Search

Cloud infrastructure is the "backbone" technology of the internet era. Ever-growing scale of cloud network concerns the sustainability of centralized cloud. Fog computing aims to decentralizes cloud computing distributing computational processes across network devices, offers a potential solution. If application are distributed effectively in available nodes, network resource usage can be reduce while reducing latency by existing closer to data sources and end points. However, the lack of standardization of fog networks, researcher must list its evaluation setups to contextualize placement algorithm's potential abilities. Thus, selecting an evaluation environment is crucial in researching fog application placement problem. There are several reviews about evaluation environment, but there is a lack of information regarding important aspect placement problem such as algorithm type, placement objective and performance metric available in each evaluation environment. In this paper we discuss the capabilities of several evaluation environments such as iFogSim, YAFS, MATLAB, Python, real world testbed, solver, and other evaluation environments. We surveyed usage trend per year, algorithm type usage, and performance metric that can be produced by each evaluation environment. This survey aims to help future researchers on fog application placement problems to identify evaluation environment based on selected algorithm type and objective metrics. [ABSTRACT FROM AUTHOR]

Widespread use of high-resolution satellite images may be found in many fields and applications. Its ability to record the earth's surface in more detail benefits regional spatial management, natural resources and disaster monitoring, and several other fields. The smaller coverage is unfortunate if areas are not visible due to cloud contamination. The presence of clouds can reduce or even eliminate the information in the image. Cloud detection on high-resolution images is a challenge because this image only has four channels: blue, green, red, and NIR. While the thermal channel, which is often used to detect the presence of clouds, is not owned by this image. This study proposes a method to identify clouds in high-resolution satellite imagery based on this limitation. The cloud detection software in this paper uses U-Net version 1.0. This software can be executed on a server or personal computer (PC). The model applied to the Dice coefficient and IoU to know how the segmentation model performs. The results of this cloud detection process are cloud detection raster data. This software generates the percentage of clouds in an image as a.txt file. The dice model is recommended for the cloud detection method based on the accuracy assessment. Users can utilize these results, especially in overcoming cloud constraints on high-resolution satellite imagery. This software is expected to fulfill the needs of remote-sensing data users. [ABSTRACT FROM AUTHOR]

The quick development of technology not only makes life easier but also raises several security concerns, so cyber security has become very important and vital research area, rather an inevitable part of computer system. Still, various research being done on the development of effective intrusion detection system (IDS). An IDS is one of the suspicious network activities. An IDS is used to identify many types of malicious actions that can undermine a computer system's protection and confidence. Recently, ensemble algorithms are applied in IDS in order to identify and classify the security threats. In this paper author intends to do a brief review of various Ensemble learning Algorithms in ML, which are most frequently used in IDS for several applications; with specific interest in dataset and metric. This work provides broad study and investigation on current literature, the gap for improving and creating efficient IDS can be determined. [ABSTRACT FROM AUTHOR]

Clustering is the process of assembling related data items into a group that stands out from the other things. Finding groupings of genes that share co-expression in various settings through the analysis of microarray data is possible through the use of clustering. This study's primary goal is to compare the effectiveness of various clustering methods while grouping microarray data both with and without outliers. Six microarray datasets were analysed using the same way. The clustering algorithms are widely used by researchers which include the agglomerative hierarchical clustering, K-means algorithm, Self-Organizing Maps (SOM) and Partitioning Around Medoids (PAM). The measures of performance were internal validation measures (connectivity, Dunn index and silhouette width) and stability validation measures (Average of Proportion of Non-overlap and Average Distance of Means). The findings demonstrate that various clustering techniques generate various numbers of clusters. According to internal and stability performance criteria, the agglomerative hierarchical clustering method with two clusters produces the best clustering results for data sets with and without an outlier issue. [ABSTRACT FROM AUTHOR]

This article largely focused on the effective study of a body of norms to detect the Brute Force on the inner surface of a provided guided or unguided game theory in the Financial System. One of the most fascinating areas of conceptual arithmetic is guided or unguided game theory.A focus: the idea of guided or unguided Game theory outcomes in agreement with tracking down and unguided Game theory is shown to be a Game theory design if they are linked to one another. Using guided or unguided Behavioural economics, find a key demonstration for the simple investor for the client to the financial institution. [ABSTRACT FROM AUTHOR]

Algorithms are increasingly being used and recognized for their ability to improve the performance of diagnostic tools such as contemporary electrocardiogram (ECG). For instance, evidence from previous studies reveals that QRS enhancement and detection algorithms have enabled the ECG device to measure and classify heartbeat more accurately. Based on the review of the previous works on QRS detection in ECG, this paper examines the key components of the ECG, QRS detection features, the different techniques used for developing QRS enhancement and detection algorithms as well as the criteria for evaluating their performance. [ABSTRACT FROM AUTHOR]

