Efficient Selection Algorithm Research Articles

Relay selection schemes for SWIPT-enabled cooperative wireless networks with partial CSI

This study investigates the problem of relay selection in a cooperative network with Nakagami-m fading channels, where the energy of the relays is solely replenished by simultaneous wireless information and power transfer (SWIPT). Two efficient relay selection algorithms which require partial channel state information (CSI) at the source are proposed. The first scheme selects a relay based on the fading channel qualities of the source-relay and the relay-destination. The second one selects a relay based on the harvested power at relay and the fading channel quality of the relay-destination. In terms of coverage probability, the latter scheme is superior and is shown to have a performance close to that of the optimal relay selection scheme. Furthermore, the analytical performance bounds for the two proposed schemes are formulated. The performance analysis along with the simulation results are presented, demonstrating the superiority of the proposed schemes over the existing algorithms.

Enabling Application-Aware Traffic Engineering in IPv6 Networks

The Internet hosts numerous applications with different requirements for network delay, bandwidth, jitter, packet loss, and so on. However, in the TCP/IP network architecture, the network and application layers are decoupled, which means that the network does not have a fine-grained understanding of the application requirements. Therefore, it is not easy to provide truly fine-grained traffic operations for applications and guarantee their corresponding service level agreement requirements. In this article, we propose ATE6, which is an application-aware traffic engineering (TE) framework. For the control plane, we define a request language that can be used by applications to express their requirements, which allows networks to associate IPv6 addresses with the communication requirements of applications. We also devise an efficient path selection algorithm that allows the network operator to deploy an optimal TE path for an application. For the data plane, ATE6 uses segment routing over the IPv6 data plane to enforce and control network paths based on network policies. We implemented a prototype, and evaluation results show that ATE6 is a flexible, privacy-preserving, lightweight, and cost-efficient application-aware TE framework.

Molecular Diversity Assessment using Chemotypes.

Many techniques to design chemical libraries for screening have been put forward over time. General use libraries are still important when screening against novel targets, and their design has relied on the use of molecular descriptors. In contrast, chemotype or scaffold analysis has been used less often. We describe a simple method to assess chemical diversity based on counts of the chemotypes that offers an alternative to model chemical diversity. We describe a simple method to assess chemical diversity based on counts of the chemotypes that offers an alternative to model chemical diversity based on computed molecular properties. We show how chemotype counts can be used to evaluate the diversity of a library and compare diversity selection algorithms. We demonstrate an efficient compound selection algorithm based on chemotype analysis. We use automated chemotype perception algorithms and compare them to traditional techniques for diversity analysis to check their effectiveness in designing diverse libraries for screening. The best type of molecular fingerprints for diversity selection in our analysis are extended circular fingerprints, but they can be outperformed by the use of a chemotype diversity algorithm, which can be more intuitive than traditional techniques based on molecular descriptors. Chemotype- -based algorithms retrieve a larger share of the chemotypes contained in a library when picking a subset of the chemicals in a collection. Chemotype analysis offers an alternative for the generation of a general-purpose screening library as it maximizes the number of chemotypes present in a subset with the smallest number of compounds. The applications of methods based on chemotype analysis that does not resort to the use of molecular descriptors are a very promising but seldom explored area of chemoinformatics.

An efficient binary chimp optimization algorithm for feature selection in biomedical data classification

An efficient binary chimp optimization algorithm for feature selection in biomedical data classification

Improved Test Case Selection Algorithm to Reduce Time in Regression Testing

Regression testing (RT) is an essential but an expensive activity in software development. RT confirms that new faults/errors will not have occurred in the modified program. RT efficiency can be improved through an effective technique of selected only modified test cases that appropriate to the modifications within the given time frame. Earlier, several test case selection approaches have been introduced, but either these techniques were not sufficient according to the requirements of software tester experts or they are ineffective and cannot be used for available test suite specifications and architecture. To address these limitations, we recommend an improved and efficient test case selection (TCS) algorithm for RT. Our proposed technique decreases the execution time and redundancy of the duplicate test cases (TC) and detects only modified changes that appropriate to the modifications in test cases. To reduce execution time for TCS, evaluation results of our proposed approach are established on fault detection, redundancy and already executed test case. Results indicate that proposed technique decreases the inclusive testing time of TCS to execute modified test cases by, on average related to a method of Hybrid Whale Algorithm (HWOA), which is a progressive TCS approach in regression testing for a single product.

