Search results

Class imbalance learning, which exists in many domain problem datasets, is an important research topic in data mining and machine learning. One-class classification techniques, which aim to identify anomalies as the minority class from the normal data as the majority class, are one representative solution for class imbalanced datasets. Since one-class classifiers are trained using only normal data to create a decision boundary for later anomaly detection, the quality of the training set, i.e. the majority class, is one key factor that affects the performance of one-class classifiers.

In this paper, we focus on two data cleaning or preprocessing methods to address class imbalanced datasets. The first method examines whether performing instance selection to remove some noisy data from the majority class can improve the performance of one-class classifiers. The second method combines instance selection and missing value imputation, where the latter is used to handle incomplete datasets that contain missing values.

The experimental results are based on 44 class imbalanced datasets; three instance selection algorithms, including IB3, DROP3 and the GA, the CART decision tree for missing value imputation, and three one-class classifiers, which include OCSVM, IFOREST and LOF, show that if the instance selection algorithm is carefully chosen, performing this step could improve the quality of the training data, which makes one-class classifiers outperform the baselines without instance selection. Moreover, when class imbalanced datasets contain some missing values, combining missing value imputation and instance selection, regardless of which step is first performed, can maintain similar data quality as datasets without missing values.

The novelty of this paper is to investigate the effect of performing instance selection on the performance of one-class classifiers, which has never been done before. Moreover, this study is the first attempt to consider the scenario of missing values that exist in the training set for training one-class classifiers. In this case, performing missing value imputation and instance selection with different orders are compared.

On-time fault diagnosis in electrical machines is a critical issue, as it can prevent the development of fault and also reduce the repairing time and cost. In brushless synchronous generators, the significance of the fault diagnosis is even more because they are widely used to generate electrical power all around the world. Therefore, this study aims to propose a fault detection approach for the brushless synchronous generator. In this approach, a novel extension of Relief feature selection method is developed.

In this paper, by taking the advantages of the finite element method (FEM), a brushless synchronous machine is modeled to evaluate the machine performance under two conditions. These conditions include the normal condition of the machine and one diode open-circuit of the rotating rectifier. Therefore, the harmonic behavior of the terminal voltage of the machine is obtained under these situations. Then, the harmonic components are ranked by using the extension of Relief to extract the most appropriate components for fault detection. Therefore, a fault detection approach is proposed based on the ranked harmonic components and support vector machine classifier.

The proposed diagnosis approach is verified by using an experimental test. Results show that by this approach open-circuit fault on the diode rectifier can effectively be detected by the accuracy of 98.5% and by using five harmonic components of the terminal voltage [1].

In this paper, a novel feature selection method is proposed to select the most effective FFT components based on an extension of Relief method, and besides, FEM modeling of a brushless synchronous generator for normal and one diode open-circuit fault.

The purpose of this paper is to provide adaptive access to learning resources in the digital library.

A novel method using ontology-based multi-attribute collaborative filtering is proposed. Digital libraries are those which are fully automated and all resources are in digital form and access to the information available is provided to a remote user as well as a conventional user electronically. To satisfy users' information needs, a humongous amount of newly created information is published electronically in digital libraries. While search applications are improving, it is still difficult for the majority of users to find relevant information. For better service, the framework should also be able to adapt queries to search domains and target learners.

This paper improves the accuracy and efficiency of predicting and recommending personalized learning resources in digital libraries. To facilitate a personalized digital learning environment, the authors propose a novel method using ontology-supported collaborative filtering (CF) recommendation system. The objective is to provide adaptive access to learning resources in the digital library. The proposed model is based on user-based CF which suggests learning resources for students based on their course registration, preferences for topics and digital libraries. Using ontological framework knowledge for semantic similarity and considering multiple attributes apart from learners' preferences for the learning resources improve the accuracy of the proposed model.

The results of this work majorly rely on the developed ontology. More experiments are to be conducted with other domain ontologies.

The proposed approach is integrated into Nucleus, a Learning Management System (https://nucleus.amcspsgtech.in). The results are of interest to learners, academicians, researchers and developers of digital libraries. This work also provides insights into the ontology for e-learning to improve personalized learning environments.

This paper computes learner similarity and learning resources similarity based on ontological knowledge, feedback and ratings on the learning resources. The predictions for the target learner are calculated and top N learning resources are generated by the recommendation engine using CF.

