Many companies are increasingly using MapReduce for efficient large scale data processing such as personalized advertising, spam detection, and different data mining tasks. Cloud computing offers an attractive option for businesses to rent a suitable size Hadoop cluster, consume resources as a service, and pay only for resources that were utilized. One of the open questions in such environments is the amount of resources that a user should lease from the service provider. Often, a user targets specific performance goals and the application needs to complete data processing by a certain time deadline. However, currently, the task of estimating required resources to meet application performance goals is solely the users' responsibility. In this work, we introduce a novel framework and technique to address this problem and to offer a new resource sizing and provisioning service in MapReduce environments. For a MapReduce job that needs to be completed within a certain time, the job profile is built from the job past executions or by executing the application on a smaller data set using an automated profiling tool. Then, by applying scaling rules combined with a fast and efficient capacity planning model, we generate a set of resource provisioning options. Moreover, we design a model for estimating the impact of node failures on a job completion time to evaluate worst case scenarios. We validate the accuracy of our models using a set of realistic applications. The predicted completion times of generated resource provisioning options are within 10% of the measured times in our 66-node Hadoop cluster.

Resource provisioning framework for mapreduce jobs with performance goals

This paper suggests an IoT based smart farming system along with an efficient prediction method called WPART based on machine learning techniques to predict crop productivity and drought for proficient decision support making in IoT based smart farming systems. The crop productivity and drought predictions is very important to the farmers and agriculture’s executives, which greatly help agriculture-affected countries around the world. Drought prediction plays a significant role in drought early warning to mitigate its impacts on crop productivity, drought prediction research aims to enhance our understanding of the physical mechanism of drought and improve predictability skill by taking full advantage of sources of predictability. In this work, an intelligent method based on the blend of a wrapper feature selection approach, and PART classification technique is proposed for crop productivity and drought predicting. Five datasets are used for estimating the proposed method. The results indicated that the projected method is robust, accurate, and precise to classify and predict crop productivity and drought in comparison with the existing techniques. From the results, the proposed method proved to be most accurate in providing drought prediction as well as the productivity of crops like Bajra, Soybean, Jowar, and Sugarcane. The WPART method attains the maximum accuracy compared to the existing supreme standard algorithms, it is obtained up to 92.51%, 96.77%, 98.04%, 96.12%, and 98.15% for the five datasets for drought classification, and crop productivity respectively. Likewise, the proposed method outperforms existing algorithms with precision, sensitivity, and F Score metrics.

An efficient IoT based smart farming system using machine learning algorithms

Introductory real analysis , Introductory real analysis , کتابخانه دیجیتال جندی شاپور اهواز

Introductory Real Analysis. By A. N. Kolmogorov and S. V. Fomin, translated by Richard A. Silverman. Pp. xii, 403. (Prentice-Hall Inc.)

One Dimensional Convolutional Neural Networks for Seizure Onset Detection Using Long-term Scalp and Intracranial EEG

Universally, the volume of data has increased, with the collection rate doubling every 40 months, since the 1980s “Big data” is a term that was introduced in the 1990s to include data sets too lar

https://journals.sagepub.com/doi/pdf/10.1177/2050312120934839

A review of big data and medical research

Nowadays, there is a strong demand for increasing the protection of resource-constrained devices such as Radio frequency identification (RFID) systems. Current cryptographic algorithms are sufficient for high-resource desktop computers. RFID systems are commonly used in high-security applications such as access control systems, transaction banking systems, and payment systems. The attacker attempts to mislead RFIDs for unauthorized access to services without payment or to circumvent security mechanisms by detecting a secret password. The biggest challenge in RFID systems is how to ensure successful protection against such infringements. Lightweight cryptography can provide security assurance for protecting RFID systems. This article presents a new ultra-lightweight cryptography algorithm for RFID systems called SLIM. SLIM is a 32-bit block cipher based on the Feistel structure since block ciphers are the most used cryptographic and provide very tight protection for IoT devices. The key challenge in designing a lightweight block cipher is to cope with performance, cost, and security. SLIM, like all symmetric block cipher, uses the same key for encryption and decryption. The proposed algorithm has an excellent performance in both hardware and software environments, with a limited implementation area, an acceptable cost/security for RFID systems, and an energy-efficient behaviour. SLIM has demonstrated high immunity against the most effective linear and differential cryptanalysis attacks and has a sufficient margin of defence against these attacks.

