Search results for: user classification accuracy

Authors: P. S. Jagadeesh Kumar, Yang Yung, Wenli Hu

Abstract:

Speech emotion classification is a dominant research field in finding a sturdy and profligate classifier appropriate for different real-life applications. This effort accentuates on classifying different emotions from speech signal quarried from the features related to pitch, formants, energy contours, jitter, shimmer, spectral, perceptual and temporal features. Tensor deep stacking neural networks were supported to examine the factors that influence the classification success rate. Facial electromyography signals were composed of several forms of focuses in a controlled atmosphere by means of audio-visual stimuli. Proficient facial electromyography signals were pre-processed using moving average filter, and a set of arithmetical features were excavated. Extracted features were mapped into consistent emotions using bilinear mapping. With facial electromyography signals, a database comprising diverse emotions will be exposed with a suitable fine-tuning of features and training data. A success rate of 92% can be attained deprived of increasing the system connivance and the computation time for sorting diverse emotional states.

Keywords: speech emotion classification, tensor deep stacking neural networks, facial electromyography, bilinear mapping, audio-visual stimuli

Procedia PDF Downloads 244

Authors: Naduni Ranasinghe

Abstract:

E-learning environments are getting more popular than any other due to the impact of COVID19. Even though e-learning is one of the best solutions for the teaching-learning process in the academic process, it’s not without major challenges. Nowadays, machine learning approaches are utilized in the analysis of how behavioral factors lead to better adoption and how they related to better performance of the students in eLearning environments. During the pandemic, we realized the academic process in the eLearning approach had a major issue, especially for the performance of the students. Therefore, an approach that investigates student behaviors in eLearning environments using a data-intensive machine learning approach is appreciated. A hybrid approach was used to understand how each previously told variables are related to the other. A more quantitative approach was used referred to literature to understand the weights of each factor for adoption and in terms of performance. The data set was collected from previously done research to help the training and testing process in ML. Special attention was made to incorporating different dimensionality of the data to understand the dependency levels of each. Five independent variables out of twelve variables were chosen based on their impact on the dependent variable, and by considering the descriptive statistics, out of three models developed (Random Forest classifier, SVM, and Decision tree classifier), random forest Classifier (Accuracy – 0.8542) gave the highest value for accuracy. Overall, this work met its goals of improving student performance by identifying students who are at-risk and dropout, emphasizing the necessity of using both static and dynamic data.

Keywords: academic performance prediction, e learning, learning analytics, machine learning, predictive model

Procedia PDF Downloads 143

Authors: Parisa Mansour

Abstract:

Cystic fibrosis (CF) is one of the most common autosomal recessive diseases among whites. It mostly affects the lungs, causing infections and inflammation that account for 90% of deaths in CF patients. Because of this high variability in clinical presentation and organ involvement, investigating treatment responses and evaluating lung changes over time is critical to preventing CF progression. High-resolution computed tomography (HRCT) greatly facilitates the assessment of lung disease progression in CF patients. Recently, artificial intelligence was used to analyze chest CT scans of CF patients. In this paper, we propose a convolutional neural network (CNN) approach to classify CF lung patterns in HRCT images. The proposed network consists of two convolutional layers with 3 × 3 kernels and maximally connected in each layer, followed by two dense layers with 1024 and 10 neurons, respectively. The softmax layer prepares a predicted output probability distribution between classes. This layer has three exits corresponding to the categories of normal (healthy), bronchitis and inflammation. To train and evaluate the network, we constructed a patch-based dataset extracted from more than 1100 lung HRCT slices obtained from 45 CF patients. Comparative evaluation showed the effectiveness of the proposed CNN compared to its close peers. Classification accuracy, average sensitivity and specificity of 93.64%, 93.47% and 96.61% were achieved, indicating the potential of CNNs in analyzing lung CF patterns and monitoring lung health. In addition, the visual features extracted by our proposed method can be useful for automatic measurement and finally evaluation of the severity of CF patterns in lung HRCT images.

Keywords: HRCT, CF, cystic fibrosis, chest CT, artificial intelligence

Procedia PDF Downloads 57

Authors: Byron Joseph A. Hallar, Annjeannette Alain D. Galang, Maria Visitacion N. Gumabay

Abstract:

The widespread adoption and increasing proliferation of smartphones that started during the first decade of the twenty-first century have enabled their users to communicate and access information in ways that were merely thought of as possibilities in the few years before the smartphone revolution. A product of the convergence of the cellular phone and portable computer, the smartphone provides an additional important function that used to be the exclusive domain of desktop-bound computers and portable computers: Web Browsing. For increasing numbers of users, the smartphone and allied devices such as tablet computers have become their first and often their only means of accessing the World Wide Web. This has led to the development of websites that cater to the needs of the new breed of smartphone-carrying web users. The smaller size of smartphones as compared with conventional computers has provided unique challenges to web interface designers. The smaller screen size and touchscreen interface have made it much more difficult to read and navigate through web pages that were in most part designed for traditional desktop and portable computers. Although increasing numbers of websites now provide an alternate website formatted for smartphones, problems with ease of use, reliability and usability still remain. This study focuses on the identification of the problems associated with smartphone web interfaces, the compliance with accepted standards of user-oriented web interface design, the strategies that could be utilized to ensure the design of user-centric web interfaces for smartphones, and the identification of the current trends and developments related to user-centric web interface design intended for the consumption of smartphone users.

