Search results for: SURF features

Authors: Xiang Shijie, Zhou Dong, Tian Dan

Abstract:

Speaker recognition is a crucial task in the field of speech processing, aimed at identifying individuals based on their vocal characteristics. However, existing speaker recognition methods face numerous challenges. Traditional methods primarily rely on audio signals, which often suffer from limitations in noisy environments, variations in speaking style, and insufficient sample sizes. Additionally, relying solely on audio features can sometimes fail to capture the unique identity of the speaker comprehensively, impacting recognition accuracy. To address these issues, we propose a multi-modal network architecture that simultaneously processes both audio and text signals. By gradually integrating audio and text features, we leverage the strengths of both modalities to enhance the robustness and accuracy of speaker recognition. Our experiments demonstrate significant improvements with this multi-modal approach, particularly in complex environments, where recognition performance has been notably enhanced. Our research not only highlights the limitations of current speaker recognition methods but also showcases the effectiveness of multi-modal fusion techniques in overcoming these limitations, providing valuable insights for future research.

Keywords: feature fusion, memory network, multimodal input, speaker recognition

Procedia PDF Downloads 39

Authors: Kenan Saatcioglu, Fatma Koc

Abstract:

When the immigration is considered, it has been found that communities were continuously influenced by the immigrations from the date of the emergence of mankind until the day. The political, social and economic reasons seen at the various periods caused the communities go to new places from where they have lived before. Immigrations have occurred as a result of unequal opportunities among communities, social exclusion and imposition, compulsory homeland emerging politically, exile and war. Immigration is a social tool that is defined as a geographical relocation of people from a housing unit (city, village etc.) to another to spend all or part of their future lives. Immigrations have an effect on the history of humanity directly or indirectly, revealing new dimensions for communities to evaluate the concept of homeland. With these immigrations, communities carried their cultural values to their new settlements leading to a new interaction process. With this interaction process both migrant and native community cultures were reshaped and richer cultural values emerged. The clothes of these communities are amongst the most important visual evidence of this rich cultural interaction. As a result of these immigrations, communities affected each other culture’s clothing mutually and they started adding features of other cultures to the garments of its own, resulting new clothing cultures in time. The cultural and historical differences between these communities are seem to be the most influential factors of keeping the clothing cultures of the people alive. The most important and tragic of these immigrations took place after the Turkish War of Independence that was fought against Greece in 1922. The concept of forced immigration was a result of Lausanne Peace Treaty, which was signed between Turkish and Greek governments on 30th January 1923. As a result Greek Orthodoxes, who lived in Turkey (Anatolia and Thrace) and Muslim Turks, who lived in Greece were forced to immigrate. In this study, clothing features of Greek Orthodox woman immigrants who emigrated from Turkey to Greece in the period of the ‘1923 Greek-Turkish Population Exchange’ are aimed to be examined. In the study using the descriptive research method, before the ‘1923 Greek-Turkish Population Exchange’, the clothings belong to Greek Orthodox woman immigrants who lived in ‘Konya (Iconium)’ region in the Ottoman Empire, are discussed. In the study that is based on two different clothings belonging to ‘Konya (Iconium)’ region in the clothing collection archive at the ‘National Historical Museum’ in Greece, clothings of the Greek Orthodox woman immigrants are discussed with cultural norms, beliefs, values as well as in terms of form, ornamentation and dressing styles. Technical drawings are provided demonstrating formal features of the clothing parts that formed clothing integrity and their properties are described with the use of related literature in this study. This study is of importance that that it contains Greek Orthodox refugees’ clothings that are found in the clothing collection archive at the ‘National Historical Museum’ in Greece reflecting the cultural identities, providing information and documentation on the clothing features of the ‘1923 Greek-Turkish Population Exchange’.

Keywords: clothing, Greece, Greek Orthodoxes, immigration, national historical museum, Turkey

Procedia PDF Downloads 250

Authors: Eyal Boers

Abstract:

This paper shall demonstrate how films can offer a valuable and innovative approach to the study of images, stereotypes, and national identity. "Black Book" ("Zwartboek", 2006), a World War Two film directed by Paul Verhoeven, tells the story of Rachel Stein, a young Jewish woman who becomes a member of a resistance group in the Netherlands. The main hypothesis in this paper maintains that Rachel's character possesses both features of the Dutch prototype (a white, secular, sexual, freedom-loving individualist who seems "Dutch" enough to be accepted into a Dutch resistance group and even infiltrate the local Nazi headquarters) and features which can be defined as specifically Jewish (a black-haired victim persecuted by the Nazis, transforming herself into a gentile, while remaining loyal to her fellow Jews and ultimately immigrating to Israel and becoming a Hebrew teacher in a Kibbutz). Finally, this paper claims that Rachel's "Dutchness" is symptomatic of Dutch nostalgia in the 21st century for the Jews as "others" who blend into dominant Dutch culture, while Rachel's "Jewish Otherness" reflects a transnational identity – one that is always shifting and traverses cultural and national boundaries. In this sense, a film about Dutch Jews in the Second World War reflects on issues of identity in the 21st Century.

