Search results for: features selection for CBIR

Authors: Manverpreet Kaur, Amarpreet Singh

Abstract:

The demand of Vehicular ad hoc networks is increasing day by day, due to offering the various applications and marvelous benefits to VANET users. Clustering in VANETs is most important to overcome the connectivity problems of VANETs. In this paper, we proposed a new clustering technique Enhanced cluster based connectivity maintenance in vehicular ad hoc network. Our objective is to form long living clusters. The proposed approach is grouping the vehicles, on the basis of the longest list of neighbors to form clusters. The cluster formation and cluster head selection process done by the RSU that may results it reduces the chances of overhead on to the network. The cluster head selection procedure is the vehicle which has closest speed to average speed will elect as a cluster Head by the RSU and if two vehicles have same speed which is closest to average speed then they will be calculate by one of the new parameter i.e. distance to their respective destination. The vehicle which has largest distance to their destination will be choosing as a cluster Head by the RSU. Our simulation outcomes show that our technique performs better than the existing technique.

Keywords: VANETs, clustering, connectivity, cluster head, intelligent transportation system (ITS)

Procedia PDF Downloads 246

Authors: Dev Ras Pandey, Bharat Mishra, S. K. Tripathi

Abstract:

Cloud computing is ready to transform the structure of businesses and learning through supplying the real-time applications and provide an immediate help for small to medium sized businesses. The ability to run a hypervisor inside a virtual machine is important feature of virtualization and it is called nested virtualization. In today’s growing field of information technology, many of the virtualization models are available, that provide a convenient approach to implement, but decision for a single model selection is difficult. This paper explains the applications of operating system based virtualization in cloud computing with an appropriate/suitable model with their different specifications and user’s requirements. In the present paper, most popular models are selected, and the selection was based on container and hypervisor based virtualization. Selected models were compared with a wide range of user’s requirements as number of CPUs, memory size, nested virtualization supports, live migration and commercial supports, etc. and we identified a most suitable model of virtualization.

Keywords: virtualization, OS based virtualization, container based virtualization, hypervisor based virtualization

Procedia PDF Downloads 326

Authors: Ben G. Weber, Michael Mateas

Abstract:

We present a case-based reasoning technique for selecting build orders in a real-time strategy game. The case retrieval process generalizes features of the game state and selects cases using domain-specific recall methods, which perform exact matching on a subset of the case features. We demonstrate the performance of the technique by implementing it as a component of the integrated agent framework of McCoy and Mateas. Our results demonstrate that the technique outperforms nearest-neighbor retrieval when imperfect information is enforced in a real-time strategy game.

Keywords: case based reasoning, real time strategy systems, requirements elicitation, requirement analyst, artificial intelligence

Procedia PDF Downloads 440

Authors: Guilhermina Torrao

Abstract:

An extensive number of studies have been conducted to determine the factors which influence crash injury risk (CIR); however, uncertainties inherent to selected variables have been neglected. A review of existing literature is required to not only obtain an overview of the variables and measures but also ascertain the implications when comparing studies without a systematic view of variable taxonomy. Therefore, the aim of this literature review is to examine and report on peer-reviewed studies in the field of crash analysis and to understand the implications of broad variations in variable selection in CIR analysis. The objective of this study is to demonstrate the variance in variable selection and classification when modeling injury risk involving occupants of light vehicles by presenting an analytical review of the literature. Based on data collected from 64 journal publications reported over the past 21 years, the analytical review discusses the variables selected by each study across an organized list of predictors for CIR analysis and provides a better understanding of the contribution of accident and vehicle factors to injuries acquired by occupants of light vehicles. A cross-comparison analysis demonstrates that almost half the studies (48%) did not consider vehicle design specifications (e.g., vehicle weight), whereas, for those that did, the vehicle age/model year was the most selected explanatory variable used by 41% of the literature studies. For those studies that included speed risk factor in their analyses, the majority (64%) used the legal speed limit data as a ‘proxy’ of vehicle speed at the moment of a crash, imposing limitations for CIR analysis and modeling. Despite the proven efficiency of airbags in minimizing injury impact following a crash, only 22% of studies included airbag deployment data. A major contribution of this study is to highlight the uncertainty linked to explanatory variable selection and identify opportunities for improvements when performing future studies in the field of road injuries.

