Aggregation Techniques Research Articles

A Multi-modal CBIR Framework with Image Segregation using Autoencoders and Deep Learning-based Pseudo-labeling

Various modulated techniques of Content-Based Image Retrieval (CBIR) using deep learning provide better search outputs even though they are computationally challenging. These methods can be enhanced further, if the search key can be tagged effectively and directed towards target images. In this paper, we have developed a new multilevel aggregation technique along with autoencoders, to be implemented on image features for precise feature selection and accurate search output. Locally significant datasets and generic ones are dealt separately for obtaining better hit rates along with the process of query expansion. The concept of pseudo-labelling by deep learning is introduced to classify images into positive and negative classes, where positive class consists of the images that are similar to the query image. The feature spaces of query images are compared with the images in the search pool based on their assigned weights. The target images are finally ranked and selected based on an adaptive threshold level. The methodology for this enhanced CBIR technique is tested on public datasets and its results are collated with recent approaches proposed in the literature. The proposed method has attained significant improvements in precision, recall and computation and thereby the use of images from connected devices has been proven to be significant. Given the importance of more accurate image retrieval in CBIR, this method can be experimented for other similar applications as well.

Certain Investigation on Improved Cluster Protocol with Trust security for Wireless Sensor Networks

Immense development of Micro Electro Mechanical Systems (MEMS) made an incredible advancement in wireless technology. The Wireless Sensor Network (WSN) has created many opportunities for the development of various applications in the fields of military, research, medical, engineering, etc. In this research article, a novel trust-based energy-aware clustering protocol is proposed. The clustering algorithm concentrates on reducing the time spent on cluster formation, controlling redundant data forwarding, and prolonging the network's lifespan. In this model, clustered nodes are classified into three levels like Cluster heads (CH), secondary CHs, and sensor nodes (SN) are used to sense the environmental changes and report to the Base Station (BS). An extension of the lifetime of a WSN is possible by the use of secure multi-hop routing with an aggregation technique to forward data from a cluster to the BS. Compared to relevant works on clustering with the routing protocol, the simulation result showed improved energy efficiency and network lifetime.

Multi-Criteria Decision-Making Method Based on Complex t-Spherical Fuzzy Aczel–Alsina Aggregation Operators and Their Application

The complex t-spherical fuzzy set (Ct-SFS) is a potent tool for representing fuzziness and uncertainty compared to the picture fuzzy sets and spherical fuzzy sets. It plays a key role in modeling problems that require two-dimensional data. The present study purposes the aggregation technique of Ct-SFSs with the aid of Aczel–-Alsina (AA) operations. We first introduce certain novel AA operations of Ct-SFSs, such as the AA sum, AA product, AA scalar multiplication, and AA scalar power. Subsequently, we propound a series of complex t-spherical fuzzy averaging and geometric aggregation operators to efficiently aggregate complex t-spherical fuzzy data. In addition, we explore the different characteristics of these operators, discuss certain peculiar cases, and prove their fundamental results. Thereafter, we utilize these operators and propose entropy measures to frame a methodology for dealing with complex t-spherical fuzzy decision-making problems with unknown criteria weight data. Finally, we provide a case study about vehicle model selection to illustrate the presented method’s applicability followed by a parameter analysis and comparative study.

Quantum homomorphic broadcast multi-signature based on homomorphic aggregation

Quantum multi-signature has attracted extensive attention since it was put forward. Beside its own improvement, related research is often combined with other quantum signature. However, this type of quantum signature has one thing in common, that is, the generation and verification of signature depend heavily on the shared classical secret key. In order to increase the reliability of signature, the homomorphic aggregation technique is applied to quantum multi-signature, and then we propose a quantum homomorphic multi-signature protocol. Unlike previous quantum multi-signature protocols, this protocol utilizes homomorphic properties to complete signature generation and verification. In the signature generation phase, entanglement swapping is introduced, so that the individual signatures of multiple users are aggregated into a new multi-signature. The original quantum state is signed by the shared secret key to realize the verification of the signature in the verification phase. The signature process satisfies the homomorphic property, which can improve the reliability of the signature.

