VOLUME 9, ISSUE 12, DECEMBER 2021

Abstract: The electric propulsion system of Unmanned Aerial Vehicles (UAV) is shifting from open propeller to the shrouded or ducted propeller due to its several advantages over open propellers. Numerous efforts and works have been made to improve the efficiency of the ducted propeller since its introduction in the 1930s. There was a significant increase in flight time due to increase in propulsive efficiency. One factor taken in consideration for overall efficiency of a UAV is its flight time. There has been much research and work on optimization of UAV to increase the flight time, either through minimizing the weight/introducing composite materials or by improving the efficiency of the electronic system or both. This work is an attempt to develop an onboard electricity generation system through an efficient duct equipped with a generator-turbine assembly. This is to increase the flight time without reducing the overall efficiency of the Unmanned Aerial Vehicle (UAV).

Keywords: Re-charging while flying, dynamo, ducted propeller, increased flight time, long range, high endurance, onboard power generation, increased overall efficiency and FM.

Abstract: The most promising materials in today’s engineering environment are light weight hybrid composites. They have a high strength-to-weight ratio and are used in variety of industries, including aviation and automobiles. When the chose reinforcements are cost-effective, the production of these prospective hybrid composites is less expensive. Aluminum alloy, rice husk, and silicon carbide were used as composite materials. Fabrication of composite materials has been completed. The hardness of several combinations of Aluminum, Silicon, and Rice husk ash reinforcements was investigated in fabricated metal matrix composites. As the content of rice husk and SiC increases, the shear strength of Al Composites improves. These composites can be employed anywhere lightweight materials with good stiffness and strength are required, resulting in low-cost aluminum.

Abstract: Winglets being a small structure play an important role in reducing induced drag in an aircraft. The drag breakdown of a typical transport aircraft shows that the lift-induced drag can amount to as much as 40% of the total drag at cruise conditions and 80–90% of the total drag in take-off configuration. One way of reducing lift-induced drag is by using wingtip devices. GEO-777 specifications are taken to perform with a spiroid winglet. Indeed, the total drag count reduced with the help of winglets. A model composed of wing of boeing-777 is designed using CATIA and also the spiroid winglet are designed and attached with a boeing 777 wing using CATIA. Then the modelled wing is meshed using CFD. The meshed model will be analysed using ANSYS FLUENT. Finally, the difference in calculations is calculated using the analysis results.

Keywords: Winglet, Induced drag, Spiroid winglet, CATIA, CFD, ANSYS FLUENT.

Abstract: In recent years, drones have undergone tremendous development. Due to low price and ease of use, drones have been widely utilized in many application scenarios, which potentially pose great threats to public security and personal privacy. To mitigate these threats, it is necessary to deploy an anti-drone system in the sensitive area to detect, localize and defend against the intruding drones. In this paper, a comprehensive technology utilized for drone surveillance implemented to the existing anti drone systems. A counter drone system includes a cueing sensor to detect the presence of an object wherein the cueing sensor cues the presence of a target drone. A long-range LIDAR system having a sensor pointed in a direction of the target drone to acquire and track at long range the target drone to provide an accurate location of the target drone. The motion of the target drone used to maintain the track of the target drone and a threat detector. The LIDAR data augmented to determine the target drone.

Keywords: LIDAR, Cueing Sensors, Anti-Drone, Intruding Drones.

Abstract: The main objective of this project is for security system. If vehicle moves very near to the opposite Vehicle, then it applies brake automatically. It is used for avoiding accident over by racing in highways and parking or busy traffic areas through Electronic braking.
Electronic braking system works faster when compared to other devices. So we can achieve the high efficient operation by programming the microcontroller.
They are often applied to the rear wheels since most of the stopping happens in the disk. Front of the vehicle and therefore the heat generated in the rear is significantly less. Drum brakes are also occasionally fitted as the parking (and emergency) brake even when the rear wheels use disk brakes as the main brakes. In this situation, a small drum is usually fitted within or as part of the brake.