Keywords: Dutch, film, stereotypes, identity

Procedia PDF Downloads 128

Authors: B. Farahani, R. Fadil, A. Aboonabi, B. Hoffmann, J. Loscheider, K. Tavakolian, S. Arzanpour

Abstract:

Wheelchair users spend long hours in a sitting position, and selecting the right cushion is highly critical in preventing pressure ulcers in that demographic. Pressure mapping systems (PMS) are typically used in clinical settings by therapists to identify the sitting profile and pressure points in the sitting area to select the cushion that fits the best for the users. A PMS is a flexible mat composed of arrays of distributed networks of flexible sensors. The output of the PMS systems is a color-coded image that shows the intensity of the pressure concentration. Therapists use the PMS images to compare different cushions fit for each user. This process is highly subjective and requires good visual memory for the best outcome. This paper aims to develop an image processing technique to analyze the images of PMS and provide an objective measure to assess the cushions based on their pressure distribution mappings. In this paper, we first reviewed the skeletal anatomy of the human sitting area and its relation to the PMS image. This knowledge is then used to identify the important features that must be considered in image processing. We then developed an algorithm based on those features to analyze the images and rank them according to their fit to the users' needs.

Keywords: dynamic cushion, image processing, pressure mapping system, wheelchair

Procedia PDF Downloads 171

Authors: Abe Degale D., Cheng Jian

Abstract:

When creating automated video surveillance systems, violent action recognition is crucial. In recent years, hand-crafted feature detectors have been the primary method for achieving violence detection, such as the recognition of fighting activity. Researchers have also looked into learning-based representational models. On benchmark datasets created especially for the detection of violent sequences in sports and movies, these methods produced good accuracy results. The Hockey dataset's videos with surveillance camera motion present challenges for these algorithms for learning discriminating features. Image recognition and human activity detection challenges have shown success with deep representation-based methods. For the purpose of detecting violent images and identifying aggressive human behaviours, this research suggested a deep representation-based model using the transfer learning idea. The results show that the suggested approach outperforms state-of-the-art accuracy levels by learning the most discriminating features, attaining 99.34% and 99.98% accuracy levels on the Hockey and Movies datasets, respectively.

Keywords: violence detection, faster RCNN, transfer learning and, surveillance video

Procedia PDF Downloads 109

Authors: Elia Favarelli, Enrico Testi, Andrea Giorgetti

Abstract:

Autonomous structural health monitoring (SHM) of many structures and bridges became a topic of paramount importance for maintenance purposes and safety reasons. This paper proposes a set of machine learning (ML) tools to perform automatic feature selection and detection of anomalies in a bridge from vibrational data and compare different feature extraction schemes to increase the accuracy and reduce the amount of data collected. As a case study, the Z-24 bridge is considered because of the extensive database of accelerometric data in both standard and damaged conditions. The proposed framework starts from the first four fundamental frequencies extracted through operational modal analysis (OMA) and clustering, followed by density-based time-domain filtering (tracking). The fundamental frequencies extracted are then fed to a dimensionality reduction block implemented through two different approaches: feature selection (intelligent multiplexer) that tries to estimate the most reliable frequencies based on the evaluation of some statistical features (i.e., mean value, variance, kurtosis), and feature extraction (auto-associative neural network (ANN)) that combine the fundamental frequencies to extract new damage sensitive features in a low dimensional feature space. Finally, one class classifier (OCC) algorithms perform anomaly detection, trained with standard condition points, and tested with normal and anomaly ones. In particular, a new anomaly detector strategy is proposed, namely one class classifier neural network two (OCCNN2), which exploit the classification capability of standard classifiers in an anomaly detection problem, finding the standard class (the boundary of the features space in normal operating conditions) through a two-step approach: coarse and fine boundary estimation. The coarse estimation uses classics OCC techniques, while the fine estimation is performed through a feedforward neural network (NN) trained that exploits the boundaries estimated in the coarse step. The detection algorithms vare then compared with known methods based on principal component analysis (PCA), kernel principal component analysis (KPCA), and auto-associative neural network (ANN). In many cases, the proposed solution increases the performance with respect to the standard OCC algorithms in terms of F1 score and accuracy. In particular, by evaluating the correct features, the anomaly can be detected with accuracy and an F1 score greater than 96% with the proposed method.

Keywords: anomaly detection, frequencies selection, modal analysis, neural network, sensor network, structural health monitoring, vibration measurement

Procedia PDF Downloads 124

Authors: Kay Thinzar Phu, Lwin Lwin Oo

Abstract:

In an intelligent transport system and advanced driver assistance system, the developing of real-time traffic sign detection and recognition (TSDR) system plays an important part in recent research field. There are many challenges for developing real-time TSDR system due to motion artifacts, variable lighting and weather conditions and situations of traffic signs. Researchers have already proposed various methods to minimize the challenges problem. The aim of the proposed research is to develop an efficient and effective TSDR in real time. This system proposes an adaptive thresholding method based on RGB color for traffic signs detection and new features for traffic signs recognition. In this system, the RGB color thresholding is used to detect the blue and yellow color traffic signs regions. The system performs the shape identify to decide whether the output candidate region is traffic sign or not. Lastly, new features such as termination points, bifurcation points, and 90’ angles are extracted from validated image. This system uses Myanmar Traffic Sign dataset.