ACS: Accuracy-based client selection mechanism for federated industrial IoT

This study proposes secure federated learning (FL)-based architecture for the industrial internet of things (IIoT) with a novel client selection mechanism to enhance the learning performance. In order to secure the FL architecture and ensure that available clients are trustworthy, a certificate authority (CA) is adopted. In traditional FL, an aggregation technique known as federated averaging (FedAvg) is utilized to collect local model parameters by selecting a random subset of clients for the training process. However, the random selection may lead to uncertainty and negatively influence the overall FL performance. Moreover, state-of-the-art studies on client selection mainly rely on client’s additional information, which raises a privacy issue. Therefore, a novel client selection mechanism based on client evaluation accuracy called ACS is introduced in this work to improve FL performance while preserving client privacy. Unlike other client selection methods, ACS relies only on the updated local parameter, which is evaluated in the FL server. The proposed ACS considers the highest-performing clients to fasten the convergence time in the FL. Based on the extensive performance evaluation performed in this work using MNIST and F-MNIST datasets with non-independent identically distributed (non-IID) conditions, the adoption of ACS successfully improved the overall performance of FL in terms of accuracy and F1-score with an average of 4.62%. Furthermore, comparative analysis shows that the proposed ACS can achieve specific accuracy with 2.29% lower communication rounds and stable performance compared to other client selection mechanisms.

Engineering Human Mesenchymal Bodies in a Novel 3D-Printed Microchannel Bioreactor for Extracellular Vesicle Biogenesis.

Human Mesenchymal Stem Cells (hMSCs) and their derived products hold potential in tissue engineering and as therapeutics in a wide range of diseases. hMSCs possess the ability to aggregate into "spheroids", which has been used as a preconditioning technique to enhance their therapeutic potential by upregulating stemness, immunomodulatory capacity, and anti-inflammatory and pro-angiogenic secretome. Few studies have investigated the impact on hMSC aggregate properties stemming from dynamic and static aggregation techniques. hMSCs' main mechanistic mode of action occur through their secretome, including extracellular vesicles (EVs)/exosomes, which contain therapeutically relevant proteins and nucleic acids. In this study, a 3D printed microchannel bioreactor was developed to dynamically form hMSC spheroids and promote hMSC condensation. In particular, the manner in which dynamic microenvironment conditions alter hMSC properties and EV biogenesis in relation to static cultures was assessed. Dynamic aggregation was found to promote autophagy activity, alter metabolism toward glycolysis, and promote exosome/EV production. This study advances our knowledge on a commonly used preconditioning technique that could be beneficial in wound healing, tissue regeneration, and autoimmune disorders.

Multi-objective automatic analysis of lung ultrasound data from COVID-19 patients by means of deep learning and decision trees

COVID-19 raised the need for automatic medical diagnosis, to increase the physicians’ efficiency in managing the pandemic. Among all the techniques for evaluating the status of the lungs of a patient with COVID-19, lung ultrasound (LUS) offers several advantages: portability, cost-effectiveness, safety. Several works approached the automatic detection of LUS imaging patterns related COVID-19 by using deep neural networks (DNNs). However, the decision processes based on DNNs are not fully explainable, which generally results in a lack of trust from physicians. This, in turn, slows down the adoption of such systems. In this work, we use two previously built DNNs as feature extractors at the frame level, and automatically synthesize, by means of an evolutionary algorithm, a decision tree (DT) that aggregates in an interpretable way the predictions made by the DNNs, returning the severity of the patients’ conditions according to a LUS score of prognostic value. Our results show that our approach performs comparably or better than previously reported aggregation techniques based on an empiric combination of frame-level predictions made by DNNs. Furthermore, when we analyze the evolved DTs, we discover properties about the DNNs used as feature extractors. We make our data publicly available for further development and reproducibility.

