Data Aggregation Techniques Research Articles

From prediction to practice: mitigating bias and data shift in machine-learning models for chemotherapy-induced organ dysfunction across unseen cancers

ObjectivesRoutine monitoring of renal and hepatic function during chemotherapy ensures that treatment-related organ damage has not occurred and clearance of subsequent treatment is not hindered; however, frequency and timing are not optimal. Model bias and data heterogeneity concerns have hampered the ability of machine learning (ML) to be deployed into clinical practice. This study aims to develop models that could support individualised decisions on the timing of renal and hepatic monitoring while exploring the effect of data shift on model performance.Methods and analysisWe used retrospective data from three UK hospitals to develop and validate ML models predicting unacceptable rises in creatinine/bilirubin post cycle 3 for patients undergoing treatment for the following cancers: breast, colorectal, lung, ovarian and diffuse large B-cell lymphoma.ResultsWe extracted 3614 patients with no missing blood test data across cycles 1–6 of chemotherapy treatment. We improved on previous work by including predictions post cycle 3. Optimised for sensitivity, we achieve F2 scores of 0.7773 (bilirubin) and 0.6893 (creatinine) on unseen data. Performance is consistent on tumour types unseen during training (F2 bilirubin: 0.7423, F2 creatinine: 0.6820).ConclusionOur technique highlights the effectiveness of ML in clinical settings, demonstrating the potential to improve the delivery of care. Notably, our ML models can generalise to unseen tumour types. We propose gold-standard bias mitigation steps for ML models: evaluation on multisite data, thorough patient population analysis, and both formalised bias measures and model performance comparisons on patient subgroups. We demonstrate that data aggregation techniques have unintended consequences on model bias.

Ai-Driven Big Data Transformation And Personally Identifiable Information Security In Financial Data: A Systematic Review

This systematic review explores the impact of adopting artificial intelligence (AI) to analyze and transform big data in financial and economic contexts, with a specific focus on the privacy and security of personally identifiable information (PII). By examining 37 articles spanning the latest advancements in AI-driven big data technologies, the review identifies both opportunities and challenges in safeguarding PII during financial data transformation. Key findings reveal that while AI enhances data processing capabilities—enabling faster insights and predictive accuracy in economic trends—PII faces increased risks due to sophisticated data aggregation and correlation techniques. The review categorizes major AI methodologies used, including machine learning algorithms, natural language processing, and predictive analytics, highlighting how each can affect data privacy. The findings suggest that, to maintain trust, organizations must adopt AI responsibly, integrating privacy-by-design principles and adhering to data governance standards. This review contributes to a clearer understanding of the interplay between AI and PII protection, offering practical insights for stakeholders in the financial sector aiming to harness AI while prioritizing ethical data handling.

A Comparative Study of Sensor Quantity and Data Granularity in AAL Systems for Activity Recognition

Abstract As populations age, the demand for non-intrusive elderly care solutions increases, highlighting the need for efficient AAL systems. Current research predominantly focuses on wearable sensors at high data frequencies. There is a critical gap in research in understanding the effectiveness of model performance using ambient sensors operating at varied granularities and with varied numbers of sensors. This study addresses this gap by investigating how sensor quantity and data frequency affect an artificial intelligence model’s ability to detect various activities of daily living. The methodology employs a quantitative, experimental design to systematically assess the performance of artificial intelligence models across sensor quantity and data frequencies. This assessment will be conducted through a multi-study approach involving different populations to ensure robust and generalizable findings. Each model’s efficacy will be evaluated using 5-fold cross-validation and GridSearchCV for rigorous hyperparameter tuning, employing diverse data aggregation and imputations techniques to maintain comprehensive analysis integrity. The primary goal of this research is to determine the optimal data granularity and number of sensors that maximize AI models’ ability to detect daily living activities while minimizing resource demands, thereby enhancing the sustainability and scalability of AAL systems. This work aims to advance the field of ambient sensing in elderly care, offering significant implications for designing and implementing future AAL technologies and potentially improving the quality of life for the elderly population. Key messages • The study explores the optimal configuration of data granularity and sensor quantity to maximize AI model efficiency in detecting activities of daily living among older adults. • The study investigates the impact of data frequency and sensor count on AI model performance in detecting daily activities, aiming to optimize Ambient Assisted Living systems for the elderly.