Keywords: crash, exploratory, injury, risk, variables, vehicle

Procedia PDF Downloads 131

Authors: Eman A. Al-Hilo, Hawraa H. Al-Waelly

Abstract:

In this work, fractal compression (FIC) technique is introduced based on using moment features to block indexing the zero-mean range-domain blocks. The moment features have been used to speed up the IFS-matching stage. Its moments ratio descriptor is used to filter the domain blocks and keep only the blocks that are suitable to be IFS matched with tested range block. The results of tests conducted on Lena picture and Cat picture (256 pixels, resolution 24 bits/pixel) image showed a minimum encoding time (0.89 sec for Lena image and 0.78 of Cat image) with appropriate PSNR (30.01dB for Lena image and 29.8 of Cat image). The reduction in ET is about 12% for Lena and 67% for Cat image.

Keywords: fractal gray level image, fractal compression technique, iterated function system, moments feature, zero-mean range-domain block

Procedia PDF Downloads 490

Authors: Rosa Figueroa, Christopher Flores

Abstract:

Text categorization is the problem of assigning a new document to a set of predetermined categories, on the basis of a training set of free-text data that contains documents whose category membership is known. To train a classification model, it is necessary to extract characteristics in the form of tokens that facilitate the learning and classification process. In text categorization, the feature extraction process involves the use of word sequences also known as N-grams. In general, it is expected that documents belonging to the same category share similar features. The Smith-Waterman (SW) algorithm is a dynamic programming algorithm that performs a local sequence alignment in order to determine similar regions between two strings or protein sequences. This work explores the use of SW algorithm as an alternative to feature extraction in text categorization. The dataset used for this purpose, contains 2,610 annotated documents with the classes Obese/Non-Obese. This dataset was represented in a matrix form using the Bag of Word approach. The score selected to represent the occurrence of the tokens in each document was the term frequency-inverse document frequency (TF-IDF). In order to extract features for classification, four experiments were conducted: the first experiment used SW to extract features, the second one used unigrams (single word), the third one used bigrams (two word sequence) and the last experiment used a combination of unigrams and bigrams to extract features for classification. To test the effectiveness of the extracted feature set for the four experiments, a Support Vector Machine (SVM) classifier was tuned using 20% of the dataset. The remaining 80% of the dataset together with 5-Fold Cross Validation were used to evaluate and compare the performance of the four experiments of feature extraction. Results from the tuning process suggest that SW performs better than the N-gram based feature extraction. These results were confirmed by using the remaining 80% of the dataset, where SW performed the best (accuracy = 97.10%, weighted average F-measure = 97.07%). The second best was obtained by the combination of unigrams-bigrams (accuracy = 96.04, weighted average F-measure = 95.97) closely followed by the bigrams (accuracy = 94.56%, weighted average F-measure = 94.46%) and finally unigrams (accuracy = 92.96%, weighted average F-measure = 92.90%).

Keywords: comorbidities, machine learning, obesity, Smith-Waterman algorithm

Procedia PDF Downloads 296

Authors: Musaab Hasan, Farkhund Iqbal, Patrick C. K. Hung, Benjamin C. M. Fung, Laura Rafferty

Abstract:

In modern societies, the smart cities concept raised simultaneously with the projection towards adopting smart devices. A smart grid is an essential part of any smart city as both consumers and power utility companies benefit from the features provided by the power grid. In addition to advanced features presented by smart grids, there may also be a risk when the grids are exposed to malicious acts such as security attacks performed by terrorists. Considering advanced security measures in the design of smart meters could reduce these risks. This paper presents a security study for smart metering systems with a prototype implementation of the user interfaces for future works.

Keywords: security design, smart city, smart meter, smart grid, smart metering system

Procedia PDF Downloads 333

Authors: Gaetano Zazzaro, Angelo Martone, Roberto V. Montaquila, Luigi Pavone

Abstract:

Seizure is the main factor that affects the quality of life of epileptic patients. The diagnosis of epilepsy, and hence the identification of epileptogenic zone, is commonly made by using continuous Electroencephalogram (EEG) signal monitoring. Seizure identification on EEG signals is made manually by epileptologists and this process is usually very long and error prone. The aim of this paper is to describe an automated method able to detect seizures in EEG signals, using knowledge discovery in database process and data mining methods and algorithms, which can support physicians during the seizure detection process. Our detection method is based on Artificial Neural Network classifier, trained by applying the multilayer perceptron algorithm, and by using a software application, called Training Builder that has been developed for the massive extraction of features from EEG signals. This tool is able to cover all the data preparation steps ranging from signal processing to data analysis techniques, including the sliding window paradigm, the dimensionality reduction algorithms, information theory, and feature selection measures. The final model shows excellent performances, reaching an accuracy of over 99% during tests on data of a single patient retrieved from a publicly available EEG dataset.

