Search results for: PDF to story feature

Authors: Jiahao Cui

Abstract:

In the past centuries, due to climate change and intense whaling, the global whale population has dramatically declined. Among the various whale species, the fin whale experienced the most drastic drop in number due to its popularity in whaling. Under this background, identifying fin whale calls could be immensely beneficial to the preservation of the species. This paper uses feature extraction to process the input audio signal, then a network based on AlexNet and three networks based on the ResNet model was constructed to classify fin whale calls. A mixture of the DOSITS database and the Watkins database was used during training. The results demonstrate that a modified ResNet network has the best performance considering precision and network complexity.

Keywords: convolutional neural network, ResNet, AlexNet, fin whale preservation, feature extraction

Procedia PDF Downloads 125

Authors: Hironori Karachi, Haruka Yamashita

Abstract:

Recently, the system of quick response (QR) code is getting popular. Many companies introduce new QR code payment services and the services are competing with each other to increase the number of users. For increasing the number of users, we should grasp the difference of feature of the demographic information, usage information, and value of users between services. In this study, we conduct an analysis of real-world data provided by Nomura Research Institute including the demographic data of users and information of users’ usages of two services; LINE Pay, and PayPay. For analyzing such data and interpret the feature of them, Nonnegative Matrix Factorization (NMF) is widely used; however, in case of the target data, there is a problem of the missing data. EM-algorithm NMF (EMNMF) to complete unknown values for understanding the feature of the given data presented by matrix shape. Moreover, for comparing the result of the NMF analysis of two matrices, there is Discriminant NMF (DNMF) shows the difference of users features between two matrices. In this study, we combine EMNMF and DNMF and also analyze the target data. As the interpretation, we show the difference of the features of users between LINE Pay and Paypay.

Keywords: data science, non-negative matrix factorization, missing data, quality of services

Procedia PDF Downloads 131

Authors: Niousha Bagheri Khulenjani, Mohammad Saniee Abadeh

Abstract:

Learning from very big datasets is a significant problem for most present data mining and machine learning algorithms. MicroRNA (miRNA) is one of the important big genomic and non-coding datasets presenting the genome sequences. In this paper, a hybrid method for the classification of the miRNA data is proposed. Due to the variety of cancers and high number of genes, analyzing the miRNA dataset has been a challenging problem for researchers. The number of features corresponding to the number of samples is high and the data suffer from being imbalanced. The feature selection method has been used to select features having more ability to distinguish classes and eliminating obscures features. Afterward, a Convolutional Neural Network (CNN) classifier for classification of cancer types is utilized, which employs a Genetic Algorithm to highlight optimized hyper-parameters of CNN. In order to make the process of classification by CNN faster, Graphics Processing Unit (GPU) is recommended for calculating the mathematic equation in a parallel way. The proposed method is tested on a real-world dataset with 8,129 patients, 29 different types of tumors, and 1,046 miRNA biomarkers, taken from The Cancer Genome Atlas (TCGA) database.

Keywords: cancer classification, feature selection, deep learning, genetic algorithm

Procedia PDF Downloads 112

Authors: Loulwah Bokhari, Jori Nazer, Hala Sultan

Abstract:

Nowadays, artificial intelligence (AI) is used as a foundation for many activities in modern computing applications at home, in vehicles, and in businesses. Many modern machines are built to carry out a specific activity or purpose. This is where the Amazon Alexa application comes in, as it is used as a virtual assistant. The purpose of this paper is to explore the use of Amazon Alexa among people and how it has improved and made simple daily tasks easier for many people. We gave our participants several questions regarding Amazon Alexa and if they had recently used or heard of it, as well as the different tasks it provides and whether it successfully satisfied their needs. Overall, we found that participants who have recently used Alexa have found it to be helpful in their daily tasks.

Keywords: artificial intelligence, Echo system, machine learning, feature for feature match

Procedia PDF Downloads 121

Authors: Hassan Eshkiki, Benjamin Mora

Abstract:

The Neighbor Migrating Generator is a simple and efficient approach to finding the closest potential neighbor(s) with a different label for a given instance and so without the need to calibrate any kernel settings at all. This allows determining and explaining the most important features that will influence an AI model. It can be used to either migrate a specific sample to the class decision boundary of the original model within a close neighborhood of that sample or identify global features that can help localising neighbor classes. The proposed technique works by minimizing a loss function that is divided into two components which are independently weighted according to three parameters α, β, and ω, α being self-adjusting. Results show that this approach is superior to past techniques when detecting the smallest changes in the feature space and may also point out issues in models like over-fitting.

