Search results for: feature exponentiation

Authors: Rita Emília Szabó, Róbert Polanek, Tünde Tőkés, Zoltán Szabó, Szabolcs Czifrus, Katalin Hideghéty

Abstract:

Purpose: Several feature of zebrafish are making them amenable for investigation on therapeutic approaches such as ionizing radiation. The establishment of zebrafish model for comprehensive radiobiological research stands in the focus of our investigation, comparing the radiation effect curves of neutron and photon irradiation. Our final aim is to develop an appropriate vertebrate model in order to investigate the relative biological effectiveness of laser driven ionizing radiation. Methods and Materials: After careful dosimetry series of viable zebrafish embryos were exposed to a single fraction whole-body neutron-irradiation (1,25; 1,875; 2; 2,5 Gy) at the research reactor of the Technical University of Budapest and to conventional 6 MeV photon beam at 24 hour post-fertilization (hpf). The survival and morphologic abnormalities (pericardial edema, spine curvature) of each embryo were assessed for each experiment at 24-hour intervals from the point of fertilization up to 168 hpf (defining the dose lethal for 50% (LD50)). Results: In the zebrafish embryo model LD50 at 20 Gy dose level was defined and the same lethality were found at 2 Gy dose from the reactor neutron beam resulting RBE of 10. Dose-dependent organ perturbations were detected on macroscopic (shortening of the body length, spine curvature, microcephaly, micro-ophthalmia, micrognathia, pericardial edema, and inhibition of yolk sac resorption) and microscopic (marked cellular changes in skin, cardiac, gastrointestinal system) with the same magnitude of dose difference. Conclusion: In our observations, we found that zebrafish embryo model can be used for investigating the effects of different type of ionizing radiation and this system proved to be highly efficient vertebrate model for preclinical examinations.

Keywords: ionizing radiation, LD50, relative biological effectiveness, zebrafish embryo

Procedia PDF Downloads 307

Authors: Axelle Bertrand, Tom Bauer, Carole Charbuillet, Martin Bonte, Marie Voyer, Nicolas Perry

Abstract:

The complexity of Life Cycle Assessment (LCA) can be identified as the ultimate obstacle to massification. Due to these obstacles, the diffusion of eco-design and LCA methods in the manufacturing sectors could be impossible. This article addresses the research question: How to adapt the LCA method to generalize it massively and improve its performance? This paper aims to develop an approach for automating LCA in order to carry out assessments on a massive scale. To answer this, we proceeded in three steps: First, an analysis of the literature to identify existing automation methods. Given the constraints of large-scale manual processing, it was necessary to define a new approach, drawing inspiration from certain methods and combining them with new ideas and improvements. In a second part, our development of automated construction is presented (reconciliation and implementation of data). Finally, the LCA case study of a conduit is presented to demonstrate the feature-based approach offered by the developed tool. A computerized environment supports effective and efficient decision-making related to materials and processes, facilitating the process of data mapping and hence product modeling. This method is also able to complete the LCA process on its own within minutes. Thus, the calculations and the LCA report are automatically generated. The tool developed has shown that automation by code is a viable solution to meet LCA's massification objectives. It has major advantages over the traditional LCA method and overcomes the complexity of LCA. Indeed, the case study demonstrated the time savings associated with this methodology and, therefore, the opportunity to increase the number of LCA reports generated and, therefore, to meet regulatory requirements. Moreover, this approach also presents the potential of the proposed method for a wide range of applications.

Keywords: automation, EEE, life cycle assessment, life cycle inventory, massively

Procedia PDF Downloads 88

Authors: Jin Uk Han, Hye Won Han, Hyo Lim Kang, Tae An Kim, Seung Ho Han

Abstract:

Direct-drive generators for large-scale wind turbine, which are divided into AFPM(Axial Flux Permanent Magnet) and RFPM(Radial Flux Permanent Magnet) type machine, have attracted interest because of a higher energy density in comparison with gear train type generators. Each type of the machines provides distinguishable geometrical features such as narrow width with a large diameter for the AFPM-type machine and wide width with a certain diameter for the RFPM-type machine. When the AFPM-type machine is applied, an increase of electric power production through a multi-stage arrangement in axial direction is easily achieved. On the other hand, the RFPM-type machine can be applied by using its geometric feature of wide width. In this study, a hybrid two-stage direct-drive generator for 6.2MW class wind turbine was proposed, in which the two-stage AFPM-type machine for 5 MW was composed of two models arranged in axial direction with a hollow shape topology of the rotor with annular disc, the stator and the main shaft mounted on coupled slew bearings. In addition, the RFPM-type machine for 1.2MW was installed at the empty space of the rotor. Analytic results obtained from an electro-magnetic and structural interaction analysis showed that the structural weight of the proposed hybrid two-stage direct-drive generator can be achieved as 155tonf in a condition satisfying the requirements of structural behaviors such as allowable air-gap clearance and strength. Therefore, it was sure that the 6.2MW hybrid two-stage direct-drive generator is competitive than conventional generators. (NRF grant funded by the Korea government MEST, No. 2017R1A2B4005405).

Keywords: AFPM-type machine, direct-drive generator, electro-magnetic analysis, large-scale wind turbine, RFPM-type machine

Procedia PDF Downloads 166

Authors: Abdulaziz Alsadhan, Naveed Khan

Abstract:

In recent years intrusions on computer network are the major security threat. Hence, it is important to impede such intrusions. The hindrance of such intrusions entirely relies on its detection, which is primary concern of any security tool like Intrusion Detection System (IDS). Therefore, it is imperative to accurately detect network attack. Numerous intrusion detection techniques are available but the main issue is their performance. The performance of IDS can be improved by increasing the accurate detection rate and reducing false positive. The existing intrusion detection techniques have the limitation of usage of raw data set for classification. The classifier may get jumble due to redundancy, which results incorrect classification. To minimize this problem, Principle Component Analysis (PCA), Linear Discriminant Analysis (LDA), and Local Binary Pattern (LBP) can be applied to transform raw features into principle features space and select the features based on their sensitivity. Eigen values can be used to determine the sensitivity. To further classify, the selected features greedy search, back elimination, and Particle Swarm Optimization (PSO) can be used to obtain a subset of features with optimal sensitivity and highest discriminatory power. These optimal feature subset used to perform classification. For classification purpose, Support Vector Machine (SVM) and Multilayer Perceptron (MLP) used due to its proven ability in classification. The Knowledge Discovery and Data mining (KDD’99) cup dataset was considered as a benchmark for evaluating security detection mechanisms. The proposed approach can provide an optimal intrusion detection mechanism that outperforms the existing approaches and has the capability to minimize the number of features and maximize the detection rates.