Keywords: adaptive thresholding based on RGB color, blue color detection, feature extraction, yellow color detection

Procedia PDF Downloads 313

Authors: Parisa Golbayani, Dan Wang, Ionut¸ Florescu

Abstract:

In this work we implement machine learning techniques to financial statement reports in order to asses company’s credit rating. Specifically, the work analyzes the performance of four neural network architectures (MLP, CNN, CNN2D, LSTM) in predicting corporate credit rating as issued by Standard and Poor’s. The paper focuses on companies from the energy, financial, and healthcare sectors in the US. The goal of this analysis is to improve application of machine learning algorithms to credit assessment. To accomplish this, the study investigates three questions. First, we investigate if the algorithms perform better when using a selected subset of important features or whether better performance is obtained by allowing the algorithms to select features themselves. Second, we address the temporal aspect inherent in financial data and study whether it is important for the results obtained by a machine learning algorithm. Third, we aim to answer if one of the four particular neural network architectures considered consistently outperforms the others, and if so under which conditions. This work frames the problem as several case studies to answer these questions and analyze the results using ANOVA and multiple comparison testing procedures.

Keywords: convolutional neural network, long short term memory, multilayer perceptron, credit rating

Procedia PDF Downloads 236

Authors: Akeel Noori Al-Mulla Hwaish

Abstract:

The environmental impact, economics, social and cultural factors, and the processes by which people define history and meaning had influenced the dynamic shape and character of the traditional Islamic Arabic city. Therefore, in regard to the period when Islam was at its peak (7th- 13th Centuries), Islamic city wasn’t the highly dynamited at the scale of buildings and city planning that demonstrates a distinguished city as an ‘Islamic’ as appeared after centuries when the function of the buildings and their particular arrangement and planning scheme in relation to one another that defined an Islamic city character. The architectural features of the urban fabric of the traditional Arabic Islamic city are a ‎reflection of the spiritual, social, and cultural characteristics of the people. It is a ‎combination of Islamic values ‘Din’ and life needs ‘Dunia’ as Prophet Muhammad built the first Mosque in ‎Madinah in the 1st year of his migration to it, then the Suq or market on 2nd of Hijrah, attached to ‎the mosque to signify the birth of a new Muslims community which considers both, ‎‎’Din’ and ‘Dunia’ and initiated nucleus for what which called after that as an ‘Islamic’ city. This research will discuss the main characteristics and components of the traditional Arab cities and demonstrate the impact of the Islamic values on shaping the planning layout and general built environment features of the early traditional Arab cities.

Keywords: urban, Islamic, Arabic, city

Procedia PDF Downloads 201

Authors: Ajitesh Pal, Arpan Datta Roy, H. K. Pratihari

Abstract:

The different illegal firearms crudely made by skilled gunsmith from scrap materials are popularly known as country made firearms. Such firearms along with improvised ammunition are clandestinely marketed at the cheaper price without any license to the extremist group, criminal, poachers and firearm lovers. As per National Crime Records Bureau (NCRB), MHA, Govt of India about 80% firearm cases are committed by country made/improvised firearms. The ballistic division of the laboratory has examined a good number of cases. The analysis of firearm cases received for forensic examination revealed that 7.65mm calibre pistols mostly improvised firearm are commonly used in firearm related crime cases. In the present communication, physical parameters and other characteristics features of some 7.65mm calibre pistols have been discussed in detail. The detailed study on country made (CM) firearm will help to prepare a database related to type of material used, origin of the raw material and tools used for inscription. The study also includes to establish the chemistry of propellants & head stamp pattern. The database will be helpful to the firearm examiners, researchers, students pursuing study on forensic science as reference material.

Keywords: improvised pistol, stringent gun law, working mechanism, parameters, database

Procedia PDF Downloads 71

Authors: Ebenezer O. Olaniyi, Oyebade K. Oyedotun, Khashman Adnan

Abstract:

In the food industry high quality production is required within a limited time to meet up with the demand in the society. In this research work, we have developed a model which can be used to replace the human operator due to their low output in production and slow in making decisions as a result of an individual differences in deciding the defective and healthy banana. This model can perform the vision attributes of human operators in deciding if the banana is defective or healthy for food production based. This research work is divided into two phase, the first phase is the image processing where several image processing techniques such as colour conversion, edge detection, thresholding and morphological operation were employed to extract features for training and testing the network in the second phase. These features extracted in the first phase were used in the second phase; the classification system phase where the multilayer perceptron using backpropagation neural network was employed to train the network. After the network has learned and converges, the network was tested with feedforward neural network to determine the performance of the network. From this experiment, a recognition rate of 97% was obtained and the time taken for this experiment was limited which makes the system accurate for use in the food industry.

Keywords: banana, food processing, identification system, neural network

Procedia PDF Downloads 471

Authors: Sanjay Saraf

Abstract:

The oral cavity can be the site for early manifestations of mucocutaneous disorders (MD) or the only site for occurrence of these disorders. It can also exhibit oral lesions with simultaneous associated skin lesions. The MD involving the oral mucosa commonly presents with signs such as ulcers, vesicles and bullae. The unique environment of the oral cavity may modify these signs of the disease, thereby making the clinical diagnosis an arduous task. In addition to the unique environment of oral cavity, the overlapping of the signs of various mucocutaneous disorders, also makes the clinical diagnosis more intricate. The aim of this review is to present the oral signs of dermatological disorders having common oral involvement and emphasize their importance in early detection of the systemic disorders. The aim is also to highlight the necessity of oral examination by a dermatologist while examining the skin lesions. Prior to the oral examination, it must be imperative for the dermatologists and the dental clinicians to have the knowledge of oral anatomy. It is also important to know the impact of various diseases on oral mucosa, and the characteristic features of various oral mucocutaneous lesions. An initial clinical oral examination is may help in the early diagnosis of the MD. Failure to identify the oral manifestations may reduce the likelihood of early treatment and lead to more serious problems. This paper reviews the oral manifestations of immune mediated dermatological disorders with common oral manifestations.

