Cloud Infrastructure Research Articles

Neural network inspired differential evolution based task scheduling for cloud infrastructure

In recent years, cloud computing has become an essential technology for businesses and individuals alike. Task scheduling is a critical aspect of cloud computing that affects the performance and efficiency of cloud infrastructure. During this pandemic where most of the healthcare services like COVID-19 sampling, vaccination process, patient management and other services are dependent on cloud infrastructure. These services come with huge clients and server load in a small instance of time. These task loads can only be managed at cloud infrastructure where an efficient resource management algorithm plays an important role. The optimal utilization of cloud infrastructure and optimization algorithms plays a vital role. The cloud resources rely on the allocation policy of the tasks on cloud resources. Simple static, dynamic, and meta-heuristic techniques provide a solution but not the optimal solution. In such a scenario machine learning and evolutionary algorithms are only the solution. In this work, a hybrid model based on meta-heuristic technique and neural network is proposed. The presented neural network inspired differential evolution hybrid technique provides an optimal assignment of the tasks on cloud infrastructure. The performance of the DE-ANN hybrid approach is performed using performance metrics, average start time(ms), average finish time(ms), average execution time(ms), total completion time(ms), simulation time(ms), and average resource utilization respectively. The proposed DE-ANN approach is validated against BB-BC, and Genetic approaches. It outperforms the existing meta-heuristic techniques i.e. Genetic approach, and Big-Bang Big-Crunch. The performance is evaluated using two configuration scenarios using 5 virtual machines and 10 virtual machines with varying tasks from 1000 to 4500. Experimental results show that the DE-ANN technique significantly improves task scheduling performance compared to other traditional techniques. The technique achieves an average improvement of 19.15% in total completion time(ms), 32.23% in average finish time(ms), 51.95% in average execution time(ms), and 33.24% in average resource utilization respectively. The DE-ANN technique is also effective in handling dynamic and uncertain environments, making it suitable for real-world cloud infrastructures.

Research trends in health information management

Context: Because of the recent pandemic COVID-19, research on management systems health information grew rapidly, underscoring the importance of knowing the investigative trends in these issues to identify the findings and global networks knowledge. Aims: To examine the developments and research trends in information management in health. Methods: A bibliometric analysis was carried out with the 215 results obtained from a search equation performed in the Scopus database. Documents were selected using the inclusion criteria according to the recommendations of the international declaration PRISMA and calculation was performed indicators of quality, quantity, and trend analysis. Results: These were identified as trends: Managing information and knowledge, Educational model/Curriculum design, information-seeking behavior. A research agenda also arises with the themes: reconfiguration of health policies, design and collaborative use in digital resources, telemedicine, meta-analysis tools for decision-making and cloud infrastructures. Conclusions: The United States leads the production in the subject, but there is a gap in Latin America in research in this field of knowledge. Likewise, as new routes in which the research exercise should be deepened are the reconfiguration of health policies, design and collaborative use of digital resources, telemedicine, meta-analysis of tools for decision making and Cloud infrastructures.

IMPLEMENTASI PLATFORM AS A SERVICE (PAAS) PADA DATABASE E-COMMERCE BERBASIS CLOUD COMPUTING

Business competition in the field of information technology continues to increase, one of the technologies itself is cloud computing. Cloud computing can be public or private. One type of cloud computing service used in this study is PaaS. The PaaS cloud computing service provides a platform that users can use to create applications. The Byna Cake shop is a shop that opens a cake business in Aceh, which is located on Pulau Tiga, Aceh, Tamiang. This shop sells various types of cakes which have been produced manually by themselves since 2021. The sales system uses WhatsApp and Instagram media and comes directly to the store, so this system is considered to be less effective and efficient. Therefore, an online sales system is needed, namely by building a web-based E-Commerce application. In implementing this web-based e-commerce application, the author utilizes cloud infrastructure as a cloud provider, namely Microsoft Azure. Computing service used in this research is CMS AbanteCart. Web-based e-commerce application at the Byna Cake store created by configuring a virtual machine to install CMS AbanteCart Packaged By Bitnami on the Microsoft Azure platform. The design used in creating web-based e-commerce applications at the Byna Cake store uses Use Cases and Class Diagrams.

