Huge Amount Of Data Research Articles

Utilizing Generative Adversarial Network for Synthetic Image Generation to Address Imbalance Challenges in Chest X-Ray Image Classification

Deep learning-based classifiers need lots of image data to train. Unfortunately, not all real-world cases are supported by a huge amount of image data. One of the cases are images for classification of pneumonia infections with chest X-rays images. This study proposes a way of synthesizing chest X-rays with abnormal conditions in order to use the synthesized images for classification purposes. A GAN-based technique can generate synthetic images with greater quality that resemble original images thus can provide a more balanced data distribution than other approaches. To indirectly evaluate the quality of our GAN-based synthetic images, we used CNN-based classification architectures on diverse datasets. Three scenarios examined the effects of synthetic picture categorization. Scenario-1: adding 90% of synthesized images to the original images into the training dataset. Scenario-2: adding 50% of synthesized images to the original images. Scenario-3: adding 10% of synthesized image to the original images. The classification test revealed significantly increased F1 scores in all scenarios. Our study also emphasizes the significance of addressing the problem of imbalanced collections of chest X-ray images and the capability of GANs to alleviate this issue.

A Novel Additive Internet of Things (IoT) Features and Convolutional Neural Network for Classification and Source Identification of IoT Devices

The inter-class classification and source identification of IoT devices has been studied by several researchers recently due to the vast amount of available IoT devices and the huge amount of data these IoT devices generate almost every minute. As such there is every need to identify the source where the IoT data is generated and also separate an IoT device from the other using on the data they generate. This paper proposes a novel additive IoT features with the CNN system for the purpose of IoT source identification and classification. Experimental results shows that indeed the proposed method is very effective achieving an overall classification and source identification accuracy of 99.67 %. This result has a practical application to forensics purposes due to the fact that accurately identifying and classifying the source of an IoT device via the generated data can link organisations/persons to the activities they perform over the network. As such ensuring accountability and responsibility by IoT device users.

Detection of Face-Mask in Real Time: A Cascaded Bi-Level Feature Extraction Technique Approach

Due to COVID-19's rapid spread, millions of people around the world have been affected and there has been extensive destruction. One of the most effective ways of preventing its spread and transmission during the pandemic period wearing of a mask and was required then in most public areas. As a result, this necessitate the use of programmed real-time mask detection devices in place of manual reminders. Face mask detection requires real-time processing of a huge amount of data with constrained processing resources, hence local descriptors that are quick to calculate, quick to match, and cheap to store are highly sought after. To achieve improved matching and reduction in memory use and computational complexity, the study offers a combination of Features from Accelerated Segment Test (FAST) corner detector with Histogram of Oriented Gradient (HOG) feature descriptor to allow faster matching and minimize memory usage and computation cost. The features obtained were then classified into face mask present and face mask absent using SVM, NB and CNN. Results obtained gives an accuracy of 99.41% which was higher than that previous results of 99.27% and 95% accuracy. Furthermore, it took the system only 48secs to extract the features obtained from face for training and testing. This outcome confirmed the suitability of the suggested method for real-time face mask detection.

SURVEY OF USAGE ARTIFICIAL INTELLIGENCE MECHANISM IN THE LOAD BALANCER

Nowadays, there is no way to imagine artificial intelligence applications without using high-performance computing systems. The huge amount of processing data, the complex structure of learning technology, time limitations, and the necessity of real-time operation require powerful computational resources and parallel algorithms. This paper analyzed another direction of convergence between high-performance computing and artificial intelligence: using artificial intelligence techniques in one of the main problems of distributed systems load balancing. The primary objective of this work is to examine the necessity of using AI concepts in load balancing and the definition of providing facilities for load balancers.

Feature Extraction Techniques to Analyze Competitive Exam Result Data to Improvise Educational Policies

The increase in e-learning resources and online facilities for applications, examinations and evaluations has generated huge amount of data in educational field. As quality of education plays vital role in development of individuals, this work aims at analyzing the quantity as well as quality of education district wise, in a state, by utilizing a competitive exam result database. In some district, the results may be better quantitatively, while in others, number of students cleared may be less, but scores may be higher. The aim is to understand the strength and weakness of existing educational infrastructure and how to bring up its level in rural districts, thus helping policymakers to reform and improvise. The collected database undergoes pre-processing phase to ensure its quality and feature engineering is done for missing values, data validation, inconsistencies, data dependencies and outliers. Data inconsistency is handled to ensure data integrity and reliability. Outliers are detected and removed to avoid skewing the predictions on examination results. Machine learning and deep learning models will be applied to Exam-result database to analyse and extract valuable insights. This knowledge can aid in optimizing resource allocation, improving policies to enhance overall educational outcomes and implementing targeted interventions. The accurate predictions generated from this work can help to identify applicants’ risk of underperforming and can provide personalized support Key Words: Feature extraction, Information retrieval, Classification, Data pre-processing, Data analysis, Education assessment, Correlation analysis, Skewness, Kurtosis, KNN algorithm, Gaussian Naïve Bayes algorithm, Bernoulli Naïve Bayes algorithm