Keywords: Security System, Electromagnetic Braking System, Brake, Microcontroller

Abstract: In the current period, because of the far reaching accessibility of the Internet, it is incredibly simple for individuals to convey and share interactive media substance with one another. Nonetheless, simultaneously, secure exchange of individual and protected material has turned into a basic issue. Thusly, secure method for information move are the most dire need of the time. Steganography is the science and specialty of shielding the restricted information from an unapproved access. The steganographic approaches hide restricted information into a cover record of type sound, video, text or potentially image. The genuine test in steganography is to accomplish high strength and limit without dealing on the subtlety of the cover document. In this article, a proficient steganography strategy is proposed for the exchange of privileged information in computerized images utilizing number hypothesis. For this reason, the proposed technique addresses the cover image utilizing the Fibonacci grouping. The portrayal of an image in the Fibonacci succession permits expanding the bit planes from 8-bit to 12-bit planes. The test aftereffects of the proposed strategy in examination with other existing steganographic strategies display that our technique accomplishes high installing of privileged information as well as gives top caliber of stego images as far as pinnacle signal-to-clamor proportion (PSNR). Besides, the power of the technique is likewise assessed within the sight of salt and pepper clamor assault on the cover images.

Keywords: Security, Object , Integrity , Manipulation , Information , Hiding, Partition , Technique

Abstract: India is an agricultural country cultivating more number of ground nuts, corns, etc., in the village sides of the country. The available sowing machines are imported from foreign countries. The imported machines are not only bulk in size but cost also very high. In this proposal an attempt has been made for the design and fabrication of maintenance free seed sowing machine exclusively for farmers at low cost. The different components of above multipurpose seed sowing machine are modelled using one of the end parametric modelling software Solid Works and it was simulated by the software Automation Studio. The modelled components are fabricated and assembled together to form a complete machine. The electro-pneumatic action is a control system for pipe organs, whereby air pressure, controlled by an electric current and operated by the keys of an organ console, opens and closes valves within wind chests. This method is used for seed sowing technique. According to the cylinder controlled action seed will show in the land. Here we are using cascade method for cylinder control. This method is very useful for short term and long term crops. In cascade method, we are use only four sequence for seed sowing those are A+, B+, B-, A-. Due to hopper open and close condition seed will easily have sowed in land.

Keywords: Pneumatic, Solid works, Automation studio, electro-pneumatic, sowing machine.

Abstract: Credit card fraud is the most serious problem in today's world, and there is an urgent need to combat it. "Credit card fraud is the process of cleaning dirty money, making the source of funds untraceable." On a daily basis, huge amounts of money are exchanged in the global market, making detecting credit card fraud activity a difficult task. As previously stated, (Anti-credit card fraud Suite) is introduced to detect suspicious activities, but it is only applicable to individual transactions and not to other bank account transactions. To address these issues, we propose a machine learning method based on 'Structural Similarity.' This method identifies common attributes and behaviour with other bank account transactions. It is difficult to detect credit card fraud transactions from large datasets, so we propose case reduction methods to reduce the input dataset and then find pairs of transactions with other bank accounts that share common attributes and behaviour.

Keywords: Machine learning ,SVM algorithm

Abstract: The present study determines the mental health of Chess Players and Non Chess Players. The, Mental health was measured by the using General Health Questionnaire (GHQ -12) . The General Health Questionnaire (GHQ) is a measure of current mental health and since its development by Goldberg in the 1970s it has been extensively used in different settings and different cultures. The 12-item GHQ-12 comprises six ‘positive’ and six ‘negative’ items . The sample consisted of 50 Chess Players and 50 and non Chess Players from Nanded at the end of 2015-2016 academic year in their study. The findings of the study revealed that Chess Players was found to have got more Capable of making Decision , Been able to enjoy and Been feeling reasonably happy as compare to Non- Chess Players . The findings of the study revealed that Chess Players was found to have got more Capable of making Decision as compare to Non- Chess Players and The findings of the study revealed that Chess Players was found to have got more Been feeling reasonably happy as compare to Non- Chess Players

Abstract: The aim of the research was to determine the effects of physical fitness training programmes on Self-esteem and Ethics of volleyball players. Only one group was targeted experimental group, there was no control group. The 30 male volleyball players participated in the study and their age ranged between 19-30 years. Training was given to the experimental groups. The data was collected through respondents in the form of different experimental tests. A training program was planned for 12 weeks, 5 days a week and 90 minutes a day. Exercise that use large muscles groups that can be maintained continuously and are aerobic in nature. These exercises include walking, running, jogging, climbing, jumping row and cross country. The result reveals that there was significant effects of Physical fitness training programme was found in Self-esteem and Ethics aspect of Volleyball players.