Keywords: human-computer interaction, user-centered design, web interface, mobile, smartphone

Procedia PDF Downloads 342

Authors: Dmytro Zubov, Francesco Volponi

Abstract:

In this paper, D-Wave quantum computing Ising model is used for the forecasting of positive extremes of daily mean air temperature. Forecast models are designed with two to five qubits, which represent 2-, 3-, 4-, and 5-day historical data respectively. Ising model’s real-valued weights and dimensionless coefficients are calculated using daily mean air temperatures from 119 places around the world, as well as sea level (Aburatsu, Japan). In comparison with current methods, this approach is better suited to predict heat wave values because it does not require the estimation of a probability distribution from scarce observations. Proposed forecast quantum computing algorithm is simulated based on traditional computer architecture and combinatorial optimization of Ising model parameters for the Ronald Reagan Washington National Airport dataset with 1-day lead-time on learning sample (1975-2010 yr). Analysis of the forecast accuracy (ratio of successful predictions to total number of predictions) on the validation sample (2011-2014 yr) shows that Ising model with three qubits has 100 % accuracy, which is quite significant as compared to other methods. However, number of identified heat waves is small (only one out of nineteen in this case). Other models with 2, 4, and 5 qubits have 20 %, 3.8 %, and 3.8 % accuracy respectively. Presented three-qubit forecast model is applied for prediction of heat waves at other five locations: Aurel Vlaicu, Romania – accuracy is 28.6 %; Bratislava, Slovakia – accuracy is 21.7 %; Brussels, Belgium – accuracy is 33.3 %; Sofia, Bulgaria – accuracy is 50 %; Akhisar, Turkey – accuracy is 21.4 %. These predictions are not ideal, but not zeros. They can be used independently or together with other predictions generated by different method(s). The loss of human life, as well as environmental, economic, and material damage, from extreme air temperatures could be reduced if some of heat waves are predicted. Even a small success rate implies a large socio-economic benefit.

Keywords: heat wave, D-wave, forecast, Ising model, quantum computing

Procedia PDF Downloads 489

Authors: José A. Menezes, Giordano Cabral, Bruno T. Gomes

Abstract:

Choosing good features is an essential part of machine learning. Recent techniques aim to automate this process. For instance, feature learning intends to learn the transformation of raw data into a useful representation to machine learning tasks. In automatic audio classification tasks, this is interesting since the audio, usually complex information, needs to be transformed into a computationally convenient input to process. Another technique tries to generate features by searching a feature space. Genetic algorithms, for instance, have being used to generate audio features by combining or modifying them. We find this approach particularly interesting and, despite the undeniable advances of feature learning approaches, we wanted to take a step forward in the use of genetic algorithms to find audio features, combining them with more conventional methods, like PCA, and inserting search control mechanisms, such as constraints over a confusion matrix. This work presents the results obtained on particular audio classification problems.

Keywords: feature generation, feature learning, genetic algorithm, music information retrieval

Procedia PDF Downloads 425

Authors: Khin Mar Yee, Mu Mu Than, Kyi Lint, Aye Aye Oo, Chan Mya Hmway, Khin Zar Chi Winn

Abstract:

The dynamic changes of Land Use and Land Cover (LULC) changes in Yangon have generally resulted the improvement of human welfare and economic development since the last twenty years. Making map of LULC is crucially important for the sustainable development of the environment. However, the exactly data on how environmental factors influence the LULC situation at the various scales because the nature of the natural environment is naturally composed of non-homogeneous surface features, so the features in the satellite data also have the mixed pixels. The main objective of this study is to the calculation of accuracy based on change detection of LULC changes by Support Vector Machines (SVMs). For this research work, the main data was satellite images of 1996, 2006 and 2015. Computing change detection statistics use change detection statistics to compile a detailed tabulation of changes between two classification images and Support Vector Machines (SVMs) process was applied with a soft approach at allocation as well as at a testing stage and to higher accuracy. The results of this paper showed that vegetation and cultivated area were decreased (average total 29 % from 1996 to 2015) because of conversion to the replacing over double of the built up area (average total 30 % from 1996 to 2015). The error matrix and confidence limits led to the validation of the result for LULC mapping.