Keywords: explainable AI, EX AI, feature importance, counterfactual explanations

Procedia PDF Downloads 195

Authors: Shamsundar Kulkarni

Abstract:

Video capturing by non-professionals will lead to unanticipated effects. Such as image distortion, image blurring etc. Hence, many researchers study such drawbacks to enhance the quality of videos. In this paper, an algorithm is proposed to stabilize jittery videos .A stable output video will be attained without the effect of jitter which is caused due to shaking of handheld camera during video recording. Firstly, salient points from each frame from the input video are identified and processed followed by optimizing and stabilize the video. Optimization includes the quality of the video stabilization. This method has shown good result in terms of stabilization and it discarded distortion from the output videos recorded in different circumstances.

Keywords: video stabilization, point feature matching, salient points, image quality measurement

Procedia PDF Downloads 313

Authors: Tamara Matevosyan

Abstract:

In this globalized world, intercultural communication is becoming essential for understanding communication among people, for developing understanding of cultures, to appreciate the opportunities and challenges that each culture presents to people. Moreover, it plays an important role in developing an ideal personification to understand different behaviors in different cultures. Native speakers assimilate sociolinguistic knowledge in natural conditions, while it is a great problem for language learners, and in this context feature films reveal cultural peculiarities and involve students in real communication. As we know nowadays the key role of language learning is the development of intercultural competence as communicating with someone from a different cultural background can be exciting and scary, frustrating and enlightening. Intercultural competence is important in FL learning classroom and here feature films can perform as essential tools to develop this competence and overcome the intercultural gap that foreign students face. Current proposal attempts to reveal the correlation of the given culture and language through feature films. To ensure qualified, well-organized and practical classes on Intercultural Communication for language learners a number of methods connected with movie watching have been implemented. All the pre-watching, while watching and post-watching methods and techniques are aimed at developing students’ communicative competence. The application of such activities as Climax, Role-play, Interactive Language, Daily Life helps to reveal and overcome mistakes of cultural and pragmatic character. All the above-mentioned activities are directed at the assimilation of the language vocabulary with special reference to the given culture. The study dwells into the essence of culture as one of the core concepts of intercultural communication. Sometimes culture is not a priority in the process of language learning which leads to further misunderstandings in real life communication. The application of various methods and techniques with feature films aims at developing students’ cultural competence, their understanding of norms and values of individual cultures. Thus, feature film activities will enable learners to enlarge their knowledge of the particular culture and develop a fundamental insight into intercultural communication.

Keywords: climax, intercultural competence, interactive language, role-play

Procedia PDF Downloads 346

Authors: Linhang Zhu, Hongyu Zhu, Jiahe Liu

Abstract:

This paper investigated a method of indoor real-time positioning and mapping based on the Manhattan world assumption. In indoor environments, relying solely on feature matching techniques or other geometric algorithms for sensor pose estimation inevitably resulted in cumulative errors, posing a significant challenge to indoor positioning. To address this issue, we adopt the Manhattan world hypothesis to optimize the camera pose algorithm based on feature matching, which improves the accuracy of camera pose estimation. A special processing method was applied to image data frames that conformed to the Manhattan world assumption. When similar data frames appeared subsequently, this could be used to eliminate drift in sensor pose estimation, thereby reducing cumulative errors in estimation and optimizing mapping and positioning. Through experimental verification, it is found that our method achieves high-precision real-time positioning in indoor environments and successfully generates maps of indoor environments. This provides effective technical support for applications such as indoor navigation and robot control.

Keywords: Manhattan world hypothesis, real-time positioning and mapping, feature matching, loopback detection

Procedia PDF Downloads 62

Authors: Gulsah Olgun, Ozgur Bozdag, Yildirim Ertutar

Abstract:

This paper mainly focuses on performance assessment of buildings by associating the damage level with the damage cost. For this purpose a methodology is explained and applied to the representative mid-rise concrete building residing in Izmir. In order to consider uncertainties in occurrence of earthquakes, the structural analyses are conducted for all possible earthquakes in the region through the hazard curve. By means of the analyses, probability of the structural response being in different limit states are obtained and used to calculate expected damage cost. The expected damage cost comprises diverse cost components related to earthquake such as cost of casualties, replacement or repair cost of building etc. In this study, inter-story drift is used as an effective response variable to associate expected damage cost with different damage levels. The structural analysis methods performed to obtain inter story drifts are response spectrum method as a linear one, accurate push-over and time history methods to demonstrate the nonlinear effects on loss estimation. Comparison of the results indicates that each method provides similar values of expected damage cost. To sum up, this paper explains an approach which enables to minimize the expected damage cost of buildings and relate performance level to damage cost.