Securing Cloud Application using SHA-256 Hash Algorithm and Antiforgery Token

The cloud supplier has no proposals for cloud data and information that is put away anyplace in the cloud and served around the world. Encryption technology generally serves as the foundation for privacy protection strategies. There are numerous ways of safeguarding security by keeping information from being moved to the cloud. A cloud-based three-tier storage structure is what we propose. The proposed structure is secure and able to make full use of cloud storage. The Hash-Solomon code, which is intended to divide the data into various parts, is utilized in this algorithm. We have lost data-related information in the event that just one piece of data is missing. In this design, we use calculations in light of the idea of containers and information assurance, and afterward can show the security and adequacy of our plan. Additionally, this algorithm is capable of calculating the cloud, cloud, and local computer distribution ratios, respectively, in terms of computational intelligence. SaaS (software as a service): A customer provides a hosted application that can be accessed by a variety of clients over a network. utilized by users With the possible exception of a few user configuration settings, the underlying cloud infrastructure is not managed or controlled by the customer. Examples of SaaS include Microsoft Office 365 and Google Apps

Towards realistic privacy-preserving deep learning over encrypted medical data.

Cardiovascular disease supposes a substantial fraction of healthcare systems. The invisible nature of these pathologies demands solutions that enable remote monitoring and tracking. Deep Learning (DL) has arisen as a solution in many fields, and in healthcare, multiple successful applications exist for image enhancement and health outside hospitals. However, the computational requirements and the need for large-scale datasets limit DL. Thus, we often offload computation onto server infrastructure, and various Machine-Learning-as-a-Service (MLaaS) platforms emerged from this need. These enable the conduction of heavy computations in a cloud infrastructure, usually equipped with high-performance computing servers. Unfortunately, the technical barriers persist in healthcare ecosystems since sending sensitive data (e.g., medical records or personally identifiable information) to third-party servers involves privacy and security concerns with legal and ethical implications. In the scope of Deep Learning for Healthcare to improve cardiovascular health, Homomorphic Encryption (HE) is a promising tool to enable secure, private, and legal health outside hospitals. Homomorphic Encryption allows for privacy-preserving computations over encrypted data, thus preserving the privacy of the processed information. Efficient HE requires structural optimizations to perform the complex computation of the internal layers. One such optimization is Packed Homomorphic Encryption (PHE), which encodes multiple elements on a single ciphertext, allowing for efficient Single Instruction over Multiple Data (SIMD) operations. However, using PHE in DL circuits is not straightforward, and it demands new algorithms and data encoding, which existing literature has not adequately addressed. To fill this gap, in this work, we elaborate on novel algorithms to adapt the linear algebra operations of DL layers to PHE. Concretely, we focus on Convolutional Neural Networks. We provide detailed descriptions and insights into the different algorithms and efficient inter-layer data format conversion mechanisms. We formally analyze the complexity of the algorithms in terms of performance metrics and provide guidelines and recommendations for adapting architectures that deal with private data. Furthermore, we confirm the theoretical analysis with practical experimentation. Among other conclusions, we prove that our new algorithms speed up the processing of convolutional layers compared to the existing proposals.

System Level Benchmarking of Public Clouds

It is important for cloud users to be able to evaluate and compare different cloud services to achieve high performance and maximize cost savings. To that end, this research benchmarked Amazon web services elastic compute cloud and Rackspace cloud infrastructure and compared the results for the two public cloud providers. The intent of the study was to determine how these selected providers perform with regards to system parameter usage and hence three system-level benchmarks: STREAM, IOR, and NPB-EP were run on different configurations to provide an insight to the cloud users in selection of provider on VM clusters of 1,2,4,6, and 8 nodes. The clusters were created with similar virtual machines from both providers. The benchmarks examined bandwidth, I/O and CPU performance. A comparison of results for the two providers is presented graphically and T-test applied to determine if differences are significant. Observations were taken at multiple times at different time periods on weekdays and weekends to examine variance of cloud performance.