Artificial intelligence is a realistic option for developing accurate predictions of outcomes, particularly in health research. It is often referred to as a component of artificial intelligence, such as the computerized intelligence of Python and the R language, depending on the amount of service provided relative to the population density of each area. Machine learning algorithms have also been used in Anaconda Navigator and ArcGIS software for positioning and classification, based on Euclidean distance, for spatial analysis of medical services. The methodology has regularly provided insight into service models by processing the huge amount of semi-structured, multi-domain medical data already available. The outcome of risk identification is where AI can be used in healthcare to improve disease models, provide opportunities for personalization and treatment discovery in primary health centers and distribute services to populations in all cities. This study aims at analysis to determine the pattern and classification of medical services using machine learning methodology for Dhi-Qar Governorate, which is mainly characterized by its large area (about 13738.67 square kilometers), and its division into 15 administrative units according to the official administration of Iraq. The databases used were compiled between January 2019 and June 2021. The maps created as a result depict healthcare around population density and track outcomes in the average and above-average (13 percent) categories. On the other hand, the mediocre healthcare sector constitutes 33% of the total percentage (5 administrative units). Health laboratories in the governorate fall within the normal and above-average categories (13%). [ABSTRACT FROM AUTHOR]

As the Internet of Things (IoT) becomes more widely used, the danger of information leakage, the danger of information leakage, data leakage and theft of the internet of things is continuous increasing, as the communication channel for data transfer is open to the public. A considerable portion of this data includes sensitive and personal information for the user and the company as well. Because of the openness, distributed nature, and lack of control over the entire IoT environment, the number of attack vectors for bad users is significant. End-users must trust the system for the IoT to become a viable service platform. Consequently, in critical infrastructures like smart home, smart city, smart healthcare, and smart industry, information security and privacy are the major concern in the Internet of Things. In this paper, we present an information concealment strategy using steganography to protect communication in critical IoT infrastructure. RGB photographs are employed as the information carrier. Deep layers of low-distortion image channels in the least significant bit (LSB) are used to hide the data to be used as a data marker. Both mathematically and experimentally, we evaluate our method. We display mathematically that the striker's analysis cannot expect the current information. The proposed strategy outperformed previous strategies in terms of imperceptibility and capacity, as well as resilience to steganalysis attacks like histogram analysis, as demonstrated experimentally. [ABSTRACT FROM AUTHOR]

One of the most important uses is for storing data in the cloud. Users should make sure that the data they store in the cloud is encrypted before doing so, as this will ensure that their information is safe. The wait will continue until reliable data is saved, despite the fact that this device is among the most widely used ones that allow for one-on-one code dumping. The system that has been proposed ensures the safety of data stored in the cloud. The cloud will experience maintenance issues that will require a significant amount of data in order to correct even a single mistake. The data is encrypted in its entirety and then stored in several distinct clouds. In order to partition the data, the Merkle Hash tree (MHT) algorithm is utilised. Create a copy to serve as a backup for your data. There are no master keys stored, and they are kept in a different cloud. It is possible to store data across multiple clouds. The data that is shared is saved in multiple clouds. Even in the event that there is an ongoing uprising in the cloud, data can now be retrieved. [ABSTRACT FROM AUTHOR]

Mathematical programming techniques determine the optimal functional configuration of a Wireless Sensor Network (WSN). However, the high computational complexity of these techniques has been regarded as a Non-Polynomial problem. Hence, Machine Learning (ML) approaches are used for WSN parameter prediction with improved accuracy and less computing complexity. This study aims to predict the reliability of clustering algorithms in WSNs using supervised ML classification approaches. ML algorithms, namely, decision tree and K-nearest neighbor classifications are implemented on the obtained dataset to predict the reliability of clustering in WSNs on the basis of high packet delivery ratio, low delay, and high residual energy. The reliability parameter accepts binary values, where zero represents the absence of reliability and one represents the presence of reliability metrics. Then the predictions from each classifier are compared with one another. The results show that the accuracy rate of the decision tree is 97.98% and the error rate is 2.02% which shows that the decision tree performs better than the K-nearest neighbor in predicting the reliability of the proposed approach. [ABSTRACT FROM AUTHOR]