Keywords: expected damage cost, limit states, loss estimation, performance based design

Procedia PDF Downloads 270

Authors: Ágoston Nagy

Abstract:

This paper introduces a method of using unsupervised machine learning to visualize the feature space of a dataset in 2D, in order to find most characteristic segments in the set. After dimension reduction, users can select clusters by manual drawing. Selected clusters are recorded into a data model that is used for later predictions, based on realtime data. Predictions are made with supervised learning, using Gesture Recognition Toolkit. The paper introduces two example applications: a semantic audio organizer for analyzing incoming sounds, and a gesture database organizer where gestural data (recorded by a Leap motion) is visualized for further manipulation.

Keywords: gesture recognition, machine learning, real-time interaction, visualization

Procedia PDF Downloads 354

Authors: Mila Fantinelli

Abstract:

Cairo is the perfect modern representation of a living hell between rising temperatures and failing architecture. The works of Egyptian writer Mohamed Makhzangi may prove to add more depth to the debate that surrounds the topic of pollution in Arab literature. This Egyptian writer, who studied medicine and psychiatry before dedicating his life to writing, sheds indeed further light on the ecological condition of Cairo. In relation to this, the short story “The breeze hunter” (2018) tackles the topic of “environmental architecture”, citing the research of Hassan Fathy in “Architecture for the Poor: An Experiment in Rural Egypt” which provides examples from history of inventions to counter the effects of the hot weather. Specifically, the main character of the story is a man living in Cairo in a small apartment, which turns into a living hell in the summer season because of the high temperatures. Catastrophic urban planning, therefore, prevents the mitigation of the torrid climate but rather worsens it. Makhzangi indeed refers to the environmental issue of pollution caused by the excessive number of air conditioners, which transform Cairo into an infernal island of heat while our country becomes warmer with the passing of time. His description of the city already intersects ecocriticism and environmental issues, tackling the topic of pollution inside of cities and the impact of climate change, of which Cairo is a perfect example. History has indeed provided ways in order to reduce the heat inside houses. Yet, these have all been ignored. As a result, through the teachings of Hassan Fathy, the narrator of the story builds an opening in the house to catch the natural breeze coming from the north. He, therefore, becomes the breeze hunter of Mansoura. However, polluted waves interrupt this brief rest, thus leading to a worsening of his conditions, leading to him suffering from the effects of crowding and the consequences of climate change and pollution. Makhzangi, therefore, reflects on how architecture and urbanism affect the psychological sanity of people and how the situation is worsened by the catastrophic consequences of climate change and pollution.

Keywords: ecocriticism, Arabic literature, pollution, environmental architecture, crowding

Procedia PDF Downloads 27

Authors: N. F. Hanna, A. M. Haridy

Abstract:

One of the main drawbacks of the Modal Pushover Analysis (MPA) is the need to perform nonlinear time-history analysis, which complicates the analysis method and time. A simplified version of the MPA has been proposed based on the concept of the inelastic deformation ratio. Furthermore, the effect of the higher modes of vibration is considered by assuming linearly-elastic responses, which enables the use of standard elastic response spectrum analysis. In this thesis, the simplified MPA (SMPA) method is applied to determine the target global drift and the inter-story drifts of steel frame building. The effect of the higher vibration modes is considered within the framework of the SMPA. A comprehensive survey about the inelastic deformation ratio is presented. After that, a suitable expression from literature is selected for the inelastic deformation ratio and then implemented in the SMPA. The estimated seismic demands using the SMPA, such as target drift, base shear, and the inter-story drifts, are compared with the seismic responses determined by applying the standard MPA. The accuracy of the estimated seismic demands is validated by comparing with the results obtained by the nonlinear time-history analysis using real earthquake records.