Keywords: land use and land cover change, change detection, image processing, support vector machines

Procedia PDF Downloads 121

Authors: Varun Agarwal

Abstract:

Introduction: With the advent of personalized medicine, histopathological review of whole slide images (WSIs) for cancer diagnosis presents an exceedingly time-consuming, complex task. Specifically, detecting metastatic regions in WSIs of sentinel lymph node biopsies necessitates a full-scanned, holistic evaluation of the image. Thus, digital pathology, low-level image manipulation algorithms, and machine learning provide significant advancements in improving the efficiency and accuracy of WSI analysis. Using Camelyon16 data, this paper proposes a deep learning pipeline to automate and ameliorate breast cancer metastasis localization and WSI classification. Methodology: The model broadly follows five stages -region of interest detection, WSI partitioning into image tiles, convolutional neural network (CNN) image-segment classifications, probabilistic mapping of tumor localizations, and further processing for whole WSI classification. Transfer learning is applied to the task, with the implementation of Inception-ResNetV2 - an effective CNN classifier that uses residual connections to enhance feature representation, adding convolved outputs in the inception unit to the proceeding input data. Moreover, in order to augment the performance of the transfer learning CNN, a stack of convolutional denoising autoencoders (CDAE) is applied to produce embeddings that enrich image representation. Through a saliency-detection algorithm, visual training segments are generated, which are then processed through a denoising autoencoder -primarily consisting of convolutional, leaky rectified linear unit, and batch normalization layers- and subsequently a contrast-normalization function. A spatial pyramid pooling algorithm extracts the key features from the processed image, creating a viable feature map for the CNN that minimizes spatial resolution and noise. Results and Conclusion: The simplified and effective architecture of the fine-tuned transfer learning Inception-ResNetV2 network enhanced with the CDAE stack yields state of the art performance in WSI classification and tumor localization, achieving AUC scores of 0.947 and 0.753, respectively. The convolutional feature retention and compilation with the residual connections to inception units synergized with the input denoising algorithm enable the pipeline to serve as an effective, efficient tool in the histopathological review of WSIs.

Keywords: breast cancer, convolutional neural networks, metastasis mapping, whole slide images

Procedia PDF Downloads 123

Authors: Ghazi Bouaziz, Abderrahim Derouiche, Damien Brulin, Hélène Pigot, Eric Campo

Abstract:

Automatic ADL classification is a crucial part of ambient assisted living technologies. It allows to monitor the daily life of the elderly and to detect any changes in their behavior that could be related to health problem. But detection of ADLs is a challenge, especially because each person has his/her own rhythm for performing them. Therefore, we used a correlation matrix to extract custom rules that enable to detect ADLs, including eating activity. Data collected from 3 different individuals between 35 and 105 days allows the extraction of personalized eating patterns. The comparison of the results of the process of eating activity extracted from the correlation matrices with the declarative data collected during the survey shows an accuracy of 90%.

Keywords: elderly monitoring, ADL identification, matrix correlation, meal-taking activity

Procedia PDF Downloads 86

Authors: Obokhai Kess Asikhia

Abstract:

This work explores design concept generation by understanding user needs through observation and interview. The aim is to examine several principles and guidelines in obtaining evidence from observing how users interact with the targeted product and interviewing them to acquire deep insights of their needs. With the help of Quality Function Deployment (QFD), the identified needs of the users while interacting with the product were ranked using the normalised weighting approach. Furthermore, a low fidelity prototype of the alarm clock is developed with a view of addressing the identified needs of the users. Finally, the low fidelity prototype design was evaluated with two design prototypes already existing in the market through a study involving 30 participants. Preliminary results reveal higher performance ratings by the majority of the participants of the new prototype compared to the other existing alarm clocks in the market used in the study.

Keywords: design concept, low fidelity prototype, normalised weighting approach, quality function deployment, user needs

Procedia PDF Downloads 175

Authors: Harpreet Singh

Abstract:

Finding relevant information on the World Wide Web is becoming highly challenging day by day. Web usage mining is used for the extraction of relevant and useful knowledge, such as user behaviour patterns, from web access log records. Web access log records all the requests for individual files that the users have requested from the website. Web usage mining is important for Customer Relationship Management (CRM), as it can ensure customer satisfaction as far as the interaction between the customer and the organization is concerned. Web usage mining is helpful in improving website structure or design as per the user’s requirement by analyzing the access log file of a website through a log analyzer tool. The focus of this paper is to enhance the accessibility and usability of a guitar selling web site by analyzing their access log through Deep Log Analyzer tool. The results show that the maximum number of users is from the United States and that they use Opera 9.8 web browser and the Windows XP operating system.