Keywords: Particle Swarm Optimization (PSO), Principle Component Analysis (PCA), Linear Discriminant Analysis (LDA), Local Binary Pattern (LBP), Support Vector Machine (SVM), Multilayer Perceptron (MLP)

Procedia PDF Downloads 364

Authors: Amit Kumar Happy

Abstract:

This paper is motivated by the importance of multi-sensor image fusion with a specific focus on infrared (IR) and visual image (VI) fusion for various applications, including military reconnaissance. Image fusion can be defined as the process of combining two or more source images into a single composite image with extended information content that improves visual perception or feature extraction. These images can be from different modalities like visible camera & IR thermal imager. While visible images are captured by reflected radiations in the visible spectrum, the thermal images are formed from thermal radiation (infrared) that may be reflected or self-emitted. A digital color camera captures the visible source image, and a thermal infrared camera acquires the thermal source image. In this paper, some image fusion algorithms based upon multi-scale transform (MST) and region-based selection rule with consistency verification have been proposed and presented. This research includes the implementation of the proposed image fusion algorithm in MATLAB along with a comparative analysis to decide the optimum number of levels for MST and the coefficient fusion rule. The results are presented, and several commonly used evaluation metrics are used to assess the suggested method's validity. Experiments show that the proposed approach is capable of producing good fusion results. While deploying our image fusion algorithm approaches, we observe several challenges from the popular image fusion methods. While high computational cost and complex processing steps of image fusion algorithms provide accurate fused results, they also make it hard to become deployed in systems and applications that require a real-time operation, high flexibility, and low computation ability. So, the methods presented in this paper offer good results with minimum time complexity.

Keywords: image fusion, IR thermal imager, multi-sensor, multi-scale transform

Procedia PDF Downloads 114

Authors: Deepti Mishra, K. K Pant, Xiu Song Zhao, Muxina Konarova

Abstract:

Catalytic transformation of simplest hydrocarbon methane into benzene and valuable chemicals over Mo/HZSM-5 has a great economic potential, however, it suffers serious hurdles due to the blockage in the micropores because of extensive coking at high temperature during methane dehydroaromatization (MDA). Under such conditions, it necessitates the design of micro/mesoporous ZSM-5, which has the advantages viz. uniform dispersibility of MoOx species, consequently the formation of active Mo sites in the micro/mesoporous channel and lower carbon deposition because of improved mass transfer rate within the hierarchical pores. In this study, we report a unique strategy to control the porous structures of ZSM-5 through a dual templating approach, utilizing C6 and C12 -surfactants as porogen. DFT studies were carried out to correlate the ZSM-5 framework development using the C6 and C12 surfactants with structure directing agent. The structural and morphological parameters of the synthesized ZSM-5 were explored in detail to determine the crystallinity, porosity, Si/Al ratio, particle shape, size, and acidic strength, which were further correlated with the physicochemical and catalytic properties of Mo modified HZSM-5 catalysts. After Mo incorporation, all the catalysts were tested for MDA reaction. From the activity test, it was observed that C6 surfactant-modified hierarchically porous Mo/HZSM-5(H) showed the highest benzene formation rate (1.5 μmol/gcat. s) and longer catalytic stability up to 270 min of reaction as compared to the conventional microporous Mo/HZSM-5(C). In contrary, C12 surfactant modified Mo/HZSM-5(D) is inferior towards MDA reaction (benzene formation rate: 0.5 μmol/gcat. s). We ascribed that the difference in MDA activity could be due to the hierarchically interconnected meso/microporous feature of Mo/HZSM-5(H) that precludes secondary reaction of coking from benzene and hence contributing substantial stability towards MDA reaction.

Keywords: hierarchical pores, Mo/HZSM-5, methane dehydroaromatization, coke deposition

Procedia PDF Downloads 80

Authors: Ahmed Khalil, Elhamy Tarabees, Svetlana Kovacikova

Abstract:

The Red Sea Mountains have been famous for their ore deposits since ancient times. Also, petrographic analysis and previous potential field surveys indicated large unexplored accumulations of ore minerals in the area. Therefore, the main goal of the presented study is to contribute to the discovery of hitherto unknown ore mineral deposits in the Red Sea region. To achieve this goal, we used two geophysical techniques: land magnetic survey and magnetotelluric data. A high-resolution land magnetic survey has been acquired using two proton magnetometers, one instrument used as a base station for the diurnal correction and the other used to measure the magnetic field along the study area. Two hundred eighty land magnetic stations were measured over a mesh-like area with a 500m spacing interval. The necessary reductions concerning daily variation, regional gradient and time observation were applied. Then, the total intensity anomaly map was constructed and transformed into the reduced magnetic pole (RTP). The magnetic interpretation was carried out using the analytical signal as well as regional–residual separation is carried out using the power spectrum. Also, the tilt derivative method (TDR) technique is applied to delineate the structure and hidden anomalies. Data analysis has been performed using trend analysis and Euler deconvolution. The results indicate that magnetic contacts are not the dominant geological feature of the study area. The magnetotleruric survey consisted of two profiles with a total of 8 broadband measurement points with a duration of about 24 hours crossing a wadi um Gheig approximately 50 km south of El Quseir. Collected data have been inverted to the electrical resistivity model using the 3D modular 3D inversion technique ModEM. The model revealed a non-conductive body in its central part, probably corresponding to a dolerite dyke, with which possible ore mineralization could be related.