Keywords: Self-esteem, Ethics, volleyball, Physical fitness

Abstract: The advancement of the new technologies in the field of automotive electronics has brought abundant changes in day to day life of every human being. The driver assistance system are meant to support driver with driving process in order to avoid accidents which enable various users to be better informed and makes safer, more coordinated and smarter use of transport network. The current work says about one such system which uses Alcohol Sensor, Bio- Metric Sensor, and GPS module driving by various applications.

Keywords: Alcohol Sensor, Bio-Metric Sensor and GPS module, Arduino Pro Mini

Abstract: Shunt Active power filters have been proved as useful elements to correct distorted currents caused by non- linear loads in power distribution systems. This paper deals with a Novel Adaptive Hysteresis Band Current Controller, a new control scheme for an Shunt Active Power Filter (APF) to reduce harmonics and to compensate the reactive power of three-phase rectifier. The switching dynamics of a voltage source inverter (VSI) Four pole based three-phase, four- wire shunt APF system with adaptive hysteresis band current control has been studied and verified by simulation. The simulation results of Active Power Filter (APF) control technique, carried out in MATLAB environment, are presented in this paper and are quite satisfactory to reduce harmonics and reactive power components from utility current.

Keywords: Active Power Filter (APF), d-q-0 reference frame, and adaptive hysteresis band current controller.

Abstract: Over the past decade, machine learning has become a game-changing technology in healthcare. In detecting and predicting severity of COVID-19, they build machine learning models that use two datasets: the CT images for COVID-19 patients and those of normal patients and are found to obtain an accuracy of 99.1 percent. Here, researchers propose a cloud approach using two machine learning models that are trained and tested on COVID-19 and non-COVID- 19 (normal) patients by using only data of normal CT chest images. Each of their models predicts COVID-19 patients and severity levels. Major findings would help primary healthcare centers, general medical practitioners, and healthcare workers located far away from hospitals or web-based healthcare systems to care for patients at risk of COVID-19. The rapid increase in health-related data opens a new dimension for information and knowledge discovery in the health domain. Machine learning (ML)/deep learning (DL) technology has attracted a lot of attention in healthcare data analytics among researchers from both academia and industry. ML/DL models are being developed to provide early expertise and intelligent decision support for healthcare systems. Traditional ML approaches rely heavily on a great deal of high-quality labeled data. However, circa 80% of healthcare data is typically stored in unstructured forms such as short messages, free-text records, or images. Such a high percentage of free-text data presents both an opportunity and a challenge for data mining in the healthcare domain. Free-text data offers a fantastic chance for healthcare analytics. However, the information contained in these unstructured data is often not utilized for reasons such as data sparsity, lack of clean patterns, or increased noise. Most regions of the world have stepped into the twenty-first century with a legacy health infrastructure largely based on conventional thinking. Health systems in many developing countries, especially, are still struggling to meet the basic needs of their populations. Many MICs face a tsunami of change, driven by urbanization, demographic transition to aging, and cancer and productivity loss due to COVID-19.
Accurate assessment of the health burden from these demographics for timely predictions of societal long-term impact is a major challenge. Despite facing many challenges, some LMICs have made rapid strides in improving the quality and efficiency of their health systems through leapfrogging. Earth observation offers an amazing potential to provide scalable information highly relevant to health inequalities. The integration of inferring and predicting health burden from earth observation and environmental and climate data with insights from artificial intelligence holds great potential in a further leap forward for the understanding of health inequalities and improvement of the equity of health decisions in sustainable urbanization and development. Cloud computing provides the construction of intelligent and scalable multimedia healthcare systems. However, the latest ML/DL approaches still lack reliable and practical public platforms.

