Additive Aggregation Functions Research Articles

Assessing energy vulnerability in Colombia using a multidimensional index

Energy vulnerability studies are conducted to identify and address the multidimensional causes of energy problems of a territory. Colombia faces substantial energy challenges, including sustained excess demand, slow supply expansion, rising tariffs, flow intermittency and power instability. It is a tropical developing country undergoing an energy transition and characterized by significant cultural, geographical, and demographic diversity. This article assesses the energy vulnerability of Colombia's 32 departments and its capital district through a Multidimensional Energy Vulnerability Index (MEVI). The MEVI is a measure ranging from 0 to 1 that evaluates energy vulnerability through 12 indicators across four dimensions: social, environmental, technical, and economic. To construct the index, a multivariate analysis using Cronbach's Alpha was conducted, and the min-max normalization method was employed. Additionally, a specific weighting system of the dimensions accompanied by an additive aggregation function was utilized to synthesize the various indicators into a unified index. Furthermore, a sensitivity analysis was performed to assess the robustness of the index, incorporating variations in key inputs such as the weighting scheme and data processing methods. The mean energy vulnerability score was 0.6, indicating that the departments of Colombia do not have extreme energy vulnerability. The territories with the highest energy vulnerability include the Departments of Vaupés, Guainía, Vichada, and Amazonas. In these cases, effective government policy is necessary to provide more energy security, which requires improvements across nearly all indicators involved in the calculation of the index. A discussion on the policies that could be implemented is presented in the document.

A new deep neural network for forecasting: Deep dendritic artificial neural network

Deep artificial neural networks have become a good alternative to classical forecasting methods in solving forecasting problems. Popular deep neural networks classically use additive aggregation functions in their cell structures. It is available in the literature that the use of multiplicative aggregation functions in shallow artificial neural networks produces successful results for the forecasting problem. A type of high-order shallow artificial neural network that uses multiplicative aggregation functions is the dendritic neuron model artificial neural network, which has successful forecasting performance. In this study, the transformation of the dendritic neuron model turned into a multi-output architecture. A new dendritic cell based on the multi-output dendritic neuron model and a new deep artificial neural network is proposed. The training of this new deep dendritic artificial neural network is carried out with the differential evolution algorithm. The forecasting performance of the deep dendritic artificial neural network is compared with basic classical forecasting methods and some recent shallow and deep artificial neural networks over stock market time series. As a result, it has been observed that deep dendritic artificial neural network produces very successful forecasting results for the forecasting problem.

International trade privacy data management system combining Internet of Things blockchain

Currently, international trade (Int’l Trade) often faces risks such as privacy data leakage and transaction security during transactions, which seriously affect the protection of privacy data in trade. Therefore, this article used the Internet of Things and blockchain to attempt to address these risk issues and improve the security of privacy data. By analyzing the security threats in Int’l Trade transactions, this article used additive aggregation functions to analyze the protection effect of privacy data and studied the core issues of Int’l Trade privacy data. This article analyzed the privacy protection model using the Internet of Things blockchain and proposed corresponding Int’l Trade privacy data protection strategies. Among the five surveyed enterprises, data audit and data backup were all above the standard value, while data query only exceeded the standard value for enterprises 2, 3, 4, and 5. The average abnormal value of the enterprise in data anomalies decreased by 0.06 compared to the standard value. Through experimental testing, it has been found that Internet of Things blockchain can effectively improve the privacy data protection effect of Int’l Trade and promote the convenience of Int’l Trade transactions.

Intelligent Financial Forecasting With an Improved Chemical Reaction Optimization Algorithm Based Dendritic Neuron Model