Keywords: magnetic survey, magnetotelluric, mineralization, 3d modeling

Procedia PDF Downloads 23

Authors: Chia-Chih Wei, Yun-Qi Li, Ssu-Ying Chen, Hsuan-Jung Chen, Hsi-Wen Yang, Chih-Yuan Chen, Chien-Chon Chen

Abstract:

In this paper we used high quality anodization technique to make colored wind chime with a nano-tube structure anodic film, which controls the length to diameter ratio of an aluminum rod and controls the oxide film structure on the surface of the aluminum rod by anodizing method. The research experiment used hard anodization to grow a controllable thickness of anodic film on aluminum alloy surface. The hard anodization film has high hardness, high insulation, high temperature resistance, good corrosion resistance, colors, and mass production properties can be further applied to transportation, electronic products, biomedical fields, or energy industry applications. This study also in-depth research and detailed discussion in the related process of aluminum alloy surface hard anodizing including pre-anodization, anodization, and post-anodization. The experiment parameters of anodization including using a mixed acid solution of sulfuric acid and oxalic acid as an anodization electrolyte, and control the temperature, time, current density, and final voltage to obtain the anodic film. In the experiments results, the properties of anodic film including thickness, hardness, insulation, and corrosion characteristics, microstructure of the anode film were measured and the hard anodization efficiency was calculated. Thereby obtaining different transmission speeds of sound in the aluminum rod and different audio sounds can be presented on the aluminum rod. Another feature of the present invention is the use of anodizing method dyeing method, laser engraving patterning and electrophoresis method to make colored aluminum wind chimes.

Keywords: anodization, colored, high quality, wind chime, nano-tube

Procedia PDF Downloads 242

Authors: Bahram Fathi, Karim Alizadeh, Azam Mohammadbagheri

Abstract:

The aim of this paper is to investigate the role of oil price shocks in explaining business cycles in Iran using a dynamic stochastic general equilibrium approach. This model incorporates both productivity and oil revenue shocks. The results indicate that productivity shocks are relatively more important to business cycles than oil shocks. The model with two shocks produces different values for volatility, but these values have the same ranking as that of the actual data for most variables. In addition, the actual data are close to the ratio of standard deviations to the output obtained from the model with two shocks. The results indicate that productivity shocks are relatively more important to business cycles than the oil shocks. The model with only a productivity shock produces the most similar figures in term of volatility magnitude to that of the actual data. Next, we use the Impulse Response Functions (IRF) to evaluate the capability of the model. The IRF shows no effect of an oil shock on the capital stocks and on labor hours, which is a feature of the model. When the log-linearized system of equations is solved numerically, investment and labor hours were not found to be functions of the oil shock. This research recommends using different techniques to compare the model’s robustness. One method by which to do this is to have all decision variables as a function of the oil shock by inducing the stationary to the model differently. Another method is to impose a bond adjustment cost. This study intends to fill that gap. To achieve this objective, we derive a DSGE model that allows for the world oil price and productivity shocks. Second, we calibrate the model to the Iran economy. Next, we compare the moments from the theoretical model with both single and multiple shocks with that obtained from the actual data to see the extent to which business cycles in Iran can be explained by total oil revenue shock. Then, we use an impulse response function to evaluate the role of world oil price shocks. Finally, I present implications of the findings and interpretations in accordance with economic theory.

Keywords: oil price, shocks, dynamic stochastic general equilibrium, Iran

Procedia PDF Downloads 437

Authors: Maryam Umar Ladan, Arshad Munir

Abstract:

Poverty has always been a constant feature of society throughout history. It has existed in the lives of people and it is a fact that although the majority of people lives in poverty, the remaining minority lives in luxury. While some countries called the first World countries lives in luxury, the third World countries lives in poverty. It remains an undesirable phenomenon affecting a vast number of people across the globe despite governmental, institutional and private organizations’ interventions with measures aimed at cushioning its adverse effects. Unequal distribution of societal resources, accumulated wealth in the hands of few, lack of access to education and employment, individual responsibility among others, were highlighted as factors associated with poverty. Poverty predisposes the poor individual to malnutrition and starvation, exposure to disease, thereby resulting to violence, crimes, and experiencing lifelong problems. Evidence show that about 50 percent of the world population lives on less than 2.50 dollar a day, 90 percent of whom are from Sub-Saharan Africa and South Asia including countries where Islam is the major if not one adherent religion. As a solution to poverty, Islam prescribes a system of annual Zakat (charity). The Islamic law prescribes that every person who has a saving that reaches a certain limit should give out 2.5 percent of the total annual earning (as in income, money, farm produce) to deserving and prescribed citizens. This is to, among others; reduce the level of inequality through distribution of wealth among the Muslim Ummah (community). Furthermore, Islam encourages the rich in several places in the Qur’an to spend their wealth on poor people other than the compulsory 2.5%. Therefore, it is inarguable that the Islamic system of distribution of resources (as zakat) is the best strategy to poverty eradication. Thus, strongly recommended for desired results in poverty eradication efforts. If every rich person gives Zakat sincerely, poverty will be eradicated in the world, and not a single person will die of want of food or material things.

Keywords: Islam, charity, poverty, zakat

Procedia PDF Downloads 284

Authors: Hanwei Cheng, Chengbei Xu, Yijie Wang

Abstract:

More and more college students are accustomed to surfing the Internet everyday. As community members, college students have ability to express opinions and participate in social affairs, they not only accept information passively, but also voice their concerns on the Internet. We interpret the online discourses featured with anonymization, so it helps us more effectively and conveniently understand the behaviors and thoughts of college students, and educators can thus grasp the scales and directions in guiding online language. We analyzed online comments in both content and form aspects in one student forum (named Dandan, the BNU’s campus forum), and through methods of literature review and interview, we found that in term of content, college students pay attention to practical information online, emphasize on personal development and pursue hot issues; in term of form, college students' online language displays cross-border quality sometimes under the general feature of normative, and they often explore a certain topic in the form of question or discussion, and they like to show feelings in ironic and stream-of-consciousness ways. It is argued that college students intend to establish a community to facilitate personal development and meet emotional needs through the student forum, and by making comments at the forum they are also able to get involved in public affairs. We should pay attention to problems of college students' online discourse, such as boundary issues (like informal advertisement and information authenticity), emotional issues and the spread of gossip. Some possible solutions to solving online discourse problems can be applied, like we can improve access systems of student forum, clarify principles of Internet langue use, change oversimplified management approaches and use some other tactics, in order to form a mechanism of student self-regulation, also deepen the trust and cooperation between school administrators and students.