Keywords: dermatological investigations, genodermatosis, histological features, oral examination

Procedia PDF Downloads 358

Authors: A. Baqqal, O. Abduhamid, H. Abdul-Hameed, T. Messager, G. Ayoub

Abstract:

In this contribution, the effect of crystal content on the cyclic response of semi-crystalline polyethylene is studied over a large strain range. Experimental observations on a high-density polyethylene with 72% crystal content and an ultralow density polyethylene with 15% crystal content are reported. The cyclic stretching does appear a thermoplastic-like response for high crystallinity and an elastomeric-like response for low crystallinity, both characterized by a stress-softening, a hysteresis and a residual strain, whose amount depends on the crystallinity and the applied strain. Based on the experimental observations, a unified viscoelastic-viscoplastic constitutive model capturing the polyethylene cyclic response features is proposed. A two-phase representation of the polyethylene microstructure allows taking into consideration the effective contribution of the crystalline and amorphous phases to the intermolecular resistance to deformation which is coupled, to capture the strain hardening, to a resistance to molecular orientation. The polyethylene cyclic response features are captured by introducing evolution laws for the model parameters affected by the microstructure alteration due to the cyclic stretching.

Keywords: cyclic loading unloading, polyethylene, semi-crystalline polymer, viscoelastic-viscoplastic constitutive model

Procedia PDF Downloads 224

Authors: Fatma El-Zahraa El-Taher, Ayman Taha, Jane Courtney, Susan Mckeever

Abstract:

Understanding road networks plays an important role in navigation applications such as self-driving vehicles and route planning for individual journeys. Intersections of roads are essential components of road networks. Understanding the features of an intersection, from a simple T-junction to larger multi-road junctions, is critical to decisions such as crossing roads or selecting the safest routes. The identification and profiling of intersections from satellite images is a challenging task. While deep learning approaches offer the state-of-the-art in image classification and detection, the availability of training datasets is a bottleneck in this approach. In this paper, a labelled satellite image dataset for the intersection recognition problem is presented. It consists of 14,692 satellite images of Washington DC, USA. To support other users of the dataset, an automated download and labelling script is provided for dataset replication. The challenges of construction and fine-grained feature labelling of a satellite image dataset is examined, including the issue of how to address features that are spread across multiple images. Finally, the accuracy of the detection of intersections in satellite images is evaluated.

Keywords: satellite images, remote sensing images, data acquisition, autonomous vehicles

Procedia PDF Downloads 147

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: Ning Kang, Marius Doornenbal

Abstract:

Funding is a very important – if not crucial – resource for research projects. Usually, funding organizations will publish a description of the funded research to describe the scope of the funding award. Logically, we would expect research outcomes to align with this funding award. For that reason, we might be able to predict future research topics based on present funding award data. That said, it remains to be shown if and how future research topics can be predicted by using the funding information. In this paper, we extract funding project information and their generated paper abstracts from the Gateway to Research database as a group, and use the papers from the same domains and publication years in the Scopus database as a baseline comparison group. We annotate both the project awards and the papers resulting from the funded projects with linguistic features (noun phrases), and then calculate tf-idf and cosine similarity between these two set of features. We show that the cosine similarity between the project-generated papers group is bigger than the project-baseline group, and also that these two groups of similarities are significantly different. Based on this result, we conclude that the funding information actually correlates with the content of future research output for the funded project on the topical level. How funding really changes the course of science or of scientific careers remains an elusive question.

Keywords: natural language processing, noun phrase, tf-idf, cosine similarity

Procedia PDF Downloads 246

Authors: Ting-Yu Hsu, Shyu-Yu Wu, Shieh-Kung Huang, Hung-Wei Chiang, Kung-Chun Lu, Pei-Yang Lin, Kuo-Liang Wen

Abstract:

Regional earthquake early warning (EEW) systems are not suitable for Taiwan, as most destructive seismic hazards arise due to in-land earthquakes. These likely cause the lead-time provided by regional EEW systems before a destructive earthquake wave arrives to become null. On the other hand, an on-site EEW system can provide more lead-time at a region closer to an epicenter, since only seismic information of the target site is required. Instead of leveraging the information of several stations, the on-site system extracts some P-wave features from the first few seconds of vertical ground acceleration of a single station and performs a prediction of the oncoming earthquake intensity at the same station according to these features. Since seismometers could be triggered by non-earthquake events such as a passing of a truck or other human activities, to reduce the likelihood of false alarms, a seismometer was installed at three different locations on the same site and the performance of the EEW system for these three sensor locations were discussed. The results show that the location on the ground of the first floor of a school building maybe a good choice, since the false alarms could be reduced and the cost for installation and maintenance is the lowest.

