina Castelo

Abstract:

The increasing number of learners of Portuguese as Foreign Language in China justifies the need to define the phonetic profile of these learners and to design didactic materials that are adjusted to their specific problems in pronunciation. Different aspects of this topic have been studied, but the production of oral vowels still needs to be investigated. This study aims: (i) to identify the problems the Chinese learners of Portuguese experience in the pronunciation of oral vowels; (ii) to discuss the didactic implications drawn from those problems. The participants were eight native speakers of Mandarin Chinese that had been learning Portuguese in College for almost a year. They named pictured objects and their oral productions were recorded and phonetically transcribed. The selection of the objects to name took into account some linguistic variables (e.g. stress pattern, syllable structure, presence of the Portuguese oral vowels in different word positions according to stress location). The results are analysed in two ways: the impact of linguistic variables on the success rate in the vowels' production; the replacement strategies used in the non-target productions. Both analyses show that the Chinese learners of Portuguese (i) have significantly more difficulties with the mid vowels as well as the high central vowel and (ii) do not master the vowel height feature. These findings contribute to define the phonetic profile of these learners in terms of oral vowel production. Besides, they have important didactic implications for the pronunciation teaching to these specific learners. Those implications are discussed and exemplified.

Keywords: Chinese learners, learners’ phonetic profile, linguistic variables, Portuguese as foreign language, production data, pronunciation teaching, oral vowels

Procedia PDF Downloads 223

Authors: Seung Hwan Park, Cheng-Sool Park, Jun Seok Kim, Youngji Yoo, Daewoong An, Jun-Geol Baek

Abstract:

Depending on the big data analysis becomes important, yield prediction using data from the semiconductor process is essential. In general, yield prediction and analysis of the causes of the failure are closely related. The purpose of this study is to analyze pattern affects the final test results using a die map based clustering. Many researches have been conducted using die data from the semiconductor test process. However, analysis has limitation as the test data is less directly related to the final test results. Therefore, this study proposes a framework for analysis through clustering using more detailed data than existing die data. This study consists of three phases. In the first phase, die map is created through fail bit data in each sub-area of die. In the second phase, clustering using map data is performed. And the third stage is to find patterns that affect final test result. Finally, the proposed three steps are applied to actual industrial data and experimental results showed the potential field application.

Keywords: die-map clustering, feature extraction, pattern recognition, semiconductor manufacturing process

Procedia PDF Downloads 403

Authors: Ezeni Brzovska, Durdana Ozretic-Dosen

Abstract:

The purpose of this paper is to deepen the understanding of the product cues that influence purchase decision for a specific product category – chocolate, and to identify demographic differences in the buying behavior. ANOVA was employed for analyzing the significance level for nine product cues, and the survey showed statistically significant differences among different age and gender groups, and between respondents with different levels of education. From the theoretical perspective, the study adds to the existing knowledge by contributing with the research results from the new environment (Southeast Europe, Macedonia), which has been neglected so far. Establishing the level of significance for the product cues that affect buying behavior in the chocolate consumption context might help managers to improve marketing decision-making, and better meet consumer needs through identifying opportunities for packaging innovations and/or personalization toward different target groups.

Keywords: chocolate consumption context, chocolate selection, demographic characteristics, product cues

Procedia PDF Downloads 253

Authors: Paul W. Murray, Marco Barajas

Abstract:

Recent changes in supply chains, especially globalization and collaboration, have created new risks for enterprises of all sizes. A variety of complex frameworks, often based on enterprise risk management strategies have been presented under the heading of Supply Chain Risk Management (SCRM). The literature on promotes the benefits of a robust SCRM strategy; however, implementing SCRM is difficult and resource demanding for Large Enterprises (LEs), and essentially out of reach for Small and Medium Enterprises (SMEs). This research debunks the idea that SCRM is necessary for all enterprises and instead proposes a simple and effective Vendor Selection Template (VST). Empirical testing and a survey of supply chain practitioners provide a measure of validation to the VST. The resulting VSTis a valuable contribution because is easy to use, provides practical results, and is sufficiently flexible to be universally applied to SMEs.