Threshold Cryptography-Based Secure Vehicle-to-Everything (V2X) Communication in 5G-Enabled Intelligent Transportation Systems

Implementing 5G-enabled Vehicle-to-Everything (V2X) intelligent transportation systems presents a promising opportunity to enhance road safety and traffic flow while facilitating the integration of artificial intelligence (AI) based solutions. Yet, security and privacy concerns pose significant challenges that must be addressed. Therefore, researchers have focused on improving the security and integrity of vehicle data sharing, with a particular emphasis on V2X application layer security and privacy requirements. This is crucial given that V2X networks can consist of vehicles manufactured by different companies and registered in various jurisdictions, which may only be within communication range for a few seconds. Thus, it is necessary to establish a trusting relationship between vehicles quickly. The article proposes a threshold cryptography-based key exchange protocol that meets the key requirements for V2X data sharing and privacy, including the rapid establishment of trust, the maintenance of vehicle anonymity, and the provision of secure messages. To evaluate the feasibility and performance of the proposed protocol, a tailored testbed that leverages the NS-3 network simulator, a commercial 5G network, and public cloud infrastructure is used. Overall, the proposed protocol provides a potential solution for addressing security and privacy concerns in V2X networks, which is essential for successfully implementing and adopting this technology.

Abstract LB073: NCI’s broad-use collections: Accelerating discovery process by improving access to individual-level genomics and other -omics data

Abstract Genomic data sharing increases our understanding of factors that influence health and diseases by enabling additional research questions from secondary data users, increasing statistical power through combining multiple data sources, facilitating reproducibility and validation of research results, and supporting innovation with the development of research tools and methodologies. Research using large-scale genomic and other-omics data is no longer limited by storage space or slow downloading speed for individual datasets. Innovations like cloud infrastructure enable computing over many datasets at multiple locations at once. These developments have increased the need for faster, more efficient processes for data access and sharing. To support scientific exploration and meet the demand for analysis of biomedical data, the National Cancer Institute (NCI) has created two large collections of the broad-use studies within the database of Genotypes and Phenotypes (dbGaP). These collections comply with the consent of the study (data use limitations) for how secondary access to studies are determined. NCI’s Collection of Datasets for General Research Use comprises 284 studies with individual-level data sets, and permits approved users to explore broad research interest, including methods and tool development. NCI’s Collection of Datasets for Health, Medical, and Biomedical (HMB) Research Purposes is comprised of 65 studies of individual-level that are permitted for research interests specific to any health, medical, or biomedical research only. The HMB collection could be used for methods and tool development; research interests involving ancestry/populations studies must be dependent on a health/medical condition. Through these collections, investigators will have the potential to add access to 349 datasets to their approved research projects or submit a new project request for access to the broad-use collections. As new genomic studies are registered by NCI for release through dbGaP, they will be automatically added to these collections. NCI anticipates through the implementation of these broad-use collections a requestor could have access to approximately 70% of NCI’s studies in controlled-access repositories.The streamlined access to broad-use datasets expedites data sharing and potentially accelerates the discovery process. This approach reduces redundancies for obtaining controlled-access data. Citation Format: Freddie L. Pruitt, Michael Feolo, Subhashini Jagu, Jaime Guidry Auvil. NCI’s broad-use collections: Accelerating discovery process by improving access to individual-level genomics and other -omics data [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 2 (Clinical Trials and Late-Breaking Research); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(8_Suppl):Abstract nr LB073.