Keywords: earthquake early warning, on-site, seismometer location, support vector machine

Procedia PDF Downloads 244

Authors: Ghada Badr, Arwa Alturki

Abstract:

The biological function of an RNA molecule depends on its structure. The objective of the alignment is finding the homology between two or more RNA secondary structures. Knowing the common functionalities between two RNA structures allows a better understanding and a discovery of other relationships between them. Besides, identifying non-coding RNAs -that is not translated into a protein- is a popular application in which RNA structural alignment is the first step A few methods for RNA structure-to-structure alignment have been developed. Most of these methods are partial structure-to-structure, sequence-to-structure, or structure-to-sequence alignment. Less attention is given in the literature to the use of efficient RNA structure representation and the structure-to-structure alignment methods are lacking. In this paper, we introduce an O(N2) Component-based Pairwise RNA Structure Alignment (CompPSA) algorithm, where structures are given as a component-based representation and where N is the maximum number of components in the two structures. The proposed algorithm compares the two RNA secondary structures based on their weighted component features rather than on their base-pair details. Extensive experiments are conducted illustrating the efficiency of the CompPSA algorithm when compared to other approaches and on different real and simulated datasets. The CompPSA algorithm shows an accurate similarity measure between components. The algorithm gives the flexibility for the user to align the two RNA structures based on their weighted features (position, full length, and/or stem length). Moreover, the algorithm proves scalability and efficiency in time and memory performance.

Keywords: alignment, RNA secondary structure, pairwise, component-based, data mining

Procedia PDF Downloads 459

Authors: Mariana Panayotova-Pencheva, Anetka Trifonova, Vassilena Dakova

Abstract:

790 lungs from brown hares (Lepus europeus L.) from different regions of Bulgaria were investigated during the period 2009-2017. The parasitological status and pathomorphological features in the lungs were recorded. The following parasite species were established: one nematode - Protostrongylus tauricus (7.59% prevalence), one tapeworm – larva of Taenia pisiformis – Cysticercus pisiformis (3.04% prevalence) and one arthropod – larva of Linguatula serrata – Pentastomum dentatum (0.89% prevalence). Macroscopic lesions in the lungs were different depending on the causative agents. The infections with C. pisiformis and P. dentatum were attended with small, mainly superficial changes in the lungs. Protostrongylid infections were connected with different in appearance and burden macroscopic changes. In 77.7%, they were nodular, and in the rest of cases, they diffuse. The consistency of the lesions was compact. In most of the cases, alterations were grey in colour, rarely were dark-red or marble-like. In 91.7% of these cases, they were spread on the apical parts of large lung lobes. In 36.7% middle parts of the large lung lobes, and, in 26.7% small lung lobes, were also affected. The small lung lobes were never independently infected.

Keywords: Cysticercus pisiformis, Lepus europeus, lung lesions, Pentastomum dentatum, Protostrongylus tauricus

Procedia PDF Downloads 214

Authors: Merve Begum Terzi, Orhan Arikan, Adnan Abaci, Mustafa Candemir

Abstract:

Acute myocardial infarction is a major cause of death in the world. Therefore, its fast and reliable diagnosis is a major clinical need. ECG is the most important diagnostic methodology which is used to make decisions about the management of the cardiovascular diseases. In patients with acute myocardial ischemia, temporary chest pains together with changes in ST segment and T wave of ECG occur shortly before the start of myocardial infarction. In this study, a technique which detects changes in ST/T sections of ECG is developed for the early diagnosis of acute myocardial ischemia. For this purpose, a database of real ECG recordings that contains a set of records from 75 patients presenting symptoms of chest pain who underwent elective percutaneous coronary intervention (PCI) is constituted. 12-lead ECG’s of the patients were recorded before and during the PCI procedure. Two ECG epochs, which are the pre-inflation ECG which is acquired before any catheter insertion and the occlusion ECG which is acquired during balloon inflation, are analyzed for each patient. By using pre-inflation and occlusion recordings, ECG features that are critical in the detection of acute myocardial ischemia are identified and the most discriminative features for the detection of acute myocardial ischemia are extracted. A classification technique based on support vector machine (SVM) approach operating with linear and radial basis function (RBF) kernels to detect ischemic events by using ST-T derived joint features from non-ischemic and ischemic states of the patients is developed. The dataset is randomly divided into training and testing sets and the training set is used to optimize SVM hyperparameters by using grid-search method and 10fold cross-validation. SVMs are designed specifically for each patient by tuning the kernel parameters in order to obtain the optimal classification performance results. As a result of implementing the developed classification technique to real ECG recordings, it is shown that the proposed technique provides highly reliable detections of the anomalies in ECG signals. Furthermore, to develop a detection technique that can be used in the absence of ECG recording obtained during healthy stage, the detection of acute myocardial ischemia based on ECG recordings of the patients obtained during ischemia is also investigated. For this purpose, a Gaussian mixture model (GMM) is used to represent the joint pdf of the most discriminating ECG features of myocardial ischemia. Then, a Neyman-Pearson type of approach is developed to provide detection of outliers that would correspond to acute myocardial ischemia. Neyman – Pearson decision strategy is used by computing the average log likelihood values of ECG segments and comparing them with a range of different threshold values. For different discrimination threshold values and number of ECG segments, probability of detection and probability of false alarm values are computed, and the corresponding ROC curves are obtained. The results indicate that increasing number of ECG segments provide higher performance for GMM based classification. Moreover, the comparison between the performances of SVM and GMM based classification showed that SVM provides higher classification performance results over ECG recordings of considerable number of patients.