Keywords: Cloud Computing,Machine Learning (ML),Real-Time Diagnosis,Predictive Analytics,Healthcare Analytics,Artificial Intelligence (AI),Health Data Streaming,Telemedicine,Medical Data Prediction,Cloud Infrastructure,Big Data in Healthcare,Data Security in Healthcare,Diagnostic Algorithms,Medical IoT (Internet of Things),Health Monitoring Systems

Abstract: Agriculture plays a significant role in the global economy, and there has been a trend in industrializing agriculture machinery and equipment. This paper proposes a framework that integrates data engineering and machine learning for the predictive maintenance of smart agriculture machinery. This framework is built upon existing state-of- the-art solutions, concepts, and techniques for data engineering and machine learning, along with the innovations of new solutions. This paper highlights the major elements of the collaboration. Challenges, societal impact, and future works are further discussed.

The agriculture sector is a key contributor to the global economy, with an estimated total value of more than 3 trillion dollars per year and corresponding employment of over 1 billion people worldwide. The rapid growth of population increases the demand for basic agricultural supplies. In the era of IoT, pollution prevention, and food safety assurance, agriculture has also been trending towards intelligence, automation, and standardization. There has been a trend in industrializing agriculture machinery and equipment, where a wide range of data sources from working conditions are equipped on agricultural machinery. These data sources may include 1D, 2D, 3D, and 4D data from cameras, LIDARs, radars, and sensor networks. These data sources by design have the potential of being a bridge to connect agriculture and smart city. However, the wide-scale deployments of data-driven smart agriculture have been hindered by the challenge of data engineering for the large-scale, heterogeneous, and sparsely-distributed agriculture data, and insufficient integration of data exploitation and exploration technologies including machine learning for deep analysis, insight mining, and knowledge discovery of agriculture data.

Moreover, a variety of application scenarios in smart agriculture have appeared in recent years, including but not limited to predictive maintenance of agriculture machinery, soil monitoring with sensor networks, and enviromonitoring with remote sensing data for crop estimation. The laboratory research has made promising achievements in devising precise models with techniques from data analytics, machine learning, artificial intelligence, computer vision, and other similar fields. However, these achievements are hardly used in practice because of integration challenges. Integrating data engineering and machine learning for the collaborative, collaborative-wise, and process-wise predictive maintenance of smart agriculture machinery is yet to be studied comprehensively and in-depth.

Keywords: Predictive Maintenance,Smart Agriculture,Machine Learning,Data Engineering,IoT Sensors,Time Series Analysis,Remote Monitoring,Failure Prediction,Remaining Useful Life (RUL),Condition-Based Maintenance,Edge Computing,Big Data Analytics,Sensor Fusion,Agricultural Machinery,Maintenance Optimization.

Abstract: The Data Big Bang that the development of the ICTs has raised is providing us with a stream of fresh and digitized data related to how people, companies, and other organizations interact. To turn these data into knowledge about the underlying behavior of social and economic agents, organizations, and researchers must deal with unstructured and heterogeneous data [1]. Technologies like the Internet, Smartphones, and Smart sensors are generating tons of digitized and fresh data about people and firms' activities that, if properly analyzed, could help reveal trends and monitor economic, industrial, and social behaviors. This new data paradigm is called Big Data, which refers to Volume, Velocity, Variety, and Value in the context of data analysis.

Identifying which data sources are available, what type of data they provide, and how to treat these data is basic to generate as much value as possible for organizations [2]. A Big Data architecture adapted to the specific domain and purpose of the organization contributes to systematizing the process of generating value. The Big Data paradigm also offers many advantages and benefits for companies, governments, and society. The purpose of this paper is to review some sources of Big Data to analyze social and economic behaviors and trends. A classification into three types of sources (article content, audiovisual/social content, and registration content) is made, together with a description of some databases and types of analyses that can be drawn from them. The aim is also to analyze how these sources can be used to analyze social and economic behaviors and trends, with examples that show the potential knowledge that could be achieved. Finally, the limitations and challenges posed by Big Data for social and economic analyses are discussed.