Keywords: artificial neural network, data mining, electroencephalogram, epilepsy, feature extraction, seizure detection, signal processing

Procedia PDF Downloads 187

Authors: Melody Yin

Abstract:

Concussions impact a large amount of adolescents; they make up as much as half of the diagnosed concussions in America. This research proposes a hybrid machine learning model based on the combination of human/knowledge-based domains and computer-generated feature rankings to improve the accuracy of diagnosing sports related concussion (SRC). Using a data set of symptoms collected on the sideline post-SRC events, the symptom selection criteria method has been developed by using Google AutoML's important score function to identify the top 10 symptom features. In addition, symptom domains have been introduced as another parameter, categorizing the symptoms into physical, cognitive, sleep, and emotional domains. The hybrid machine learning model has been trained with a combination of the top 10 symptoms and 4 domains. From the results, the hybrid model was the best performer for symptom resolution time prediction in 2 and 4-week thresholds. This research is a proof of concept study in the use of domains along with machine learning in order to improve concussion prediction accuracy. It is also possible that the use of domains can make the model more efficient due to reduced training time. This research examines the use of a hybrid method in predicting sports-related concussion. This achievement is based on data preprocessing, using a hybrid method to select criteria to achieve high performance.

Keywords: hybrid model, machine learning, sports related concussion, symptom resolution time

Procedia PDF Downloads 167

Authors: Punnoose A. K.

Abstract:

This paper presents an approach for identifying noisy speech recording using a multi-layer perception (MLP) trained to predict phonemes from acoustic features. Characteristics of the MLP posteriors are explored for clean speech and noisy speech at the frame level. Appropriate density functions are used to fit the softmax probability of the clean and noisy speech. A function that takes into account the ratio of the softmax probability density of noisy speech to clean speech is formulated. These phoneme independent scoring is weighted using a phoneme-specific weightage to make the scoring more robust. Simple thresholding is used to identify the noisy speech recording from the clean speech recordings. The approach is benchmarked on standard databases, with a focus on precision.

Keywords: noisy speech identification, speech pre-processing, noise robustness, feature engineering

Procedia PDF Downloads 126

Authors: Gaafar Omer BaOmer, Abdulmohsin A. Al-Sofyani, Hassan A. Ramadan

Abstract:

Drupella is found on coral reefs throughout the tropical and subtropical shallow waters of the Indo-Pacific region. Drupella is muricid gastropod, obligate corallivorous and their population outbreak can cause significant coral mortality. Belt transect surveys were conducted at two sites (Bohairat and Baydah) in Jeddah coast, Saudi Arabia to assess prey preferences for D. cornus with respect to prey availability through resource selection ratios. Results revealed that there are different levels of prey preferences at the different age stages and at the different sites. Acropora species with a caespitose, corymbose and digitate growth forms were preferred prey for recruits and juveniles of Drupella cornus, whereas Acropora variolosa was avoided by D. cornus because of its arborescent colony growth form. Pocillopora, Stylophora, and Millipora were occupied by Drupella cornus less than expected, whereas massive corals genus Porites were avoided. High densities of D. cornus were observed on two fragments of Pocillopora damicornis which may because of the absence of coral guard crabs genus Trapezia. Mean densities of D. cornus per colony for each species showed significant differentiation between the two study sites. Low availability of Acropora colonies in Bayadah patch reef caused high mean density of D. cornus per colony to compare to that in Bohairat, whereas higher mean density of D. cornus per colony of Pocillopora in Bohairat than that in Bayadah may because of most of occupied Pocillopora colonies by D. cornus were physical broken by anchoring compare to those colonies in Bayadah. The results indicated that prey preferences seem to depend on both coral genus and colony shape, while mean densities of D. cornus depend on availability and status of coral colonies.

Keywords: prey availability, resource selection, Drupella cornus, Jeddah, Saudi Arabia

Procedia PDF Downloads 146

Authors: Abdullah Al Farwan, Ya Zhang

Abstract:

In today’s educational arena, it is critical to understand educational data and be able to evaluate important aspects, particularly data on student achievement. Educational Data Mining (EDM) is a research area that focusing on uncovering patterns and information in data from educational institutions. Teachers, if they are able to predict their students' class performance, can use this information to improve their teaching abilities. It has evolved into valuable knowledge that can be used for a wide range of objectives; for example, a strategic plan can be used to generate high-quality education. Based on previous data, this paper recommends employing data mining techniques to forecast students' final grades. In this study, five data mining methods, Decision Tree, JRip, Naive Bayes, Multi-layer Perceptron, and Random Forest with wrapper feature selection, were used on two datasets relating to Portuguese language and mathematics classes lessons. The results showed the effectiveness of using data mining learning methodologies in predicting student academic success. The classification accuracy achieved with selected algorithms lies in the range of 80-94%. Among all the selected classification algorithms, the lowest accuracy is achieved by the Multi-layer Perceptron algorithm, which is close to 70.45%, and the highest accuracy is achieved by the Random Forest algorithm, which is close to 94.10%. This proposed work can assist educational administrators to identify poor performing students at an early stage and perhaps implement motivational interventions to improve their academic success and prevent educational dropout.

Keywords: classification algorithms, decision tree, feature selection, multi-layer perceptron, Naïve Bayes, random forest, students’ academic performance

Procedia PDF Downloads 165

Authors: Manana Lobzhanidze

Abstract:

Introduction: The paper will argue that labor migration is the most important problem Georgia faces today. The structure of labor migration by age and gender of Georgia is analyzed. The main driving factors of circular labor migration during the last ten years are identified. While studying migration, it is necessary to discuss the interconnection of economic, social, and demographic features, also taking into consideration the policy of state regulations in terms of education and professional training. Methodology: Different research methods are applied in the presented paper: statistical, such as selection, grouping, observation, trend, and qualitative research methods, namely; analysis, synthesis, induction, deduction, comparison ones. Main Findings: Labour migrants are filling the labor market as a low salary worker. The main positive feedback of migration from developing countries is poverty eradication, but this process is accompanied by problems, such as 'Brain Drain'. The country loses an important part of its intellectual potential, and it is invested by households or state itself. Conclusions: Labor migration is characterized to be temporary, but socio-economic problems of the country often push the labor migration in the direction of longterm and illegal migration. Countries with developed economies try to stricter migration policy and fight illegal migration with different methods; circular migration helps solve this problem. Conclusions and recommendations are included about circular labor migration consequences in Georgia and its influence on the reduction of unemployment level.

Keywords: migration, circular labor migration, labor migration employment, unemployment

Procedia PDF Downloads 177

Authors: Chetan Mahawar, Sarath Chandran, Sridhar Panigrahi, V. P. Shaji

Abstract:

The ever-growing advancement in space exploration has led to an alarming concern for space debris removal as it restricts further launch operations and adventurous space missions; hence numerous studies have come up with technologies for re-entry predictions and material selection processes for mitigating space debris. The selection of material and operating conditions is determined with the objective of lightweight structure and ability to demise faster subject to spacecraft survivability during its mission. Since the demisability of spacecraft depends on evolving thermal material properties such as emissivity, specific heat capacity, thermal conductivity, radiation intensity, etc. Therefore, this paper presents the analysis of evolving thermal material properties of spacecraft, which affect the demisability process and thus estimate demise time using the demisability model by incorporating evolving thermal properties for sensible heating followed by the complete or partial break-up of spacecraft. The demisability analysis thus concludes the best suitable spacecraft material is based on the least estimated demise time, which fulfills the criteria of design-for-survivability and as well as of design-for-demisability.

Keywords: demisability, emissivity, lightweight, re-entry, survivability

Procedia PDF Downloads 113

Authors: Je-Seok Shin, Wook-Won Kim, Jin-O Kim

Abstract:

The offshore wind farm needs to be designed carefully considering economics and reliability aspects. There are many decision-making problems for designing entire offshore wind farm, this paper focuses on an inner grid layout which means the connection between wind turbines as well as between wind turbines and an offshore substation. A methodology proposed in this paper determines the connections and the cable type for each connection section using K-clustering, minimum spanning tree and cable selection algorithms. And then, a cost evaluation is performed in terms of investment, power loss and reliability. Through the cost evaluation, an optimal layout of inner grid is determined so as to have the lowest total cost. In order to demonstrate the validity of the methodology, the case study is conducted on 240MW offshore wind farm, and the results show that it is helpful to design optimally offshore wind farm.