The aggregation of Z-numbers based on overlap functions and grouping functions and its application on group decision-making

In this paper, we propose a series of novel aggregation techniques based on overlap and grouping functions for group decision-making (GDM) issues in the Z-number environment. Firstly, we introduce an optimization model to determine the underlying distribution for Z-numbers, meanwhile, the mean function of Z-numbers is revised to better reflect the three-dimensional structure of the Z-numbers. And then, a series of operations for Z-numbers using overlap and grouping function are defined, and their properties are also investigated. Subsequently, we construct the overlap function-based Z-number weighted Bonferroni mean (OZWBM) operator to integrate the information in the Z-number environment. Furthermore, to verify the efficiency of novel aggregation techniques, a new energy investment selection issue is addressed. Besides giving the rankings of alternatives, by analyzing the calculation results, we can also derive the degree of preference from investment experts in scoring each investment object. Finally, by comparing the existing methodologies, we confirm that the new approach is effective and reasonable for the multi-criteria group decision-making (MCGDM).

Data transmission reduction using prediction and aggregation techniques in IoT-based wireless sensor networks

Currently, broad ranges of economic sectors exploit the Internet of Things (IoT) and Wireless Sensor Networks (WSNs) technology generating problems to be managing, processing and organizing the big data streams. Given the inherent sensor constraints (battery-dependent life, lack of memory space, limited processor power), there is a need for systems capable of reducing data transmission flux of the distributed IoT-based WSNs applications to mitigate the continuously increasing network traffic. Prediction and data aggregation techniques are promising solutions to meet this requirement. These techniques are particularly powerful solutions in forecasting processes where a huge data to be collected, transmitted and recorded. This is right even if we consider the integration of IoT-based WSNs with cloud computing technology. This paper proposes the combination of the recently developed prediction scheme EADPS (Extended Adaptive Dual Prediction Scheme) and the temporal correlation based data aggregation technique as a power tool to address the problem of communication reduction in connected IoT-based WSNs. First, we studied separately the impact of each technique before considering their combination. To achieve this goal, we consider the multi-hop ring model of the IoT-based WSNs. The results show that the aggregation technique is powerful compared to the DPS prediction scheme but loses its superiority for small WSNs size (with lesser than five rings) when the EADPS schema is applied. In addition, the data correlation has a feeble impact on reduction of transmission rates. According to the imposed tolerance thresholds, we show that the proposed scheme reduced the average transmission rates in the range 85%–96% for the entire network. The obtained results are presented and discussed.

Multistate Modeling of Clinical Trajectories and Outcomes in the ICU: A Proof-of-Concept Evaluation of Acute Kidney Injury Among Critically Ill Patients With COVID-19.

To demonstrate the utility of these models in critical care, we examined acute kidney injury (AKI) development, progression, and outcomes in COVID-19 critical illness through multistate analyses. Retrospective cohort study at an urban tertiary-care academic hospital in the United States. All patients greater than or equal to 18 years in an ICU with COVID-19 in 2020, excluding patients with preexisting end-stage renal disease. Using electronic health record data, we determined AKI presence/stage in discrete 12-hour time windows and fit multistate models to determine longitudinal transitions and outcomes. Of 367 encounters, 241 (66%) experienced AKI (maximal stages: 88 stage-1, 49 stage-2, 104 stage-3 AKI [51 received renal replacement therapy (RRT), 53 did not]). Patients receiving RRT overwhelmingly received invasive mechanical ventilation (IMV) (n = 60, 95%) compared with the AKI-without-RRT (n = 98, 53%) and no-AKI groups (n = 39, 32%; p < 0.001), with similar mortality patterns (RRT: n = 36, 57%; AKI: n = 74, 40%; non-AKI: n = 23, 19%; p < 0.001). After 24 hours in the ICU, almost half the cohort had AKI (44.9%; 95% CI, 41.6-48.2%). At 7 days after stage-1 AKI, 74.0% (63.6-84.4) were AKI-free or discharged. By contrast, fewer patients experiencing stage-3 AKI were recovered (30.0% [24.1-35.8%]) or discharged (7.9% [5.2-10.7%]) after 7 days. Early AKI occurred with similar frequency in patients receiving and not receiving IMV: after 24 hours in the ICU, 20.9% of patients (18.3-23.6%) had AKI and IMV, while 23.4% (20.6-26.2%) had AKI without IMV. In a multistate analysis of critically ill patients with COVID-19, AKI occurred early and heterogeneously in the course of critical illness. Multistate methods are useful and underused in ICU care delivery science as tools for understanding trajectories, prognoses, and resource needs.