Chemical reaction optimization (CRO) algorithm is a robust metaheuristic by simulating the process of natural chemical reaction and has been applied for solving numerous realistic problems. However, it is suffering from low population diversity, slow convergence, and deprived from local search ability. To boost the search operation of CRO, this article proposes an improved CRO method termed as ICRO. We achieve the improvements in two phases. First, to start the search operation with a better-quality population, we propose a new method to initialize population which helps in enhancing diversification of the search space. Second, to intensify the local search ability we integrate Nelder-Mead simplex method with CRO. The ICRO is then evaluated on a few benchmark functions for optimization and found apposite. Dendritic neuron model (DNM) using additive and multiplicative-based aggregation functions has been emerging as a machine learning approach and found successful in many engineering applications. This study attempts to advance the predictive accuracy of DNM through maintaining a decent steadiness between exploitation and exploration of its search space with the proposed ICRO, termed as ICRO-DNM. The powerful global search ability of ICRO synergies with better approximation capability of DNM thus, able to overcome the limitations of conventional back propagation learning based DNM. ICRO-DNM is evaluated on closing price prediction for four stock index and net asset values of four mutual fund datasets and found efficient. The consequences of this attempt are: (1) Proposed ICRO shows robust parameter optimization ability for benchmark functions and DNM compared to basic CRO, particle swarm optimization (PSO), and genetic algorithm (GA); (2) The learning paradigm formed due to reasonable amalgamation of ICRO and DNM is pretty able to capture the underlying uncertainties coupled with financial data, produces more precise and steady predictions and significantly different from other forecasts.

Dendritic neuron model neural network trained by modified particle swarm optimization for time‐series forecasting

AbstractDifferent types of artificial neural networks (NNs), such as nonprobabilistic and computation‐based time‐series forecasting tools, are widely and successfully used in the time‐series literature. Whereas some of them use an additive aggregation function, others use a multiplicative aggregation function in the structure of their neuron models. In particular, recently proposed sigma‐pi NNs and dendritic NNs have additional and multiplicative neuron models. This study aims to take advantage of the dendritic neuron model neural network (DNM‐NN) in forecasting and hence uses the DNM‐NN trained by a modified particle swarm optimization as the main contribution of the study optimization in time‐series forecasting to improve the forecasting accuracy. To evaluate the forecasting performance of the DNM‐NN, the Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX) was analyzed, and the obtained results were discussed together with the results produced by other time‐series forecasting models, including traditional, fuzzy‐based, and computational‐based models.

Secure In-Network Aggregation in Wireless Sensor Networks

In-network aggregation is a natural approach in wireless sensor networks (WSNs) to collaboratively process data generated by the sensor nodes. Besides processing, in-network aggregation also achieves effective energy consumption and bandwidth utilization. Since the sensing devices of a WSN are prone to a variety of attacks due to wireless communication and limited resources, secure in-network aggregation is a great challenge. This article proposes a secure in-network aggregation (SINA) protocol for additive aggregation functions. This protocol integrates privacy homomorphism (PH) and secret sharing to achieve both data confidentiality and data integrity. Additionally, the proposed protocol ensures message authentication and data freshness. Moreover, it achieves false data screening in-network should be changed as in-network false data screening which considerably saves energy by not transmitting false packets. Security analysis reveals that SINA protects the network from variety of attacks. Performance analysis shows that SINA consumes less energy while achieving end-to-end security, and thereby increases the lifetime of the WSN.

Additive Aggregation Functions: Generalizations and Modifications of Additivity

In this paper we study some modifications and generalizations of additivity in the case of aggregation functions on the unit interval [0, 1]. We prove that some common properties of aggregation functions can be viewed as modifications of additivity — additivity with constraints.We also generalize additivity into pseudo-additivity and k-pseudo-additivity, and provide characterization of pseudo-additive and k-pseudo-additive aggregation functions, including maxitive and k-maxitive aggregation functions.

The need for unconventional value aggregation techniques: experiences from eliciting stakeholder preferences in environmental management

Despite the large literature about non-additive value aggregation techniques, in the large majority of applied decision support processes, additive value aggregation functions are used. The main reasons for this may be the simplicity of the approach, minimum elicitation requirements, software availability, and the appeal of the underlying preference independence concepts that may be strengthened by an adequate choice of sub-objectives and attributes. However, in an applied decision support process, the decision maker(s) or the stakeholders decide on the sub-objectives and attributes to characterize the state of a system and they have to provide information that allows the decision analyst to express their preferences as a value function of these attributes. It is the task of the decision analyst to find the parameterization and parameter values of a value function that fits best the expressed preferences. We describe a value function elicitation process for the ideal morphological state of a lake shore, performed with stakeholders from federal and cantonal authorities and from environmental consulting companies in Switzerland. This process led to the elicitation of strongly non-additive and partly even non-concave value aggregation functions. The objective of this paper is to raise the awareness about the importance of carefully testing the assumptions underlying parameterized (often additive) value aggregation techniques during the preferences elicitation process and to be flexible regarding evaluating value functions that deviate from the often used additive aggregation scheme. This can lead to a higher confidence that additive aggregation is suitable for the specific decision problem or to the selection of alternative aggregation techniques that better represent the decision maker’s preferences in case additivity is violated.