Keywords: offshore wind farm, optimal layout, k-clustering algorithm, minimum spanning algorithm, cable type selection, power loss cost, reliability cost

Procedia PDF Downloads 384

Authors: Ahlem Dhahri, Audrey Becuwe

Abstract:

This study examines the adoption of sustainable purchasing practices among Tunisian SMEs, with a focus on assessing how environmental and social sustainability maturity affects the implementation of sustainable supplier selection (SSS) criteria. Using institutional theory to classify coercive, normative, and mimetic pressures, as well as emerging drivers and barriers, this study explores the institutional factors influencing sustainable purchasing practices and the specific barriers faced by Tunisian SMEs in this area. An exploratory, abductive qualitative research design was adopted for this multiple case study, which involved 19 semi-structured interviews with owners and managers of 17 Tunisian manufacturing SMEs. The Gioia method was used to analyze the data, thus enabling the identification of key themes and relationships directly from the raw data. This approach facilitated a structured interpretation of the institutional factors influencing sustainable purchasing practices, with insights drawn from the participants' perspectives. The study reveals that Tunisian SMEs are at different levels of sustainability maturity, with a significant impact on their procurement practices. SMEs with advanced sustainability maturity integrate both environmental and social criteria into their supplier selection processes, while those with lower maturity levels rely on mostly traditional criteria such as cost, quality, and delivery. Key institutional drivers identified include regulatory pressure, market expectations, and stakeholder influence. Additional emerging drivers—such as certifications and standards, economic incentives, environmental commitment as a core value, and group-wide strategic alignment—also play a critical role in driving sustainable procurement. Conversely, the study reveals significant barriers, including economic constraints, limited awareness, and resource limitations. It also identifies three main categories of emerging barriers: (1) logistical and supply chain constraints, including retailer/intermediary dependency, tariff regulations, and a perceived lack of direct responsibility in B2B supply chains; (2) economic and financial constraints; and (3) operational barriers, such as unilateral environmental responsibility, a product-centric focus and the influence of personal relationships. Providing valuable insights into the role of sustainability maturity in supplier selection, this study is the first to explore sustainable procurement practices in the Tunisian SME context. Integrating an analysis of institutional drivers, including emerging incentives and barriers, provides practical implications for SMEs seeking to improve sustainability in procurement. The results highlight the need for stronger regulatory frameworks and support mechanisms to facilitate the adoption of sustainable practices among SMEs in Tunisia.

Keywords: Tunisian SME, sustainable supplier selection, institutional theory, determinant, qualitative study

Procedia PDF Downloads 9

Authors: Tusar Kanti Dash, Ganapati Panda

Abstract:

The evaluation of speech quality and intelligence is critical to the overall effectiveness of the Speech Enhancement Algorithms. Several intrusive and non-intrusive measures are employed to calculate these parameters. Non-Intrusive Evaluation is most challenging as, very often, the reference clean speech data is not available. In this paper, a novel non-intrusive speech evaluation measure is proposed using audio features derived from the Stockwell transform. These features are used with the Light Gradient Boosting Machine for the effective prediction of speech quality and intelligibility. The proposed model is analyzed using noisy and reverberant speech from four databases, and the results are compared with the standard Intrusive Evaluation Measures. It is observed from the comparative analysis that the proposed model is performing better than the standard Non-Intrusive models.

Keywords: non-Intrusive speech evaluation, S-transform, light GBM, speech quality, and intelligibility

Procedia PDF Downloads 257

Authors: Sanjit Kumar Paul, A. A. Mamun, M. R. Amin

Abstract:

The Linear propagation of the dust-acoustic wave in a dusty plasma consisting of Boltzmann distributed electrons and ions and mobile charge fluctuating positive dust grains has been investigated by employing the reductive perturbation method. It has been shown that the dust charge fluctuation is a source of dissipation and its responsible for the formation of the dust-acoustic waves in such a dusty plasma. The basic features of such dust-acoustic waves have been identified. It has been proposed to design a new laboratory experiment which will be able to identify the basic features of the dust-acoustic waves predicted in this theoretical investigation.

Keywords: dust acoustic waves, dusty plasma, Boltzmann distributed electrons, charge fluctuation

Procedia PDF Downloads 633

Authors: S. Sharan Sundar, Nithish B. Moudhgalya, Nidhi Bhandari, Vineeth Vijayaraghavan

Abstract:

Automatic Short Answer Grading is one of the prime applications of artificial intelligence in education. Several approaches involving the utilization of selective handcrafted features, graphical matching techniques, concept identification and mapping, complex deep frameworks, sentence embeddings, etc. have been explored over the years. However, keeping in mind the real-world application of the task, these solutions present a slight overhead in terms of computations and resources in achieving high performances. In this work, a simple and effective solution making use of elemental features based on statistical, linguistic properties, and word-based similarity measures in conjunction with tree-based classifiers and regressors is proposed. The results for classification tasks show improvements ranging from 1%-30%, while the regression task shows a stark improvement of 35%. The authors attribute these improvements to the addition of multiple similarity scores to provide ensemble of scoring criteria to the models. The authors also believe the work could reinstate that classical natural language processing techniques and simple machine learning models can be used to achieve high results for short answer grading.