Keywords: web usage mining, web mining, log file, data mining, deep log analyzer

Procedia PDF Downloads 242

Authors: Malika Yaici, Assia Arab, Betitra Yakouben, Samia Zermani

Abstract:

Ubiquitous computing is nowadays a reality through the networking of a growing number of computing devices. It allows providing users with context aware information and services in a heterogeneous environment, anywhere and anytime. Selection of the best context-aware service, between many available services and providers, is a tedious problem. In this paper, a service selection method based on Constraint Satisfaction Problem (CSP) formalism is proposed. The services are considered as variables and domains; and the user context, preferences and providers characteristics are considered as constraints. The Backtrack algorithm is used to solve the problem to find the best service and provider which matches the user requirements. Even though this algorithm has an exponential complexity, but its use guarantees that the service, that best matches the user requirements, will be found. A comparison of the proposed method with the existing solutions finishes the paper.

Keywords: ubiquitous computing, services selection, constraint satisfaction problem, backtrack algorithm

Procedia PDF Downloads 232

Authors: Hui Zhang, Ye Tian, Fang Ye, Ziming Guo

Abstract:

Communication signal modulation recognition technology is one of the key technologies in the field of modern information warfare. At present, communication signal automatic modulation recognition methods are mainly divided into two major categories. One is the maximum likelihood hypothesis testing method based on decision theory, the other is a statistical pattern recognition method based on feature extraction. Now, the most commonly used is a statistical pattern recognition method, which includes feature extraction and classifier design. With the increasingly complex electromagnetic environment of communications, how to effectively extract the features of various signals at low signal-to-noise ratio (SNR) is a hot topic for scholars in various countries. To solve this problem, this paper proposes a feature extraction algorithm for the communication signal based on the improved Holder cloud feature. And the extreme learning machine (ELM) is used which aims at the problem of the real-time in the modern warfare to classify the extracted features. The algorithm extracts the digital features of the improved cloud model without deterministic information in a low SNR environment, and uses the improved cloud model to obtain more stable Holder cloud features and the performance of the algorithm is improved. This algorithm addresses the problem that a simple feature extraction algorithm based on Holder coefficient feature is difficult to recognize at low SNR, and it also has a better recognition accuracy. The results of simulations show that the approach in this paper still has a good classification result at low SNR, even when the SNR is -15dB, the recognition accuracy still reaches 76%.

Keywords: communication signal, feature extraction, Holder coefficient, improved cloud model

Procedia PDF Downloads 143

Authors: Devi Srinivas, K. Sindhuja

Abstract:

This paper presents architecture to improve surveillance applications based on the usage of the service oriented paradigm, with smart phones as user terminals, allowing application dynamic composition and increasing the flexibility of the system. According to the result of moving object detection research on video sequences, the movement of the people is tracked using video surveillance. The moving object is identified using the image subtraction method. The background image is subtracted from the foreground image, from that the moving object is derived. So the Background subtraction algorithm and the threshold value is calculated to find the moving image by using background subtraction algorithm the moving frame is identified. Then, by the threshold value the movement of the frame is identified and tracked. Hence, the movement of the object is identified accurately. This paper deals with low-cost intelligent mobile phone-based wireless video surveillance solution using moving object recognition technology. The proposed solution can be useful in various security systems and environmental surveillance. The fundamental rule of moving object detecting is given in the paper, then, a self-adaptive background representation that can update automatically and timely to adapt to the slow and slight changes of normal surroundings is detailed. While the subtraction of the present captured image and the background reaches a certain threshold, a moving object is measured to be in the current view, and the mobile phone will automatically notify the central control unit or the user through SMS (Short Message System). The main advantage of this system is when an unknown image is captured by the system it will alert the user automatically by sending an SMS to user’s mobile.

Keywords: security, graphical password, persuasive cued click points

Procedia PDF Downloads 527

Authors: Olena Kavats, Dmitry Khramov, Kateryna Sergieieva, Vladimir Vasyliev, Iurii Kavats

Abstract:

Geoinformation technologies of space agromonitoring are a means of operative decision making support in the tasks of managing the agricultural sector of the economy. Existing technologies use satellite images in the optical range of electromagnetic spectrum. Time series of optical images often contain gaps due to the presence of clouds and haze. A geoinformation technology is created. It allows to fill gaps in time series of optical images (Sentinel-2, Landsat-8, PROBA-V, MODIS) with radar survey data (Sentinel-1) and use information about agrometeorological conditions of the growing season for individual monitoring years. The technology allows to perform crop classification and mapping for spring-summer (winter and spring crops) and autumn-winter (winter crops) periods of vegetation, monitoring the dynamics of crop state seasonal changes, crop yield forecasting. Crop classification is based on supervised classification algorithms, takes into account the peculiarities of crop growth at different vegetation stages (dates of sowing, emergence, active vegetation, and harvesting) and agriculture land state characteristics (row spacing, seedling density, etc.). A catalog of samples of the main agricultural crops (Ukraine) is created and crop spectral signatures are calculated with the preliminary removal of row spacing, cloud cover, and cloud shadows in order to construct time series of crop growth characteristics. The obtained data is used in grain crop growth tracking and in timely detection of growth trends deviations from reference samples of a given crop for a selected date. Statistical models of crop yield forecast are created in the forms of linear and nonlinear interconnections between crop yield indicators and crop state characteristics (temperature, precipitation, vegetation indices, etc.). Predicted values of grain crop yield are evaluated with an accuracy up to 95%. The developed technology was used for agricultural areas monitoring in a number of Great Britain and Ukraine regions using EOS Crop Monitoring Platform (https://crop-monitoring.eos.com). The obtained results allow to conclude that joint use of Sentinel-1 and Sentinel-2 images improve separation of winter crops (rapeseed, wheat, barley) in the early stages of vegetation (October-December). It allows to separate successfully the soybean, corn, and sunflower sowing areas that are quite similar in their spectral characteristics.