Keywords: ECG classification, Gaussian mixture model, Neyman–Pearson approach, support vector machine

Procedia PDF Downloads 162

Authors: Michael N. O'Sullivan, Con Sheahan

Abstract:

Mass customization is the idea of offering custom products or services to satisfy the needs of each individual customer while maintaining the efficiency of mass production. Technologies like 3D printing and artificial intelligence have many start-ups hoping to capitalize on this dream of creating personalized products at an affordable price, and well established companies scrambling to innovate and maintain their market share. However, the majority of them are failing as they struggle to understand one key question – where does customization make sense? Customization and personalization only make sense where the value of the perceived benefit outweighs the cost to implement it. In other words, will people pay for it? Looking at the Kano Model makes it clear that it depends on the product. In products where customization is an inherent need, like prosthetics, mass customization technologies can be highly beneficial. However, for products that already sell as a standard, like headphones, offering customization is likely only an added bonus, and so the product development team must figure out if the customers’ perception of the added value of this feature will outweigh its premium price tag. This can be done through the use of a ‘serious game,’ whereby potential customers are given a limited budget to collaboratively buy and bid on potential features of the product before it is developed. If the group choose to buy customization over other features, then the product development team should implement it into their design. If not, the team should prioritize the features on which the customers have spent their budget. The level of customization purchased can also be translated to an appropriate production method, for example, the most expensive type of customization would likely be free-form design and could be achieved through digital fabrication, while a lower level could be achieved through short batch production. Twenty-five teams of final year students from design, engineering, construction and technology tested this methodology when bringing a product from concept through to production specification, and found that it allowed them to confidently decide what level of customization, if any, would be worth offering for their product, and what would be the best method of producing it. They also found that the discussion and negotiations between players during the game led to invaluable insights, and often decided to play a second game where they offered customers the option to buy the various customization ideas that had been discussed during the first game.

Keywords: Kano model, mass customization, new product development, serious game

Procedia PDF Downloads 136

Authors: Ebru Turgal, Beyza Doganay Erdogan

Abstract:

Machine learning aims to model the relationship between the response and features. Medical decision-making researchers would like to make decisions about patients’ course and treatment, by examining the repeated measurements over time. Boosting approach is now being used in machine learning area for these aims as an influential tool. The aim of this study is to show the usage of multivariate tree boosting in this field. The main reason for utilizing this approach in the field of decision-making is the ease solutions of complex relationships. To show how multivariate tree boosting method can be used to identify important features and feature-time interaction, we used the data, which was collected retrospectively from Ankara University Chest Diseases Department records. Dataset includes repeated PF ratio measurements. The follow-up time is planned for 120 hours. A set of different models is tested. In conclusion, main idea of classification with weighed combination of classifiers is a reliable method which was shown with simulations several times. Furthermore, time varying variables will be taken into consideration within this concept and it could be possible to make accurate decisions about regression and survival problems.

Keywords: boosted multivariate trees, longitudinal data, multivariate regression tree, panel data

Procedia PDF Downloads 203

Authors: Forouzan Salehi Fergeni

Abstract:

Converting the movement intents of a person into commands for action employing brain signals like electroencephalogram signals is a brain-computer interface (BCI) system. When left or right-hand motions are imagined, different patterns of brain activity appear, which can be employed as BCI signals for control. To make better the brain-computer interface (BCI) structures, effective and accurate techniques for increasing the classifying precision of motor imagery (MI) based on electroencephalography (EEG) are greatly needed. Subject dependency and non-stationary are two features of EEG signals. So, EEG signals must be effectively processed before being used in BCI applications. In the present study, after applying an 8 to 30 band-pass filter, a car spatial filter is rendered for the purpose of denoising, and then, a method of analysis of variance is used to select more appropriate and informative channels from a category of a large number of different channels. After ordering channels based on their efficiencies, a sequential forward channel selection is employed to choose just a few reliable ones. Features from two domains of time and wavelet are extracted and shortlisted with the help of a statistical technique, namely the t-test. Finally, the selected features are classified with different machine learning and neural network classifiers being k-nearest neighbor, Probabilistic neural network, support-vector-machine, Extreme learning machine, decision tree, Multi-layer perceptron, and linear discriminant analysis with the purpose of comparing their performance in this application. Utilizing a ten-fold cross-validation approach, tests are performed on a motor imagery dataset found in the BCI competition III. Outcomes demonstrated that the SVM classifier got the greatest classification precision of 97% when compared to the other available approaches. The entire investigative findings confirm that the suggested framework is reliable and computationally effective for the construction of BCI systems and surpasses the existing methods.