Using Amazon Kinesis Service for Data Transfer from IoT Devices to Cloud Infrastructure

IoT devices connected to the Amazon Web Services (AWS) cloud use the loT interface and the MQTT protocol for communication purposes. In addition to these basic communication tools, AWS has developed specialized services for transmitting telemetry data from smart devices. Firehose allows you to upload data directly to the AWS S3 data warehouse (cloud-specific file system). Kinesis service is even more powerful; it enables the user to build back-end data logic, which is automatically applied when data arrives. Also, Kinesis allows running analytics of the telemetry data using artificial intelligence techniques to discover hidden trends and consistent patterns. This article describes how to set up an IoT device using the AWS C++ SDK so that telemetry data it generates is processed by Kinesis services. The firmware of the device connects to the AWS provider using the SDK APIs and sends telemetry data as Kinesis service data packets; a Kinesis lambda function is created on the server side in the cloud to store the received data in S3 storage and send the data to the DynamoDB database after processing. Using Kinesis services allows the user to utilize all power tools provided by the AWS framework for processing and analyzing their data (Amazon constantly develops and enhances this set of tools).

The role of capabilities in digital service development and delivery: the case of start-up organisations

PurposeDigital technologies create myriad innovation opportunities and have inspired the establishment of many new start-ups in recent years. Despite the growing knowledge on digital entrepreneurship, few studies explore how start-ups exploit these opportunities to achieve entrepreneurial success. The purpose of this paper is to explore start-ups’ capabilities for successful delivery of digital artefacts in a cloud computing infrastructure.Design/methodology/approachEmpirical data were collected during a qualitative case study of an established start-up in the Chinese market by interviewing 41 interviewees. Informed by the notion of dynamic capabilities and using the Gioia methodology, the case firm's life cycle was analysed in detail.FindingsThe study identifies start-ups’ ordinary and dynamic capabilities for successful development and delivery of digital services. The findings provide insights into a portfolio of start-ups’ capabilities, namely adaptation, networking, reengineering and refinement.Originality/valueThe study suggests that start-ups’ capabilities and underlying entrepreneurial actions determine the degree to which adoption of digital technologies create and transfer value to customers. The study offers specific insights into how start-ups successfully develop and deliver digital artefacts in a cloud infrastructure based on entrepreneurs' prior expertise, vision and accumulated experience.

ReaLPrune: ReRAM Crossbar-Aware Lottery Ticket Pruning for CNNs

Training machine learning (ML) models at the edge (on-chip training on end user devices) can address many pressing challenges including data privacy/security, increase the accessibility of ML applications to different parts of the world by reducing the dependence on the communication fabric and the cloud infrastructure, and meet the real-time requirements of AR/VR applications. However, existing edge platforms do not have sufficient computing capabilities to support complex ML tasks such as training large CNNs. ReRAM-based architectures offer high-performance yet energy efficient computing platforms for on-chip CNN training/inferencing. However, ReRAM-based architectures are not scalable with the size of the CNN. Larger CNNs have more weights, which requires more ReRAM cells that cannot be integrated in a single chip. Moreover, training larger CNNs on-chip will require higher power, which cannot be afforded by these smaller devices. Pruning is an effective way to solve this problem. However, existing pruning techniques are either targeted for inferencing only, or they are not crossbar-aware. This leads to sub-optimal hardware savings and performance benefits for CNN training on ReRAM-based architectures. In this paper, we address this problem by proposing a novel crossbar-aware pruning strategy, referred as ReaLPrune, which can prune more than 90% of CNN weights. The pruned model can be trained from scratch without any accuracy loss. Experimental results indicate that ReaLPrune reduces hardware requirements by 77.2% and accelerates CNN training by ∼20× compared to unpruned CNNs. ReaLPrune also outperforms other crossbar-aware pruning techniques in terms of both performance and hardware savings. In addition, ReaLPrune is equally effective for diverse datasets and more complex CNNs.