Stroke recurrence prediction using machine learning and segmented neural network risk factor aggregation

Stroke has remained a major cause of mortality and disability in the United States for years, and its recurrence significantly increased the risks. For predicting stroke recurrence, traditional data aggregation methods have limitations in effectively handling the numerous subcategories of stroke risk factors. This pilot study proposed a Segmented Neural Network-Driven Aggregation (SNA) method, and it aimed to improve the prediction model’s accuracy. Utilizing the TriNetX diagnosis dataset, we processed various risk factors and demographic information through traditional and our proposed data aggregation techniques. We applied logistic regression and random forest classifiers to predict stroke recurrence. Our findings revealed that using the SNA method significantly outperformed other aggregation methods for both classifiers. Using the SNA method with a random forest classifier achieved higher accuracy (84.2%) and a better balance between sensitivity and specificity (AUC of ROC = 0.928, AUC of PR = 0.940) compared to other combinations. These results showed the potential of machine-learning supervised encoding methods in stroke recurrence predictions, providing implications for clinical practice and future epidemiological research.

RDSC: Range-Based Device Spatial Clustering for IoT Networks.

The growth of the Internet of Things (IoT) has become a crucial area of modern research. While the increasing number of IoT devices has driven significant advancements, it has also introduced several challenges, such as data storage, data privacy, communication protocols, complex network topologies, and IoT device management. In essence, the management of IoT devices is becoming more and more challenging, especially with the limited capacity and power of the IoT devices. The devices, having limited capacities, cannot store the information of the entire environment at once. In addition, device power consumption can affect network performance and stability. The devices' sensing areas with device grouping and management can simplify further networking tasks and improve response quality with data aggregation and correction techniques. In fact, most research papers are looking forward to expanding network lifetimes by relying on devices with high power capabilities. This paper proposes a device spatial clustering technique that covers crucial challenges in IoT. Our approach groups the dispersed devices to create clusters of connected devices while considering their coverage, their storage capacities, and their power. A new clustering protocol alongside a new clustering algorithm is introduced, resolving the aforementioned challenges. Moreover, a technique for non-sensed area extraction is presented. The efficiency of the proposed approach has been evaluated with extensive experiments that gave notable results. Our technique was also compared with other clustering algorithms, showing the different results of these algorithms.

Adaptive and Priority-Based Data Aggregation and Scheduling Model for Wireless Sensor Network

Wireless Sensor Networks (WSN) use sensor nodes placed in potential places to collect sensitive information. These sensor nodes monitor necessary data and send it to the sink node. Sensor nodes have resource constraints, especially energy and power depletion. The majority of sensor and battery power is wasted on redundant data transmission. The redundant data transmission consumes a significant amount of the sensor and battery life, decreasing the total lifespan of the sensor nodes. Data aggregation is an approach that expands the useful lifetime of sensor nodes overall and removes unnecessary data and delays. There are many types of data aggregation techniques, such as centralized, tree-based, in-network, and cluster-based. The available tree-based data aggregation mechanism performs well, but the whole tree may be down due to single-node failure. Due to bottlenecks, node data aggregation suffers from an increased packet failure ratio. Another limitation is that every node aggregates data into slices, which consumes more energy. For this purpose, an adaptive and priority-based data aggregation and scheduling model (APB-DASM) for WSNs is proposed in this paper to address these issues. It is proposed that APB-DASM be used to improve quality of service (QoS) with regard to energy consumption and data transmission. The APB-DASM model aggregates sensor data into cluster heads and divides it into three formats: The first format categorizes the most important data that consists of four slices, and the second format categorizes the important data that consists of three slices. Format three data is represented in two slices, which is normal data. These three types of format data are aggregated on a priority basis, such that the highest priority is given to the first format, i.e., most important data; moderate priority is given to the second format, i.e., important data; and then low priority is given to the normal data. Due to an efficient priority-based data aggregation and scheduling algorithm, our proposed model sends the most important data first, and so on. Theoretical study and simulation research demonstrate that our proposed approach improves the existing tree-based models. By using APB-DASM, significant decreases in energy usage, packet delivery ratio, and overall QoS are achieved, and as a result, the WSNs' lifetime is thus increased. The proposed model is implemented in MATLAB, and the results are compared with existing tree-based models. Simulations comparing our model to the most recent models indicate that it worked effectively, reducing the packet failure ratio and energy usage by 36.8% and 30%, respectively, for CBF-ADA, D-SMART, and WDARS. This article emphasizes how the suggested methodology can be effectively used in the aggregation of coronavirus patient data. It demonstrates how adaptable and applicable our method is in the real world.