Keywords: brain-computer interface, channel selection, motor imagery, support-vector-machine

Procedia PDF Downloads 52

Authors: Duncan Wallace, M-Tahar Kechadi

Abstract:

In recent years, Machine Learning (ML) approaches have been successfully applied to an analysis of patient symptom data in the context of disease diagnosis, at least where such data is well codified. However, much of the data present in Electronic Health Records (EHR) are unlikely to prove suitable for classic ML approaches. Furthermore, as scores of data are widely spread across both hospitals and individuals, a decentralized, computationally scalable methodology is a priority. The focus of this paper is to develop a method to predict outliers in an out-of-hours healthcare provision center (OOHC). In particular, our research is based upon the early identification of patients who have underlying conditions which will cause them to repeatedly require medical attention. OOHC act as an ad-hoc delivery of triage and treatment, where interactions occur without recourse to a full medical history of the patient in question. Medical histories, relating to patients contacting an OOHC, may reside in several distinct EHR systems in multiple hospitals or surgeries, which are unavailable to the OOHC in question. As such, although a local solution is optimal for this problem, it follows that the data under investigation is incomplete, heterogeneous, and comprised mostly of noisy textual notes compiled during routine OOHC activities. Through the use of Deep Learning methodologies, the aim of this paper is to provide the means to identify patient cases, upon initial contact, which are likely to relate to such outliers. To this end, we compare the performance of Long Short-Term Memory, Gated Recurrent Units, and combinations of both with Convolutional Neural Networks. A further aim of this paper is to elucidate the discovery of such outliers by examining the exact terms which provide a strong indication of positive and negative case entries. While free-text is the principal data extracted from EHRs for classification, EHRs also contain normalized features. Although the specific demographical features treated within our corpus are relatively limited in scope, we examine whether it is beneficial to include such features among the inputs to our neural network, or whether these features are more successfully exploited in conjunction with a different form of a classifier. In this section, we compare the performance of randomly generated regression trees and support vector machines and determine the extent to which our classification program can be improved upon by using either of these machine learning approaches in conjunction with the output of our Recurrent Neural Network application. The output of our neural network is also used to help determine the most significant lexemes present within the corpus for determining high-risk patients. By combining the confidence of our classification program in relation to lexemes within true positive and true negative cases, with an inverse document frequency of the lexemes related to these cases, we can determine what features act as the primary indicators of frequent-attender and non-frequent-attender cases, providing a human interpretable appreciation of how our program classifies cases.

Keywords: artificial neural networks, data-mining, machine learning, medical informatics

Procedia PDF Downloads 132

Authors: Zelalem Fantahun

Abstract:

Part-of-speech tagging is the process of assigning a part-of-speech or other lexical class marker to each word into naturally occurring text. Part-of-speech tagging is the most fundamental and basic task almost in all natural language processing. In natural language processing, the problem of providing large amount of manually annotated data is a knowledge acquisition bottleneck. Since, Amharic is one of under-resourced language, the availability of tagged corpus is the bottleneck problem for natural language processing especially for POS tagging. A promising direction to tackle this problem is to provide a system that does not require manually tagged data. In unsupervised learning, the learner is not provided with classifications. Unsupervised algorithms seek out similarity between pieces of data in order to determine whether they can be characterized as forming a group. This paper explicates the development of unsupervised part-of-speech tagger using K-Means clustering for Amharic language since large amount of data is produced in day-to-day activities. In the development of the tagger, the following procedures are followed. First, the unlabeled data (raw text) is divided into 10 folds and tokenization phase takes place; at this level, the raw text is chunked at sentence level and then into words. The second phase is feature extraction which includes word frequency, syntactic and morphological features of a word. The third phase is clustering. Among different clustering algorithms, K-means is selected and implemented in this study that brings group of similar words together. The fourth phase is mapping, which deals with looking at each cluster carefully and the most common tag is assigned to a group. This study finds out two features that are capable of distinguishing one part-of-speech from others these are morphological feature and positional information and show that it is possible to use unsupervised learning for Amharic POS tagging. In order to increase performance of the unsupervised part-of-speech tagger, there is a need to incorporate other features that are not included in this study, such as semantic related information. Finally, based on experimental result, the performance of the system achieves a maximum of 81% accuracy.

Keywords: POS tagging, Amharic, unsupervised learning, k-means

Procedia PDF Downloads 452

Authors: Kaushik Sathupadi, Sandesh Achar

Abstract:

Human action recognition modeling is a critical task in machine learning. These systems require better techniques for recognizing body parts and selecting optimal features based on vision sensors to identify complex action patterns efficiently. Still, there is a considerable gap and challenges between images and videos, such as brightness, motion variation, and random clutters. This paper proposes a robust approach for classifying human actions over cloud-based image data. First, we apply pre-processing and detection, human and outer shape detection techniques. Next, we extract valuable information in terms of cues. We extract two distinct features: fuzzy local binary patterns and sequence representation. Then, we applied a greedy, randomized adaptive search procedure for data optimization and dimension reduction, and for classification, we used a random forest. We tested our model on two benchmark datasets, AAMAZ and the KTH Multi-view football datasets. Our HMR framework significantly outperforms the other state-of-the-art approaches and achieves a better recognition rate of 91% and 89.6% over the AAMAZ and KTH multi-view football datasets, respectively.