Machine Learning based Frame Size Optimization in WLAN Downlink MU-MIMO Channel with the Least Cost of Delay

The key enhancement in the medium access control (MAC) layer is frame aggregation introduced by the IEEE 802.11n/ac standard to accommodate the growing traffic demand in the WLAN by allowing multiple packets aggregated per transmission. Frame aggregation efficiently reduces control overhead in the MAC layer, such as the MAC header and thus it helps to enhance transmission efficiency and throughput performance of WLAN. However, heterogeneous traffic demand among streams in the WLAN downlink MU-MIMO channel creates a challenge to efficiently utilize the benefits of frame aggregation. Transmission efficiency is also compromised during frame size setting determination because when a frame size is larger, the impact of the overhead frame can be lower, but they are also more vulnerable to transmission errors. Thus, this trade-off between maximizing frame size and minimizing overhead frames should be addressed by employing an adaptive frame aggregation technique to derive the optimal frame size that would maximize the throughput in WLAN downlink MU-MIMO channel. Moreover, when frame aggregation approach is employed, more frames must wait before transmission in a buffer which causes a delay in the performance of WLAN. Thus, analysing the trade-off between maximizing throughput and minimizing delay is a critical issue that should also be addressed to enhance the performance of WLAN. However, the majority of the existing adaptive aggregation algorithms in the WLAN downlink MU-MIMO channel are focused to maximize the throughput or minimize the delay. The main contribution of this paper is to propose a machine learning-based frame size optimization algorithm by extending our earlier approach in considering the cost of delay to maximize the system throughput of WLAN. The effectiveness of the proposed scheme is evaluated over the FIFO Baseline Approach and earlier conventional approaches under the effects of various traffic patterns, channel conditions, and the number of STAs.

Evaluating urban environment quality (UEQ) for Class-I Indian city: an integrated RS-GIS based exploratory spatial analysis

Urban environmental quality consisting of ecological, physical, and socio-economic components, often deteriorates due to rapid urbanization. Therefore, using Remote sensing and GIS environment, a composite measure is applied to quantify the spatial heterogeneity of urban environmental quality for the Class-1 Indian city (Siliguri). In this study, the Urban Environmental Quality Index was constructed using 15 indicators and three interconnected dimensions (eco-environment, landscape and built-up, and socio-economy). The three domains and Urban Environmental Quality Index were computed utilizing Principal Component Analysis with average aggregation techniques. Exploratory Spatial Data Analysis includes Moran’s I and Local indicator of spatial auto-correlation, were used to leverage the information of spatial clusters, spatial heterogeneity, and outliers based on the Urban Environmental Quality Index. The results show that Siliguri’s northern, north-western, and southern parts experience good environmental quality. The effectiveness of the employed model was checked using R2 (0.832), providing a good fit for the model. Moreover, the spatial pattern of urban environmental quality and the constructed domains (except socio-economy) revealed that the Low-Low values were predominantly clustered in the city centre, while High-High patterns are concentrated towards the periphery. Also, the value of Moran’s I indicated the existence of spatial autocorrelation and non-randomness pattern in Siliguri City. The results obtained from the analysis indicate spatial heterogeneity and spatial differentiation across the study area. The study’s outcome is relevant for urban planning, frequent monitoring of urban environmental quality, urban governance, and the well-being of urban inhabitants for a sustainable urban space.

