Towards secure IoT networks: A comprehensive study of metaheuristic algorithms in conjunction with CNN using a self-generated dataset.

The Internet of Things (IoT) has radically reformed various sectors and industries, enabling unprecedented levels of connectivity and automation. However, the surge in the number of IoT devices has also widened the attack surface, rendering IoT networks potentially susceptible to a plethora of security risks. Addressing the critical challenge of enhancing security in IoT networks is of utmost importance. Moreover, there is a considerable lack of datasets designed exclusively for IoT applications. To bridge this gap, a customized dataset that accurately mimics real-world IoT scenarios impacted by four different types of attacks-blackhole, sinkhole, flooding, and version number attacks was generated using the Contiki-OS Cooja Simulator in this study. The resulting dataset is then consequently employed to evaluate the efficacy of several metaheuristic algorithms, in conjunction with Convolutional Neural Network (CNN) for IoT networks. •The proposed study's goal is to identify optimal hyperparameters for CNNs, ensuring their peak performance in intrusion detection tasks.•This study not only intensifies our comprehension of IoT network security but also provides practical guidance for implementation of the robust security measures in real-world IoT applications.

Artificial intelligence and internet of things oriented sustainable precision farming: Towards modern agriculture.

Agriculture encompasses the study, practice, and discipline of plant cultivation. Agriculture has an extensive history dating back thousands of years. Depending on climate and terrain, it began independently in various locations on the planet. In comparison to what could be sustained by foraging and gathering, agriculture has the potential to significantly increase the human population. Throughout the twenty-first century, precision farming (PF) has increased the agricultural output. precision agriculture (PA) is a technology-enabled method of agriculture that assesses, monitors, and evaluates the needs of specific fields and commodities. The primary objective of this farming method, as opposed to conventional farming, is to increase crop yields and profitability through the precise application of inputs. This work describes in depth the development and function of artificial intelligence (AI) and the internet of things (IoT) in contemporary agriculture. Modern day-to-day applications rely extensively on AI and the IoT. Modern agriculture leverages AI and IoT for technological advancement. This improves the accuracy and profitability of modern agriculture. The use of AI and IoT in modern smart precision agricultural applications is highlighted in this work and the method proposed incorporates specific steps in PF and demonstrates superior performance compared to existing classification methods. It achieves a remarkable accuracy of 98.65%, precision of 98.32%, and recall rate of 97.65% while retaining competitive execution time of 0.23 s, when analysing PF using the FAOSTAT benchmark dataset. Additionally, crucial equipment and methods used in PF are described and the vital advantages and real-time tools utilised in PA are covered in detail.

A Novel Generative Adversarial Network-Based Approach for Automated Brain Tumour Segmentation.

Background: Medical image segmentation is more complicated and demanding than ordinary image segmentation due to the density of medical pictures. A brain tumour is the most common cause of high mortality. Objectives: Extraction of tumorous cells is particularly difficult due to the differences between tumorous and non-tumorous cells. In ordinary convolutional neural networks, local background information is restricted. As a result, previous deep learning algorithms in medical imaging have struggled to detect anomalies in diverse cells. Methods: As a solution to this challenge, a deep convolutional generative adversarial network for tumour segmentation from brain Magnetic resonance Imaging (MRI) images is proposed. A generator and a discriminator are the two networks that make up the proposed model. This network focuses on tumour localisation, noise-related issues, and social class disparities. Results: Dice Score Coefficient (DSC), Peak Signal to Noise Ratio (PSNR), and Structural Index Similarity (SSIM) are all generally 0.894, 62.084 dB, and 0.88912, respectively. The model's accuracy has improved to 97 percent, and its loss has reduced to 0.012. Conclusions: Experiments reveal that the proposed approach may successfully segment tumorous and benign tissues. As a result, a novel brain tumour segmentation approach has been created.

Energy efficiency in cloud computing data centers: a survey on software technologies.