Keywords: multiple regression analysis, supply chain management, risk assessment, vendor selection

Procedia PDF Downloads 465

Authors: Kassa Endalamaw Rewnu

Abstract:

The variability properties of a quasar sample, spectroscopically complete to magnitude J = 22.0, are investigated on a time baseline of 2 years using three different photometric bands (U, J and F). The original sample was obtained using a combination of different selection criteria: colors, slitless spectroscopy and variability, based on a time baseline of 1 yr. The main goals of this work are two-fold: first, to derive the percentage of variable quasars on a relatively short time baseline; secondly, to search for new quasar candidates missed by the other selection criteria; and, thus, to estimate the completeness of the spectroscopic sample. In order to achieve these goals, we have extracted all the candidate variable objects from a sample of about 1800 stellar or quasi-stellar objects with limiting magnitude J = 22.50 over an area of about 0.50 deg2. We find that > 65% of all the objects selected as possible variables are either confirmed quasars or quasar candidates on the basis of their colors. This percentage increases even further if we exclude from our lists of variable candidates a number of objects equal to that expected on the basis of `contamination' induced by our photometric errors. The percentage of variable quasars in the spectroscopic sample is also high, reaching about 50%. On the basis of these results, we can estimate that the incompleteness of the original spectroscopic sample is < 12%. We conclude that variability analysis of data with small photometric errors can be successfully used as an efficient and independent (or at least auxiliary) selection method in quasar surveys, even when the time baseline is relatively short. Finally, when corrected for the different intrinsic time lags corresponding to a fixed observed time baseline, our data do not show a statistically significant correlation between variability and either absolute luminosity or redshift.

Keywords: nuclear activity, galaxies, active quasars, variability

Procedia PDF Downloads 82

Authors: Goodness Onwuka, Khaled Abou-El-Hossein

Abstract:

Borosilicate-crown (BK7) glass has found broad application in the optic and automotive industries and the growing demands for nanometric surface finishes is becoming a necessity in such applications. Thus, it has become paramount to optimize the parameters influencing the surface roughness of this precision lens. The research was carried out on a 4-axes Nanoform 250 precision lathe machine with an ultra-high precision grinding spindle. The experiment varied the machining parameters of feed rate, wheel speed and depth of cut at three levels for different combinations using Box Behnken design of experiment and the resulting surface roughness values were measured using a Taylor Hobson Dimension XL optical profiler. Acoustic emission monitoring technique was applied at a high sampling rate to monitor the machining process while further signal processing and feature extraction methods were implemented to generate the input to a neural network algorithm. This paper highlights the training and development of a back propagation neural network prediction algorithm through careful selection of parameters and the result show a better classification accuracy when compared to a previously developed response surface model with very similar machining parameters. Hence artificial neural network algorithms provide better surface roughness prediction accuracy in the ultra-high precision grinding of BK7 glass.

Keywords: acoustic emission technique, artificial neural network, surface roughness, ultra-high precision grinding

Procedia PDF Downloads 305

Authors: M. Mohemmed Sha, T. Manesh, A. Ahmed Mohamed Mustaq

Abstract:

In this corporate world, the technology of Web services has grown rapidly and its significance for the development of web based applications gradually rises over time. The success of Business to Business integration rely on finding novel partners and their services in a global business environment. But the selection of the most suitable Web service from the list of services with the identical functionality is more vital. The satisfaction level of the customer and the provider’s reputation of the Web service are primarily depending on the range it reaches the customer’s requirements. In most cases the customer of the Web service feels that he is spending for the service which is undelivered. This is because the customer always thinks that the real functionality of the web service is not reached. This will lead to change of the service frequently. In this paper, a framework is proposed to evaluate the Quality of Service (QoS) and its cost that makes the optimal correlation between each other. Also this research work proposes some management decision against the functional deviancy of the web service that are guaranteed at time of selection.