/pdf/slim-a-lightweight-block-cipher-for-internet-of-health-1izj2s8zy2.pdf

SLIM: A Lightweight Block Cipher for Internet of Health Things

Seizure is an abnormal electrical activity of the brain. Neurologists can diagnose the seizure using several methods such as neurological examination, blood tests, computerized tomography (CT), magnetic resonance imaging (MRI) and electroencephalogram (EEG). Medical data, such as the EEG signal, usually includes a number of features and attributes that do not contains important information. This paper proposes an automatic seizure classification system based on extracting the most significant EEG features for seizure diagnosis. The proposed algorithm consists of five steps. The first step is the channel selection to minimize dimensionality by selecting the most affected channels using the variance parameter. The second step is the feature extraction to extract the most relevant features, 11 features, from the selected channels. The third step is to average the 11 features extracted from each channel. Next, the fourth step is the classification of the average features using the classification step. Finally, cross-validation and testing the proposed algorithm by dividing the dataset into training and testing sets. This paper presents a comparative study of seven classifiers. These classifiers were tested using two different methods: random case testing and continuous case testing. In the random case process, the KNN classifier had greater precision, specificity, positive predictability than the other classifiers. Still, the ensemble classifier had a higher sensitivity and a lower miss-rate (2.3%) than the other classifiers. For the continuous case test method, the ensemble classifier had higher metric parameters than the other classifiers. In addition, the ensemble classifier was able to detect all seizure cases without any mistake.

/pdf/automated-seizure-diagnosis-system-based-on-feature-53iamat1da.pdf

Automated seizure diagnosis system based on feature extraction and channel selection using EEG signals

online transaction is the most popular mode of payment over the internet. Financial institutes such as banking organization provides various online services for customers such as e-commerce and e-cash. Credit card is one of the supreme conventional methods of online transaction. In recent times, criminal can use illegal ways to carry out fraud transaction by credit card over e-services. Due to the growing volume of electronic payments, the monetary strain of credit-card fraud is turning into a substantial challenge for financial institutions and service providers, thus forcing them to continuously improve their fraud detection systems. Therefore, there is a serious need to develop efficient credit card fraud detection for mortgage companies, financial institutes, credit card enterprises, and banking system.  One of the most common problems in with building credit card detection model is imbalanced data sets. The data set can be imbalanced when the examples of one class significantly outnumber the examples of the other one, i.e., classification becomes very tough as the result may get biased by the dominating class values. In this paper, we will apply two techniques to get rid of this problem for credit card data. Then, the imbalanced dataset used in developing an efficient credit card fraud detection model. In the proposed model, different machine learning algorithms are used such as K-Nearest Neighbor (KNN), Logistic Regression (REG), Latent Dirichlet Allocation (LDA), Classification And Regression Tree (CART), and Naive Bayes (NB). The results show that LDA gives 99.9543 which is best accuracy results while CART algorithm gives 99.9797 which is the higher accuracy in case of up-sampling, and finally, in down-sampling, LDA gives 94.9238 which is the higher accuracy result.

An Efficient Credit Card Fraud Detection Model

With the emergence of one of this century's deadliest pandemics, coronavirus disease (COVID-19) has an enormous effect globally with a quick spread worldwide This made the World Health Organization announce it as a pandemic COVID-19 has pushed countries to follow new behaviors such as social distancing, hand washing, and remote work and to shut down organizations, businesses, and airports At the same time, white hats are doing their best to accommodate the pandemic However, while white hats are protecting people, black hats are taking advantage of the situation, which creates a cybersecurity pandemic on the other hand This paper discusses the cybersecurity issues at this period due to finding information or finding another related research that had not been discussed before This paper presents the cybersecurity attacks during the COVID-19 epidemic time A lot of information has been collected from the World Health Organization (WHO), trusted organizations, news sources, official governmental reports, and available research articles This paper then classifies the cybersecurity attacks and threats at the period of COVID-19 and provides recommendations and countermeasures for each type This paper surveys the cybersecurity attacks and their countermeasures and reports the ongoing cybersecurity attacks and threats at this period of time Moreover, it is also a step towards analyzing the efficiency of the country's infrastructure as well as hackers and criminals' social behavior at the time of the pandemic [ABSTRACT FROM AUTHOR] Copyright of Journal of Advanced Transportation is the property of Hindawi Limited and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission However, users may print, download, or email articles for individual use This abstract may be abridged No warranty is given about the accuracy of the copy Users should refer to the original published version of the material for the full abstract (Copyright applies to all Abstracts )

/pdf/cybersecurity-and-countermeasures-at-the-time-of-pandemic-3tyhdsb4fl.pdf

Ayman El-Sayed

Papers

An efficient IoT based smart farming system using machine learning algorithms

SLIM: A Lightweight Block Cipher for Internet of Health Things

Automated seizure diagnosis system based on feature extraction and channel selection using EEG signals

An Efficient Credit Card Fraud Detection Model

Cybersecurity and Countermeasures at the Time of Pandemic