For a developing country like India, aquaculture is a lucrative business as it contributes to its economic growth. Cod liver oil is a nutrient-dense dietary supplement that boosts the immune system and prevents various diseases that affect humans. Aquaculture is the process of raising and breeding fish. It is a form of ocean stewardship that promotes a healthy marine environment and provides a sustainable source of food and commercial products. To ensure a pollution-free environment, detecting infectious fish on the seafloor is a complex and challenging task that requires specialized infrastructure. The accelerated spread of secondary diseases in fish could be detected at an early stage with the help of a planned smartphone app. [ABSTRACT FROM AUTHOR]

Aim: The proposed work is to improve thyroid prediction accuracy based on nodule size by using an optimized XGBoost Machine learning algorithm and compared with Non-Linear machine algorithm. Materials and Methods: Thyroid disease dataset used in Optimized XGBoost algorithm. From this Optimized XGBoost, the sample of each group was 20 with a tool simulation environment, the data of XGBoost was stored in a Compressed column format it decreases the overfitting possibility which shrinks the complexity which tends to work in a smooth learning process. Results: The accuracy of predicting thyroid nodules size prediction using XGBoost machine learning algorithm compared with Non-Linear machine learning algorithm bit significant of accuracy of 97.61% the Non-Linear machine learning algorithm 93.47% the statistical significant difference between XGBoost and Non-Linear algorithm is 0.001 (p<0.05). Discussion: Accuracy and performance in all conditions than Non-Linear machine learning algorithm. The limitations of the XGBoost machine learning algorithm were the versions which were not compatible to execute all required modules for the algorithm. Conclusion: Optimized XGBoost used in the significance of accuracy seen in thyroid nodules size prediction compared to the Non-Linear machine learning algorithm. [ABSTRACT FROM AUTHOR]

The research aims to enhance liver tumour prediction using an unique K-Nearest Neighbor (KNN) machine learning technique. Materials and Methods: The research employed 52 samples with two groups of algorithms with a g-power of 80% and datasets from different online sources with current study results, threshold 0.05 percent, confidence interval 95 percent mean and standard deviation. Logistic regression predicts liver cancers with 71.11 percent accuracy, thus this work needs to improve innovative liver tumour prediction using KNN. Results: The innovative K-Nearest Neighbor method achieved 74.29 percent accuracy in liver tumour prediction, with a significant value of 0.045 (p<0.05) and a 95% confidence range. This research found that KNN predicts liver tumours better than Logistic regression. [ABSTRACT FROM AUTHOR]

The proposed project is a comparative study of the accuracy of OCR-based image-to-speech conversion using novel FKM and FCM algorithms from low-resolution images that have high accuracy. Method and material: Two classes are contrasted, novel Fuzzy k-means clustering (FKM) (N=10) and Fuzzy c-means clustering (FCM) (N=10) with the G Power software, the total volume is determined with alpha equal to 0.05, the enrollment ratio is equal to 0.1, the confidence interval is 95%, and the power is 80%. SPSS' software was used to conduct an independent sample t-test to assess the accuracy rate. Conclusion: The results of the MATLAB simulation are 90 % accurate and have a precision of 84 % in the conversion of text to speech. In SPSS' statistical analysis, a significant degree of success (0.001) was achieved. Conclusion: A novel FKM classifier is demonstrated to be superior to the FCM Classifier for OCR-based images to speech. [ABSTRACT FROM AUTHOR]

One of the most used computer and storage technologies is cloud computing. This article's objective is to offer an affordable and secure platform for the personnel management system. Materials and Methods: There are a total of 2 groups in this study; group 1 analyses the message digest 5 algorithm (434 samples), whereas group 2 analyses the advanced encryption standard (434 samples). Each model's efficacy and accuracy are contrasted. Result: The goal of this essay is to make the algorithm employed in the personnel management system more effective. The suggested model looks to be more effective and quick than the current approach, and the mean detection accuracy is within one standard deviation. An independent sample T test yields a mean value of 1.3648 and a significant value of 0.226 (p>0.01). Conclusion: When the results of the advanced encryption standard method and the message digest 5 algorithm for the current system were compared, the proposed innovative standalone framework technique was shown to be more efficient (1.4 times faster) than the current model. [ABSTRACT FROM AUTHOR]

Technological advances have enabled skin cancer detection studies utilising machine learning algorithms. Machine learning is best for early, curable head and neck non-melanoma skin cancer (NMSC) detection and diagnosis. Techniques and Substances: This study examined real-world machine learning disease diagnosis algorithms. This research uses Novel Logistic Regression (LR) and Support Vector Machine classification algorithms, which use training and validation sets, respectively (SVM). SVM and LR algorithms were assigned to Groups 1 and 2 based on their g-power values of 80% and current study findings using images of squamous cell carcinoma from online sources (threshold: 0.05 percent, Confidence Interval: 95 percent mean and standard deviation). This study's findings will help machine learning systems predict such illnesses. The two-tailed significance value of 0.035 (p0.05) with a 95% confidence range shows that the SVM algorithm is 81.58 percent accurate and the LR algorithm is 85.47 percent accurate. This study recommends POC skin cancer prevention and early diagnosis based on a Machine Learning analysis of the data. [ABSTRACT FROM AUTHOR]