Keywords: web service, service level agreement, quality of a service, cost of a service, QoS, CoS, SOA, WSLA, WsRF

Procedia PDF Downloads 419

Authors: Akrem Sellami, Imed Riadh Farah

Abstract:

Hyperspectral imagery (HSI) typically provides a wealth of information captured in a wide range of the electromagnetic spectrum for each pixel in the image. Hence, a pixel in HSI is a high-dimensional vector of intensities with a large spectral range and a high spectral resolution. Therefore, the semantic interpretation is a challenging task of HSI analysis. We focused in this paper on object classification as HSI semantic interpretation. However, HSI classification still faces some issues, among which are the following: The spatial variability of spectral signatures, the high number of spectral bands, and the high cost of true sample labeling. Therefore, the high number of spectral bands and the low number of training samples pose the problem of the curse of dimensionality. In order to resolve this problem, we propose to introduce the process of dimensionality reduction trying to improve the classification of HSI. The presented approach is a semi-supervised band selection method based on spatial hypergraph embedding model to represent higher order relationships with different weights of the spatial neighbors corresponding to the centroid of pixel. This semi-supervised band selection has been developed to select useful bands for object classification. The presented approach is evaluated on AVIRIS and ROSIS HSIs and compared to other dimensionality reduction methods. The experimental results demonstrate the efficacy of our approach compared to many existing dimensionality reduction methods for HSI classification.

Keywords: dimensionality reduction, hyperspectral image, semantic interpretation, spatial hypergraph

Procedia PDF Downloads 306

Authors: S. Zith Dey Babu, S. Kour, S. Verma, C. Verma, V. Pathania, A. Agrawal, V. Chaudhary, A. Manoj Puthur, R. Goyal, A. Pal, T. Danti Dey, A. Kumar, K. Wadhwa, O. Ved

Abstract:

Background: Skin cancer is now is the buzzing button in the field of medical science. The cyst's pandemic is drastically calibrating the body and well-being of the global village. Methods: The extracted image of the skin tumor cannot be used in one way for diagnosis. The stored image contains anarchies like the center. This approach will locate the forepart of an extracted appearance of skin. Partitioning image models has been presented to sort out the disturbance in the picture. Results: After completing partitioning, feature extraction has been formed by using genetic algorithm and finally, classification can be performed between the trained and test data to evaluate a large scale of an image that helps the doctors for the right prediction. To bring the improvisation of the existing system, we have set our objectives with an analysis. The efficiency of the natural selection process and the enriching histogram is essential in that respect. To reduce the false-positive rate or output, GA is performed with its accuracy. Conclusions: The objective of this task is to bring improvisation of effectiveness. GA is accomplishing its task with perfection to bring down the invalid-positive rate or outcome. The paper's mergeable portion conflicts with the composition of deep learning and medical image processing, which provides superior accuracy. Proportional types of handling create the reusability without any errors.

Keywords: computer-aided system, detection, image segmentation, morphology

Procedia PDF Downloads 150

Authors: Rashini Maduka, C. R. Wijesinghe, A. R. Weerasinghe

Abstract:

Drug-drug interactions (DDIs) can happen when two or more drugs are taken together. Today DDIs have become a serious health issue due to adverse drug effects. In vivo and in vitro methods for identifying DDIs are time-consuming and costly. Therefore, in-silico-based approaches are preferred in DDI identification. Most machine learning models for DDI prediction are used chemical and biological drug properties as features. However, some drug features are not available and costly to extract. Therefore, it is better to make automatic feature engineering. Furthermore, people who have diabetes already suffer from other diseases and take more than one medicine together. Then adverse drug effects may happen to diabetic patients and cause unpleasant reactions in the body. In this study, we present a model with a graph convolutional autoencoder and a graph decoder using a dataset from DrugBank version 5.1.3. The main objective of the model is to identify unknown interactions between antidiabetic drugs and the drugs taken by diabetic patients for other diseases. We considered automatic feature engineering and used Known DDIs only as the input for the model. Our model has achieved 0.86 in AUC and 0.86 in AP.