Keywords: online language, youth discourse, content and form, implication and strategy

Procedia PDF Downloads 141

Authors: Kailash Pattanaik, Giribala Mohanty

Abstract:

Dhanujatra is a folk performance of ODISHA, India, that transports the participants, on lookers and all alike into a mythical atmosphere for eleven days and nights as well. In this performance the whole town becomes stage. The uniqueness of the festival lies in the fact that all the episodes of this Jatra enacted in different parts of the town making it the largest open air theatre in the world. The paper would emphasize on the uniqueness and the impact of this performance.Different episodes are enacted at different places in the regime. So, Dhanujatra does not confine itself to a fixed static or dead stage, as in case of other Jatra’s; it rather becomes the stage for the world at large. For that, it is said that, Worlds biggest open air theatre held in the tiny town called Bargarh in the western part of Orissa. The play moves sequentially day after day and the audience moves from locale to locale. Here it is analogues to the Ramleela of Ramnagar of Benars. Parallal enactment is a significant feature of this Jatra. From the second day, parallal performances take place in both Bargarh town and Ambapalli epitomising ‘Mathura’ and ‘Gokul’ respectively. Krishna is born in the prison on the second day of the jatra. Basudeb exchanges the child with the Nanda’s newborn baby in Gokul. In this way, parallal performances go on both in Mathura and Gokul. The ordinary persons who act as the mythological characters, or become historical heroes or the legendary Saints or Bhaktas in a Jatra in the evening, lead the lives of ordinary persons during day time. The dramatic personas of those individuals are shed with the end of the Jatra. On the contrary, the persons who act as the main characters of Dhanujatra are exceptions in this regard. They are identified as the characters they enact for the whole period of performance, both in the evenings and during daytime. It is worth mentioning that generally in the folk performances there is an ample scope to touch upon or interpret or comment or satirize the issues of contemporary relevance with the sole purpose to convey some specific message. Dhanujatra is no exception to that.

Keywords: folk performance, Jatra, parallel enactment, open-air stage, Odisha

Procedia PDF Downloads 285

Authors: Vladimir Klepikov

Abstract:

Countries of Central and Southern Europe have a typical feature: oil consumption in the region exceeds own commodity production capacity by far. So crude oil import prevails in the region’s crude oil consumption structure. Transportation using marine and pipeline transport is a common method of the imported oil delivery in the region. For certain refineries, in addition to possible transportation by oil pipelines from seaports, oil is delivered from Russian oil fields. With the view to these specific features and geographic location of the region’s refineries, three ways of imported oil delivery can be singled out: oil delivery by tankers to the port and subsequent transportation by pipeline transport of the port and the refinery; oil delivery by tanker fleet to the port and subsequent transportation by oil trunk pipeline transport; oil delivery from the fields by oil trunk pipelines to refineries. Oil is also delivered by road, internal water, and rail transport. However, the volumes transported this way are negligible in comparison to the three above transportation means. Multimodal oil transportation to refineries using the pipeline and marine transport is one of the biggest cargo flows worldwide. However, in scientific publications this problem is considered mainly for certain modes of transport. Therefore, this study is topical. To elaborate an efficient transportation policy of crude oil supply to Central and Southern Europe, in this paper the geographic concentration of oil refineries was determined and the capacities of the region’s refineries were assessed. The quantitative analysis method is used as a tool. The port infrastructure and the oil trunk pipeline system capacity were assessed in terms of delivery of raw materials to the refineries. The main groups of oil consuming countries were determined. The trends of crude oil production in the region were reviewed. The changes in production capacities and volumes at refineries in the last decade were shown. Based on the revealed refining trends, the scope of possible crude oil supplies to the refineries of the region under review was forecast. The existing transport infrastructure is able to handle the increased oil flow.

Keywords: European region, infrastructure, oil terminal capacity, pipeline capacity, refinery capacity, tanker draft

Procedia PDF Downloads 156

Authors: Jonathan R. Olsen, Natalie Nicholls, Jenna Panter, Hannah Burnett, Michael Tornow, Richard Mitchell

Abstract:

The 20-minute neighborhood is a policy priority for governments worldwide and a key feature of this policy is providing access to natural space within 800 meters of home. The study aims were to (1) examine the association between distance to nearest natural space and frequent use over time and (2) examine whether frequent use and changes in use were patterned by income and housing tenure over time. Bi-annual Scottish Household Survey data were obtained for 2013 to 2019 (n:42128 aged 16+). Adults were asked the walking distance to their nearest natural space, the frequency of visits to this space and their housing tenure, as well as age, sex and income. We examined the association between distance from home of nearest natural space, housing tenure, and the likelihood of frequent natural space use (visited once a week or more). Two-way interaction terms were further applied to explore variation in the association between tenure and frequent natural space use over time. We found that 87% of respondents lived within 10 minute walk of a natural space, meeting the policy specification for a 20-minute neighbourhood. Greater proximity to natural space was associated with increased use; individuals living a 6 to 10 minute walk and over 10 minute walk were respectively 53% and 78% less likely to report frequent natural space use than those living within a 5 minute walk. Housing tenure was an important predictor of frequent natural space use; private renters and homeowners were more likely to report frequent natural space use than social renters. Our findings provide evidence that proximity to natural space is a strong predictor of frequent use. Our study provides important evidence that time-based access measures alone do not consider deep-rooted socioeconomic variation in use of Natural space. Policy makers should ensure a nuanced lens is applied to operationalising and monitoring the 20-minute neighbourhood to safeguard against exacerbating existing inequalities.