Keywords: modal analysis, pushover analysis, seismic performance, target displacement

Procedia PDF Downloads 361

Authors: Muhammad Usman, Munir Ahmed

Abstract:

The demand of high-rise buildings has grown fast during the past decades. The design of these buildings by using RC core wall have been widespread nowadays in many countries. The RC core wall (RCCW) buildings encompasses central core wall and boundary columns joined through post tension slab at different floor levels. The core wall often provides greater stiffness as compared to the collective stiffness of the boundary columns. Hence, the core wall dominantly resists lateral loading i.e. wind or earthquake load. Non-linear response history analysis (NLRHA) procedure is the finest seismic design procedure of the times for designing high-rise buildings. The modern design tools for nonlinear response history analysis and performance based design has provided more confidence to design these structures for high-rise buildings. NLRHA requires selection and scaling of ground motions to match design spectrum for site specific conditions. Designers use several techniques for scaling ground motion records (time series). Time domain and frequency domain scaling are most commonly used which comprises their own benefits and drawbacks. Due to lengthy process of NLRHA, application of only one technique is conceivable. To the best of author’s knowledge, no consensus on the best procedures for the selection and scaling of the ground motions is available in literature. This research aims to provide the finest ground motion scaling technique specifically for designing 40 story high-rise RCCW buildings. Seismic response of 40 story RCCW building is checked by applying both the frequency domain and time domain scaling. Variable sites are selected in three critical seismic zones of Pakistan. The results indicates that there is extensive variation in seismic response of building for these scaling. There is still a need to build a consensus on the subjected research by investigating variable sites and buildings heights.

Keywords: 40-storied RC core wall building, nonlinear response history analysis, ground motions, time domain scaling, frequency domain scaling

Procedia PDF Downloads 132

Authors: T. L. Granzyk, S. Scarborough, J. DeCosmo

Abstract:

The use of health-related or medical narratives has gained increasing anecdotal and research-based support as a successful device for changing health behavior and outcomes. These narratives, in the form of oral storytelling, short films, and educational documentaries, for example, are most effective when including empathetic characters that transport viewers into the story and command both their attention and emotional response. This case study outlines how and why one large health system created a short narrative film for their internal Sepsis Awareness campaign, which told the dramatic story of a patient recovering from a missed sepsis diagnosis, leaving her a quad-amputee. Results include positive global anecdotal response to the film from healthcare professionals and patients, as well as use of the film to support legislation, ultimately passed in favor of the formation of Sepsis Awareness Workgroups in Maryland. Authors conclude that narrative films can be used successfully to initiate healthcare legislation and to increase internal and external awareness of health-related areas in need of greater improvement and support. As such, healthcare leaders and stakeholders would benefit from learning how to intentionally create, cultivate, and curate narratives from within their own health systems that elicit an empathetic response.

Keywords: healthcare policy, healthcare narratives, sepsis awareness, short films

Procedia PDF Downloads 103

Authors: Steffy Maria Joseph, Abdu Rahiman V, Abdul Hameed K. M.

Abstract:

Online handwritten character recognition is a challenging field in Artificial Intelligence. The classification success rate of current techniques decreases when the dataset involves similarity and complexity in stroke styles, number of strokes and stroke characteristics variations. Malayalam is a complex south indian language spoken by about 35 million people especially in Kerala and Lakshadweep islands. In this paper, we consider the significant feature extraction for the similar stroke styles of Malayalam. This extracted feature set are suitable for the recognition of other handwritten south indian languages like Tamil, Telugu and Kannada. A classification scheme based on support vector machines (SVM) is proposed to improve the accuracy in classification and recognition of online malayalam handwritten characters. SVM Classifiers are the best for real world applications. The contribution of various features towards the accuracy in recognition is analysed. Performance for different kernels of SVM are also studied. A graphical user interface has developed for reading and displaying the character. Different writing styles are taken for each of the 44 alphabets. Various features are extracted and used for classification after the preprocessing of input data samples. Highest recognition accuracy of 97% is obtained experimentally at the best feature combination with polynomial kernel in SVM.

Keywords: SVM, matlab, malayalam, South Indian scripts, onlinehandwritten character recognition

Procedia PDF Downloads 576

Authors: K. S. Parlak, E. Turan

Abstract:

The separation of marbles according to the pattern quality is a process made according to expert decision. The classification phase is the most critical part in terms of economic value. In this study, a self-learning system is proposed which performs the classification of marbles quickly and with high success. This system performs ten feature extraction by taking ten marble images from the camera. The marbles are classified by decision tree method using the obtained properties. The user forms the training set by training the system at the marble classification stage. The system evolves itself in every marble image that is classified. The aim of the proposed system is to minimize the error caused by the person performing the classification and achieve it quickly.