Keywords: drug-drug interaction prediction, graph embedding, graph convolutional networks, adverse drug effects

Procedia PDF Downloads 100

Authors: Berfin Yildiz

Abstract:

These days, increasing global warming effects, limited amount of energy resources, etc., necessitates the awareness that must be present in every profession group. The architecture and construction sectors are responsible for both the embodied and operational energy of the materials. This responsibility has led designers to seek alternative solutions for energy-efficient material selection. The choice of energy-efficient material requires consideration of the entire life cycle, including the building's production, use, and disposal energy. The aim of this study is to investigate the method of material selection of external thermal insulation composite systems (ETICS). Embodied and in-use energy values of material alternatives were used for the evaluation in this study. The operational energy is calculated according to the u-value calculation method defined in the TS 825 (Thermal Insulation Requirements) standard for Turkey, and the embodied energy is calculated based on the manufacturer's Energy Performance Declaration (EPD). ETICS consists of a wall, adhesive, insulation, lining, mechanical, mesh, and exterior finishing materials. In this study, lining, mechanical, and mesh materials were ignored because EPD documents could not be obtained. The material selection problem is designed as a hypothetical volume area (5x5x3m) and defined as a multi-objective discrete optimization problem for external thermal insulation composite systems. Defining the problem as a discrete optimization problem is important in order to choose between materials of various thicknesses and sizes. Since production and use energy values, which are determined as optimization objectives in the study, are often conflicting values, material selection is defined as a multi-objective optimization problem, and it is aimed to obtain many solution alternatives by using Hypervolume (HypE) algorithm. The enrollment process started with 100 individuals and continued for 50 generations. According to the obtained results, it was observed that autoclaved aerated concrete and Ponce block as wall material, glass wool, as insulation material gave better results.

Keywords: embodied energy, multi-objective discrete optimization, performative design, thermal insulation

Procedia PDF Downloads 141

Authors: Amir Mukhtar, Dr. Likun Xia

Abstract:

An improved, robust and efficient visual target tracking algorithm using particle filtering is proposed. Particle filtering has been proven very successful in estimating non-Gaussian and non-linear problems. In this paper, the particle filter is used with color feature to estimate the target state with time. Color distributions are applied as this feature is scale and rotational invariant, shows robustness to partial occlusion and computationally efficient. The performance is made more robust by choosing the different (YIQ) color scheme. Tracking is performed by comparison of chrominance histograms of target and candidate positions (particles). Color based particle filter tracking often leads to inaccurate results when light intensity changes during a video stream. Furthermore, background subtraction technique is used for size estimation of the target. The qualitative evaluation of proposed algorithm is performed on several real-world videos. The experimental results demonstrate that the improved algorithm can track the moving objects very well under illumination changes, occlusion and moving background.

Keywords: tracking, particle filter, histogram, corner points, occlusion, illumination

Procedia PDF Downloads 381

Authors: Shibo Wei, Ting Jiang

Abstract:

Convolutional-recurrent neural networks (CRN) have achieved much success recently in the speech enhancement field. The common processing method is to use the convolution layer to compress the feature space by multiple upsampling and then model the compressed features with the LSTM layer. At last, the enhanced speech is obtained by deconvolution operation to integrate the global information of the speech sequence. However, the feature space compression process may cause the loss of information, so we propose to model the upsampling result of each step with the residual LSTM layer, then join it with the output of the deconvolution layer and input them to the next deconvolution layer, by this way, we want to integrate the global information of speech sequence better. The experimental results show the network model (RES-CRN) we introduce can achieve better performance than LSTM without residual and overlaying LSTM simply in the original CRN in terms of scale-invariant signal-to-distortion ratio (SI-SNR), speech quality (PESQ), and intelligibility (STOI).