Модель синтезу гідроакустичних сигналів із використанням нейронних мереж

Underwater acoustics (also called hydroacoustics), which is associated with the study of the patterns of propagation of sound waves in water, is a driving force in the research and development of systems of hydroacoustic technologies and means of communication, monitoring and detection of surface and underwater objects of biological or artificial origin, study of marine resources and environments, noise measurement, etc. This kind of research requires the analysis of huge amounts of data, revealing non-obvious patterns and creating models for the mathematical description of physical phenomena, such as sound propagation in a medium with random characteristics and radiation from different sources, as well as radiation from sources with different apertures or sound scattering, etc. That is why, in order to create the latest technologies in this area, it is necessary to solve complex specialized problems of a fundamental and applied nature using machine learning algorithms and artificial intelligence. Neural networks are nonlinear systems that allow you to effectively classify data compared to mathematical and statistical methods, which are currently quite widely used. In this paper, the authors propose to use a pre-trained neural network for the analysis and classification of hydroacoustic signals. This procedure for distinguishing acoustic signals has a number of advantages, in particular, individual objects are divided into groups based on information about one or more characteristics inherent in these objects, and on the basis of a training sample of pre-labeled objects. Thus, the proposed model of signal synthesis using neural networks is characterized by increased informativeness of the characteristics of the propagation of hydroacoustic signals, which will have prospects in further practical implementation.

Optimization-enabled deep learning model for disease detection in IoT platform

ABSTRACT Nowadays, Internet of things (IoT) and IoT platforms are extensively utilized in several healthcare applications. The IoT devices produce a huge amount of data in healthcare field that can be inspected on an IoT platform. In this paper, a novel algorithm, named artificial flora optimization-based chameleon swarm algorithm (AFO-based CSA), is developed for optimal path finding. Here, data are collected by the sensors and transmitted to the base station (BS) using the proposed AFO-based CSA, which is derived by integrating artificial flora optimization (AFO) in chameleon swarm algorithm (CSA). This integration refers to the AFO-based CSA model enhancing the strengths and features of both AFO and CSA for optimal routing of medical data in IoT. Moreover, the proposed AFO-based CSA algorithm considers factors such as energy, delay, and distance for the effectual routing of data. At BS, prediction is conducted, followed by stages, like pre-processing, feature dimension reduction, adopting Pearson’s correlation, and disease detection, done by recurrent neural network, which is trained by the proposed AFO-based CSA. Experimental result exhibited that the performance of the proposed AFO-based CSA is superior to competitive approaches based on the energy consumption (0.538 J), accuracy (0.950), sensitivity (0.965), and specificity (0.937).

A deep learning approach combining autoencoder with supervised classifiers for IoT anomaly detection

Anomaly detection for IoT networks is a challenging issue due to the huge number of devices that connect to each other and generate huge amounts of data. In this study, we propose a model combining Autoencoder with classification algorithms to build an end-to-end architecture for processing, feature extraction and data classification. Autoencoder is used to extract valuable hidden features of the original data, while supervised learning algorithms such as Softmax, Random Forest, Decision Trees, XGBoost, etc. are used for training and testing on AE’s encoder output data. We then test our recommended models on nine recent devices in the NBaIoT dataset and evaluate their performance. According to the experimental results, the proposed model greatly improves the performance of IoT anomaly detection methods.

Reversible data hiding in encrypted images with multi-prediction and adaptive huffman encoding

With the rapid development of multimedia technology and the massive accumulation of user data, a huge amount of data is rapidly generated and shared over the network, while the problems of inappropriate data access and abuse persist. Reversible data hiding in encrypted images (RDHEI) is a privacy-preserving method that embeds protected data in an encrypted domain and accurately extracts the embedded data without affecting the original content. However, the amount of embedded data has been one of the major limitations in the performance and application of RDHEI. Currently, the main approaches to improve the capacity of RDHEI are either to increase the overall capacity or to reduce the length of the auxiliary information. In this paper, we propose a novel RDHEI scheme based on multi-prediction and adaptive Huffman encoding. To increase the overall capacity, we propose a multi-prediction, called MED+GAP predictor, to generate the label map data of non-reference pixels prior to image encryption. Then, an adaptive Huffman coding is designed to compress the generated labels in order to reduce the embedding length of the auxiliary information used for the extraction and recovery. Experiments show that the proposed method with MED+GAP predictor and adaptive Huffman coding improves 0.052 bpp, 0.023 bpp, and 0.047 bpp on average over the other state-of-the-art methods on the BOSSBase, BOWS-2, and UCID datasets, respectively, while maintaining security and reversibility.