Keywords: decision tree, feature extraction, k-means clustering, marble classification

Procedia PDF Downloads 383

Authors: Fateme Montazeri

Abstract:

Literary approaches towards the text of the Quran predate the modern period. Suyuti (d.1505)’s encyclopedia of Quranic sciences, Al-Itqan, provides a notable example. In the modern era, the study of the Quranic rhetorics received particular attention in the second half of the twentieth century by Egyptian scholars. Amin Al-Khouli (d. 1966), who might be considered the first to argue for the necessity of applying a literary-rhetorical lens toward the tafseer, Islamic exegesis, and his students championed the literary analysis as the most effective approach to the comprehension of the holy text. Western scholars continued the literary criticism of the Islamic scripture by applying to the Quran similar methodologies used in biblical studies. In the history of the literary examination of the Quran, the scope of the critical methods applied to the Quranic text has been limited. For, the rhetorical approaches to the Quran, in the premodern as well as the modern period, concerned almost exclusively with the lexical layer of the text, leaving the narratological dimensions insufficiently examined. Recent contributions, by Leyla Ozgur Alhassen, for instance, attempt to fill this lacunae. This paper aims at advancing the studies of the Quranic narratives by investigating the application of a literary device whose role in the Quranic stories remains unstudied, that is, “foreshadowing.” This paper shall focus on Chapter 12, “Surah al-Yusuf,” as its case study. Chapter 12, the single chapter that includes the story of Joseph in one piece, contains several instances in which the events of the story are foreshadowed. As shall be discussed, foreshadowing occurs either through a monolog or dialogue whereby one or more of the characters allude to the future happenings or through the manner in which the setting is described. Through a close reading of the text, it will be demonstrated that the usage of the rhetorical tool of foreshadowing meets a dual purpose: on the one hand, foreshadowing prepares the reader/audience for the upcoming events in the plot, and on the other hand, it highlights the psychological dimensions of the characters, their thoughts, intentions, and disposition. In analyzing the story, this study shall draw on psychoanalytical criticism to explore the layers of meanings embedded in the Quranic narrative that are unfolded through foreshadowing.

Keywords: foreshadowing, quranic narrative, literary criticism, surah yusuf

Procedia PDF Downloads 155

Authors: R. Dimitri Halley

Abstract:

The research within Jungian Psychology presented here is on the wave state of Self. What has been discovered via shared dreaming, independently correlating dreams across dreamers, is beyond the Self stage into the deepest layer or the wave state Self: the very quantum ocean, the Self archetype is embedded in. A quantum wave or rhyming of meaning constituting synergy across several dreamers was discovered in dreams and in extensively shared dream work with small groups at a post therapy stage. Within the format of shared dreaming, we find synergy patterns beyond what Jung called the Self archetype. Jung led us up to the phase of Individuation and delivered the baton to Von Franz to work out the next synchronistic stage, here proposed as the finding of the quantum patterns making up the wave state of Self. These enfolded synchronistic patterns have been found in group format of shared dreaming of individuals approximating individuation, and the unfolding of it is carried by belief and faith. The reason for this format and operating system is because beyond therapy and of living reality, we find no science – no thinking or even awareness in the therapeutic sense – but rather a state of mental processing resembling more like that of spiritual attitude. Thinking as such is linear and cannot contain the deepest layer of Self, the quantum core of the human being. It is self reflection which is the container for the process at the wave state of Self. Observation locks us in an outside-in reactive flow from a first-person perspective and hence toward the surface we see to believe, whereas here, the direction of focus shifts to inside out/intrinsic. The operating system or language at the wave level of Self is thus belief and synchronicity. Belief has up to now been almost the sole province of organized religions but was viewed by Jung as an inherent property in the process of Individuation. The shared dreaming stage of the synchronistic patterns forms a larger story constituting a deep connectivity unfolding around individual Selves. Dreams of independent dreamers form larger patterns that come together as puzzles forming a larger story, and in this sense, this group work level builds on Jung as a post individuation collective stage. Shared dream correlations will be presented, illustrating a larger story in terms of trails of shared synchronicity.

Keywords: belief, shared dreaming, synchronistic patterns, wave state of self

Procedia PDF Downloads 196

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 298

Authors: Lee Jeong Min, Lee Mi Hee, Eo Yang Dam

Abstract:

Geospatial feature extraction is a very important issue in the remote sensing research. In the meantime, the image classification based on statistical techniques, but, in recent years, data mining and machine learning techniques for automated image processing technology is being applied to remote sensing it has focused on improved results generated possibility. In this study, artificial neural network and decision tree technique is applied to classify the high-resolution satellite images, as compared to the MLC processing result is a statistical technique and an analysis of the pros and cons between each of the techniques.