Keywords: geoinformation technology, crop classification, crop yield prediction, agricultural monitoring, EOS Crop Monitoring Platform

Procedia PDF Downloads 440

Authors: Laxuman Thakuri

Abstract:

Community-based forest management is often glorified as one of the best forest management alternatives in the developing countries like Nepal. It is also believed that the transfer of forest management authorities to local communities is decisive to take efficient decisions, maximize the forest benefits and improve the people’s livelihood. The community forestry of Nepal also aims to maximize the forest benefits; share them among the user households and improve their livelihood. However, how the local communities fix the price of forest products and local pricing made by the forest user groups affects to equitable forest benefits-sharing among the user households and their livelihood improvement objectives, the answer is largely silent among the researchers and policy-makers alike. This study examines local pricing system of forest products in the lowland community forestry and its effects on equitable benefit-sharing and livelihood improvement objectives. The study discovered that forest user groups fixed the price of forest products based on three criteria: i) costs incur in harvesting, ii) office operation costs, and iii) livelihood improvement costs through community development and income generating activities. Since user households have heterogeneous socio-economic conditions, the forest user groups have been applied low pricing strategy even for high-value forest products that the access of socio-economically worse-off households can be increased. However, the results of forest products distribution showed that as a result of low pricing strategy the access of socio-economically better-off households has been increasing at higher rate than worse-off and an inequality situation has been created. Similarly, the low pricing strategy is also found defective to livelihood improvement objectives. The study suggests for revising the forest products pricing system in community forest management and reforming the community forestry policy as well.

Keywords: community forestry, forest products pricing, equitable benefit-sharing, livelihood improvement, Nepal

Procedia PDF Downloads 290

Authors: Patrick Santos, João Casal, João Santos Luis Varandas, Tiago Alves, Carlos Romeiro, Sérgio Lourenço

Abstract:

Nowadays, technology makes it possible to, in one hand, communicate with various objects of the daily life through the Internet, and in the other, put these objects interacting with each other through this channel. Simultaneously, with the raise of smartphones as the most ubiquitous technology on persons lives, emerge new agents for these devices - Intelligent Personal Assistants. These agents have the goal of helping the user manage and organize his information as well as supporting the user in his/her day-to-day tasks. Moreover, other emergent concept is the Cloud Computing, which allows computation and storage to get out of the users devices, bringing benefits in terms of performance, security, interoperability and others. Connecting these three paradigms, in this work we propose an architecture for an intelligent system which provides an interface that assists the user on smart environments, informing, suggesting actions and allowing to manage the objects of his/her daily life.

Keywords: internet of things, cloud, intelligent personal assistant, architecture

Procedia PDF Downloads 503

Authors: Sungkyung Kim, Jee-Hyeon Na, Dong-Seung Kwon

Abstract:

Future mobile networks following 5th generation will be characterized by one thousand times higher gains in capacity; connections for at least one hundred billion devices; user experience capable of extremely low latency and response times. To be close to the capacity requirements and higher reliability, advanced technologies have been studied, such as multiple connectivity, small cell enhancement, heterogeneous networking, and advanced interference and mobility management. This paper is focused on the multiple connectivity in heterogeneous cellular networks. We investigate the performance of coverage and user throughput in several deployment scenarios. Using the stochastic geometry approach, the SINR distributions and the coverage probabilities are derived in case of dual connection. Also, to compare the user throughput enhancement among the deployment scenarios, we calculate the spectral efficiency and discuss our results.