Keywords: artificial intelligence, intelligent systems, natural language processing, text mining

Procedia PDF Downloads 131

Authors: Irina Khutsishvili

Abstract:

In the present research, a decision support methodology for the multi-attribute group decision-making (MAGDM) problem is developed, namely for the selection of investment projects. The objective of the investment project selection problem is to choose the best project among the set of projects, seeking investment, or to rank all projects in descending order. The project selection is made considering a set of weighted attributes. To evaluate the attributes in our approach, expert assessments are used. In the proposed methodology, lingual expressions (linguistic terms) given by all experts are used as initial attribute evaluations, since they are the most natural and convenient representation of experts' evaluations. Then lingual evaluations are converted into trapezoidal fuzzy numbers, and the aggregate trapezoidal hesitant fuzzy decision matrix will be built. The case is considered when information on the attribute weights is completely unknown. The attribute weights are identified based on the De Luca and Termini information entropy concept, determined in the context of hesitant fuzzy sets. The decisions are made using the extended Technique for Order Performance by Similarity to Ideal Solution (TOPSIS) method under a hesitant fuzzy environment. Hence, a methodology is based on a trapezoidal valued hesitant fuzzy TOPSIS decision-making model with entropy weights. The ranking of alternatives is performed by the proximity of their distances to both the fuzzy positive-ideal solution (FPIS) and the fuzzy negative-ideal solution (FNIS). For this purpose, the weighted hesitant Hamming distance is used. An example of investment decision-making is shown that clearly explains the procedure of the proposed methodology.

Keywords: In the present research, a decision support methodology for the multi-attribute group decision-making (MAGDM) problem is developed, namely for the selection of investment projects. The objective of the investment project selection problem is to choose the best project among the set of projects, seeking investment, or to rank all projects in descending order. The project selection is made considering a set of weighted attributes. To evaluate the attributes in our approach, expert assessments are used. In the proposed methodology, lingual expressions (linguistic terms) given by all experts are used as initial attribute evaluations since they are the most natural and convenient representation of experts' evaluations. Then lingual evaluations are converted into trapezoidal fuzzy numbers, and the aggregate trapezoidal hesitant fuzzy decision matrix will be built. The case is considered when information on the attribute weights is completely unknown. The attribute weights are identified based on the De Luca and Termini information entropy concept, determined in the context of hesitant fuzzy sets. The decisions are made using the extended Technique for Order Performance by Similarity to Ideal Solution (TOPSIS) method under a hesitant fuzzy environment. Hence, a methodology is based on a trapezoidal valued hesitant fuzzy TOPSIS decision-making model with entropy weights. The ranking of alternatives is performed by the proximity of their distances to both the fuzzy positive-ideal solution (FPIS) and the fuzzy negative-ideal solution (FNIS). For this purpose, the weighted hesitant Hamming distance is used. An example of investment decision-making is shown that clearly explains the procedure of the proposed methodology.

Procedia PDF Downloads 116

Authors: Y. Xu, L. Xiong, Z. Xu

Abstract:

In order to protect data privacy, image with sensitive or private information needs to be encrypted before being outsourced to the cloud. However, this causes difficulties in image retrieval and data management. A secure image retrieval method based on orthogonal decomposition is proposed in the paper. The image is divided into two different components, for which encryption and feature extraction are executed separately. As a result, cloud server can extract features from an encrypted image directly and compare them with the features of the queried images, so that the user can thus obtain the image. Different from other methods, the proposed method has no special requirements to encryption algorithms. Experimental results prove that the proposed method can achieve better security and better retrieval precision.

Keywords: secure image retrieval, secure search, orthogonal decomposition, secure cloud computing

Procedia PDF Downloads 481

Authors: Natalia Efremova, Sergey Tarasenko

Abstract:

We propose a novel neural network architecture for visual saliency detections, which utilizes neuro physiologically plausible mechanisms for extraction of salient regions. The model has been significantly inspired by recent findings from neuro physiology and aimed to simulate the bottom-up processes of human selective attention. Two types of features were analyzed: color and direction of maximum variance. The mechanism we employ for processing those features is PCA, implemented by means of normalized Hebbian learning and the waves of spikes. To evaluate performance of our model we have conducted psychological experiment. Comparison of simulation results with those of experiment indicates good performance of our model.