A wavelet based PSD approach for fault detection and classification in grid connected inverter interfaced microgrid

The recent progress in the area of microgrid protection has led to the application of data-driven and signal processing techniques for fault detection in microgrids. The deployment of inverter interfaced distributed generators makes the traditional protection schemes ineffective. In this paper a wavelet based power spectral density (PSD) has been utilized to detect fault, identify faulty phases and locate fault in the microgrid. Wavelet based PSD decouples the frequency information from the time information and it is the optimal technique to reveal the change of distribution of harmonics in non-stationary faulty signals as for fault analysis it can consider the faulty frequency band instead of one particular harmonic. The proposed technique can detect fault and identify faulty phases by analyzing current signals from the substation only. The normalized value of PSD of three phase current signals has been considered for fault detection and probabilistic distribution of PSD has been considered for faulty phase identification. The normalized value of PSD of the current signals collected from both ends of the main feeders and one end of the non-DG sub-feeder have been used to locate the faulty feeder and sub-feeder. Appropriate threshold values have been considered to detect fault and to locate the faulty feeder. To locate faults, the technique does not require synchronized signals and thus provides a promising and economical solution for inverter interfaced microgrid. It does not require huge amount of data set for training and testing as it is essentially a threshold based technique and also does not require collection of data at high sampling rate. The proposed scheme has been extensively tested for high impedance fault (HIF), unbalanced loading, load switching, variation of DG parameters, measurement uncertainty and presence of noise in the signal with signal to noise ratio up to 10 dB. This technique provides accurate results for fault resistance from 0 Ω to 300 Ω and up to 10% measurement error. The performance of the proposed technique has been verified for feeder length variation up to 20%. Half cycle of current signal only after fault is required and three levels of wavelet decomposition has been considered. The simulation results and comparative assessment demonstrate the efficacy of the proposed scheme.

The role of artificial intelligence and macnine learning in business intelligence

This article explores how Artificial Intelligence (AI) and Machine Learning (ML) are changing the way businesses use data. In a world where data is super important, many companies are using AI and ML to make the most of their data. This study looks at how AI and ML are being used in Business Intelligence (BI), which is all about collecting and analyzing data to help businesses make smart decisions. First, we look at the old way of doing BI and how it couldn't handle the huge amount of data we have today. Then, we see how AI and ML are being used to solve this problem. These technologies help by automatically processing data, predicting future trends, and finding important information in big piles of data. We also check out some real-life examples from different industries to see how AI and ML are helping companies make better decisions. These examples show how businesses can get more accurate data, make decisions faster, and predict things better by using AI and ML in their BI. We also talk about some challenges and things we need to think about when using AI and ML in BI, like making sure we use these technologies in a responsible and fair way. In summary, this research shows that AI and ML are not just tools, but they're changing the way we do BI. By using these technologies, companies can get better insights from their data, stay competitive, and take their BI to the next level.

Heartbeat Pattern and Arrhythmia Classification: A Review

In today’s era, the lifestyle of people has become much more sophisticated due to the involvement of stress, anxiety, and depression in the daily routine of human beings. In such a scenario, cardiac diseases are growing rapidly in youngsters and senior citizens. It is also observed that cardiac diseases are crucial and sensitive, including life-threatening chances. So, it is essential to detect and prevent such cardiac disorders within the required time for recovery. Since there has been a lot of research in the prediction and prevention of cardiac disorders, cardiac arrhythmia is also one of the majorly occurring diseases in the bulk of the population. The electrocardiogram is the cheap and best way to diagnose the problem of cardiac arrhythmia, and a huge amount of data is collected daily in hospitals and pathological centers. Previously, various automated models were developed for detecting cardiac arrhythmia using deep learning approaches and machine learning. In this work, we have reviewed recently developed automated models and evaluated their performance based on specific parameters like deployed datasets, variation of input data, applied application, methodology, and results obtained by the developed model. The limitations of reviewed papers are also mentioned in addition to their future scope for improvement.