A participative methodology for prioritising intervention logic in the design of the Italian CAP Strategic Plan

The new CAP implementation model requires each Member State to design a CAP Strategic Plan (CSP) to deliver operational actions under the two CAP pillars. Each CSP must be built from an evidence-based needs assessment that undergoes rigorous prioritisation to plan comprehensive and achievable interventions. In Italy, the institutional context requires all the Regions and Autonomous Provinces to express their preferences and to discuss the CSP collectively, both as regards identifying territorial needs and their prioritisation. In this framework, it became pertinent to introduce a specific instrument to facilitate participation in this process. The Italian Ministry, in collaboration with the National Rural Network, developed a participatory route to assess the prioritisation of the identified needs, to support the decision-making process in CSP drafting process. The process is primarily based on a voting aggregation technique called the Constrained Cumulative Voting method. The process identified makes it possible, on the one hand, to formulate a shared consensus on the level of importance of each need; on the other one, via the definition of natural breaks, to determine homogeneous groups of needs by importance of intervention. This process is in line with the European Commission’s legislative proposals requiring a sound and well-founded logic of intervention.

Verification, validation, and accreditation for models and simulations in the Australian defence context: a review

Building simulation models that are valid and credible is an enduring challenge in the Australian Defence Organisation (ADO) context. Establishing validity and credibility can be achieved through the rigorous use of appropriate Verification, Validation, and Accreditation (VVA) processes. Such processes are well-known in modeling and simulation (M&amp;S) practice. However, these are generally not applied within the ADO, typically due to resourcing concerns and a lack of authoritative guidance. Even if there are any, due to security concerns and commercial reasons, the application of M&amp;S within ADO is generally not published in open-access platforms. Depending on where in the M&amp;S life-cycle VVA is started, it may also serve a secondary aim of risk reduction, assisting in the early discovery of possible problems or mistakes. This research reviews current VVA practices from academic literature and recommends processes that are appropriate for application to combat simulation tools within the ADO context. A scoping review has been conducted to gather insight into current VVA practice in the M&amp;S community. The results of this review are presented in the form of charting relevant characteristics from selected references. The scoping review shows that executable validation of simulation results against referent data sourced from physical experiments is the most prevalent form of VVA, with referent data from comparative models being a prevalent alternative. Furthermore, there is evident reliance on graphical comparison of data; this could be enhanced with objective data comparators, such as aggregate error measures or statistical techniques. Finally, there is an evident gap in VVA references from Australia, which could be addressed through the propagation and reporting of prevalent VVA practices within the ADO context.

ACRDA: An adaptive combined relay based dynamic data aggregation technique for wireless sensor networks

Based on the monitoring environment, the frequent generation of extensive amounts of redundant sensing data is processed in the WSN applications. For reducing the consumption of energy in a network, aggregation of all these data with efficient methods of data aggregation is playing a key role. For aggregating the generated large amounts of data from sensor nodes, various clustering techniques have been used. In the closed and less or partially-dense sensor environments only, effectiveness shows by such type of algorithms of data aggregation. Also, in most of the clustering environments, the CH nodes are forced to send the sink node which locates distant away from the CHs, due to the ineffectiveness of the clustering and CH selection algorithms. Here, an adaptive combined relay based Dynamic data aggregation technique was proposed that could dynamically adapts with the network and aggregate the data in two ways. If the hop count between the sensors and CHs is higher than the hop count between sensors and sink directly, the sensors can be transmitted the data directly to the SINK without the requirement of data aggregation at CH levels. If the hop count exceeds, then the normal data aggregation at the CHs would apply. Also to improve the stable CH selection, the CHs are selected based on ERROR RATE & QUEUE LENGTH. This dynamic data aggregation technique can adaptively aggregate the data at any kind of environments and the efficiency of data aggregation and energy consumption can improve over the network. The proposed data aggregation mechanism has been proved the better performance than the earlier algorithms based on the experimental results.