Additive Aggregate Function-based Data Privacy Protection Algorithm

Data privacy protection is a key problem in the research and application of the internet of things that in wireless sensor networks has broad application prospects, such as agriculture environmental monitoring, healthcare, etc. For the core part of the internet of things, wireless sensor network, it is a very challenging task to provide effective privacy protection in the process of data transmission. In this paper, a new type of data privacy protection strategy based on the additive aggregation function is proposed (hereafter referred to as DPPA). On the one hand, applying the superposition property of the node data, the paper introduces the class aggregation protocol. On the other hand, taking advantage of the algebraic properties of the polynomials and the correlation properties of the superposed data, it can reduce the data of the header files of the data packages, and reduce the data size, while improving the privacy preservation. Simulation results show that DPPA can effectively protect data privacy, and get accurate data fusion results, while reducing the amount of data traffic.

Additive aggregate function-based data privacy protection algorithm

Data privacy protection is a key problem in the research and application of the internet of things that in wireless sensor networks has broad application prospects, such as agriculture environmental monitoring, healthcare, etc. For the core part of the internet of things, wireless sensor network, it is a very challenging task to provide effective privacy protection in the process of data transmission. In this paper, a new type of data privacy protection strategy based on the additive aggregation function is proposed (hereafter referred to as DPPA). On the one hand, applying the superposition property of the node data, the paper introduces the class aggregation protocol. On the other hand, taking advantage of the algebraic properties of the polynomials and the correlation properties of the superposed data, it can reduce the data of the header files of the data packages, and reduce the data size, while improving the privacy preservation. Simulation results show that DPPA can effectively protect data privacy, and get accurate data fusion results, while reducing the amount of data traffic.

A survey on Privacy Preserving Data Aggregation Schemes in People Centric Sensing Systems and Wireless Domains

Background: The technological advances in mobile and wireless communication have paved way for a new era of large scale sensing network. Smart phones used by people are nowadays equipped with rich set of sensing capabilities. These mobile devices carried by people can be used together to form a network called people centric sensing network. Methods: Since people are the mobile custodians, privacy becomes a threat to the network. This paper focuses on a study about the various privacy preserving aggregation schemes existing in other domains of the wireless network including people centric sensing. The design goals and challenges that arise when attempting to protect the user’s sensitive data are analyzed. The techniques commonly used to achieve user’s privacy are the homomorphic property of encryption schemes, Data slicing and Mix schemes. Findings: A study about the existing privacy preserving aggregation schemes enables us to design a new method that is more suitable for people centric sensing network. The design considerations involved in developing a security and privacy framework are also identified. The privacy preserving aggregation scheme should support spatial and temporal aggregation with fault tolerance. The scheme has to be adaptable for both additive and non-additive statistical aggregation functions. Also maintaining the data integrity, data privacy and data accuracy with less computational and communication overhead is essential. Applications: Privacy protection is important for user’s participation which supports large set of cooperative sensing applications. Irrespective of various domains in wireless networks, the privacy preserving data aggregation model is discussed that is suitable for the context of the applications.

Two Tier Cluster Based Data Aggregation (TTCDA) for Efficient Bandwidth Utilization in Wireless Sensor Network

Wireless Sensor Networks are often used for monitoring and control applications where sensor nodes collect data and send it to the sink. Direct transmission of data packets to the sink from nodes in the network causes increased communication costs in terms of energy, network lifetime and bandwidth utilization. In this context, this paper proposes Two Tier Cluster-based Data Aggregation (TTCDA) algorithm for the randomly distributed nodes in the network to minimize computation and communication cost. The TTCDA effectively considers the packet and data aggregation using additive and divisible aggregation functions at cluster head and sink. The aggregation functions are applied according to spatial and temporal correlation of packets and data generated by each node. It also prevents transmission of redundant data by improving energy consumption and bandwidth utilization as compared with state-of-the-art solution. The performance of the algorithm is validated using examples and simulations. Also, it is seen that packet aggregation in TTCDA is better for the bandwidth utilization as it reduces average energy consumption by 3.13 % as compared to data aggregation.