This study compares the performance of the Support Vector Machine (SVM) classification method with that of the Self Organizing Map (SOM) algorithm for predicting agricultural relief rains over a given time period (SOM). The Components and Techniques: There were 88 participants in all (44 in Group 1 and 44 in Group 2) for the relief rainfall prediction study. Relief rainfall prediction for the selected time of agriculture is compared using the Self Organizing Map (SOM) and the Support Vector Machine (SVM) algorithms, both of which take into account a large number of samples (N=10). Findings show that the SOM has a 93.37 percent accuracy rate, while the SVM method only has an accuracy rating of 84.032 percent. The accuracy rate difference confidence range is 95%, and two-tailed test P is 0.0303. (p0.05). We conclude that the Self Organizing Map (SOM) method predicts relief rainfall for a specific agricultural period more accurately than the Support Vector Machine (SVM) technique. [ABSTRACT FROM AUTHOR]

The aim of the study is to diminish the power loss with reference to sensitivity and precision in power transmissions and consumptions. As power theft is considered as non-technical loss, it is hard to track the total transmission. So the Random forest algorithm is proposed over the K-NN Algorithm to compare accuracy in power theft detection. Materials and Methods: There are two groups in this study each with a sample size of 21400 per group. Analysis is done with the pretest power 0.8. Results: The mean value for accuracy in the Random Forest algorithm is 90.6215 which is high when compared to K-NN algorithm whose accuracy is 82.2200. It has an insignificant value of 0.07 (p>0.05). These values are evaluated using SPSS for statistical analysis. Conclusion: This analysis shows that the novel Random Forest algorithm has more reliable accuracy and sensitivity of power theft detection compared to the K-NN algorithm. [ABSTRACT FROM AUTHOR]

The purpose of this study effort is to undertake the comparative analysis of detection rate in real time innovative face recognition systems using K-Nearest Neighbor algorithm in comparison with Linear Discriminant Analysis method. Materials and Methods: The sample size of a real time face recognition system with increased detection rate utilising Linear Discriminant Analysis algorithm in comparison with K-Nearest Neighbor algorithm was 20 by considering 10 numbers of samples for each approach with pre-test power of 80 percent. Findings: The detection rate of K-Nearest Neighbor method is 93.0258 percent while results of Linear Discriminant Analysis technique detection rate are 89.762 percent. There is a significant variation in Detection rate (P=0.0421). The findings obtained were judged to be error-free as it was having the significant value p<0.05 in SPSS statistical analysis. Conclusion: K-Nearest Neighbor method depicts the greater performance in discovering the detection rate in a real-time face recognition system when compared to Linear Discriminant Analysis algorithm. [ABSTRACT FROM AUTHOR]

The fundamental objective of this research is to investigate several approaches that may be used to enhance the precision of recent machine learning algorithms that are used to anticipate road accidents, in particular the Random Forest Algorithm and the Naive Bayes Algorithm. Both the Materials and the Procedures are: Both the Random Forest and the Naive Bayes algorithms were run through 20 iterations in order to see how well they could predict future traffic incidents. The results show that in terms of accuracy, the Random Forest approach performs better than the Naive Bayes algorithm (89.95 percent). The significant independent samples T-test for the Random Forest approach is 0.001, as stated in the previous sentence (p0.05). When the data were compared, it was evident that the Random Forest approach surpassed the Naive Bayes algorithm in terms of the prediction of traffic accidents. This was the conclusion reached after analysing the data. [ABSTRACT FROM AUTHOR]

The aim is to improve reduction of network traffic for cloud-based communication by analysing and predicting the network traffic using Novel linear and logistic regressions. Materials and Methods: The network traffic analysis of linear regression is compared with the analysis of logistic regression, using the accuracy of the trained model and the predicted values. Results: The linear regression has significantly higher accuracy than the logistic regression. The accuracy obtained in linear regression was 81% and 77% of accuracy for logistic regression. Sample size for group 1 is 65 and group 2 is 65.and the total sample size of the research work is 130. There is a statistically significant difference between Linear regression and Logistic regression with (p<0.05) Conclusion: Within the limits of this study, linear regression is the best algorithm for reduction of network traffic in cloud-based communication. [ABSTRACT FROM AUTHOR]