Keywords: heterogeneous networks, multiple connectivity, small cell enhancement, stochastic geometry

Procedia PDF Downloads 321

Authors: Anusha Konduru, Zhiyong Shan, Preethi Santhanam, Vinod Namboodiri, Rajiv Bagai

Abstract:

Mobile applications are increasing in a significant amount, each to address the requirements of many users. However, the quick developments and enhancements are resulting in many underlying defects. Android apps create and handle a large variety of 'instance' data that has to persist across runs, such as the current navigation route, workout results, antivirus settings, or game state. Due to the nature of Android, an app can be paused, sent into the background, or killed at any time. If the instance data is not saved and restored between runs, in addition to data loss, partially-saved or corrupted data can crash the app upon resume or restart. However, it is difficult for the programmer to manually test this issue for all the activities. This results in the issue of data loss that the data entered by the user are not saved when there is any interruption. This issue can degrade user experience because the user needs to reenter the information each time there is an interruption. Automated testing to detect such data loss is important to improve the user experience. This research proposes a tool, DroidDL, a data loss detector for Android, which detects the instance data loss from a given android application. We have tested 395 applications and found 12 applications with the issue of data loss. This approach is proved highly accurate and reliable to find the apps with this defect, which can be used by android developers to avoid such errors.

Keywords: Android, automated testing, activity, data loss

Procedia PDF Downloads 226

Authors: Ali Asheibi

Abstract:

The rapid increase in the size of databases required to store power quality monitoring data has demanded new techniques for analysing and understanding the data. One suggested technique to assist in analysis is data mining. Preparing raw data to be ready for data mining exploration take up most of the effort and time spent in the whole data mining process. Clustering is an important technique in data mining and machine learning in which underlying and meaningful groups of data are discovered. Large amounts of harmonic data have been collected from an actual harmonic monitoring system in a distribution system in Australia for three years. This amount of acquired data makes it difficult to identify operational events that significantly impact the harmonics generated on the system. In this paper, harmonic data preparation processes to better understanding of the data have been presented. Underlying classes in this data has then been identified using clustering technique based on the Minimum Message Length (MML) method. The underlying operational information contained within the clusters can be rapidly visualised by the engineers. The C5.0 algorithm was used for classification and interpretation of the generated clusters.

Keywords: data mining, harmonic data, clustering, classification

Procedia PDF Downloads 236

Authors: Shamatha Shetty, Sakshi Dhabadi, Prerana M., Indushree B.

Abstract:

About 66% of firms claim that insider attacks are more likely to happen. The frequency of insider incidents has increased by 47% in the last two years. The goal of this work is to prevent dangerous employee behavior by using keyloggers and the Machine Learning (ML) model. Every keystroke that the user enters is recorded by the keylogging program, also known as keystroke logging. Keyloggers are used to stop improper use of the system. This enables us to collect all textual data, save it in a CSV file, and analyze it using an ML algorithm and the VirusTotal API. Many large companies use it to methodically monitor how their employees use computers, the internet, and email. We are utilizing the SVM algorithm and the VirusTotal API to improve overall efficiency and accuracy in identifying specific patterns and words to automate and offer the report for improved monitoring.

Keywords: cyber security, machine learning, cyclic process, email notification

Procedia PDF Downloads 46

Authors: Budhvin T. Withana, Sulochana Rupasinghe

Abstract:

The educational system faces a significant concern with regards to Dyslexia and Dysgraphia, which are learning disabilities impacting reading and writing abilities. This is particularly challenging for children who speak the Sinhala language due to its complexity and uniqueness. Commonly used methods to detect the risk of Dyslexia and Dysgraphia rely on subjective assessments, leading to limited coverage and time-consuming processes. Consequently, delays in diagnoses and missed opportunities for early intervention can occur. To address this issue, the project developed a hybrid model that incorporates various deep learning techniques to detect the risk of Dyslexia and Dysgraphia. Specifically, Resnet50, VGG16, and YOLOv8 models were integrated to identify handwriting issues. The outputs of these models were then combined with other input data and fed into an MLP model. Hyperparameters of the MLP model were fine-tuned using Grid Search CV, enabling the identification of optimal values for the model. This approach proved to be highly effective in accurately predicting the risk of Dyslexia and Dysgraphia, providing a valuable tool for early detection and intervention. The Resnet50 model exhibited a training accuracy of 0.9804 and a validation accuracy of 0.9653. The VGG16 model achieved a training accuracy of 0.9991 and a validation accuracy of 0.9891. The MLP model demonstrated impressive results with a training accuracy of 0.99918, a testing accuracy of 0.99223, and a loss of 0.01371. These outcomes showcase the high accuracy achieved by the proposed hybrid model in predicting the risk of Dyslexia and Dysgraphia.