Keywords: remote sensing, artificial neural network, decision tree, maximum likelihood classification

Procedia PDF Downloads 347

Authors: Annalakshmi G., Sakthivel Murugan S.

Abstract:

This paper presents a local directional encoded derivative binary pattern (LDEDBP) feature extraction method that can be applied for the classification of submarine coral reef images. The classification of coral reef images using texture features is difficult due to the dissimilarities in class samples. In coral reef image classification, texture features are extracted using the proposed method called local directional encoded derivative binary pattern (LDEDBP). The proposed approach extracts the complete structural arrangement of the local region using local binary batten (LBP) and also extracts the edge information using local directional pattern (LDP) from the edge response available in a particular region, thereby achieving extra discriminative feature value. Typically the LDP extracts the edge details in all eight directions. The process of integrating edge responses along with the local binary pattern achieves a more robust texture descriptor than the other descriptors used in texture feature extraction methods. Finally, the proposed technique is applied to an extreme learning machine (ELM) method with a meta-heuristic algorithm known as weighted distance grey wolf optimizer (GWO) to optimize the input weight and biases of single-hidden-layer feed-forward neural networks (SLFN). In the empirical results, ELM-WDGWO demonstrated their better performance in terms of accuracy on all coral datasets, namely RSMAS, EILAT, EILAT2, and MLC, compared with other state-of-the-art algorithms. The proposed method achieves the highest overall classification accuracy of 94% compared to the other state of art methods.

Keywords: feature extraction, local directional pattern, ELM classifier, GWO optimization

Procedia PDF Downloads 164

Authors: Boukerch Haroun, Luo Qing Sheng, Li Hua Shi, Boukraa Sebti

Abstract:

In this paper we present the design and the implementation of a target tracking system where the target is set to be a moving person in a video sequence. The system can be applied easily as a vision system for mobile robot. The system is composed of two major parts the first is the detection of the person in the video frame using the SVM learning machine based on the “HOG” descriptors. The second part is the tracking of a moving person it’s done by using a combination of the Kalman filter and a modified version of the Camshift tracking algorithm by adding the target motion feature to the color feature, the experimental results had shown that the new algorithm had overcame the traditional Camshift algorithm in robustness and in case of occlusion.

Keywords: camshift algorithm, computer vision, Kalman filter, object tracking

Procedia PDF Downloads 448

Authors: Galih Permana, Yuskar Lase

Abstract:

In recent years, damping device has been experimentally studied to replace diagonally reinforced coupling beams, to mitigate rebar congestion problem. This study focuses on evaluating the effectiveness of various damping devices in a high-rise building. The type of damping devices evaluated is Viscoelastic Damper (VCD) and Rotational Friction Damper (RFD), with study case of a 15-story reinforced concrete apartment building with a dual system (column-beam and shear walls). The analysis used is a nonlinear time history analysis with 11 pairs of ground motions matched to the Indonesian response spectrum based on ASCE 41-17 and ASCE 7-16. In this analysis, each damper will be varied with a different position, namely the first model, the damper will be installed on the entire floor and in the second model, the damper will be installed on the 5th floor to the 9th floor, which is the floor with the largest drift. The results show that the model using both dampers increases the level of structural performance both globally and locally in the building, which will reduce the level of damage to the structural elements. But between the two dampers, the coupling beam that uses RFD is more effective than using VCD in improving building performance. The damper on the coupling beam has a good role in dissipating earthquakes and also in terms of ease of installation.

Keywords: building, coupling beam, damper, nonlinear time history analysis

Procedia PDF Downloads 172

Authors: Vishnu Satya

Abstract:

Rural communities form the backbone of our society. These communities are self-contained, for the most part, in how they can sustain themselves. Except for the essentials, they are primarily dependent on the state for their development and prosperity. The state claims to provide these through policies and agencies which are designed to guide their livelihood and future. It is assumed that the state-run policies are effective and are reaching the intended audience. Though in reality, there is an ever-widening gap between the two. The interviews conducted with farmers suggests that the support provided by the state to this marginalized community falls far short of their expectations, leaving them helpless. This paper discusses the methods used in bringing the status quo of the marginalized farmers to the forefront by comparing-and-contrasting the existing rhetoric and reality of the rural diaspora. It is seen from the hands-on oral accounts of farmers that they are left hanging between the state and their farms. Unrepresented, this community's progress and future stand severely affected. The paper presents how the visual medium acts as a catalyst for social advocacy by bridging the gap between administrative services and the marginalized rural communities. The finding was that there exists a disconnect between policymakers and the farming community, which has hindered the progress of the farmers. These two communities live exclusively from each other. In conclusion, it is seen that when the gaps between administrators and farmers are plugged through grass-root efforts utilizing visual medium, the farmer's economic situation got better, and the community prospered.