CRSExtractor: Automated configuration option read sites extraction towards IoT cloud infrastructure

There are a large number of solutions for big data processing in the Internet of Things (IoT) environments, among which the IoT cloud infrastructure is one of the most mature solutions. Typically, modern IoT cloud infrastructures have different kinds of configuration options. The diversity of configurations leads to frequent software configuration errors. Generally, troubleshooting configuration errors relies on finding the mapping relationship between configuration options in the documents (e.g., official manuals) and their read sites in the source code. Most current works still manually extract configuration read sites. Automated methods are not always interchangeable and they incur considerable time overheads and low extraction rates.In this paper, we propose CRSExtractor, an automatic technique for extracting configuration read sites based on intra-procedural analysis. Using our technique, configuration option read sites can be automatically identified and built into maps with configuration options. Evaluations on several core software systems of IoT cloud platforms, such as Hadoop and Cassandra, show that our approach performs well, with an accuracy rate of over 90% and efficiency nearly 20 times faster than previous works.

PerfSim: A Performance Simulator for Cloud Native Microservice Chains

Cloud native computing paradigm allows microservice-based applications to take advantage of cloud infrastructure in a scalable, reusable, and interoperable way. However, in a cloud native system, the vast number of configuration parameters and highly granular resource allocation policies can significantly impact the performance and deployment cost. For understanding and analyzing these implications in an easy, quick, and cost-effective way, we present PerfSim, a discrete-event simulator for approximating and predicting the performance of cloud native service chains in user-defined scenarios. To this end, we proposed a systematic approach for modeling the performance of microservices endpoint functions by collecting and analyzing their performance and network traces. With a combination of the extracted models and user-defined scenarios, PerfSim can then simulate the performance behavior of all services over a given period and provide an approximation for system KPIs, such as requests' average response time. Using the processing power of a single laptop, we evaluated both simulation accuracy and speed of PerfSim in 104 prevalent scenarios and compared the simulation results with the identical deployment in a real Kubernetes cluster. We achieved ~81-99% simulation accuracy in approximating the average response time of incoming requests and ~16-1200 times speed-up factor for the simulation.

Medium access in cloud-based for the internet of things based on mobile vehicular infrastructure

Smart cities are made up of a large number of smart, intelligent gadgets that can sense, compute, act, and communicate. Focusing on how data is transferred between sensory devices and applications in the internet of things (IoT), and cyber-physical systems have led to 5G/IoT integration. This paper proposes a revolutionary architecture for mobile vehicular cloud infrastructure that takes variable weather, road, and traffic circumstances into consideration. It proposes a dynamic speed management system for smart cities. To optimize system flexibility and reduce costs, the system makes advantage of the most recent advancements in wireless communication and utilizes current telecommunication infrastructures utilized in data streaming, sound, and video. The study presents an internet protocol (IP) real-time subsystem-network-based framework for requesting bandwidth from free wireless channel resources using the channell quality indicator channel.

Investigation of Efficient Backup Tecniques To Reduce Late In Cloud Systems: A Modeling Study

From the formation stages of the information society to the present day, new developments have been experienced in many areas such as data formation, processing, storage and sharing of data in electronic environments. In this context, many new technological concepts have been included in our lives. When it comes to data storage environments, the concept of "Cloud Computing", which has been developing and increasing in popularity in recent years, comes to our minds. Cloud computing, with its known definition, is an internet-based technology service that provides access to the data stored on its servers at any time through internet access and allows users to benefit from the services offered by the system to the extent they want. While the advantages of cloud computing systems such as low cost, high performance, not requiring physical materials and being flexible can be mentioned, it is also emphasized that it brings many problems in terms of system. The most important of these problems; the lack of resources in cloud computing service providers, causing unpredictable delays in server response times. Based on all this information, this research is structured on the development of solution processes on these delays. In this sense, it is possible to consider three areas of cloud infrastructure; cloud computing, distributed storage and streaming communications. One of the first solutions that comes to mind is duplicating a task on multiple machines and waiting for the earliest copy to finish can reduce service latency; but intuitively, it costs additional computing resources and increases the queue load on servers. In this context, the effect of redundancy on the tail will be analyzed in the first part of the research. As a solution proposal, in this section, it will be discussed that service delays and queue load can be reduced by using the replication method, thus making the system more efficient. In a similar way, by requesting more than one copy of a file and waiting for any of them to arrive, the cloud storage requests will be accelerated for content download. In the second part of the research, generalization will be made from replication to coding and the (n, k) fork-join model will be studied to analyze the delay in accessing a storage system with (n, k) deletion code. This analysis will provide practical information that several users can access a content at the same time and provide faster service to the relevant users. Achieving low latency in streaming communication is even more difficult, as packets must be transmitted quickly and sequentially. Based on this structure, in the third part of the research, it is aimed to develop deletion codes to transmit redundant packet combinations and ensure smooth playback. Experimental modeling method was used as a research method in the study. In general, the aim of the research is to blend various mathematical tools from queuing, theory coding and renewal processes. It is foreseen that the techniques and insights to be developed with these dimensions of the research can be applied to other systems with stochastically changing components, and integrated studies can be made and contribute to the literature in this context.