The psychosocial impact of haemophilia from patients' and caregivers' point of view: The results of an Italian survey.

A huge amount of data about psychosocial issues of people with haemophilia (PwH) are available; however, these materials are fragmentary and largely outdated, failing to reflect the impact of current treatment strategies. Describing the influence of illness on psychosocial aspects of adult PwH (≥18 years) and caregivers of children with haemophilia (CPwH) without inhibitors, in Italy. Surveys (for adult PwH, CPwH and haemophilia specialists) were developed by a multidisciplinary working group and conducted from November 2019 to June 2020. A total of 120 PwH without inhibitors and 79 CPwH completed the survey. Adult patients reported a significant impairment in many psychosocial aspects, including working activities, relations with family members and social relations. Caregivers generally reported better scores in all aspects of the survey. Mobility, Pain and Mental health domains of EQ-5D were the most frequently impaired in both patients and caregivers, reducing the perceived quality of life. Genetic counselling was an important issue, 53% of CPwH declaring unawareness of their carrier status, as well as the psychological support offered by the reference center, 67.0% of respondents reporting that no psychological support was provided at the time of diagnosis communication. This study provides information about PwH's and CPwH's point of view in the current scenario of continuous innovations in haemophilia treatment and management furthermore, updated insights on psychosocial problems faced by patients and caregivers are reported.

Turbulence in the Relationships Between Governments and High Tech Firms

"The turbulent times governments all over the world are facing include the transition towards the Fourth Industrial Revolution (4IR) in which the confluence of new technological developments result in major challenges for national as well as local governments. The confluence of the newly developed technologies is only possible if huge amounts of data can be stored and transmitted at high speed in, among others, hyperscale data centers (HDCs). This paper focuses on the complex relation that arises between local governments - on whose soil the HDCs are built - and the high tech companies planning and building the HDCs. This relationship is characterized by an unequal playing field with local governments being no match for the high tech industry. The latter sometimes have annual turnovers 1000 times higher than those of local governments and impose rather different demands on decision making processes than governments do. They impose restrictions on the decision-making process that result in processes running counter to principles of good governance and, if exposed, result in a deterioration of institutional trust among the population. This is illustrated through a case study in which a small municipality in the Netherlands was faced with an offer from Meta to make a huge investment in a hyperscale data center, provided the whole process towards the permits and the approval of the building would remain secretive. Shown is an imposed secrecy by the high tech firm and information revealed about the process afterward through the Freedom of Information Act disclosing many irregularities. This changed the existing trust in the municipality into complete distrust at the end of the process and eventually forced the High Tech company to withdraw. The relevance of this paper for this special issue is that the case study shows that the new developments towards the 4IR require capacitated, knowledgeable and decisive local governments, which momentarily are not even present in a developed country like the Netherlands."

AI in Rehabilitation Medicine: Opportunities and Challenges.

Artificial intelligence (AI) tools are increasingly able to learn from larger and more complex data, thus allowing clinicians and scientists to gain new insights from the information they collect about their patients every day. In rehabilitation medicine, AI can be used to find patterns in huge amounts of healthcare data. These patterns can then be leveraged at the individual level, to design personalized care strategies and interventions to optimize each patient's outcomes. However, building effective AI tools requires many careful considerations about how we collect and handle data, how we train the models, and how we interpret results. In this perspective, we discuss some of the current opportunities and challenges for AI in rehabilitation. We first review recent trends in AI for the screening, diagnosis, treatment, and continuous monitoring of disease or injury, with a special focus on the different types of healthcare data used for these applications. We then examine potential barriers to designing and integrating AI into the clinical workflow, and we propose an end-to-end framework to address these barriers and guide the development of effective AI for rehabilitation. Finally, we present ideas for future work to pave the way for AI implementation in real-world rehabilitation practices.

A Direction-Preserved Vessel Trajectory Compression Algorithm Based on Open Window

Ship trajectory data can be used in most marine-related research, and most ship trajectory data come from AIS. The large number of ships and the short reporting period of AIS have resulted in a huge amount of ship trajectory data, which has caused a certain amount of pressure on the relevant research. This paper proposes a direction-preserved vessel trajectory compression method based on Open Window, which can effectively retain the direction change feature points while ensuring the position error. In addition, the method can work in both offline and online modes. Also, the velocity threshold and low-speed redundancy points problems are considered. In order to verify the effect of the proposed method and the adaptability of the method to different feature data, a parallel experiment was performed on port water and coastal water datasets. The results show that our method can compress vessel trajectories while retaining the feature points. Meanwhile, by comparing it with the compression method that is based on distance thresholds, the vessel trajectory compress time is drastically reduced by up to 87.3% in the port water data. The research in this paper provides a new method through which to compress vessel trajectories for research in marine-related fields on vessel trajectory.