EEG CHANNEL SELECTION USING DIFFERANTIAL EVOLUTION ALGORITHM AND PARTICLE SWARM OPTIMIZATION FOR CLASSIFICATION OF ODORANT-STIMULATED RECORDS

A significant advancement has been made in the evolutionary computing and swarm intelligence methods in past decades. These methods have been commonly used to calculate well optimized solutions. Methods select the best elements or cases among set of alternatives. In EEG signal processing applications, efficient channel selection algorithms are required to reduce high dimensionality and remove redundant features. To do this, we examined optimal 5 electrodes out of 14 using Particle Swarm Optimization (PSO) and Differential Evolution Algorithm (DEA). The proposed work is related with pleasant-unpleasant EEG odors classification problem. Classification error rates were calculated by Linear Discriminant Analysis (LDA), k-NN (k Nearest Neighbor), Naive Bayes (NB), Regression Tree (RegTree) classifiers and used as fitness function for optimization algorithms. The results showed that PSO with selected 5 channels gave lowest error rates compared with DEA for all runs. RegTree classifier generated optimal fitness function value among other classifiers. PSO algorithm can effectively support channel selection problem to identify the best channels to maximize classification performance.

Efficient algorithms for victim item selection in privacy-preserving utility mining

High-utility itemset mining has evolved as an essential and captivating research topic. It aims to extract the patterns/itemsets having high utility value; hence, they are called high utility itemsets (HUIs). From a business perspective, a utility can be the benefit associated with the sale of a particular item or the usefulness or satisfaction that a customer experiences from a product. The economic utilities are helpful to evaluate the drivers behind a customer’s purchase decision. The advances in information technology have enabled us to access the datasets related to various domains like health care, stock market, market-basket, education and bioinformatics. Companies strive to increase the utility value of their products and share their customer’s transactions data to extract high utility patterns to achieve global customer insights. However, this can lead to massive security and privacy risk if their competitors misuse the patterns that can disclose their confidential information. Privacy-preserving utility mining (PPUM) is a branch of privacy-preserving data mining (PPDM) that presents various algorithms which intend to hide sensitive high utility itemsets (SHUIs) and maintain a balance between utility-maximizing and privacy-preserving. In this paper, two SHUIs hiding algorithms, MinMax and Weighted, are proposed with three variants of each algorithm. Experiments on various datasets show that proposed algorithms perform better than the existing SHUIs hiding algorithms as fewer distortions of non-sensitive knowledge occur. This study uses six performance evaluating metrics to assess the proposed algorithms against compared algorithms.

Hybrid artificial bee colony and glow worm algorithm for energy efficient cluster head selection in wireless sensor networks

PurposeThis paper aim to find optimal cluster head and minimize energy wastage in WSNs. Wireless sensor networks (WSNs) have low power sensor nodes that quickly lose energy. Energy efficiency is most important factor in WSNs, as they incorporate limited sized batteries that would not be recharged or replaced. The energy possessed by the sensor nodes must be optimally used so as to increase the lifespan. The research is proposing hybrid artificial bee colony and glowworm swarm optimization [Hybrid artificial bee colony and glowworm swarm optimization (HABC-GSO)] algorithm to select the cluster heads. Previous research has considered fitness-based glowworm swarm with Fruitfly (FGF) algorithm, but existing research was limited to maximizing network lifetime and energy efficiency.Design/methodology/approachThe proposed HABC-GSO algorithm selects global optima and improves convergence ratio. It also performs optimal cluster head selection by balancing between exploitation and exploration phases. The simulation is performed in MATLAB.FindingsThe HABC-GSO performance is evaluated with existing algorithms such as particle swarm optimization, GSO, Cuckoo Search, Group Search Ant Lion with Levy Flight, Fruitfly Optimization algorithm and grasshopper optimization algorithm, a new FGF in the terms of alive nodes, normalized energy, cluster head distance and delay.Originality/valueThis research work is original.

Load Balancing in DCN Servers through SDN Machine Learning Algorithm

Development in Internet technologies increases Internet users exponentially. Increase in users leads to more data center network (DCN) and heavy data traffic in servers. Data traffic in servers is managed through software-defined networking (SDN). SDN improves utilisation of large-scale network resource and performance of network applications. In SDN, load balancing technique optimises the data flow during transmission through server load deviation after evaluating the network status dynamically. However, load deviation in network needs optimum server selection and routing path with respect to less time and complexity. In this paper, we proposed a multiple regression-based searching (MRBS) algorithm for optimum server selection and routing path in DCN to improve performance even under heavy load conditions such as message spikes, different message frequencies, and unpredictable traffic patterns. MRBS selects the server based on regression analysis, which predicts types of traffic and response time based on the server data parameters such as load, response time, and bandwidth and server utilisation. MRBS combines heuristic algorithm and regression model for efficient server and path selection. The proposed algorithm reduces the delay and time more than 45% and shows better sever utilisation of 83% when compared with traditional algorithms due to stochastic gradient decent weights estimation.