Keywords: farmers, social advocacy, marginalized, story telling

Procedia PDF Downloads 153

Authors: R. R. Ramsheeja, R. Sreeraj

Abstract:

For view the internal structures of the human body such as liver, brain, kidney etc have a wide range of different modalities for medical images are provided nowadays. Computer Tomography is one of the most significant medical image modalities. In this paper use CT liver images for study the use of automatic computer aided techniques to calculate the volume of the liver tumor. Segmentation method is used for the detection of tumor from the CT scan is proposed. Gaussian filter is used for denoising the liver image and Adaptive Thresholding algorithm is used for segmentation. Multiple Region Of Interest(ROI) based method that may help to characteristic the feature different. It provides a significant impact on classification performance. Due to the characteristic of liver tumor lesion, inherent difficulties appear selective. For a better performance, a novel proposed system is introduced. Multiple ROI based feature selection and classification are performed. In order to obtain of relevant features for Support Vector Machine(SVM) classifier is important for better generalization performance. The proposed system helps to improve the better classification performance, reason in which we can see a significant reduction of features is used. The diagnosis of liver cancer from the computer tomography images is very difficult in nature. Early detection of liver tumor is very helpful to save the human life.

Keywords: computed tomography (CT), multiple region of interest(ROI), feature values, segmentation, SVM classification

Procedia PDF Downloads 509

Authors: Ben Soltane Cheima, Ittansa Yonas Kelbesa

Abstract:

Speaker Identification (SI) is the task of establishing identity of an individual based on his/her voice characteristics. The SI task is typically achieved by two-stage signal processing: training and testing. The training process calculates speaker specific feature parameters from the speech and generates speaker models accordingly. In the testing phase, speech samples from unknown speakers are compared with the models and classified. Even though performance of speaker identification systems has improved due to recent advances in speech processing techniques, there is still need of improvement. In this paper, a Closed-Set Tex-Independent Speaker Identification System (CISI) based on a Multiple Classifier System (MCS) is proposed, using Mel Frequency Cepstrum Coefficient (MFCC) as feature extraction and suitable combination of vector quantization (VQ) and Gaussian Mixture Model (GMM) together with Expectation Maximization algorithm (EM) for speaker modeling. The use of Voice Activity Detector (VAD) with a hybrid approach based on Short Time Energy (STE) and Statistical Modeling of Background Noise in the pre-processing step of the feature extraction yields a better and more robust automatic speaker identification system. Also investigation of Linde-Buzo-Gray (LBG) clustering algorithm for initialization of GMM, for estimating the underlying parameters, in the EM step improved the convergence rate and systems performance. It also uses relative index as confidence measures in case of contradiction in identification process by GMM and VQ as well. Simulation results carried out on voxforge.org speech database using MATLAB highlight the efficacy of the proposed method compared to earlier work.

Keywords: feature extraction, speaker modeling, feature matching, Mel frequency cepstrum coefficient (MFCC), Gaussian mixture model (GMM), vector quantization (VQ), Linde-Buzo-Gray (LBG), expectation maximization (EM), pre-processing, voice activity detection (VAD), short time energy (STE), background noise statistical modeling, closed-set tex-independent speaker identification system (CISI)

Procedia PDF Downloads 309

Authors: Cara DiGirolamo

Abstract:

In his 2017 Ph.D. thesis, script doctor David Baboulene presented a theory of fiction in which differences in the knowledge states between participants in a literary experience, including reader, author, and characters, create many story elements, among them suspense, expectations, subtext, theme, metaphor, and allegory. This theory can be adjusted and modeled by incorporating a formal pragmatic approach that understands narrative as a speech act with a conversational function. This approach requires both the Speaker and the Listener to be understood as participants in the discourse. It also uses theories of cooperativity and the QUD to identify the existence of implicit questions. This approach predicts that what an effective literary narrative must do: provide a conversational context early in the story so the reader can engage with the text as a conversational participant. In addition, this model incorporates schema theory. Schema theory is a cognitive model for learning and processing information about the world and transforming it into functional knowledge. Using this approach can extend the QUD model. Instead of describing conversation as a form of information gathering restricted to question-answer sets, the QUD can include knowledge modeling and understanding as a possible outcome of a conversation. With this model, Baboulene’s “Knowledge Gaps” can provide real insight into storytelling as a conversational move, and extend the QUD to be able to simply and effectively apply to a more diverse set of conversational interactions and also to narrative texts.