Spectral Clustering via Adaptive Layer Aggregation for Multi-Layer Networks

One of the fundamental problems in network analysis is detecting community structure in multi-layer networks, of which each layer represents one type of edge information among the nodes. We propose integrative spectral clustering approaches based on effective convex layer aggregations. Our aggregation methods are strongly motivated by a delicate asymptotic analysis of the spectral embedding of weighted adjacency matrices and the downstream k-means clustering, in a challenging regime where community detection consistency is impossible. In fact, the methods are shown to estimate the optimal convex aggregation, which minimizes the misclustering error under some specialized multi-layer network models. Our analysis further suggests that clustering using Gaussian mixture models is generally superior to the commonly used k-means in spectral clustering. Extensive numerical studies demonstrate that our adaptive aggregation techniques, together with Gaussian mixture model clustering, make the new spectral clustering remarkably competitive compared to several popularly used methods. Supplementary materials for this article are available online.

A fuzzy intelligent group recommender method in sparse-data environments based on multi-agent negotiation

Recommender systems have attracted numerous scholars’ attention. Group recommender is a fashionable though challenging topic in the field of recommender systems. Most methods using aggregation technique performs poorly when conflict exists in members’ preferences. The group recommender method based on multi-agent negotiation covers this limitation. However, existing works ignore the imperfect rationality of members during negotiation. To cover up this deficiency, we propose a fuzzy intelligent group recommender method based on multi-agent negotiation. A new concession protocol makes some compensations to the transigent member considering his imperfect rationality. In this work, the dependency structure analysis is introduced to classify opinion terms into aspects, and the fuzzy numbers are introduced to characterize a maze of contradictory opinion terms in textual reviews. Moreover, a new user similarity method is established using normal cloud models. It tackles the problem of sparse data. In addition, a case study on data in TripAdvisor.com is conducted. Its results indicate the good performance of the proposed group recommender method.

Intermittent Demand Forecasting Using LSTM With Single and Multiple Aggregation

Intermittent demand data is data with infrequent demand with varying number of demand sizes. Intermittent demand forecasting is useful for providing inventory control decisions. It is very important to produce accurate forecasts. Based on previous research, deep learning models, especially MLP and RNN-based architectures, have not been able to provide better intermittent data forecasting results compared to traditional methods. This research will focus on analyzing the results of intermittent data forecasting using deep learning with several levels of aggregation and a combination of several levels of aggregation. In this research, the LSTM model is implemented into two traditional models that use aggregation techniques and are specifically used for intermittent data forecasting, namely ADIDA and MAPA. The result, based on tests on the six predetermined data, the LSTM model with aggregation and disaggregation is able to provide better test results than the LSTM model without aggregation and disaggregation.&#x0D;

Modal Aggregation Technique to Check the Accuracy of the Model Reduction of Array Cable Systems in Offshore Wind Farms

The need for a verification method for aggregation techniques for passive electrical systems is necessary as power systems increase in complexity. Model reduction is crucial to increase the number of simulations necessary to ensure a stable and reliable design of power systems. This paper presents a novel modal domain-based technique to identify the best aggregation technique for a given system and to indicate the validity of the aggregation. This is done by benchmarking different aggregation techniques and using the dominant contribution factor ratio as a validity parameter. The different aggregation techniques are compared via time-domain simulations against the full detailed model. It is found that (1) the power loss aggregation technique is the most precise when it weighs the equivalent impedances of the parallel feeders, (2) unequal current generation does not impact the aggregation accuracy, (3) individual string aggregation provides the best results for dynamic simulations, and (4) the validity of aggregation decreases as frequency or cable length increases.

Topology optimization of structures considering minimum weight and stress constraints by using the Overweight Approach

In this paper, a new method for structural topology optimization considering minimum weight and local stress constraints is proposed. For this purpose, the Overweight Approach, an improvement of the so-called Damage Approach, is used. In this method, a virtual relative density is defined as a function of the violation of the local stress constraints. The virtual relative density is increased as stresses exceed the maximum allowable value. The optimization algorithm will provide a design with a minimal variation of the relative density. The structural analysis is performed by means of the Finite Element Method (FEM) and the distribution of material is modelled in terms of a uniform relative density within each element. Moreover, the optimization is addressed by means of the Sequential Linear Programming algorithm (SLP). Finally, the proposed methodology is tested by means of some benchmark problems, and the results show that the Overweight Approach is a feasible alternative for the Damage Approach and the stress constraint aggregation techniques.