Hybrid rat swarm hunter prey optimization trained deep learning for network intrusion detection using CNN features

In recent years, the emerging growth of various network technologies, namely the cloud computing, 5 G networks, Internet of Things (IoT), and so on resulted in the createion of huge quantity of data and creates challenges to the security of networks. The classical firewalls failed to meet various requirements of the current security of the networks due to the increasing number of network attacks. Hence, an optimization-enabled deep learning model Rat Swarm Hunter Prey Optimization-Deep Maxout Network (RSHPO-DMN) technique is designed to effectively handle various network threats. The Z-score data normalization is applied for data pre-processing initially and by considering chord distance, the data is transformed into usable formats. The transformed data are extracted using the Convolutional Neural Network (CNN) feature and the extracted feature is converted into vector format for network intrusion detection process. The DMN is used for intrusion detection in networks and the designed RSHPO model is used to boost the intrusion detection rate exhibited in the classifier. The RSHPO-DMN model achieved superior performance under different evaluation indicators with accuracy of 90.88 %, precision of 93.58 %, recall of 96.54 %, and f1-score of 95.04 % respectively than other prevailing intrusion detection approaches.

Multilayer grid XG Boost architecture based automatic osteosarcoma classification

The application of machinelearning(ML) and deep learning (DL)methods might reduce the amount of time required by clinicians while simultaneously enhancing patient outcomes. The classification algorithm has to be provided with a huge amount of data in order to improve its accuracy. In this study, a combination of ML and DL is utilized to differentiate between images of normal and necrotic tissues utilizing a public database of osteosarcoma histological images. The data was initially preprocessed, and contour based threshold segmentation algorithms were performed. Next, the anomalous features are extracted using stochastic linear embedding-based feature extraction. Finally, stained photos are used to train the proposed multilayer grid XG Boost classifier, which improves output accuracy. The results of the experiments show that the suggested classifier is the most accurate one presently in use for categorizing illnesses. With H and E stained images, our improved model performed better at detecting osteosarcoma malignancy.

LAMIS-DMDB: A new full field digital mammography database for breast cancer AI-CAD researches

The current state of machine learning (ML) and deep learning (DL) shows that they are powerful tools that can be used to glean knowledge from a huge amount of data. While a great deal of research in this area has centered around improving the accuracy and efficiency of training and inference algorithms, there has been relatively little attention paid to the equally important problem of monitoring the quality of data. To tackle this challenge, we have created a cutting-edge breast database capable of employing ML and DL algorithms to detect and classify breast cancer. It is noteworthy that compared to other digital mammogram databases (DMDB), the Laboratory of Mathematics, Informatics and System (LAMIS) images have better resolution and are in full-field digital mammography (FFDM) format. Furthermore, the images can be accessed according to their abnormality (normal, benign, malignant), lesions classification (mass, calcification, architectural distortion, multiple finding), American College of Radiology (ACR) density classification (ACR1, ACR2, ACR3, ACR4) and Breast Imaging Reporting and Data System (BI-RADS). Specifically, the database is designed to provide a variety of metadata as well as clinical data in simple comma separated values (CSV) format that can be really beneficial to the breast cancer research community and to the development of computer-aided diagnosis (CADx) tools that rely on artificial intelligence (AI) algorithms, such as those based on DL models.

Oncolytic Viruses in the Era of Omics, Computational Technologies, and Modeling: Thesis, Antithesis, and Synthesis.

Oncolytic viruses (OVs) are the frontier therapy for refractory cancers, especially in integration with immunomodulation strategies. In cancer immunovirotherapy, the many available "omics" and systems biology technologies generate at a fast pace a challenging huge amount of data, where apparently clashing information mirrors the complexity of individual clinical situations and OV used. In this review, we present and discuss how currently big data analysis, on one hand and, on the other, simulation, modeling, and computational technologies, provide invaluable support to interpret and integrate "omic" information and drive novel synthetic biology and personalized OV engineering approaches for effective immunovirotherapy. Altogether, these tools, possibly aided in the future by artificial intelligence as well, will allow for the blending of the information into OV recombinants able to achieve tumor clearance in a patient-tailored way. Various endeavors to the envisioned "synthesis" of turning OVs into personalized theranostic agents are presented.