Keywords: natural space, housing, inequalities, 20-minute neighbourhood, urban design

Procedia PDF Downloads 118

Authors: Wade Ghribi, Abdelmoty M. Ahmed, Ahmed Said Badawy, Belgacem Bouallegue

Abstract:

In higher education institutions, the most pressing priority is to improve student performance and retention. Large volumes of student data are used in Educational Data Mining techniques to find new hidden information from students' learning behavior, particularly to uncover the early symptom of at-risk pupils. On the other hand, data with noise, outliers, and irrelevant information may provide incorrect conclusions. By identifying features of students' data that have the potential to improve performance prediction results, comparing and identifying the most appropriate ensemble learning technique after preprocessing the data, and optimizing the hyperparameters, this paper aims to develop a reliable students' performance prediction model for Higher Education Institutions. Data was gathered from two different systems: a student information system and an e-learning system for undergraduate students in the College of Computer Science of a Saudi Arabian State University. The cases of 4413 students were used in this article. The process includes data collection, data integration, data preprocessing (such as cleaning, normalization, and transformation), feature selection, pattern extraction, and, finally, model optimization and assessment. Random Forest, Bagging, Stacking, Majority Vote, and two types of Boosting techniques, AdaBoost and XGBoost, are ensemble learning approaches, whereas Decision Tree, Support Vector Machine, and Artificial Neural Network are supervised learning techniques. Hyperparameters for ensemble learning systems will be fine-tuned to provide enhanced performance and optimal output. The findings imply that combining features of students' behavior from e-learning and students' information systems using Majority Vote produced better outcomes than the other ensemble techniques.

Keywords: educational data mining, student performance prediction, e-learning, classification, ensemble learning, higher education

Procedia PDF Downloads 105

Authors: Murad Al-Rajab, Sherin Hazboun, Azhar Al-Hamamreh, Nirmeen Odeh, Siham Halaseh

Abstract:

Tourism is considered an important sector for most countries, while maintaining good tourism attractions can promote national economic development. The State of Palestine is historically considered a wealthy country full of many archaeological places. In the city of Bethlehem, for example, the Church of the Nativity is the most important touristic site, but it does not have enough technology development to attract tourists. In this paper, we propose a smart mobile application named “Pal-STAR” (Palestine Smart Tourist Augmented Reality) as an innovative solution which targets tourists and assists them to make a visit inside the Church of the Nativity. The application will use augmented reality and feature a virtual tourist guide showing views of the church while providing historical information in a smart, easy, effective and user-friendly way. The proposed application is compatible with multiple mobile platforms and is considered user friendly. The findings show that this application will improve the practice of the tourism sector in the Holy Land, it will also increase the number of tourists visiting the Church of the Nativity and it will facilitate access to historical data that have been difficult to obtain using traditional tourism guidance. The value that tourism adds to a country cannot be denied, and the more technological advances are incorporated in this sector, the better the country’s tourism sector can be served. Palestine’s economy is heavily dependent on tourism in many of its main cities, despite several limitations, and technological development is needed to enable this sector to flourish. The proposed mobile application would definitely have a good impact on the development of the tourism sector by creating an Augmented Reality environment for tourists inside the church, helping them to navigate and learn about holy places in a non-traditional way, using a virtual tourist guide.

Keywords: smartphones, tourism, tourists guide, augmented reality, Palestine

Procedia PDF Downloads 169

Authors: Osama Ahmed Ibrahim Masoud, Mohamed Ibrahim Mohamed Abdelhadi, Ahmed Mohamed Seddik Hassan

Abstract:

The problem of study focuses on thermal comfort realization in a residential building during hot and dry climate periods consumes a major electrical energy for air conditioning operation. Thermal comfort realization in a residential building during such climate becomes more difficult regarding the phenomena of climate change, and the use of building and construction materials which have the feature of heat conduction as (bricks-reinforced concrete) and the global energy crises. For that, this study aims to how to realize internal thermal comfort through how to make the best use of building services (temporarily used service spaces) for reducing the electrical energy transfer and saving self-shading. In addition, the possibility of reduction traditional energy (fossil fuel) consumed in cooling through the use of building services for reducing the internal thermal comfort and the relationship between them. This study is based on measuring the consumed electrical energy rate in cooling (by using Design-Builder program) for a residential building (the place of study is: Egypt- Suez Canal- Suez City), this design model has lots of alternatives designs for the place of building services (center of building- the eastern front- southeastern front- the southern front- the south-west front, the western front). The building services are placed on the fronts with different rates for determining the best rate on fronts which realizes thermal comfort with the lowest of energy consumption used in cooling. Findings of the study indicate to that the best position for building services is on the west front then the south-west front, and the more the building services increase, the more energy consumption used in cooling of residential building decreases. Recommendations indicate to the need to study the building services positions in the new projects progress to select the best alternatives to realize ‘Energy conservation’ used in cooling or heating into the buildings in general, residential buildings particularly.

Keywords: residential buildings, energy conservation, thermal comfort, building services, temporary used service spaces, DesignBuilder

Procedia PDF Downloads 292

Authors: Anželika Teresė

Abstract:

In order to solve issues in sign language linguistics, address matters pertaining to maintaining high quality of sign language (SL) translation, contribute to dispelling misconceptions about SL and deaf people, and raise awareness and understanding of the deaf community heritage, this presentation discusses literature in Lithuanian Sign Language (LSL) and inherent metaphors that are created by using the phonological parameter –handshape, location, movement, palm orientation and nonmanual features. The study covered in this presentation is twofold, involving both the micro-level analysis of metaphors in terms of phonological parameters as a sub-lexical feature and the macro-level analysis of the poetic context. Cognitive theories underlie research of metaphors in sign language literature in a range of SL. The study follows this practice. The presentation covers the qualitative analysis of 34 pieces of LSL literature. The analysis employs ELAN software widely used in SL research. The target is to examine how specific types of each phonological parameter are used for the creation of metaphors in LSL literature and what metaphors are created. The results of the study show that LSL literature employs a range of metaphors created by using classifier signs and by modifying the established signs. The study also reveals that LSL literature tends to create reference metaphors indicating status and power. As the study shows, LSL poets metaphorically encode status by encoding another meaning in the same sign, which results in creating double metaphors. The metaphor of identity has been determined. Notably, the poetic context has revealed that the latter metaphor can also be identified as a metaphor for life. The study goes on to note that deaf poets create metaphors related to the importance of various phenomena significance of the lyrical subject. Notably, the study has allowed detecting locations, nonmanual features and etc., never mentioned in previous SL research as used for the creation of metaphors.