Keywords: Predictive analytics, IT infrastructure, government financial management, fraud detection, data integration, advanced analytics, machine learning, public sector technology, financial oversight, anomaly detection, real-time monitoring, risk assessment, decision support systems, data-driven governance, digital transformation, cybersecurity, automated auditing, cloud computing, artificial intelligence, financial data analysis.

Abstract: In the semiconductor manufacturing industry, the yield prediction of a product is vitally essential. Its accuracy directly affects product cost and customer satisfaction. One commonly known yield prediction and management technique is statistical machine learning models due to their high generalization capacity. With the support of rapidly increasing data volume, driven by advanced wafer-level processes, an increasing number of Deep Learning architectures have recently been adopted for yield prediction in semiconductor manufacturing. With rapid advancements in wafer- level processes, it becomes feasible to collect defect density data through advanced sensors from testing equipment. However, constructing Deep Learning models from scratch requires a lot of expertise in both semiconductor manufacturing and machine learning, which is not easy to obtain in modern semiconductor industries. To automatically assist semiconductor manufacturing engineers in building accurate Deep Learning models in yield prediction, this study first designs and builds a fully-automated Deep Learning yield prediction framework. This framework can assist engineers in developing Deep Learning models in a timely manner without time-consuming data preprocessing, feature engineering, or architecture searching. It consists of yield simulation, data preparation, candidate models building, and ensembling formation. Besides yield prediction, another significant concern is the explanation of Deep Learning model outputs. On the one hand, many model-agnostic explanation algorithms have been successfully adopted in many fields, providing valuable information for improving model quality and transparency. The explanation logic is intuitive; e.g., it calculates the contribution of a feature to the output of the prediction, which helps in finding out pixel areas or categorical reasons to focus. On the other hand, due to the complexity of semiconductor manufacturing processes, existing interpretable models lack effective inductive bias for proper yield prediction in semiconductor manufacturing, and turned out to be unable to simulate disentangled understanding rules. Therefore, current model-agnostic explanation methods for explaining Deep Learning model outputs either fail to reason rules about semiconductors, due to insufficient representation ability, or contain prohibitive time complexity for searching the activation of nodes or features. As a result, existing approaches struggle to simultaneously achieve both high prediction accuracy and high-quality explanations.

Keywords: Data analytics, yield prediction, semiconductor manufacturing, machine learning, predictive modeling, process optimization, defect analysis, big data, statistical process control, anomaly detection, real-time monitoring, artificial intelligence, wafer-level data, equipment data, root cause analysis, pattern recognition, data mining, manufacturing intelligence, sensor data, quality control, production efficiency, regression analysis, classification models, predictive maintenance, deep learning, feature extraction, high-dimensional data, yield enhancement, data-driven decision-making, advanced analytics.

Abstract: The optimization of supply chain architecture is essential for sustainability among industries. Dynamic evolutionary events such as natural disasters, pandemics, terrorism attacks, political unrest, and cyberattacks have severe implications that disrupt the operations incurred by an unplanned event or attack and economic losses that reduce the agility and resilience of supply chains. Organizing initial inventory stock to meet uncertain customer demand is a primary action to counteract uncertainties during the onset of the crisis. Traditional supply chain models may not be effective enough considering past order and demand patterns, incorporate time-dependent fixed-up and shut-down costs, and respond slowly toward uncertain demand due to dissemination issues. Cloud computing, sensor, and network technologies, and distributed intelligent systems provide a universal and economical information and communication technology infrastructure for supply chain entities to share supply chain information, big data analytics, decision support tools, and systems through the Internet regardless of time and place. This innovative approach leads to create a consolidated Virtual Supply Chain (VSC) based on cloud models that associates and connects, in a dynamic fashion, any supply chain entity capable of storing, sharing, and processing information to support multiagent, collaborative, ubiquitous, instantaneous decision-making and recommending answers. The use of advanced cloud computing, the Internet of Things, and data analytics technologies provides the supply chain actors with capabilities of forecasting demand, managing risks, and optimizing supply chain design, planning, and operations in a collaborative, efficient, aligned, responsive, resilient approach. Considering that customers have become the driving agents and have the power to make a difference concerning final demand, this chapter proposes a demand perspective for modeling, optimizing, and managing the VSC by developing an advanced commercial agent-based simulation model.