An IoT-Based Solution for Monitoring and Controlling Battery Energy Storage Systems at Residential and Commercial Levels

Today, increasing numbers of batteries are installed in residential and commercial buildings; by coordinating their operation, it is possible to favor both the exploitation of renewable sources and the safe operation of electricity grids. However, how can this multitude of battery storage systems be coordinated? Using the Application Programming Interfaces of the storage systems’ manufacturers is a feasible solution, but it has a huge limitation: communication to and from storage systems must necessarily pass through the manufacturers’ cloud infrastructure. Therefore, this article presents an IoT-based solution which allows monitoring/controlling battery storage systems, independently from the manufacturers’ cloud infrastructure. More specifically, a home gateway locally controls the battery storage using local APIs via Wi-Fi on the condition that the manufacturer enables them. If not, an auxiliary device allows the home gateway to establish a wired communication with the battery storage via the SunSpec protocol. Validations tests demonstrate the effectiveness of the proposed IoT solution in monitoring and controlling ABB, Sonnen and SolarEdge storage systems.

THE DATA CENTER CANNOT HOLD: DATA COLONIALISM AND THE “NIMBUS PROJECT”

Following the infrastructural turn in media studies with its focus on the material and social practices, this paper offers to reexamine contemporary data colonialism by empirically exploring some of its most crucial infrastructural artifacts – data centers. Particularly, this paper explores six data centers currently built in Israel as part of "Project Nimbus" – a $1.2 billion tender offered by the Israeli government to move its computational infrastructure "to the cloud". The tender was won by Amazon Web Services (AWS) and Google Cloud, and has drawn considerable attention, both due to its high-cost and technical complexity; and due to attempts by these companies' workers to curtail the tech giants' involvement in Israel/Palestine on moral grounds. Power differentials are also present within the Israeli society, as intimate governmental data will be processed and stored by foreign US companies. Based on thematic analysis of local journalistic sources, public officials’ documents, local planning authorities and the tender winners themselves, we delineate the concrete materialization of this cloud infrastructure. We show that the notion of data colonialism is complicated within project Nimbus, when lines blur in terms of whose data is colonized by whom, whose lands are used (and colonized) by these centers, and whose resources (predominantly electricity and water) will be used for their functioning. Thus, this paper offers a more granular understanding of data colonialism, and of the different actors and stakeholders involved in the creation and sustainment of this emerging global regime.