Cloud computing is a commercial and economic paradigm that has gained traction since 2006 and is presently the most significant technology in IT sector. From the notion of cloud computing to its energy efficiency, cloud has been the subject of much discussion. The energy consumption of data centres alone will rise from 200 TWh in 2016 to 2967 TWh in 2030. The data centres require a lot of power to provide services, which increases CO2 emissions. In this survey paper, software-based technologies that can be used for building green data centers and include power management at individual software level has been discussed. The paper discusses the energy efficiency in containers and problem-solving approaches used for reducing power consumption in data centers. Further, the paper also gives details about the impact of data centers on environment that includes the e-waste and the various standards opted by different countries for giving rating to the data centers. This article goes beyond just demonstrating new green cloud computing possibilities. Instead, it focuses the attention and resources of academia and society on a critical issue: long-term technological advancement. The article covers the new technologies that can be applied at the individual software level that includes techniques applied at virtualization level, operating system level and application level. It clearly defines different measures at each level to reduce the energy consumption that clearly adds value to the current environmental problem of pollution reduction. This article also addresses the difficulties, concerns, and needs that cloud data centres and cloud organisations must grasp, as well as some of the factors and case studies that influence green cloud usage.

A Social Network Analysis Approach to COVID-19 Community Detection Techniques.

Machine learning techniques facilitate efficient analysis of complex networks, and can be used to discover communities. This study aimed use such approaches to raise awareness of the COVID-19. In this regard, social network analysis describes the clustering and classification processes for detecting communities. The background of this paper analyzed the geographical distribution of Tambaram, Chennai, and its public health care units. This study assessed the spatial distribution and presence of spatiotemporal clustering of public health care units in different geographical settings over four months in the Tambaram zone. To partition a homophily synthetic network of 100 nodes into clusters, an empirical evaluation of two search strategies was conducted for all IDs centrality of linkage is same. First, we analyzed the spatial information between the nodes for segmenting the sparse graph of the groups. Bipartite The structure of the sociograms 1-50 and 51-100 was taken into account while segmentation and divide them is based on the clustering coefficient values. The result of the cohesive block yielded 5.86 density values for cluster two, which received a percentage of 74.2. This research objective indicates that sub-communities have better access to influence, which might be leveraged to appropriately share information with the public could be used in the sharing of information accurately with the public.

Geospatial multivariate analysis of COVID-19: a global perspective.

This manuscript presents a geospatial and temporal analysis of the COVID'19 along with its mortality rate worldwide and an empirical evaluation of social distance policies on economic activities. Stock Market Indices, Purchasing Manager Index (PMI), and Stringency Index values are evaluated with respect to rising COVID-19 cases based on the collected data from Jan 2020 to June 2021. The findings for the stock market index reveal the highest negative correlation coefficient value, i.e., -0.2, for the Shanghai index, representing a negative relation on stock markets, whereas the value of the correlation coefficient is minimum for Indian markets, i.e., 0.3, indicating the most impact by COVID-19 spread. Further, the results concerning PMI show that the highest value of the correlation coefficient is for the China i.e., -0.52, points to the sharpest pace of contraction. This reflects the lower value of the correlation indicating that the economy is on the way of growth, which can be seen from the PMI value of the various countries. The manuscript presents a novel geospatial model by empirically evaluating the correlation coefficient of COVID-19 with stock market index, PMI, and stringency index to understand the effect of COVID-19 on the global economy.

No evidence for global decrease in CO2 concentration during the first wave of COVID-19 pandemic.

Numerous studies have reported that CO2 emissions have decreased because of global lockdown during the first wave of the COVID-19 pandemic. However, previous estimates of the global CO2 concentration before and after the outbreak of the COVID-19 pandemic are limited because they are based on energy consumption statistics or local specific in-situ observations. The aim of the study was to explore objective evidence for various previous studies that have claimed the global CO2 concentration decreased during the first wave of the COVID-19 pandemic. There are two ways to measure the global CO2 concentration: from the top-down using satellites and the bottom-up using ground stations. We implemented the time-series analysis by comparing the before and after the inflection point (first wave of COVID-19) with the long-term CO2 concentration data obtained from World Meteorological Organization Global Atmosphere Watch (WMO GAW) and Greenhouse Gases Observing Satellite (GOSAT). Measurements from the GOSAT and GAW global monitoring stations show that the CO2 concentrations in Europe, China, and the USA have continuously risen in March and April 2020 compared with the same months in 2019. These data confirm that the global lockdown during the first wave of the COVID-19 pandemic did not change the vertical CO2 profile at the global level from the ground surface to the upper layer of the atmosphere. The results of this study provide an important foundation for the international community to explore policy directions to mitigate climate change in the upcoming post-COVID-19 period.