Keywords: Supply Chain Optimization, Virtual Supply Chain, Cloud Computing, Internet Of Things, Data Analytics, Demand Forecasting, Supply Chain Resilience, Risk Management, Inventory Management, Agent-Based Simulation, Distributed Intelligent Systems, Big Data Analytics, Collaborative Decision-Making, Ubiquitous Computing, Crisis Response, Real-Time Information Sharing, Supply Chain Disruptions, Dynamic Supply Chain Design, Customer-Driven Demand, Multiagent Systems

Abstract: Disruptions in routine immunization programs can undermine population immunity and lead to outbreaks of vaccine-preventable diseases (VPDs). In addition to the direct threat posed by COVID-19, operational and logistical challenges, disruption of supply chains, and the effect of COVID-19 on the health system, health workforce, and disease surveillance can hinder vaccination and leave children unprotected against diseases such as measles, polio, and yellow fever. Monitoring vaccination coverage, adaptation of immunization activities, and strengthening sentinel surveillance can facilitate early detection of VPD outbreaks. Recovery in routine immunization programs requires not only the resumption of normal health service delivery but also catch-up campaigns, improvement in supply chains, and intensive engagement with affected communities.

Vaccination coverage is usually monitored on the basis of reported national administrative data but without formal validation, which compromises confidence in estimates of the actual number of children vaccinated, especially during wartime or severe epidemics. Coverage has fallen in many countries. Despite recommended herd immunity thresholds of at least 95%, suboptimal immunity may persist in areas with low vaccination coverage. Even in countries where high coverage is achieved at the national level, pockets of low uptake can facilitate the spread of VPDs.

Keywords: Routine immunization disruption, Vaccine coverage decline, Immunization service interruption, Vaccine- preventable disease resurgence, Herd immunity gaps, Public health system resilience, Health service disruptions, Pandemic impact on immunization, Childhood vaccination delays, Missed vaccination opportunities, Health inequities in immunization, Supply chain interruptions for vaccines, Vaccine stockouts, Community-level disease outbreaks, Maternal and child health outcomes, Surveillance gaps in immunization programs, Catch-up vaccination strategies, Immunization program recovery, Morbidity and mortality from preventable diseases, Global immunization coverage trends.

Abstract: Clinical Decision Support systems based on historical patient data represent a model for investigation of a category of Clinical Decision Support (CDS) applications that have recently gained traction — consumption of historical data to support clinical decision making. An overview of the category is provided and addressed based on five research questions: What are the properties of historical data that provide insights? How are these insights used in Analytical Methods for Clinical Decision Support based on Historical Data? How is the architecture of the Clinical Decision Support System represented? How is clinical validation and evaluation achieved? How is the presentation and user interaction with predictions controlled? Despite being a nascent area, numerous published works are available on the topic, and clinical validation efforts are in various stages of maturity.

Historical data have become increasingly more available, are generally regarded as safe, and, unlike predictive models constructed on Future Data, do not raise questions regarding biases introduced in the construction of supervised learning models. However, while safety and bias concerns are reduced, historical data are prone to their own logical shortcomings. Therefore, users must exercise caution when interpreting the insights derived from Historical Data Analytics. Properly defined and presented, such insights do not impose a decision making burden on clinicians but instead ease the decision making process. The existence of a predictive model that maps the Clinical Data relevant to a Clinical Decision to the Clinical Decision itself is often regarded as a requirement for CDS to be genuinely useful for everyday clinical practice. Such a statement suffers from circular reasoning. In summary, because no method of construction of predictive models can claim to be free from bias, the pannational nature of probability suggests that, provided sufficient Causally Uncorrelated Data points are available notwithstanding time, space and biological differences, the possibility of identifying and using a Supervised Learning Model that accurately predicts the Decision of a Clinician can not be excluded.