InSAR-Based Early Warning Monitoring Framework to Assess Aquifer Deterioration

Aquifer surveillance is key to understanding the dynamics of groundwater reservoirs. Attention should be focused on developing strategies to monitor and mitigate the adverse consequences of overexploitation. In this context, ground surface deformation monitoring allows us to estimate the spatial and temporal distribution of groundwater levels, determine the recharge times of the aquifers, and calibrate the hydrological models. This study proposes a methodology for implementing advanced multitemporal differential interferometry (InSAR) techniques for water withdrawal surveillance and early warning assessment. For this, large open-access images were used, a total of 145 SAR images from the Sentinel 1 C-band satellite provided by the Copernicus mission of the European Space Agency. InSAR processing was carried out with an algorithm based on parallel computing technology implemented in cloud infrastructure, optimizing complex workflows and processing times. The surveillance period records 6-years of satellite observation from September 2016 to December 2021 over the city of Chillan (Chile), an area exposed to urban development and intensive agriculture, where ~80 wells are located. The groundwater flow path spans from the Andes Mountain range to the Pacific Ocean, crossing the Itata river basin in the Chilean central valley. InSAR validation measurements were carried out by comparing the results with the values of continuous GNSS stations available in the area of interest. The performance analysis is based on spatial analysis, time series, meteorological stations data, and static level measurements, as well as hydrogeological structure. The results indicate seasonal variations in winter and summer, which corresponds to the recovery and drawdown periods with velocities > −10 mm/year, and an aquifer deterioration trend of up to 60 mm registered in the satellite SAR observation period. Our results show an efficient tool to monitor aquifer conditions, including irreversible consolidation and storage capacity loss, allowing timely decision making to avoid harmful exploitation.

Intrusion Detection on AWS Cloud through Hybrid Deep Learning Algorithm

The network security and cloud environment have been playing vital roles in today’s era due to increased network data transmission, the cloud’s elasticity, pay as you go and global distributed resources. A recent survey for the cloud environment involving 300 organizations in North America with 500 or more employees who had spent a minimum of USD 1 million on cloud infrastructure, as per March 2022 statistics, stated that 79% of organizations experienced at least one cloud data breach. In the year 2022, the AWS cloud provider leads the market share with 34% and a USD 200 billion cloud market, proving important and producing the motivation to improve the detection of intrusion with respect to network security on the basis of the AWS cloud dataset. The chosen CSE-CIC-IDS-2018 dataset had network attack details based on the real time attack carried out on the AWS cloud infrastructure. The proposed method here is the hybrid deep learning based approach, which uses the raw data first to do the pre-processing and then for normalization. The normalized data have been feature extracted from seventy-six fields to seven bottlenecks using Principal Component Analysis (PCA); those seven extracted features of every packet have been categorized as two-way soft-clustered (attack and non-attack) using the Smart Monkey Optimized Fuzzy C-Means algorithm (SMO-FCM). The attack cluster data have been further provided as inputs for the deep learning based AutoEncoder algorithm, which provides the outputs as attack classifications. Finally, the accuracy of the results in intrusion detection using the proposed technique (PCA + SMO-FCM + AE) is achieved as 95% over the CSE-CIC-IDS-2018 dataset, which is the highest known for state-of-the-art protocols compared with 11 existing techniques.

IoT Smart Flooring Supporting Active and Healthy Lifestyles.

The lack of physical exercise is among the most relevant factors in developing health issues, and strategies to incentivize active lifestyles are key to preventing these issues. The PLEINAIR project developed a framework for creating outdoor park equipment, exploiting the IoT paradigm to build "Outdoor Smart Objects" (OSO) for making physical activity more appealing and rewarding to a broad range of users, regardless of their age and fitness. This paper presents the design and implementation of a prominent demonstrator of the OSO concept, consisting of a smart, sensitive flooring, based on anti-trauma floors commonly found in kids playgrounds. The floor is equipped with pressure sensors (piezoresistors) and visual feedback (LED-strips), to offer an enhanced, interactive and personalized user experience. OSOs exploit distributed intelligence and are connected to the Cloud infrastructure by using a MQTT protocol; apps have then been developed for interacting with the PLEINAIR system. Although simple in its general concept, several challenges must be faced, related to the application range (which called for high pressure sensitivity) and the scalability of the approach (requiring to implement a hierarchical system architecture). Some prototypes were fabricated and tested in a public environment, providing positive feedback to both the technical design and the concept validation.