Keywords: neural networks, risk detection system, dyslexia, dysgraphia, deep learning, learning disabilities, data science

Procedia PDF Downloads 55

Authors: Wong Seng Yue

Abstract:

Game dynamics and game mechanics are the two main components that used in gamification to engage and encourage students to learn. The advantages of gamified classroom are engaging students, increasing students interest, preserving students focus and remain a positive behaviour. However, the empirical studies on gamification are still at early stage, especially the effectiveness of various gamification components have not been evaluated. Thus, this study is aimed to conduct a user experience (UX) evaluation on gamified classroom through Prezi, which focused on learning experience, gaming experience, adaptivity, and gameplay experience. This study is a further study extended from the previous exploratory study to explore more on UX of gamified classroom via Prezi by interview. A focus group study, which involves 22 students from a foundation course has been conducted for the study. Besides the empirical data from the previous study, this focus group study has significantly found that 90.9% respondents show their positive perceptions on gaming experience via Prezi. They are interested, feel fresh, good, and highly motivated of the contents of Prezi. 95.5% participants have had a positive learning experience from the gamified classroom via Prezi, which can engage them, made them concentrate on learning and easy to remember what they have learned if compared to the traditional classroom slides. The adaptivity of the gamified classroom also high due to its zooming user interface, narrative, rewards and engagement features. This study has uncovered on how far the impact of gamification components in the classroom, especially UX that implemented in gamified classroom.

Keywords: user experience (UX), gamification, gamified classroom, Prezi

Procedia PDF Downloads 201

Authors: Marta D'Onofrio

Abstract:

The debate on the digitalization of the economy has raised questions about how both labor and the regulation of work processes are changing due to the introduction of digital technologies in the productive system. Within the literature, the term ‘digital labor’ is commonly used to identify the impact of digitalization on labor. Despite the wide use of this term, it is still not available an unambiguous definition of it, and this could create confusion in the use of terminology and in the attempts of classification. As a consequence, the purpose of this paper is to provide for a definition and to propose a classification of ‘digital labor’, resorting to the theoretical approach of organizational studies.

Keywords: digital labor, digitalization, data-driven algorithms, big data, organizational studies

Procedia PDF Downloads 143

Authors: Jyotismita Talukdar

Abstract:

In this paper, a study has been made on the possibility and accuracy of early prediction of several Heart Disease using Artificial Neural Network. (ANN). The study has been made in both noise free environment and noisy environment. The data collected for this analysis are from five Hospitals. Around 1500 heart patient’s data has been collected and studied. The data is analysed and the results have been compared with the Doctor’s diagnosis. It is found that, in noise free environment, the accuracy varies from 74% to 92%and in noisy environment (2dB), the results of accuracy varies from 62% to 82%. In the present study, four basic attributes considered are Blood Pressure (BP), Fasting Blood Sugar (FBS), Thalach (THAL) and Cholesterol (CHOL.). It has been found that highest accuracy(93%), has been achieved in case of PPI( Post-Permanent-Pacemaker Implementation ), around 79% in case of CAD(Coronary Artery disease), 87% in DCM (Dilated Cardiomyopathy), 89% in case of RHD&MS(Rheumatic heart disease with Mitral Stenosis), 75 % in case of RBBB +LAFB (Right Bundle Branch Block + Left Anterior Fascicular Block), 72% for CHB(Complete Heart Block) etc. The lowest accuracy has been obtained in case of ICMP (Ischemic Cardiomyopathy), about 38% and AF( Atrial Fibrillation), about 60 to 62%.

Keywords: coronary heart disease, chronic stable angina, sick sinus syndrome, cardiovascular disease, cholesterol, Thalach

Procedia PDF Downloads 165

Authors: Wagneur Edouard

Abstract:

Tropical algebra is the algebra constructed over an idempotent semifield S. We show here that every m-dimensional tropical module M over S with strongly independent basis can be embedded into Sm, and provide an algebraic invariant -the Γ-matrix of M- which characterises the isomorphy class of M. The strong independence condition also yields a significant improvement to the Whitney embedding for tropical torsion modules published earlier We also show that the strong independence of the basis of M is equivalent to the unique representation of elements of M. Numerous examples illustrate our results.

Keywords: classification, idempotent semi-modules, strong independence, tropical algebra

Procedia PDF Downloads 365

Authors: Ananda Perera

Abstract:

Computer-Assisted Medical Evaluation of Symptoms (CAMEOS) is a medical expert system designed to help General Practices (GPs) make an accurate diagnosis. CAMEOS comprises a knowledge base, user input, inference engine, reasoning module, and output statement. The knowledge base was developed by the author. User input is an Html file. The physician user collects data in the consultation. Data is sent to the inference engine at servers. CAMEOS uses set theory to simulate diagnostic reasoning. The program output is a list of differential diagnoses, the most probable diagnosis, and the diagnostic reasoning.