Keywords: Clinical Decision Support Systems, Historical Patient Data, Clinical Decision Analytics, Healthcare Data Science, Analytical Methods For CDS, Clinical Insight Extraction, CDS System Architecture, Clinical Validation Frameworks, Evaluation Of Decision Support, User Interaction Design, Prediction Presentation Control, Bias In Clinical Data, Safety Of Historical Data, Logical Limitations Of Retrospective Analytics, Clinician Decision Support, Supervised Learning In Healthcare, Clinical Data Modeling, Evidence-Based Clinical Practice, Human-Centered CDS Design, Probabilistic Clinical Reasoning.

Abstract: Traffic flow prediction is a crucial component of developing intelligent transportation systems in smart cities. The core goal is to investigate the data engineering approaches and methodologies that support traffic flow prediction. Structured but diverse traffic flow data sets generated by sensor networks and other sources are ingested, processed, and stored in data platforms that enable operational real-time or near-real-time predictions and alternative exploratory offline analyses. Effective data engineering process solutions for traffic flow prediction require the careful design of all stages— from data sources to model application—because the dynamic and still little-understood nature of traffic flow data makes dedicated traffic prediction models sensitive to a variety of factors, including data quality, time frame, spatial resolution, external data, feature representation, and algorithm selection. Consideration of these factors can yield appropriate solutions across data scenario alternatives: data from a limited number of senors, real-time prediction with external data to better represent special events, online learning for concept drift adaptation, and feature engineering with new perspectives or resources.

Traffic flow prediction represents an operational application in the complex and multidisciplinary scenarios of a smart city. Intelligent transport systems rely on timely and accurate real-time predictions to optimize vehicle distribution, reduce waiting times, increase passenger satisfaction, and enable vehicle tracking. Such predictions also support external decision-making processes that require support from an intelligent system or subsystem. Usually classified as time-series forecasting, traffic flow prediction aims to inferring future values of a time-ordered series generated by one or more object through a range sensor, such as microwave, loop, infrared, or video camera sensor. The tasks for traffic flow prediction comprises sensor networks and the incoming traffic flow data streams, as well as multiple connected external data source that contribute to broaden the representation of predicted-related phenomena—e.g. weather conditions, official event schedule—and support data fusion.

Keywords: Traffic flow prediction, Smart cities, Data engineering, Spatio-temporal data, Intelligent transportation systems (ITS), Big data analytics, Internet of Things (IoT), Real-time data processing, Data pipelines, Feature engineering, Graph neural networks (GNN), Deep learning, Time series forecasting, Data fusion (multi-source integration), Edge computing.

Abstract: The rapid growth of healthcare-related data and research prompts investments in data storage infrastructure. Cloud systems offer on-demand storage and cost savings through resource pooling; however, service outages may prevent access to stored data, especially during clinical emergencies. Data must comply with privacy regulations, requiring patients’ consent for cross-region data transfer routing. Moreover, data distribution across multiple geographic regions delays access. A proposed system architecture employs location- and tier-agnostic data generators, along with ingestion pipelines that validate and normalize data for storage.

Healthcare data can be contracted to clouds run by third-party service providers. Although such systems reduce costs through resource pooling, they incur additional overhead for wide-area data accesses. The main cloud storing and managing the data must guarantee permanent access for the data owner, incorporating adequate penalties in service-level agreements (SLAs). Provided that the main cloud site is operational, sensitive data are stored there. Other clinical data can be accessed from replicas kept in other regions under a different privacy regime. Availability and consistency requirements therefore do not always match in low-cost cross-region accesses. These trade-offs must be managed appropriately.

Keywords: Healthcare Data Infrastructure, Cloud-Based Health Data Storage, Clinical Data Availability, Healthcare Cloud Architecture, Privacy Regulation Compliance, Patient Consent Management, Cross-Region Data Access, Geographic Data Distribution, Data Ingestion Pipelines, Data Validation And Normalization, Tier-Agnostic Storage Systems, Third-Party Cloud Providers, Resource Pooling Economics, Wide-Area Data Access Overhead, Service-Level Agreements (SLAs), Data Ownership Guarantees, Sensitive Health Data Protection, Data Replication Strategies, Availability–Consistency Trade-offs, Resilient Clinical Data Systems.