Keywords: Lithuanian sign language, sign language literature, sign language metaphor, metaphor at the phonological level, cognitive linguistics

Procedia PDF Downloads 134

Authors: Leandros A. Maglaras, Jianmin Jiang

Abstract:

The protection of the national infrastructures from cyberattacks is one of the main issues for national and international security. The funded European Framework-7 (FP7) research project CockpitCI introduces intelligent intrusion detection, analysis and protection techniques for Critical Infrastructures (CI). The paradox is that CIs massively rely on the newest interconnected and vulnerable Information and Communication Technology (ICT), whilst the control equipment, legacy software/hardware, is typically old. Such a combination of factors may lead to very dangerous situations, exposing systems to a wide variety of attacks. To overcome such threats, the CockpitCI project combines machine learning techniques with ICT technologies to produce advanced intrusion detection, analysis and reaction tools to provide intelligence to field equipment. This will allow the field equipment to perform local decisions in order to self-identify and self-react to abnormal situations introduced by cyberattacks. In this paper, an intrusion detection module capable of detecting malicious network traffic in a Supervisory Control and Data Acquisition (SCADA) system is presented. Malicious data in a SCADA system disrupt its correct functioning and tamper with its normal operation. OCSVM is an intrusion detection mechanism that does not need any labeled data for training or any information about the kind of anomaly is expecting for the detection process. This feature makes it ideal for processing SCADA environment data and automates SCADA performance monitoring. The OCSVM module developed is trained by network traces off line and detects anomalies in the system real time. The module is part of an IDS (intrusion detection system) developed under CockpitCI project and communicates with the other parts of the system by the exchange of IDMEF messages that carry information about the source of the incident, the time and a classification of the alarm.

Keywords: cyber-security, SCADA systems, OCSVM, intrusion detection

Procedia PDF Downloads 552

Authors: Mahmoud B. Rokaya

Abstract:

The study of opinion mining and sentiment analysis includes analysis of opinions, sentiments, evaluations, attitudes, and emotions. The rapid growth of social media, social networks, reviews, forum discussions, microblogs, and Twitter, leads to a parallel growth in the field of sentiment analysis. The field of sentiment analysis tries to develop effective tools to make it possible to capture the trends of people. There are two approaches in the field, lexicon-based and corpus-based methods. A lexicon-based method uses a sentiment lexicon which includes sentiment words and phrases with assigned numeric scores. These scores reveal if sentiment phrases are positive or negative, their intensity, and/or their emotional orientations. Creation of manual lexicons is hard. This brings the need for adaptive automated methods for generating a lexicon. The proposed method generates dynamic lexicons based on the corpus and then classifies text using these lexicons. In the proposed method, different approaches are combined to generate lexicons from text. The proposed method classifies the tweets into 5 classes instead of +ve or –ve classes. The sentiment classification problem is written as an optimization problem, finding optimum sentiment lexicons are the goal of the optimization process. The solution was produced based on mathematical programming approaches to find the best lexicon to classify texts. A genetic algorithm was written to find the optimal lexicon. Then, extraction of a meta-level feature was done based on the optimal lexicon. The experiments were conducted on several datasets. Results, in terms of accuracy, recall and F measure, outperformed the state-of-the-art methods proposed in the literature in some of the datasets. A better understanding of the Arabic language and culture of Arab Twitter users and sentiment orientation of words in different contexts can be achieved based on the sentiment lexicons proposed by the algorithm.

Keywords: social media, Twitter sentiment, sentiment analysis, lexicon, genetic algorithm, evolutionary computation

Procedia PDF Downloads 188

Authors: Mahan Qwamizadeh, Kun Zhou, Zuoqi Zhang, Yong Wei Zhang

Abstract:

Typical load-bearing biological materials like bone, mineralized tendon and shell, are biocomposites made from both organic (collagen) and inorganic (biomineral) materials. This amazing class of materials with intrinsic internally designed hierarchical structures show superior mechanical properties with regard to their weak components from which they are formed. Extensive investigations concentrating on static loading conditions have been done to study the biological materials failure. However, most of the damage and failure mechanisms in load-bearing biological materials will occur whenever their structures are exposed to dynamic loading conditions. The main question needed to be answered here is: What is the relation between the layout and architecture of the load-bearing biological materials and their dynamic behavior? In this work, a staggered model has been developed based on the structure of natural materials at nanoscale and Finite Element Analysis (FEA) has been used to study the dynamic behavior of the structure of load-bearing biological materials to answer why the staggered arrangement has been selected by nature to make the nanocomposite structure of most of the biological materials. The results showed that the staggered structures will efficiently attenuate the stress wave rather than the layered structure. Furthermore, such staggered architecture is effectively in charge of utilizing the capacity of the biostructure to resist both normal and shear loads. In this work, the geometrical parameters of the model like the thickness and aspect ratio of the mineral inclusions selected from the typical range of the experimentally observed feature sizes and layout dimensions of the biological materials such as bone and mineralized tendon. Furthermore, the numerical results validated with existing theoretical solutions. Findings of the present work emphasize on the significant effects of dynamic behavior on the natural evolution of load-bearing biological materials and can help scientists to design bioinspired materials in the laboratories.