The purpose of this paper is to provide insight into various swarm intelligence-based routing protocols for Internet of Things (IoT), which are currently available for the Mobile Ad-hoc networks (MANETs) and wireless sensor networks (WSNs). There are several issues which are limiting the growth of IoT. These include privacy, security, reliability, link failures, routing, heterogeneity, etc. The routing issues of MANETs and WSNs impose almost the same requirements for IoT routing mechanism. The recent work of worldwide researchers is focused on this area.

The paper provides the literature review for various standard routing protocols. The different comparative analysis of the routing protocols is done. The paper surveys various routing protocols available for the seamless connectivity of things in IoT. Various features, advantages and challenges of the said protocols are discussed. The protocols are based on the principles of swarm intelligence. Swarm intelligence is applied to achieve optimality and efficiency in solving the complex, multi-hop and dynamic requirements of the wireless networks. The application of the ant colony optimization technique tries to provide answers to many routing issues.

Using the swarm intelligence and ant colony optimization principles, it has been seen that the protocols’ efficiency definitely increases and also provides more scope for the development of more robust, reliable and efficient routing protocols for the IoT.

The existing protocols do not solve all reliability issues and efficient routing is still not achieved completely. As of now no techniques or protocols are efficient enough to cover all the issues and provide the solution. There is a need to develop new protocols for the communication which will cater to all these needs. Efficient and scalable routing protocols adaptable to different scenarios and network size variation capable to find optimal routes are required.

The various routing protocols are discussed and there is also an introduction to new parameters which can strengthen the protocols. This can lead to encouragement of readers, as well as researchers, to analyze and develop new routing algorithms.

The paper provides better understanding of the various routing protocols and provides better comparative analysis for the use of swarm-based research methodology in the development of routing algorithms exclusively for the IoT.

This is a review paper which discusses the various routing protocols available for MANETs and WSNs and provides the groundwork for the development of new intelligent routing protocols for IoT.

The purpose of this paper is to propose a distributed unmanned aerial vehicle (UAV) swarm control method to ensure safety and obstacle avoidance during swarm flight and realize effective guidance.

This paper proposes a distributed UAV swarm control framework with limited interaction. UAVs in the swarm realize the selection of limited interactive neighbors according to the random line of sight and limited field of view. The designed interaction force and obstacle avoidance mechanism are combined to ensure the safety of UAVs and avoid collisions and obstacles. Informed UAVs are deployed to guide the swarm to move in the desired direction.

The proposed distributed swarm control framework achieves high safety of swarm motion and the participation of informed UAVs is conducive to the guidance of the UAV swarm. Simulation results demonstrate the feasibility and effectiveness of the proposed approach.

The UAV swarm control method developed in this paper can be applied to the practice of UAV swarm control.

A distributed UAV swarm control method is proposed to ensure the effective control of the consistency and safety of swarm motion.

Collaborative filtering (CF), one of the most popular recommendation techniques, is based on the principle of word-of-mouth communication between other like-minded users. The process of identifying these like-minded or similar users remains crucial for a CF framework. Conventionally, a neighbor is the one among the similar users who has rated the item under consideration. To select neighbors by the existing practices, their similarity deteriorates as many similar users might not have rated the item under consideration. This paper aims to address the drawback in the existing CF method where “not-so-similar” or “weak” neighbors are selected.

The new approach proposed here selects neighbors only on the basis of highest similarity coefficient, irrespective of rating the item under consideration. Further, to predict missing ratings by some neighbors for the item under consideration, ordinal logistic regression based on item–item similarity is used here.

Experiments using the MovieLens (ml-100) data set prove the efficacy of the proposed approach on different performance evaluation metrics such as accuracy and classification metrics. Apart from higher prediction quality, coverage values are also at par with the literature.

This new approach gets its motivation from the principle of the CF method to rely on the opinion of the closest neighbors, which seems more meaningful than trusting “not-so-similar” or “weak” neighbors. The static nature of the neighborhood addresses the scalability issue of CF. Use of ordinal logistic regression as a prediction technique addresses the statistical inappropriateness of other linear models to make predictions for ordinal scale ratings data.

Privacy preservation is a significant concern in Internet of Things (IoT)-enabled event-driven wireless sensor networks (WSNs). Low energy utilization in the event-driven system is essential if events do not happen. When events occur, IoT-enabled sensor network is required to deal with enormous traffic from the concentration of demand data delivery. This paper aims to explore an effective framework for safeguarding privacy at source in event-driven WSNs.