Keywords: computer vision, human motion analysis, random forest, machine learning

Procedia PDF Downloads 41

Authors: Davoud Maleki, Neda Zamani

Abstract:

The present study aims at exploring the effective accountability model of Islamic Azad University using a qualitative approach of grounded theory. The data of this study were obtained from semi-structured interviews with 25 professors and scholars in Islamic Azad University of Tehran who were selected by theoretical sampling method. In the data analysis, the stepwise method and Strauss and Corbin analytical methods (1992) were used. After identification of the main component (balanced response to stakeholders’ needs) and using it to bring the categories together, expressions and ideas representing the relationships between the main and subcomponents, and finally, the revealed components were categorized into six dimensions of the paradigm model, with the relationships among them, including causal conditions (7 components), main component (balanced response to stakeholders’ needs), strategies (5 components), environmental conditions (5 components), intervention features (4 components), and consequences (3 components). Research findings show an exploratory model for describing the relationships between causal conditions, main components, accountability strategies, environmental conditions, university environmental features, and that consequences.

Keywords: accountability, effectiveness, Islamic Azad University, grounded theory

Procedia PDF Downloads 87

Authors: Manuela Nayantara Jeyaraj, Senuri Sucharitharathna, Chathurika Senarath, Yasanthy Kanagaraj, Indraka Udayakumara

Abstract:

PostgreSQL is an Object Relational Database Management System (ORDBMS) that has been in existence for a while. Despite the superior features that it wraps and packages to manage database and data, the database community has not fully realized the importance and advantages of PostgreSQL. Hence, this research tends to focus on provisioning a better environment of development for PostgreSQL in order to induce the utilization and elucidate the importance of PostgreSQL. PostgreSQL is also known to be the world’s most elementary SQL-compliant open source ORDBMS. But, users have not yet resolved to PostgreSQL due to the facts that it is still under the layers and the complexity of its persistent textual environment for an introductory user. Simply stating this, there is a dire need to explicate an easy way of making the users comprehend the procedure and standards with which databases are created, tables and the relationships among them, manipulating queries and their flow based on conditions in PostgreSQL to help the community resolve to PostgreSQL at an augmented rate. Hence, this research under development within the context tends to initially identify the dominant features provided by PostgreSQL over its competitors. Following the identified merits, an analysis on why the database community holds a hesitance in migrating to PostgreSQL’s environment will be carried out. These will be modulated and tailored based on the scope and the constraints discovered. The resultant of the research proposes a system that will serve as a designing platform as well as a learning tool that will provide an interactive method of learning via a visual editor mode and incorporate a textual editor for well-versed users. The study is based on conjuring viable solutions that analyze a user’s cognitive perception in comprehending human computer interfaces and the behavioural processing of design elements. By providing a visually draggable and manipulative environment to work with Postgresql databases and table queries, it is expected to highlight the elementary features displayed by Postgresql over any other existent systems in order to grasp and disseminate the importance and simplicity offered by this to a hesitant user.

Keywords: cognition, database, PostgreSQL, text-editor, visual-editor

Procedia PDF Downloads 284

Authors: Adrian-Gabriel Chifu, Sebastien Fournier

Abstract:

One of the challenges of natural language understanding is to deal with the subjectivity of sentences, which may express opinions and emotions that add layers of complexity and nuance. Sentiment analysis is a field that aims to extract and analyze these subjective elements from text, and it can be applied at different levels of granularity, such as document, paragraph, sentence, or aspect. Aspect-based sentiment analysis is a well-studied topic with many available data sets and models. However, there is no clear definition of what makes a sentence difficult for aspect-based sentiment analysis. In this paper, we explore this question by conducting an experiment with three data sets: ”Laptops”, ”Restaurants”, and ”MTSC” (Multi-Target-dependent Sentiment Classification), and a merged version of these three datasets. We study the impact of domain diversity and syntactic diversity on difficulty. We use a combination of classifiers to identify the most difficult sentences and analyze their characteristics. We employ two ways of defining sentence difficulty. The first one is binary and labels a sentence as difficult if the classifiers fail to correctly predict the sentiment polarity. The second one is a six-level scale based on how many of the top five best-performing classifiers can correctly predict the sentiment polarity. We also define 9 linguistic features that, combined, aim at estimating the difficulty at sentence level.

Keywords: sentiment analysis, difficulty, classification, machine learning

Procedia PDF Downloads 92

Authors: Prashansa Singh, Manjot Kaur, Rohit Bajaj

Abstract:

The proliferation of wireless sensor networks and Internet of Things (IoT) devices in the quickly changing digital landscape has highlighted the urgent need for strong security solutions that can handle these systems’ limited resources. A key solution to this problem is the emergence of ultralightweight security protocols, which provide strong security features while respecting the strict computational, energy, and memory constraints imposed on these kinds of devices. This in-depth analysis explores the field of ultralightweight security protocols, offering a thorough examination of their evolution, salient features, and the particular security issues they resolve. We carefully examine and contrast different protocols, pointing out their advantages and disadvantages as well as the compromises between resource limitations and security resilience. We also study these protocols’ application domains, including the Internet of Things, RFID systems, and wireless sensor networks, to name a few. In addition, the review highlights recent developments and advancements in the field, pointing out new trends and possible avenues for future research. This paper aims to be a useful resource for researchers, practitioners, and developers, guiding the design and implementation of safe, effective, and scalable systems in the Internet of Things era by providing a comprehensive overview of ultralightweight security protocols.

Keywords: wireless sensor network, machine-to-machine, MQTT broker, server, ultralightweight, TCP/IP

Procedia PDF Downloads 84