Keywords: neural network models, visual saliency detection, normalized Hebbian learning, Oja's rule, psychological experiment

Procedia PDF Downloads 348

Authors: Arian Hosseini, Mahmudul Hasan

Abstract:

To address the increasing need for efficient and accurate content moderation, we propose an efficient and lightweight deep classification ensemble structure. Our approach is based on a combination of simple visual features, designed for high-accuracy classification of violent content with low false positives. Our ensemble architecture utilizes a set of lightweight models with narrowed-down color features, and we apply it to both images and videos. We evaluated our approach using a large dataset of explosion and blast contents and compared its performance to popular deep learning models such as ResNet-50. Our evaluation results demonstrate significant improvements in prediction accuracy, while benefiting from 7.64x faster inference and lower computation cost. While our approach is tailored to explosion detection, it can be applied to other similar content moderation and violence detection use cases as well. Based on our experiments, we propose a "think small, think many" philosophy in classification scenarios. We argue that transforming a single, large, monolithic deep model into a verification-based step model ensemble of multiple small, simple, and lightweight models with narrowed-down visual features can possibly lead to predictions with higher accuracy.

Keywords: deep classification, content moderation, ensemble learning, explosion detection, video processing

Procedia PDF Downloads 52

Authors: O. Nkwonta, B. Dzwairo, F. Otieno, J. Adeyemo

Abstract:

The effective management of water resources is of great importance to ensure the supply of water resources to support changing water requirements over a selected planning horizon and in a sustainable and cost-effective way. Essentially, the purpose of the water resources planning process is to balance the available water resources in a system with the water requirements and losses to which the system is subjected. In such situations, water resources yield and planning model can be used to solve those difficulties. It has an advantage over other models by managing model runs, developing a representative system network, modelling incremental sub-catchments, creating a variety of standard system features, special modelling features, and run result output options.

Keywords: complex, water resources, planning, cost effective, management

Procedia PDF Downloads 449

Authors: Eng. M. Ahmed, A. Ibrahim, M. Ashour

Abstract:

One of the major concerns facing dam is the repair of their structures to prevent the seepage under them. In previous years, many existing dams have been treated by grouting, but with varying degrees of success. One of the major reasons for this erratic performance is the unsuitable selection of the grouting materials to reduce the seepage. Grouting is an effective way to improve the engineering properties of the soil and strengthen of the permeability of the soil to reduce the seepage. The purpose of this paper is to focus on the efficiency of current available grouting materials and techniques from construction, environmental and economical point of view. The seepage reduction usually accomplished by either chemical grouting or cementious grouting using ultrafine cement. In addition, the study shows a comparison between grouting materials according to their degree of permeability reduction and cost. The application of seepage reduction is based on the permeation grouting using grout curtain installation. The computer program (SEEP/W) is employed to model a dam rested on sandy soil, using grout curtain to reduce seepage quantity and hydraulic gradient by different grouting materials. This study presents a relationship that takes into account the permeability of the soil, grout curtain spacing and a new performance parameter that can be used to predict the best selection of grouting materials for seepage reduction.

Keywords: seepage, sandy soil, grouting, permeability

Procedia PDF Downloads 366

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

Abstract:

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

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

Procedia PDF Downloads 56

Authors: Daleesha M. Viswanathan, Sumam Mary Idicula

Abstract:

Dynamic hand gestures are an intrinsic component in sign language communication. Extracting spatial temporal features of the hand gesture trajectory plays an important role in a dynamic gesture recognition system. Finding a discrete feature descriptor for the motion trajectory based on the orientation feature is the main concern of this paper. Kalman filter algorithm and Hidden Markov Models (HMM) models are incorporated with this recognition system for hand trajectory tracking and for spatial temporal classification, respectively.

Keywords: orientation features, discrete feature vector, HMM., Indian sign language

Procedia PDF Downloads 366

Authors: Tamirat Solomon, Aberash Yohannis, Efrem Gulfo

Abstract:

The plantation of trees, which harmonizes the agroecology of the environment, has been implemented in Ethiopia with great concern for a noticeably degraded environment. This study was designed to evaluate the effectiveness of green legacy, species selection and, the rate of survival, and the management status in the study areas. A systematic sampling method was employed to collect the required data from 144 quadrants measuring a 15m radius with an interval of 40m apart. Additionally, 244 sample households were selected for the socioeconomic study in addition to secondary data collected from office recordings. The data collected was analyzed using multivariate analysis, considering exposure and outcome variables. The findings of this study indicated that four exotic tree species, namely; A. salgina, C. fistula, A. indica, and G. robusta, were commonly selected tree species for degraded land restoration in the study areas. Among the seedlings planted at the four study sites, a total of 79.9% survived, and A. salgina was the dominant and best performed species, A. indica was the least survived species in the entire study area. The age of the seedling before planting significantly (p = 0.05) affected the survival potential of most seedlings of species, and the majority (82%) of local communities expressed their positive attitudes and willingness to manage the restoration works in the study areas. It was recommended to consider the inclusion of native species in the restoration effort and evaluate the co-existence of native flora with exotic and its competition for nutrients, water, and light in addition to the invading potentials in the ecosystem. In general, before embarking on degraded land restoration, species selection, adequate preparation of seedlings, and species diversity composition that exactly fit the socioeconomic and ecological demands of the areas must get the attention for the success of the restoration.

Keywords: plantation forest, degraded land, forest restoration, plantation survival, species selection

Procedia PDF Downloads 74

Authors: Hussah Alotaishan

Abstract:

In today’s globally-driven modern cities diverse groups of new visitors face various challenges when attempting to find their desired location if culture and language are barriers. The most common way-showing tools such as directional and identificational signs are the most problematic and their usefulness can be limited or even non-existent. It is argued new methods should be implemented that could support or replace such conventional literacy and language dependent way-finding aids. It has been concluded in recent research studies that local urban features in complex pedestrian spaces are worthy of further study in order to reveal if they do function as way-showing clues. Some researchers propose a more comprehensive approach to the complex perception of buildings, façade design and surface patterns, while some have been questioning whether we necessarily need directional signs or can other methods deliver the same message but in a clearer manner for a wider range of users. This study aimed to test to what extent do existent environmental and urban features through the city center area of Swansea in the UK facilitate the way-finding process of a first time visitor. The three-hour experiment was set to attempt to find 11 visitor attractions ranging from recreational, historical, educational and religious locations. The challenge was attempting to find as many as possible when no prior geographical knowledge of their whereabouts was established. The only clues were 11 pictures representing each of the locations that had been acquired from the city of Swansea official website. An iPhone and a heart-rate tracker wristwatch were used to record the route was taken and stress levels, and take record photographs of destinations or decision-making points throughout the journey. This paper addresses: current limitations in understanding the ways that the physical environment can be intentionally deployed to facilitate pedestrians while finding their way around, without or with a reduction in language dependent signage; investigates visitor perceptions of their surroundings by indicating what urban elements manifested an impact on the way-finding process. The initial findings support the view that building facades and street features, such as width, could facilitate the decision-making process if strategically employed. However, more importantly, the anticipated features of a specific place construed from a promotional picture can also be misleading and create confusion that may lead to getting lost.

Keywords: pedestrian way-finding, environmental features, urban way-showing, environmental affordance

Procedia PDF Downloads 171

Authors: Faruk Ortes, Derya Karabulut, Yunus Ziya Arslan

Abstract:

Myoelectric features gathering from musculature environment are considered on a preferential basis to perceive muscle activation and control human arm prostheses according to recent experimental researches. EMG (electromyography) signal based human arm prostheses have shown a promising performance in terms of providing basic functional requirements of motions for the amputated people in recent years. However, these assistive devices for neurorehabilitation still have important limitations in enabling amputated people to perform rather sophisticated or functional movements. Surface electromyogram (EMG) is used as the control signal to command such devices. This kind of control consists of activating a motion in prosthetic arm using muscle activation for the same particular motion. Extraction of clear and certain neural information from EMG signals plays a major role especially in fine control of hand prosthesis movements. Many signal processing methods have been utilized for feature extraction from EMG signals. The specific objective of this study was to compare widely used time domain features of EMG signal including integrated EMG(IEMG), root mean square (RMS) and waveform length(WL) for prediction of externally applied forces to human hands. Obtained features were classified using artificial neural networks (ANN) to predict the forces. EMG signals supplied to process were recorded during only type of muscle contraction which is isometric and isotonic one. Experiments were performed by three healthy subjects who are right-handed and in a range of 25-35 year-old aging. EMG signals were collected from muscles of the proximal part of the upper body consisting of: biceps brachii, triceps brachii, pectorialis major and trapezius. The force prediction results obtained from the ANN were statistically analyzed and merits and pitfalls of the extracted features were discussed with detail. The obtained results are anticipated to contribute classification process of EMG signal and motion control of powered human arm prosthetics control.

Keywords: assistive devices for neurorehabilitation, electromyography, feature extraction, force estimation, human arm prosthesis

Procedia PDF Downloads 366