This paper discusses three algorithms in IoT-enabled event-driven WSNs: source location privacy for event detection (SLP_ED), chessboard alteration pattern (SLP_ED_CBA) and grid-based source location privacy (GB_SLP). Performance evaluation is done using simulation results and security analysis of the proposed scheme.

The sensors observe bound events or sensitive items within the network area in the field of interest. The open wireless channel lets an opponent search traffic designs, trace back and reach the start node or the event-detecting node. SLP_ED and SLP_ED_CBA provide better safety level results than dynamic shortest path scheme and energy-efficient source location privacy protection schemes. This paper discusses security analysis for the GB_SLP. Comparative analysis shows that the proposed scheme is more efficient on safety level than existing techniques.

The authors develop the privacy protection scheme in IoT-enabled event-driven WSNs. There are two categories of occurrences: nominal events and critical events. The choice of the route from source to sink relies on the two types of events: nominal or critical; the privacy level required for an event; and the energy consumption needed for the event. In addition, phantom node selection scheme is designed for source location privacy.

Continuous exposure and over‐utilization of sensors in harsh environments can lead some sensors to fail, and thereby not covering the service area effectively and efficiently. The purpose of this paper is to propose a two‐level coverage restoration scheme for the failing sensors by the existing sensors deployed in the immediate neighborhood of the failing sensors. The restoration scheme extends the search process to the set of failed sensors' corner neighbors at a second stage, with non‐available immediate active neighboring sensors at its first stage. Thus, the coverage restoration scheme attempts to sustain a maximum area of coverage with failed sensors.

The authors have considered a wireless sensor network (WSN), comprised of sensors deployed in a grid‐based arrangement in an inaccessible arena. The authors have formulated the coverage restoration problem as an optimization problem, to find the nearest and most apt neighbor sensors to reach solutions of maximizing the coverage area with failed sensors, while minimizing the energy consumption. Simulated annealing has been utilized as a search algorithm to find out the neighboring sensors with maximal energy in the vicinity of the failed node to cover its area.

The experimental results within the optimization algorithm have demonstrated that the restoration scheme shows a better trade‐off in maximizing the coverage area up to 90 per cent with a decrease of 26 per cent lifespan. The performance of the algorithm is further improved with extended search space including the corner neighbors in addition to the immediate neighbors.

The proposed coverage restoration can be embedded within applications using WSN to restore the coverage and maintain its functionality with optimized energy consumption.

The paper employs a novel framework to restore the coverage of the failed sensors by doubling the sensing area of the neighborhood sensors, and it utilizes an optimization scheme to search for neighborhood sensors with maximal energy to extend the lifespan of WSN.

The purpose of this paper is to have a review on the analysis of information diffusion based on evolutionary game theory. People now get used to interact over social networks, and one of the most important functions of social networks is information sharing. Understanding the mechanisms of the information diffusion over social networks is critical to various applications including online advertisement and rumor control.

It has been shown that the graphical evolutionary game theory (EGT) is a very efficient method to study this problem.

By applying EGT to information diffusion, the authors could predict every small change in the process, get the detailed dynamics and finally foretell the stable states.

In this paper, the authors provide a general review on the evolutionary game-theoretic framework for information diffusion over social network by summarizing the results and conclusions of works using graphical EGT.

Wireless sensor networks (WSNs) have emerged as one of the most promising technology in our day-to-day life. Limited network lifetime and higher energy consumption are two most critical issues in WSNs. The purpose of this paper is to propose an energy-efficient load balanced cluster-based routing protocol using ant colony optimization (LB-CR-ACO) which ultimately results in enhancement of the network lifetime of WSNs.

The proposed protocol performs optimal clustering based on cluster head selection weighing function which leads to novel cluster head selection. The cluster formation uses various parameters which are remaining energy of the nodes, received signal strength indicator (RSSI), node density and number of load-balanced node connections. Priority weights are also assigned among these metrics. The cluster head with the highest probability will be selected as an optimal cluster head for a particular round. LB-CR-ACO also performs a dynamic selection of optimal cluster head periodically which conserves energy, thereby using network resources in an efficient and balanced manner. ACO is used in steady state phase for multi-hop data transfer.

It has been observed through simulation that LB-CR-ACO protocol exhibits better performance for network lifetime in sparse, medium and dense WSN deployments than its peer protocols.

The proposed paper provides a unique energy-efficient LB-CR-ACO for WSNs. LB-CR-ACO performs novel cluster head selection using optimal clustering and multi-hop routing which utilizes ACO. The proposed work results in achieving higher network lifetime than its peer protocols.