Fabricating a novel colorimetric-bionic sensor coupled multivariate calibration for simultaneous determination of myoglobin proportions in pork

The quality of pork meat is of considerable importance as one of the principal sources of proteins. The study proposed the quantification of myoglobin proportions (deoxymyoglobin, oxymyoglobin and metmyoglobin) in pork meat by exploring the feasibility of colorimetric-bionic sensor array combined with efficient variable selection algorithms. Specifically, a novel colorimetric-bionic sensor array consists of nine chemically responsive dyes was fabricated. Subsequently, multivariate calibration algorithms such as partial least square (PLS), uninformative variable elimination-PLS (UVE-PLS), bootstrapping soft shrinkage-PLS (BOSS-PLS) and random frog-PLS (RF-PLS) were applied and appraised. The correlation coefficients of prediction (Rp), root mean square error of prediction (RMSEP), and residual predictive deviation (RPD) were used for the performance appraisal of the models. Optimum results were noticed with RF-PLS for myoglobin proportions (0.8412 ≤ Rp≤0.9484, 1.69 ≤ RMSEP≤3.79, and 1.68 ≤ RPD≤3.14). Therefore, this study proved that the colorimetric-bionic sensors array combined with RF-PLS could be used for rapid, simple, and non-destructive detection of quality in pork meat.

BCD-WERT: a novel approach for breast cancer detection using whale optimization based efficient features and extremely randomized tree algorithm.

Breast cancer is one of the leading causes of death in the current age. It often results in subpar living conditions for a patient as they have to go through expensive and painful treatments to fight this cancer. One in eight women all over the world is affected by this disease. Almost half a million women annually do not survive this fight and die from this disease. Machine learning algorithms have proven to outperform all existing solutions for the prediction of breast cancer using models built on the previously available data. In this paper, a novel approach named BCD-WERT is proposed that utilizes the Extremely Randomized Tree and Whale Optimization Algorithm (WOA) for efficient feature selection and classification. WOA reduces the dimensionality of the dataset and extracts the relevant features for accurate classification. Experimental results on state-of-the-art comprehensive dataset demonstrated improved performance in comparison with eight other machine learning algorithms: Support Vector Machine (SVM), Random Forest, Kernel Support Vector Machine, Decision Tree, Logistic Regression, Stochastic Gradient Descent, Gaussian Naive Bayes and k-Nearest Neighbor. BCD-WERT outperformed all with the highest accuracy rate of 99.30% followed by SVM achieving 98.60% accuracy. Experimental results also reveal the effectiveness of feature selection techniques in improving prediction accuracy.

Retracted: A smart transportation system in VANET based on vehicle geographical tracking and balanced routing protocol

SummaryIn present scenario, Vehicular Ad‐hoc Network (VANET) has obtained extensive attention because of its unique characteristics that handle high mobility of vehicles, reaping topological changes and frequent route breakages or failures. Hence, for providing smart transportation with enhanced traffic regulation and safety, a new position‐based routing protocol called Traffic Dynamism‐Balanced Routing Protocol (TDBRP) for VANET has been proposed in this paper. Moreover, the work concerns the instantaneous scenario of urban cities with the bidirectional and multilane roads. Efficient junction selection algorithm (EJSA) has been incorporated based on the traffic dynamism for establishing optimal route paths between nodes, hence, forwarding the data packets efficiently. Furthermore, the novel EJSP and the route framing between junctions are established on the basis of information gained from two‐hop neighbors, which tends to reduce end‐to‐end delay and enhances packet delivery ratio (PDR). The TDBRP has been implemented and evaluated in Network Simulator (NS 2.34). And the results are examined and compared with some existing protocols like Geographic Source Routing (GSR), Enhanced Greedy Traffic Aware Routing protocol (E‐GyTAR), and Anchor‐based Street and Traffic‐Aware Routing (A‐STAR). The outcomes outperform the existing works by minimizing the routing overhead and end‐to‐end delay by an average of 16% and 13%, respectively, and increase the PDR value by an average of 25% than others. The proposed protocol also evidences that the two‐hop neighbor information‐based packet forwarding provides better result and efficient routing than neighbor information.