MDavocado: Analysis and Visualization of Protein Motion by Time-Dependent Angular Diagrams.

Extracting meaningful information from atomistic molecular dynamics (MD) simulations of proteins remains a challenging task due to the high-dimensionality and complexity of the data. MD simulations yield trajectories that contain the positions of thousands of atoms in millions of steps. Gaining a comprehensive understanding of local dynamical events across the entire trajectory is often difficult. Here, we present a novel approach to visualize MD trajectories in the form of time-dependent Ramachandran plots. Specialized data aggregation techniques are employed to address the challenge of plotting millions of data points on a single image, thereby ensuring that the analysis is independent of the molecule size and/or length of the MD simulation. This approach facilitates quick identification of flexible and dynamic regions, and its strength is the ability to simultaneously observe the movements of all amino acids over time. The Python program MDavocado is freely available at GitHub (https://github.com/zoranstefanic/MDavocado).

BAGGING ENSEMBLE MINING TECHNIQUE WITH DEEP BELIEF NETWORK (DBN) ALGORITHM-BASED HEART DISEASE PREDICTION

Cardiovascular disease is the most important disease of the heart, and the stage of the disease is diagnosed, the disease can be diagnosed anytime. The following method is used to find out its status. The heart disease prediction is based on Bagging Ensemble Technique with Deep Belief Network (DBN) algorithms. The problem for heart disease prediction from the collection of the dataset. Feature extraction using the Bag of Words methods to the correct data and discontinuities collect the heart disease-based matching data's extraction from the dataset and the various combination of the data set is available in Kaggle. It is mostly used for text classification methods. The proposed system of data mining is the most important technique for data aggregation. Data mining has various methods available, and one of the techniques is the bagging Ensemble Technique. In this method using for homogeneous data are quickly collected and parallel processing for the data collections. The first process for collecting data using the bagging Ensemble Technique is based on collected preprocessing. The Cardiovascular Disease prediction using Deep Belief Network (DBN) algorithm is compared with the existing system heart disease prediction, to prediction for display the data past and present movement in classification time and prediction accuracy, sensitivity and specificity. The proposed system for classification is compared with various techniques, and the proposed methods are DBN algorithms compared to compare to 5000 data'. The performance of CNN is 89%, RNN is 90%, LSTMs is 92%, and DBM is 95.6%. Finally, the heart disease prediction or classifications are given by the DBN algorithm.

Two-Level Dynamic Programming-Enabled Non-Metric Data Aggregation Technique for the Internet of Things

The Internet of Things (IoT) has become a transformative technological infrastructure, serving as a benchmark for automating and standardizing various activities across different domains to reduce human effort, especially in hazardous environments. In these networks, devices with embedded sensors capture valuable information about activities and report it to the nearest server. Although IoT networks are exceptionally useful in solving real-life problems, managing duplicate data values, often captured by neighboring devices, remains a challenging issue. Despite various methodologies reported in the literature to minimize the occurrence of duplicate data, it continues to be an open research problem. This paper presents a sophisticated data aggregation approach designed to minimize the ratio of duplicate data values in the refined set with the least possible information loss in IoT networks. First, at the device level, a local data aggregation process filters out outliers and duplicates data before transmission. Second, at the server level, a dynamic programming-based non-metric method identifies the longest common subsequence (LCS) among data from neighboring devices, which is then shared with the edge module. Simulation results confirm the approach’s exceptional performance in optimizing the bandwidth, energy consumption, and response time while maintaining high accuracy and precision, thus significantly reducing overall network congestion.

RETRACTED: Efficient data management in Internet of Things: A survey of data aggregation techniques

This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433.

An Energy-Efficient Cluster-based data aggregation for agriculture irrigation management system using wireless sensor networks

Wireless Sensor Network (WSN) are becoming one of the demanding platforms, where sensor nodes are sensing and monitoring the physical or environmental conditions and transmit the data to the base station via multi-hop routing. Agriculture sector also adopted these networks to promote innovations for environmentally friendly farming methods, lower the management cost, and achieve scientific cultivation. This combination can improve crop yield, quality, and efficiency while saving energy and water. It is important to note that irrigation is one of the essential factors for agricultural success. In an agriculture irrigation application, a WSN is deployed in a specific area to control the irrigation in the field. But using WSN will generate massive redundancy in the data processing. So, there is lacking an efficient system for extensive sensor data processing. This research work presents an Energy-Efficient Cluster-Based Data Aggregation (E2CDA) Technique for agriculture irrigation systems in WSN. An improved probabilistic clustering method is used for preserving the optimal number of Cluster Head (CH) in each round of iteration. The proposed work is implemented in MATLAB, according to simulation results; the developed E2CDA method provides better result when compared with the existing approaches such as Low Energy Adaptive Clustering Hierarchical (LEACH) routing and centralized LEACH (LEACH-C) in terms of energy savings, network lifetime, packet delivery ratio, end-to-end delay, and packet drop ratio.