Keywords: convolutional-recurrent neural networks, speech enhancement, residual LSTM, SI-SNR

Procedia PDF Downloads 201

Authors: I. M. L. Nadeesha Jayaweera, Adao Alex Trindade

Abstract:

In choosing a candidate model in likelihood-based modeling via an information criterion, the practitioner is often faced with the difficult task of deciding just how far up the ranked list to look. Motivated by this pragmatic necessity, we construct an uncertainty band for a generalized (model selection) information criterion (GIC), defined as a criterion for which the limit in probability is identical to that of the normalized log-likelihood. This includes common special cases such as AIC & BIC. The method starts from the asymptotic normality of the GIC for the joint distribution of the candidate models in an independent and identically distributed (IID) data framework and proceeds by deriving the (asymptotically) exact distribution of the minimum. The calculation of an upper quantile for its distribution then involves the computation of multivariate Gaussian integrals, which is amenable to efficient implementation via the R package "mvtnorm". The performance of the methodology is tested on simulated data by checking the coverage probability of nominal upper quantiles and compared to the bootstrap. Both methods give coverages close to nominal for large samples, but the bootstrap is two orders of magnitude slower. The methodology is subsequently extended to two other commonly used model structures: regression and time series. In the regression case, we derive the corresponding asymptotically exact distribution of the minimum GIC invoking Lindeberg-Feller type conditions for triangular arrays and are thus able to similarly calculate upper quantiles for its distribution via multivariate Gaussian integration. The bootstrap once again provides a default competing procedure, and we find that similar comparison performance metrics hold as for the IID case. The time series case is complicated by far more intricate asymptotic regime for the joint distribution of the model GIC statistics. Under a Gaussian likelihood, the default in most packages, one needs to derive the limiting distribution of a normalized quadratic form for a realization from a stationary series. Under conditions on the process satisfied by ARMA models, a multivariate normal limit is once again achieved. The bootstrap can, however, be employed for its computation, whence we are once again in the multivariate Gaussian integration paradigm for upper quantile evaluation. Comparisons of this bootstrap-aided semi-exact method with the full-blown bootstrap once again reveal a similar performance but faster computation speeds. One of the most difficult problems in contemporary statistical methodological research is to be able to account for the extra variability introduced by model selection uncertainty, the so-called post-model selection inference (PMSI). We explore ways in which the GIC uncertainty band can be inverted to make inferences on the parameters. This is being attempted in the IID case by pivoting the CDF of the asymptotically exact distribution of the minimum GIC. For inference one parameter at a time and a small number of candidate models, this works well, whence the attained PMSI confidence intervals are wider than the MLE-based Wald, as expected.

Keywords: model selection inference, generalized information criteria, post model selection, Asymptotic Theory

Procedia PDF Downloads 89

Authors: Mohammad Shams Esfand Abadi, Mohammad Ranjbar, Reza Ebrahimpour

Abstract:

This work presents the distributed processing solution problem in a diffusion network based on the adapt then combine (ATC) and combine then adapt (CTA)selective partial update normalized least mean squares (SPU-NLMS) algorithms. Also, we extend this approach to dynamic selection affine projection algorithm (DS-APA) and ATC-DS-APA and CTA-DS-APA are established. The purpose of ATC-SPU-NLMS and CTA-SPU-NLMS algorithm is to reduce the computational complexity by updating the selected blocks of weight coefficients at every iteration. In CTA-DS-APA and ATC-DS-APA, the number of the input vectors is selected dynamically. Diffusion cooperation strategies have been shown to provide good performance based on these algorithms. The good performance of introduced algorithm is illustrated with various experimental results.