PDA: A Novel Privacy-Preserving Robust Data Aggregation Scheme in People-Centric Sensing System

With the advancement of wireless communication technologies, mobile phones, PDAs, and car embedded devices are equipped with sensors, such as sound and image. People can apply these devices to form a new sensing network called people-centric sensing network. And this network offers new opportunities for cooperative sensing applications. However, it introduces some challenges, including security challenge and robust challenge. As sensor nodes need to send their individual sensed data to an aggregator node and these data are related to users' real life, privacy-preserving data aggregation is a challenge issue. As a node could become offline or a message could be lost before reaching the aggregator, retaining the correctness of the aggregate computed is important. In this paper, we present the design of PDA, a novel privacy-preserving robust data aggregation scheme in people-centric sensing system. Based on K-anonymity, homomorphic encryption, and secret sharing, PDA can support a wide range of statistical additive and non-additive aggregation functions such as Sum, Subtraction, Average, Count, Max/Min, and Median without leaking individual sensed data. Moreover, PDA is robust to node failure and data loss. We also evaluate the efficacy and efficiency of PDA. The result shows that our scheme can achieve the security and robust goal under a reasonable cost.

Verifiable Privacy-Preserving Aggregation in People-Centric Urban Sensing Systems

People-centric urban sensing systems (PC-USSs) refer to using human-carried mobile devices such as smartphones and tablets for urban-scale distributed data collection, analysis, and sharing to facilitate interaction between humans and their surrounding environments. A main obstacle to the widespread deployment and adoption of PC-USSs are the privacy concerns of participating individuals as well as the concerns about data integrity. To tackle this open challenge, this paper presents the design and evaluation of VPA, a novel peer-to-peer based solution to verifiable privacy-preserving data aggregation in PC-USSs. VPA achieves strong user privacy by letting each user exchange random shares of its datum with other peers, while at the same time ensures data integrity through a combination of Trusted Platform Module and homomorphic message authentication code. VPA can support a wide range of statistical additive and non-additive aggregation functions such as Sum, Average, Variance, Count, Max/Min, Median, Histogram, and Percentile with accurate aggregation results. The efficacy and efficiency of VPA are confirmed by thorough analytical and simulation results.

PDA

Providing efficient data aggregation while preserving data privacy is a challenging problem in wireless sensor networks research. In this article, we present two privacy-preserving data aggregation schemes for additive aggregation functions, which can be extended to approximate MAX/MIN aggregation functions. The first scheme--- Cluster-based Private Data Aggregation (CPDA)---leverages clustering protocol and algebraic properties of polynomials. It has the advantage of incurring less communication overhead. The second scheme--- Slice-Mix-AggRegaTe (SMART)---builds on slicing techniques and the associative property of addition. It has the advantage of incurring less computation overhead. The goal of our work is to bridge the gap between collaborative data collection by wireless sensor networks and data privacy. We assess the two schemes by privacy-preservation efficacy, communication overhead, and data aggregation accuracy. We present simulation results of our schemes and compare their performance to a typical data aggregation scheme (TAG), where no data privacy protection is provided. Results show the efficacy and efficiency of our schemes.

On the scoring approach to admissibility of uncertainty measures in expert systems

This paper arose from our need to rigorize, clarify, and address fully the results of Lindley's paper (Scoring rules and the inevitability of probability, Internat. Statist. Rev. 50, (1982), 1–26). Herein, we develop a calculus of admissibility in a game theoretic setting. In the case of an additive aggregation function, it is shown that decomposable measures, such as those used in fuzzy logics, are admissible. Also, the problem of the admissibility of the Dempster-Shafer belief functions is investigated via the concept of random sets. It is shown that the class of admissible measures in a scoring framework depends on the assumptions concerning the aggregation function in use. In particular, for nonadditive aggregation functions, an admissible measure may not be transformable to a finitely additive probability measure.