Exploring Long Short Term Memory Algorithms for Low Energy Data Aggregation

Long short-term memory methods are employed for data consolidation in intricate low-energy devices. It has enabled accurate and efficient aggregation of statistics in limited electricity settings, facilitating the review and retrieval of data while minimizing electricity wastage. The LSTM rules analyze, organize, and consolidate vast datasets inside weakly connected structures. It has employed a recurrent neural network to handle data processing, particularly nonlinear interactions. The machine's capabilities are subsequently examined and stored utilizing memory blocks. Memory blocks retain extended temporal connections within the data, facilitating adaptive and precise information aggregation. These blocks facilitate the system's ability to shop and utilize relevant capabilities for quick retrieval. The proposed algorithm offers realistic tuning capabilities such as learning rate scheduling and total regularization based on dropout like green information aggregation. These enable systems to reduce over fitting while permitting precise adjustment of the settings. It allows for optimizing the algorithm to provide highly dependable performance within weak structures, enhancing data aggregation techniques' energy efficiency. Standard algorithms provide an efficient, accurate solution for aggregating information in low-power systems. It facilitates evaluating, retrieving, and aggregating accurate and reliable information using memory blocks, adaptive tuning, and efficient learning rate scheduling.

Optimization of Data Aggregation Techniques in IoT-Based Wireless Sensor Networks

Optimization of Data Aggregation Techniques in IoT-Based Wireless Sensor Networks

Secure and scalable data aggregation techniques for healthcare monitoring in WSN

Wireless Sensor Networks (WSN) are crucial in the healthcare field as they allow for the immediate monitoring and collection of data from medical sensors. The growing incorporation of WSN in healthcare requires the creation of authentication protocols that are both strong and energy-efficient. This study presents Lightweight Authentication Protocol for Cloud-based Health-care Systems (LAPCHS) using BLAKE2 designed specifically for WSN in medical settings for secure and scalable data aggregation. The proposed method tackles the difficulties presented by limited resources in sensor nodes, with the goal of achieving a careful equilibrium between strong security and effective energy usage. LAPCHS utilizes innovative techniques to improve the energy efficiency in WSN. The system employs the BLAKE2 cryptographic hash algorithm to establish robust mutual authentication and key agreement between the tag and the cloud server. The protocol is characterized by its low weight and high efficiency, rendering it appropriate for deployment in medical sensor networks with limited resources, which minimizes the need for global key distribution and decreases communication overhead. The proposed method is useful to meet the distinct needs of medical sensor networks, where energy preservation is of utmost importance to ensure extended device scalability. The findings demonstrate that LAPCHS surpasses current approaches in terms of energy efficiency and latency, while simultaneously upholding a robust level of security. The protocol’s novel strategy for managing encryption keys and selecting cryptographic algorithms makes it a promising solution for securing medical sensor networks while maintaining energy sustainability. This study makes a valuable contribution to the developing field of WSN security by proposing a practical solution for ensuring strong and energy-efficient authentication in healthcare applications.

Komunikasi Injil Lintas Budaya Mengenai Roh Kudus dalam Tradisi Ari-ari pada Masyarakat Jawa di Surakarta

The aim of this research is to find the communication of the gospel regarding the Holy Spirit in the ari-ari tradition in Javanese society. This research uses a qualitative approach with phenomenological methods. In this research, the data aggregation technique used by researchers is a literature study or written document review. The result of this research is the communication of the gospel regarding the Holy Spirit (local pneumatology) in the ari-ari tradition in the Javanese community in Surakarta.

Channel reconfiguration distributed interference alignment for multi-unit over-the-air computation

Over-the-air computation (AirComp) has been widely studied as an emerging technique for efficient data aggregation. In multi-unit AirComp networks, inter-unit interference seriously affects the data aggregation performance. To solve the above problem, in this paper, a novel scheme of channel reconfiguration distributed interference alignment (CRDIA) is proposed. We virtualize several devices within a unit as one transmitting device, reconstruct the channel matrix of the system, and iterate iteratively design the pre-processing and post-processing components. Based on the above, the pre-processing matrices of AirComp devices and the post-processing matrices of fusion centers are designed. The sum rate of the system is used as a metric for interference cancellation and mean-squared error (MSE) is used as a metric for data aggregation accuracy. We evaluate the proposed scheme by simulating a network with various numbers of AirComp devices and units. The simulation results show that the CRDIA scheme can achieve accurate computation of the AirComp objective function without inter-unit interference.