Keywords: selective partial update, affine projection, dynamic selection, diffusion, adaptive distributed networks

Procedia PDF Downloads 707

Authors: O. Sunantha, S. Zhenfeng, S. Phattraporn, A. Zeeshan

Abstract:

The decline of soil organic carbon (SOC) in global agriculture is a critical issue requiring rapid and accurate estimation for informed policymaking. While it is recognized that SOC predictors vary significantly when derived from remote sensing data and environmental variables, identifying the specific parameters most suitable for accurately estimating SOC in diverse agricultural areas remains a challenge. This study utilizes remote sensing data to precisely estimate SOC and identify influential factors in diverse agricultural areas, such as paddy, corn, sugarcane, cassava, and perennial crops. Extreme gradient boosting (XGBoost), random forest (RF), and support vector regression (SVR) models are employed to analyze these factors' impact on SOC estimation. The results show key factors influencing SOC estimation include slope, vegetation indices (EVI), spectral reflectance indices (red index, red edge2), temperature, land use, and surface soil moisture, as indicated by their averaged importance scores across XGBoost, RF, and SVR models. Therefore, using different machine learning algorithms for SOC estimation reveals varying influential factors from remote sensing data and environmental variables. This approach emphasizes feature selection, as different machine learning algorithms identify various key factors from remote sensing data and environmental variables for accurate SOC estimation.

Keywords: factors influencing SOC estimation, remote sensing data, environmental variables, machine learning

Procedia PDF Downloads 35

Authors: Till Gramberg, Max Kellner, Erwin Gross

Abstract:

This paper presents a comprehensive investigation into the topic of smart services and IIoT-Platforms, focusing on their selection and prioritization in manufacturing organizations. First, a literature review is conducted to provide a basic understanding of the current state of research in the area of smart services. Based on discussed and established definitions, a definition approach for this paper is developed. In addition, value propositions for smart services are identified based on the literature and expert interviews. Furthermore, the general requirements for the provision of smart services are presented. Subsequently, existing approaches for the selection and development of smart services are identified and described. In order to determine the requirements for the selection of smart services, expert opinions from successful companies that have already implemented smart services are collected through semi-structured interviews. Based on the results, criteria for the evaluation of existing methods are derived. The existing methods are then evaluated according to the identified criteria. Furthermore, a novel method for the selection of smart services in manufacturing companies is developed, taking into account the identified criteria and the existing approaches. The developed concept for the method is verified in expert interviews. The method includes a collection of relevant smart services identified in the literature. The actual relevance of the use cases in the industrial environment was validated in an online survey. The required data and sensors are assigned to the smart service use cases. The value proposition of the use cases is evaluated in an expert workshop using different indicators. Based on this, a comparison is made between the identified value proposition and the required data, leading to a prioritization process. The prioritization process follows an established procedure for evaluating technical decision-making processes. In addition to the technical requirements, the prioritization process includes other evaluation criteria such as the economic benefit, the conformity of the new service offering with the company strategy, or the customer retention enabled by the smart service. Finally, the method is applied and validated in an industrial environment. The results of these experiments are critically reflected upon and an outlook on future developments in the area of smart services is given. This research contributes to a deeper understanding of the selection and prioritization process as well as the technical considerations associated with smart service implementation in manufacturing organizations. The proposed method serves as a valuable guide for decision makers, helping them to effectively select the most appropriate smart services for their specific organizational needs.

Keywords: smart services, IIoT, industrie 4.0, IIoT-platform, big data

Procedia PDF Downloads 89

Authors: Boumediene Hamzi, Turky N. AlOtaiby, Saleh AlShebeili, Arwa AlAnqary

Abstract:

We introduce a data-driven method for seizure detection drawing on recent progress in Machine Learning. The method is based on embedding probability measures in a high (or infinite) dimensional reproducing kernel Hilbert space (RKHS) where the Maximum Mean Discrepancy (MMD) is computed. The MMD is metric between probability measures that are computed as the difference between the means of probability measures after being embedded in an RKHS. Working in RKHS provides a convenient, general functional-analytical framework for theoretical understanding of data. We apply this approach to the problem of seizure detection.