Decoupled Transmit and Receive Antenna Selection for Precoding-Aided Spatial Modulation

This paper proposes an optimal joint transmit and receive antenna subsets (TRASs) selection scheme for linear precoding-aided spatial modulation (PSM) systems. The optimal joint TRASs selection is performed by exhaustively searching, so that it is difficult to analyze an achievable diversity gain and it has a huge complexity. To tackle this problem, we propose a decoupled TRAS selection method which selects receive antenna subset (RAS) and transmit antenna subset (TAS) in a two-step serial manner. By computing a lower bound on the pairwise error probability and conducting extensive simulations, it is shown that the zero-forcing (ZF)-based PSM system with $N_{T} $ transmit antennas, $N_{S} $ selected transmit antennas, $N_{R} $ receive antennas, and $N_{D} $ selected receive antennas achieves diversity order of $(N_{T} -N_{D} +1)(N_{R} -N_{D} +1)$ even with TAS selection. Furthermore, decreasing the number of active transmit antennas by TAS selection after RAS selection is analytically shown to always degrade the bit error rate performance. The analysis results are validated by simulations. These analytical and simulation results can be regarded as natural extensions of earlier works on receive antenna selection and transmit antenna selection for the PSM systems. In addition, we study and compare two efficient algorithms for TRAS selection. First, incremental and decremental algorithms are employed for separable RAS and TAS successive selection, respectively, which have an excellent performance. It is analytically shown that the computational complexity of the first proposed decoupled suboptimal TRAS selection scheme is enormously reduced compared to the joint optimal and decoupled optimal algorithms. Second, an incremental TAS selection approach replaces the decremental strategy in the first TRAS selection algorithm to further reduce the complexity.

Energy-Efficient and Delay-Minimizing Charging Method With a Multiple Directional Mobile Charger

To prolong the battery lifetime of Internet-of-Things (IoT) devices, they can be charged by a mobile charger (MC) equipped with radio frequency (RF)-based wireless power transfer (WPT) capability. By concentrating power toward IoT devices, the energy efficiency of the MC increases when using a directional antenna instead of an omnidirectional counterpart. However, directional antennas have a narrow beamwidth, and thus, several IoT devices cannot be charged simultaneously. In this article, we propose a multiple-directional MC (MDMC) scheme that exploits multiple-directional beams to reduce the charging delay while maintaining the advantages of directional antenna with a higher charging efficiency. In our MDMC, an MC determines its charging points to visit and the directions of its beams at each charging point. The charging points can be determined in consideration of the distribution of the devices and the remaining energy. After selecting charging points, the travel paths are determined by considering the remaining energy of the IoT devices. In addition, to relax the problem complexity, we propose an efficient two-stage multiple-directional beam selection (MDBS) algorithm. In the first stage, the directions of beams are determined. The second stage calculates the charging time of each beam for minimizing delay. The simulation results show that the MDMC outperforms the existing single-directional antenna-based charging schemes in terms of the energy efficiency and charging delay approximately 15% and 25%, respectively.

Set Partition Modulation

In this paper, a novel modulation scheme called set partition modulation (SPM) is proposed. In this scheme, set partitioning and ordered subsets in the set partitions are used to form codewords. We define different SPM variants and depict a practical model for using SPM with orthogonal frequency division multiplexing (OFDM). For the OFDM-SPM schemes, different constellations are used to distinguish between different subsets in a set partition. To achieve good distance properties as well as better error performance for the OFDM-SPM codewords, we define a codebook selection problem and formulate such a problem as a clique problem in graph theory. In this regard, we propose a fast and efficient codebook selection algorithm. We analyze error and achievable rate performance of the proposed schemes and provide asymptotic results for the performance. It is shown that the proposed SPM variants are general schemes, which encompass multi-mode OFDM with index modulation (MM-OFDM-IM) and dual-mode OFDM with index modulation (DM-OFDM-IM) as special cases. It is also shown that OFDM-SPM schemes are capable of exhibiting better error performance and improved achievable rate than conventional OFDM, OFDM-IM, DM-OFDM-IM, and MM-OFDM-IM.