Effects of data aggregation (buffer) techniques on bicycle volume estimation

Effects of data aggregation (buffer) techniques on bicycle volume estimation

DAO2: Overcoming Overall Storage Overflow in Intermittently Connected Sensor Networks

Many emerging sensor network applications operate in challenging environments wherein the base station is unavailable. Data generated from such intermittently connected sensor networks (ICSNs) must be stored inside the network for some unpredictable time before uploading opportunities become available. Consequently, sensory data could overflow the limited storage capacity available in the entire network, making discarding valuable data inevitable. To overcome such overall storage overflow in ICSNs, we propose and study a new algorithmic framework called data aggregation for overall storage overflow ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\text{DAO}^2$</tex-math> </inline-formula> ). Utilizing spatial data correlation that commonly exists among sensory data, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\text{DAO}^2$</tex-math> </inline-formula> employs data aggregation techniques to reduce the overflow data size while minimizing the total energy consumption in data aggregation. At the core of our framework are two new graph theoretical problems that have not been studied. We refer to them as traveling salesmen placement problem ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\text{TSP}^2$</tex-math> </inline-formula> ) and quota traveling salesmen placement problem (Q- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\text{TSP}^2$</tex-math> </inline-formula> ). Different from the well-known multiple traveling salesman problem (mTSP) and its variants, which mainly focus on the routing of multiple salesmen initially located at fixed locations, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\text{TSP}^2$</tex-math> </inline-formula> and Q- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\text{TSP}^2$</tex-math> </inline-formula> must decide the placement as well as the routing of the traveling salesmen. We prove that both problems are NP-hard and design approximation, heuristic, and distributed algorithms. Our algorithms outperform the state-of-the-art data aggregation work with base stations by up to 71.8% in energy consumption.

Distributed intelligence for pervasive optical network telemetry

Optical network automation and failure management require measuring the status and the performance of the different network devices to anticipate any degradation and ensure the quality of the provided services, i.e., optical connectivity. Such pervasive network telemetry entails collecting large amounts of measurements and events from different sources and with very fine granularity, which given the amount and variety of telemetry sources and the size of each measurement and event, imposes requirements that are hard to achieve without large investments. In this paper, we analyze the main limitations of telemetry architectures relying exclusively on centralized systems for data analysis and propose an architecture with distributed intelligence. Data aggregation techniques, especially conceived for optical network telemetry, are presented with the objective of reducing data dimensionality. Illustrative results from our experimental telemetry system reveal a reduction of 3 orders of magnitude in terms of total data volume without introducing significant error and processing delay and, more importantly, helping network automation algorithms to identify meaningful changes in the network status.

Design and Development of Energy Efficient Algorithm for Smart Beekeeping Device to Device Communication Based on Data Aggregation Techniques

Bees, like other insects, indirectly contribute to job creation, food security, and poverty reduction. However, across many parts of the world, bee populations are in decline, affecting crop yields due to reduced pollination and ultimately impacting human nutrition. Technology holds promise for countering the impacts of human activities and climatic change on bees’ survival and honey production. However, considering that smart beekeeping activities mostly operate in remote areas where the use of grid power is inaccessible and the use of batteries to power is not feasible, there is thus a need for such systems to be energy efficient. This work explores the integration of device-to-device communication with 5G technology as a solution to overcome the energy and throughput concerns in smart beekeeping technology. Mobile-based device-to-device communication facilitates devices to communicate directly without the need of immediate infrastructure. This type of communication offers advantages in terms of delay reduction, increased throughput, and reduced energy consumption. The faster data transmission capabilities and low-power modes of 5G networks would significantly enhance the energy efficiency during the system’s idle or standby states. Additionally, the paper analyzes the application of both the discovery and communication services offered by 5G in device-to-device-based smart bee farming. A novel, energy-efficient algorithm for smart beekeeping was developed using data integration and data scheduling and its performance was compared to existing algorithms. The simulation results demonstrated that the proposed smart beekeeping device-to-device communication with data integration guarantees a good quality of service while enhancing energy efficiency.