Keywords: kernel methods, maximum mean discrepancy, seizure detection, machine learning

Procedia PDF Downloads 238

Authors: Patricia Agboro

Abstract:

The definition of a concept is quite important in any philosophical discourse as it serves as a guide in the analysis of that concept. In the sciences, arriving at a consensus regarding concepts is quite easily achievable due to the nature of the discipline. Problem arises when one delves into the realm of the humanities. Discourses in the humanities are largely perspectival because the question of values come into play. Defining the concept of Art is no different as it has yielded unresolved and problematic issues arising from attempts at definition. A major problem arising from such attempt is that of exclusion of other art forms. In this paper therefore, we call for the rejection of an attempt at providing a comprehensive definition for Art since it is clear that the collection of definitions provided so far, has failed in capturing the nuances and intricacies of the infinite varieties of the art forms that there are. Rather, a more fruitful approach to philosophical discourses on Art is not to construe the theories of Art per-se but to reconstruct them as a collection of criteria for determining artistic excellence.

Keywords: art, creativity, definition, reconstruction

Procedia PDF Downloads 175

Authors: Yifan Hou, Haibo Liu, Le Jiang, Wandong Su, Binqing Wang

Abstract:

Road defect detection is crucial for modern urban management and infrastructure maintenance. Traditional road defect detection methods mostly rely on manual labor, which is not only inefficient but also difficult to ensure their reliability. However, existing deep learning-based road defect detection models have poor detection performance in complex environments and lack robustness to multi-scale targets. To address this challenge, this paper proposes a distinct detection framework based on the one stage algorithm network structure. This article designs a deep feature extraction network based on RCSDarknet, which applies channel shuffling to enhance information fusion between tensors. Through repeated stacking of RCS modules, the information flow between different channels of adjacent layer features is enhanced to improve the model's ability to capture target spatial features. In addition, a multi-scale feature fusion mechanism with weighted dual flow paths was adopted to fuse spatial features of different scales, thereby further improving the detection performance of the model at different scales. To validate the performance of the proposed algorithm, we tested it using the RDD2022 dataset. The experimental results show that the enhancement algorithm achieved 84.14% mAP, which is 1.06% higher than the currently advanced YOLOv8 algorithm. Through visualization analysis of the results, it can also be seen that our proposed algorithm has good performance in detecting targets of different scales in complex scenes. The above experimental results demonstrate the effectiveness and superiority of the proposed algorithm, providing valuable insights for advancing real-time road defect detection methods.

Keywords: roads, defect detection, visualization, deep learning

Procedia PDF Downloads 11

Authors: Itay Harlap

Abstract:

Over the past decade, LGBT figures have become increasingly visible on Israeli television in its various channels and genres. In recent years, however, the representation of gays on Israeli television has undergone an interesting shift, whereby many television texts feature gay people as fathers. These texts, mostly news items and documentaries, usually present gay parenthood as a positive phenomenon. The question in paper is whether LGBT parenting (in reality and as representation) fated to be part of the homonormativity that characterizes the LGBT community in Israel, or can it be an alternative to the hegemonic discourse? This paper embraces a dialectical position and explores the tension between mainstream and radical, or homonormativity and queer politics in the specific Israeli Jewish context through a textual and discursive reading of a selection of television programs that revolve principally around gay parenting in Israel. The first part of this lecture addresses the cultural and social context that generated these representations, dealing with three key Israeli areas: The fertility cult, the evolution of the LGBT community, and the evolution of local television. The second part offers a queer reading of these ‘positive’ representations (mainly in special reports on the news and programs labeled as ‘documentaries’ by broadcasters) and highlight the possible price of the ‘bear hug’ given by Israeli media to gay parents. The last part focuses on a single case study, the TV serial drama Ima Veabaz, and suggests that this drama exposes the performative aspect of parenting and the connection between ethnicity and fertility, and offers an alternative to normative displays of gay parenting.

Keywords: fatherhood, heteronormativity, Israel, queer theory, television

Procedia PDF Downloads 362