Keywords: CDSS, computerized decision support systems, expert systems, general practice, diagnosis, diagnostic systems, primary care diagnostic system, artificial intelligence in medicine

Procedia PDF Downloads 144

Authors: Amirali Mahouti, Hooshang Katebi

Abstract:

Enlargement of Tabriz metropolis to the east and north-east caused urban construction to be built on Marl layers and because of increase in excavations depth, further information of this layer is inescapable. Looking at geotechnical investigation shows there is not enough information about Tabriz Marl and this soil has been classified only by color. Tabriz Marl is lacustrine carbonate sediment outcrops, surrounds eastern, northern and southern region of city in the East Azerbaijan Province of Iran and is known as bed rock of city under alluvium sediments. This investigation aims to characterize geotechnical parameters of this soil to identify and set it in classification system of carbonated soils. For this purpose, specimens obtained from 80 locations over the city and subjected to physical and mechanical tests, such as Atterberg limits, density, moisture content, unconfined compression, direct shear and consolidation. CaCO3 content, organic content, PH, XRD, XRF, TGA and geophysical downhole tests also have been done on some of them.

Keywords: carbonated soils, classification of soils, mineralogy, physical and mechanical tests for Marls, Tabriz Marl

Procedia PDF Downloads 310

Authors: Nicole Merkle, Stefan Zander

Abstract:

Ambient Assisted Living (AAL) describes a technological and methodological stack of (e.g. formal model-theoretic semantics, rule-based reasoning and machine learning), different aspects regarding the behavior, activities and characteristics of humans. Hence, a semantic representation of the user environment and its relevant elements are required in order to allow assistive agents to recognize situations and deduce appropriate actions. Furthermore, the user and his/her characteristics (e.g. physical, cognitive, preferences) need to be represented with a high degree of expressiveness in order to allow software agents a precise evaluation of the users’ context models. The correct interpretation of these context models highly depends on temporal, spatial circumstances as well as individual user preferences. In most AAL approaches, model representations of real world situations represent the current state of a universe of discourse at a given point in time by neglecting transitions between a set of states. However, the AAL domain currently lacks sufficient approaches that contemplate on the dynamic adaptions of context-related representations. Semantic representations of relevant real-world excerpts (e.g. user activities) help cognitive, rule-based agents to reason and make decisions in order to help users in appropriate tasks and situations. Furthermore, rules and reasoning on semantic models are not sufficient for handling uncertainty and fuzzy situations. A certain situation can require different (re-)actions in order to achieve the best results with respect to the user and his/her needs. But what is the best result? To answer this question, we need to consider that every smart agent requires to achieve an objective, but this objective is mostly defined by domain experts who can also fail in their estimation of what is desired by the user and what not. Hence, a smart agent has to be able to learn from context history data and estimate or predict what is most likely in certain contexts. Furthermore, different agents with contrary objectives can cause collisions as their actions influence the user’s context and constituting conditions in unintended or uncontrolled ways. We present an approach for dynamically updating a semantic model with respect to the current user context that allows flexibility of the software agents and enhances their conformance in order to improve the user experience. The presented approach adapts rules by learning sensor evidence and user actions using probabilistic reasoning approaches, based on given expert knowledge. The semantic domain model consists basically of device-, service- and user profile representations. In this paper, we present how this semantic domain model can be used in order to compute the probability of matching rules and actions. We apply this probability estimation to compare the current domain model representation with the computed one in order to adapt the formal semantic representation. Our approach aims at minimizing the likelihood of unintended interferences in order to eliminate conflicts and unpredictable side-effects by updating pre-defined expert knowledge according to the most probable context representation. This enables agents to adapt to dynamic changes in the environment which enhances the provision of adequate assistance and affects positively the user satisfaction.

Keywords: ambient intelligence, machine learning, semantic web, software agents

Procedia PDF Downloads 270

Authors: Deokho Kim, Wonwoo Lee, Jaewoong Lee, Teresa Ng, Gun-Ill Lee, Jiwon Jeong

Abstract:

This paper presents a method for improving object search accuracy using a deep learning model. A major limitation to provide accurate similarity with deep learning is the requirement of huge amount of data for training pairwise similarity scores (metrics), which is impractical to collect. Thus, similarity scores are usually trained with a relatively small dataset, which comes from a different domain, causing limited accuracy on measuring similarity. For this reason, this paper proposes a deep learning model that can be trained with a significantly small amount of data, a clustered data which of each cluster contains a set of visually similar images. In order to measure similarity distance with the proposed method, visual features of two images are extracted from intermediate layers of a convolutional neural network with various pooling methods, and the network is trained with pairwise similarity scores which is defined zero for images in identical cluster. The proposed method outperforms the state-of-the-art object similarity scoring techniques on evaluation for finding exact items. The proposed method achieves 86.5% of accuracy compared to the accuracy of the state-of-the-art technique, which is 59.9%. That is, an exact item can be found among four retrieved images with an accuracy of 86.5%, and the rest can possibly be similar products more than the accuracy. Therefore, the proposed method can greatly reduce the amount of training data with an order of magnitude as well as providing a reliable similarity metric.

Keywords: visual search, deep learning, convolutional neural network, machine learning

Procedia PDF Downloads 206