Keywords: load-bearing biological materials, nanostructure, staggered structure, stress wave decay

Procedia PDF Downloads 454

Authors: Rasha Elhawari

Abstract:

Heritage language learners (HLL) are part of the linguistic reality in Foreign Language Learning (FLL). These learners present several characteristics that are different from non-heritage language learners. They have a personal connection with the language and their motivation to learn the language is partly because of this personal connection. In Canada there is a large diversity in the foreign language learning classroom; the Arabic language classroom is no exception. The Arabic HLL is unique for more than one reason. First, is the fact that the Arabic language is spoken across twenty-two Arab countries across the Arab World. Across the Arab World there is a standard variation and a local dialect that co-exist side by side, i.e. diaglossia exists in a strong and unique way as a feature of Arabic. Second, Arabic is the language that all Muslims across the Muslim World use for their prayers. This raises a number of points when we consider Arabic as a Heritage Language; namely the role of diaglossia, culture and religion. The fact that there is a group of leaners that can be regarded as HLL who are not of Arabic speaking background but are Muslims and use the language for religious purposes is unique, thus course developers and language instructors need take this into consideration. The paper takes a closer look at this distinction and establishes sub-groups the Arabic HLLs in a language and/or culture specific way related mainly to the Arabic HLL. It looks at the learners at the beginners’ Arabic class at the undergraduate university level over a period of three years in order to define this learner. Learners belong to different groups and backgrounds but they all share common characteristics. The paper presents a detailed look at the learner types present at this class in order to help prepare and develop material for this specific learner group. The paper shows that separate HLL and non-HLL courses, especially at the introductory and intermediate level, is successful in resolving some of the pedagogical problems that occur in the Arabic as a Foreign Language classroom. In conclusion, the paper recommends the development of HLL courses at the early levels of language learning. It calls for a change in the pedagogical practices to overcome some of the challenges learner in the introductory Arabic class can face.

Keywords: Arabic, Heritage Language, langauge learner, teaching

Procedia PDF Downloads 400

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

Abstract:

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

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

Procedia PDF Downloads 42

Authors: Rohini Hariharan, Yazhini R, Bhamidipati Naga Shrikarti

Abstract:

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

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

Procedia PDF Downloads 50

Authors: Maria Ashitko

Abstract:

The Constitution of the Republic of Belarus is based on the principle of the unity of rights and obligations, including those of the child. The constitutional status of the child is aspecific system of constitutional elements established and guaranteed by the state through the current legislation and regulatory acts that ensure the special legal status of the child, his or her constitutional legal capacity, implementation of the principles of the constitutional and legal status of the child, constitutional rights of the child and their safeguards. Under the principles of the constitutional status of the child, we consider the general, normative, social-volitional rules of behavior established by the Constitution of the Republic of Belarus, laws and other regulatory acts that determine the content and social purpose of the legal status of the child. The constitutional and legal status of the child is characterized by the following special principles, which form a feature of the state legal system:1) Ensuring the interests of the child means providing for the child in accordance with his or her age, state of health, characteristics of development, life experience, family life, cultural traditions, ethnicity. 2) The principle of equal responsibility of both parents or their substitutes characterized by caring for the next generation as one of the priority tasks of the state and society, and all issues related to the implementation of children’s rights should be addressed at the constitutional level. 3) We would like to highlight such a special principle as the subprinciple of safeguards, which is the principle of ensuring the safety of the child. It is also worth noting that in legal studies, there is no relationship between safety and constitutional rights as general safeguards of individual rights and freedoms, and as special safeguards for the right to life. 4) The principle of justice is expressed by the fact that in modern conditions, the quality of life is determined not only by material wealth but also by the ability of the state to ensure the harmonization of social relations and social harmony on the basis of humanism and justice. Thus, the specificity of the constitutional status of the child is the age boundary between adulthood and minority; therefore, we propose to highlight the age characteristics of the child as an additional element. It is advisable to highlight such a special principle as the subprinciple of safeguards, which is the principle of ensuring the safety of the child.

Keywords: children’s rights, constitutional status, constitutional principles, constitutional rights

Procedia PDF Downloads 125

Authors: Saule Mussabekova

Abstract:

Recent advances in genetics have allowed increasing acutely the capacities of the formation of reliable evidence in conducting forensic examinations. Thus, traces of biological origin are important sources of information about a crime. Currently, around the world, sexual offenses have increased, and among them are those in which the criminals use various detergents to remove traces of their crime. A feature of modern synthetic detergents is the presence of biological additives - enzymes. Enzymes purposefully destroy stains of biological origin. To study the nature and extent of the impact of modern washing powders on saliva stains on the physical evidence, specially prepared test specimens of different types of tissues to which saliva was applied have been examined. Materials and Methods: Washing machines of famous manufacturers of household appliances have been used with different production characteristics and advertised brands of washing powder for test washing. Over 3,500 experimental samples were tested. After washing, the traces of saliva were identified using modern research methods of forensic medicine. Results: The influence was tested and the dependence of the use of different washing programs, types of washing machines and washing powders in the process of establishing saliva trace and identify of the stains on the physical evidence while washing was revealed. The results of experimental and practical expert studies have shown that in most cases it is not possible to draw the conclusions in the identification of saliva traces on physical evidence after washing. This is a consequence of the effect of biological additives and other additional factors on traces of saliva during washing. Conclusions: On the basis of the results of the study, the feasibility of saliva traces of the stains on physical evidence after washing is established. The use of modern molecular genetic methods makes it possible to partially solve the problems arising in the study of unlaundered evidence. Additional study of physical evidence after washing facilitates detection and investigation of sexual offenses against women and children.

Keywords: saliva research, modern synthetic detergents, laundry detergents, forensic medicine

Procedia PDF Downloads 215

Authors: Saif Ullah, Zaigham Hasan, Muhammad Ali, Qaisar Jamal, Kiran Salahuddin, Muhammad Awais

Abstract:

Survey of avian fauna of Bara Gali Summer Campus, University of Peshawar situated in Abbottabad was conducted from April to October, 2013. A total of 21 species belonging to 5 orders and 15 families were recorded. Out of these, 6 were resident, 12 summer visitor and 3 rare. Order Passeriformes was represented by 16 species which are Certhia himalayana, Megalaima virens, Phylloscopus trochiloides, Garrulax lineatus, Passer rutilans, Corvus macrorhynchos, Hypsipetes leucocephalus, Acridotheres tristis, Delichon dasypus cashmeriensis, Hirundo rustica, Muscicapa thalassina, Saxicola ferrea, Myiophoneus caeruleus, Parus melonolophus, Parus rufonuchalis, Parus monticolus, belonging to 11 families. Two species Dendrocopos himalayansis and Picus squamatus belong to only one family Picidae of order Piciformes. Among rest of the three orders each is represented by only a single species; Accipitriformes by Accipiter virgatus, Coraciformes by Upupa epops while order Psittaciformes has been represented by Psittacula himalayana. The distribution and abundance varied with season and maximum number of species were found during the monsoon season when most of the birds migrate for breeding. Some habits and behaviors like nesting, feeding, breeding and vocalizations were also studied which are very unique from other birds found at lower elevations. Among bird species adapted to diverse habitat in the field, Himalayan Jungle Crow, Common Mynas, Bulbuls, Barn Swallows, barbets were prominent. Interesting feature of the avian fauna is its familiarity with flora, was also observed during the present studies that some birds are very quick and active in their movement on a tree surface i.e Certhia himalayana.

Keywords: avifauna diversity, distribution, Bara Gali, Abbottabad

Procedia PDF Downloads 375

Authors: Gloria Chen

Abstract:

When offering conventional level-appropriate ESL classes for adults is not feasible, a multilevel adult ESL class can be formed to benefit those who need to learn English for daily function. This paper examines the rationale, the process, the contents, and the outcomes of a multilevel ESL class for adults. The action research discusses a variety of assessments, lesson plans, teaching strategies that facilitate lifelong language learning. In small towns where adult ESL learners are only a handful, often advanced students and inexperienced students have to be placed in one class. Such class might not be viewed as desirable, but with on-going assessments, careful lesson plans, and purposeful strategies, a multilevel ESL class for adults can overcome the obstacles and help learners to reach a higher level of English proficiency. This research explores some hand-on strategies, such as group rotating, cooperative learning, and modifying textbook contents for practical purpose, and evaluate their effectiveness. The data collected in this research include Needs Assessment (beginning of class term), Mid-term Self-Assessment (5 months into class term), End-of-term Student Reflection (10 months into class), and End-of-term Assessment from the Instructor (10 months into class). A descriptive analysis of the data explains the practice of this particular learning community, and reveal the areas for improvement and enrichment. This research answers the following questions: (1) How do the assessments positively help both learners and instructors? (2) How do the learning strategies prepare students to become independent, life-long English learners? (3) How do materials, grouping, and class schedule enhance the learning? The result of the research contributes to the field of teaching and learning in language, not limited in English, by (a) examining strategies of conducting a multilevel adult class, (b) involving adult language learners with various backgrounds and learning styles for reflection and feedback, and (c) improving teaching and learning strategies upon research methods and results. One unique feature of this research is how students can work together with the instructor to form a learning community, seeking and exploring resources available to them, to become lifelong language learners.

Keywords: adult language learning, assessment, multilevel, teaching strategies

Procedia PDF Downloads 351

Authors: Ahmed Abdullah Ahmed

Abstract:

The task of recognizing the writer of a handwritten text has been an attractive research problem in the document analysis and recognition community with applications in handwriting forensics, paleography, document examination and handwriting recognition. This research presents an automatic method for writer recognition from digitized images of unconstrained writings. Although a great effort has been made by previous studies to come out with various methods, their performances, especially in terms of accuracy, are fallen short, and room for improvements is still wide open. The proposed technique employs optimal codebook based writer characterization where each writing sample is represented by a set of features computed from two codebooks, beginning and ending. Unlike most of the classical codebook based approaches which segment the writing into graphemes, this study is based on fragmenting a particular area of writing which are beginning and ending strokes. The proposed method starting with contour detection to extract significant information from the handwriting and the curve fragmentation is then employed to categorize the handwriting into Beginning and Ending zones into small fragments. The similar fragments of beginning strokes are grouped together to create Beginning cluster, and similarly, the ending strokes are grouped to create the ending cluster. These two clusters lead to the development of two codebooks (beginning and ending) by choosing the center of every similar fragments group. Writings under study are then represented by computing the probability of occurrence of codebook patterns. The probability distribution is used to characterize each writer. Two writings are then compared by computing distances between their respective probability distribution. The evaluations carried out on ICFHR standard dataset of 206 writers using Beginning and Ending codebooks separately. Finally, the Ending codebook achieved the highest identification rate of 98.23%, which is the best result so far on ICFHR dataset.

Keywords: off-line text-independent writer identification, feature extraction, codebook, fragments

Procedia PDF Downloads 510

Authors: T. Bryan , V. Kepuska, I. Kostnaic

Abstract:

A method of data compression and denoising is introduced that is based on atomic decomposition of audio data using “basis vectors” that are learned from the audio data itself. The basis vectors are shown to have higher data compression and better signal-to-noise enhancement than the Gabor and gammatone “seed atoms” that were used to generate them. The basis vectors are the input weights of a Sparse AutoEncoder (SAE) that is trained using “envelope samples” of windowed segments of the audio data. The envelope samples are extracted from the audio data by performing atomic decomposition with Gabor or gammatone seed atoms. This process identifies segments of audio data that are locally coherent with the seed atoms. Envelope samples are extracted by identifying locally coherent audio data segments with Gabor or gammatone seed atoms, found by matching pursuit. The envelope samples are formed by taking the kronecker products of the atomic envelopes with the locally coherent data segments. Oracle signal-to-noise ratio (SNR) verses data compression curves are generated for the seed atoms as well as the basis vectors learned from Gabor and gammatone seed atoms. SNR data compression curves are generated for speech signals as well as early American music recordings. The basis vectors are shown to have higher denoising capability for data compression rates ranging from 90% to 99.84% for speech as well as music. Envelope samples are displayed as images by folding the time series into column vectors. This display method is used to compare of the output of the SAE with the envelope samples that produced them. The basis vectors are also displayed as images. Sparsity is shown to play an important role in producing the highest denoising basis vectors.

Keywords: sparse dictionary learning, autoencoder, sparse autoencoder, basis vectors, atomic decomposition, envelope sampling, envelope samples, Gabor, gammatone, matching pursuit

Procedia PDF Downloads 249