A game-based framework for crowdsourced data labeling

Data labeling, which assigns data with multiple classes, is indispensable for many applications, such as machine learning and data integration. However, existing labeling solutions either incur expensive cost for large datasets or produce noisy results. This paper introduces a cost-effective labeling approach and focuses on the labeling rule generation problem that aims to generate high-quality rules to largely reduce the labeling cost while preserving quality. To address the problem, we first generate candidate rules and then devise a game-based crowdsourcing approach CrowdGame to select high-quality rules by considering coverage and accuracy. CrowdGame employs two groups of crowd workers: One group answers rule validation tasks (whether a rule is valid) to play a role of rule generator, while the other group answers tuple checking tasks (whether the label of a data tuple is correct) to play a role of rule refuter. We let the two groups play a two-player game: Rule generator identifies high-quality rules with large coverage, while rule refuter tries to refute its opponent rule generator by checking some tuples that provide enough evidence to reject rules with low accuracy. This paper studies the challenges in CrowdGame. The first is to balance the trade-off between coverage and accuracy. We define the loss of a rule by considering the two factors. The second is rule accuracy estimation. We utilize Bayesian estimation to combine both rule validation and tuple checking tasks. The third is to select crowdsourcing tasks to fulfill the game-based framework for minimizing the loss. We introduce a minimax strategy and develop efficient task selection algorithms. We also develop a hybrid crowd-machine method for effective label assignment under budget-constrained crowdsourcing settings. We conduct experiments on entity matching and relation extraction, and the results show that our method outperforms state-of-the-art solutions.

An Efficient Evolutionary Algorithm for Subset Selection with General Cost Constraints

In this paper, we study the problem of selecting a subset from a ground set to maximize a monotone objective function f such that a monotone cost function c is bounded by an upper limit. State-of-the-art algorithms include the generalized greedy algorithm and POMC. The former is an efficient fixed time algorithm, but the performance is limited by the greedy nature. The latter is an anytime algorithm that can find better subsets using more time, but without any polynomial-time approximation guarantee. In this paper, we propose a new anytime algorithm EAMC, which employs a simple evolutionary algorithm to optimize a surrogate objective integrating f and c. We prove that EAMC achieves the best known approximation guarantee in polynomial expected running time. Experimental results on the applications of maximum coverage, influence maximization and sensor placement show the excellent performance of EAMC.

Maximising network lifetime and energy efficiency of wireless sensor network using group search Ant lion with Levy flight

Wireless sensor network (WSN) is one of the emerging techniques, providing pervasive computing for different implementations. Some of the renowned problems in WSN are energy consumption, as well as, the extension of network lifetime. Moreover, cluster head (CH) selection is one of the essential criteria since it has direct communication with the base station. Several researchers are in progress in designing the energy-efficient model. However, the problems are not yet rectified completely, which leads to the poor performance of WSN. This study intends to maximise the lifetime of the WSN by introducing an efficient CH selection algorithm. The CH selection is a crucial step that aids in improving the energy efficiency and network lifetime of a WSN. This study proposes a hybrid optimisation process named group search ant lion with Levy flight for choosing the CH in WSN. The proposed model is compared to the conventional models such as genetic algorithm, particle swarm optimisation, artificial bee colony, group search optimisation, ant lion optimisation and cuckoo search. The outcome of the simulation result shows the superiority of the proposed model by prolonging the lifetime of the network.

Efficient genetic algorithm for feature selection for early time series classification

This paper addresses a multi-objective feature selection problem for early time series classification. Previous research has focused on how many features to consider for a classifier, but has not considered the starting time of classification, which is also important for early classification. Motivated by this, we developed a mathematical model for which the objectives are to maximize classification performance and minimize the starting time and execution time of classification. We designed an efficient genetic algorithm to generate solutions with high probability. In experiment, we compared the proposed algorithm and general genetic algorithm under various experimental settings. From the experiment, we verified that the proposed algorithm can find a better feature set in terms of classification performance, starting time and execution time of classification than feature set found by general genetic algorithm.

An Energy Efficient Stable Clustering Approach Using Fuzzy Type-2 Bat Flower Pollinator for Wireless Sensor Networks

Wireless sensor network (WSN) is a cost-effective networking solution for information updating in the coverage radius or in the sensing region. To record a real time event, large number of sensor nodes (SNs) need to be arranged systematically, such that information collection is possible for longer span of time. But, the hurdle faced by WSN is the limited resources of SNs. Hence, there is high demand to design and implement an energy efficient scheme to prolong the operational lifetime of WSN. Clustering based routing is the most suitable approach to support for load balancing, fault tolerance, and reliable communication to prolong performance parameters of WSN. These performance parameters are achieved at the cost of reduced lifetime of cluster head (CH). To overcome such limitations in clustering based hierarchical approach, efficient CH selection algorithm, and optimized routing algorithm are essential to design efficient solution for larger scale networks. In this paper, bat flower pollinator (BFP) using fuzzy type-2 based clustering approach is proposed to enhance the network lifespan. Simulation outcomes show that the proposed algorithm outperforms competitive clustering algorithms in the context of energy consumption, stability period and system lifetime.