Keywords: literature, speech acts, QUD, literary theory

Procedia PDF Downloads 18

Authors: Linghui Meng, James Atlas, Deborah Munro

Abstract:

There is an increasing demand for prosthetics capable of mimicking natural limb movements and hand gestures, but precise movement control of prosthetics using only electrode signals continues to be challenging. This study considers the implementation of machine learning as a means of improving accuracy and presents an initial investigation into hand gesture recognition using models based on electromyographic (EMG) signals. EMG signals, which capture muscle activity, are used as inputs to machine learning algorithms to improve prosthetic control accuracy, functionality and adaptivity. Using logistic regression, a machine learning classifier, this study evaluates the accuracy of classifying two hand gestures from the publicly available Ninapro dataset using two-time series feature extraction algorithms: Time Series Feature Extraction (TSFE) and Convolutional Neural Networks (CNNs). Trials were conducted using varying numbers of EMG channels from one to eight to determine the impact of channel quantity on classification accuracy. The results suggest that although both algorithms can successfully distinguish between hand gesture EMG signals, CNNs outperform TSFE in extracting useful information for both accuracy and computational efficiency. In addition, although more channels of EMG signals provide more useful information, they also require more complex and computationally intensive feature extractors and consequently do not perform as well as lower numbers of channels. The findings also underscore the potential of machine learning techniques in developing more effective and adaptive prosthetic control systems.

Keywords: EMG, machine learning, prosthetic control, electromyographic prosthetics, hand gesture classification, CNN, computational neural networks, TSFE, time series feature extraction, channel count, logistic regression, ninapro, classifiers

Procedia PDF Downloads 38

Authors: Fatima Akhmedova, Simon Liao

Abstract:

One of the most critical decision points in the design of a face recognition system is the choice of an appropriate face representation. Effective feature descriptors are expected to convey sufficient, invariant and non-redundant facial information. In this work, we propose a set of Hahn moments as a new approach for feature description. Hahn moments have been widely used in image analysis due to their invariance, non-redundancy and the ability to extract features either globally and locally. To assess the applicability of Hahn moments to Face Recognition we conduct two experiments on the Olivetti Research Laboratory (ORL) database and University of Notre-Dame (UND) X1 biometric collection. Fusion of the global features along with the features from local facial regions are used as an input for the conventional k-NN classifier. The method reaches an accuracy of 93% of correctly recognized subjects for the ORL database and 94% for the UND database.

Keywords: face recognition, Hahn moments, recognition-by-parts, time-lapse

Procedia PDF Downloads 377

Authors: Jeff Chak-Fu Wong, Tony Chun Yin Yip

Abstract:

The transition from secondary school to university seems exciting for many first-year students but can be more challenging than expected. Enabling instructors to know students’ learning habits and styles enhances their understanding of the students’ learning backgrounds, allows teachers to provide better support for their students, and has therefore high potential to improve teaching quality and learning, especially in any mathematics-related courses. The aim of this research is to collect students’ data using online surveys, to analyze students’ factors using learning analytics and educational data mining and to discover the characteristics of the students at risk of falling behind in their studies based on students’ previous academic backgrounds and collected data. In this paper, we use correlation-based distance methods and mutual information for measuring student factor relationships. We then develop a factor network using the Minimum Spanning Tree method and consider further study for analyzing the topological properties of these networks using social network analysis tools. Under the framework of mutual information, two graph-based feature filtering methods, i.e., unsupervised and supervised infinite feature selection algorithms, are used to analyze the results for students’ data to rank and select the appropriate subsets of features and yield effective results in identifying the factors affecting students at risk of failing. This discovered knowledge may help students as well as instructors enhance educational quality by finding out possible under-performers at the beginning of the first semester and applying more special attention to them in order to help in their learning process and improve their learning outcomes.

Keywords: students' academic performance, correlation-based distance method, social network analysis, feature selection, graph-based feature filtering method

Procedia PDF Downloads 130