Description:
Event-based social networks (EBSNs) are the newly emerging social platforms for users to publish events online and attract others to attend events offline. The content information of events plays an important role in event recommendation. However, the content-based approaches in existing event recommender systems cannot fully represent the preference of each user on events since most of them focus on exploiting the content information from events' perspective, and the bag-of-words model, commonly used by them, can only capture word frequency but ignore word orders and sentence structure. In this paper, we shift the focus from events' perspective to users' perspective, and propose a Deep User Modeling framework for Event Recommendation (DUMER) to characterize the preference of users by exploiting the contextual information of events that users have attended. Specifically, we utilize convolutional neural network (CNN) with word embedding to deeply capture the contextual information of a user's interested events and build up a user latent model for each user. We then incorporate the user latent model into probabilistic matrix factorization (PMF) model to enhance the recommendation accuracy. We conduct experiments on the real-world dataset crawled from a typical EBSN, Meetup.com, and the experimental results show that DUMER outperforms the compared benchmarks.
Description:
This paper presents a novel signal processing approach for computing thickness of ferromagnetic cast iron material, widely employed in older infrastructure such as water mains or bridges. Measurements are gathered from a Pulsed Eddy Current (PEC) based sensor placed on top of the material, with unknown lift-off, as commonly used during non-destructive testing (NDT). The approach takes advantage of an analytical logarithmic model proposed in the literature for the decaying voltage induced at the PEC sensor pick-up coil. An increasingly more accurate and robust algorithm is proven here by means of an Adaptive Least Square Fitting Line (ALSFL) recursive strategy, suitable to recognize the most linear part of the sensor's logarithmic output voltage for subsequent gradient computation, from which thickness is then derived. Moreover, efficiency is also gained as processing can be carried out on only one decaying voltage signal, unlike averaging over multiple measurements as is usually done in the literature. Importantly, the new signal processing methodology demonstrates highest accuracies at the lower thicknesses, a circumstance most relevant to NDT evaluation. Experiments that verify the proposed method in real-world thickness assessment of cast iron material are presented and compared with current practices, showing promising results.
Description:
Rapidly estimating the remaining wall thickness (RWT) is paramount for the non-destructive condition assessment evaluation of large critical metallic pipelines. A robotic vehicle with embedded magnetism-based sensors has been developed to traverse the inside of a pipeline and conduct inspections at the location of a break. However, its sensing speed is constrained by the magnetic principle of operation, thus slowing down the overall operation in seeking dense RWT mapping. To ameliorate this drawback, this work proposes the partial scanning of the pipe and then employing Gaussian Processes (GPs) to infer RWT at the unseen pipe sections. Since GP prediction assumes to have normally distributed input data - which does correspond with real RWT measurements - Gaussian mixture (GM) models are proven in this work as fitting marginal distributions to effectively capture the probability of any RWT value in the inspected data. The effectiveness of the proposed approach is validated from real-world data collected in collaboration with a water utility from a cast iron water main pipeline in Sydney, Australia.
Description:
When a Pulsed Eddy Current (PEC) sensor assesses a metallic surface (i.e., a wall of finite thickness), the inverse problem involves quantification of the geometry and material properties of the wall. Once a PEC sensor is calibrated for a particular material, and the material under test happens to be considerably homogeneous, the inverse problem reduces to quantification of geometry alone. The state-of-the-art in the industry produces a quantification of this geometry only in the form of average wall thickness remaining underneath the sensor footprint, and produces a 2.5D map containing wall thickness information. Therefore, this paper contributes by proposing a solution that can jointly estimate the remaining wall thickness as well as lift-off (i.e., offset from the sensor to the surface of healthy material), in order to advance PEC sensing outputs by enabling estimation of wall condition in 3D. Since PEC maps are used as inputs for stress calculation and remaining life prediction of certain infrastructure like critical pipes, 3D profiles may become a richer form of input for such applications than 2.5D maps. Since PEC sensing is commonly used to assess ferromagnetic materials, this paper focuses on similar materials as well. The solution is demonstrated in simulation alone and future work should focus on experimental implementations.
Description:
In a social network, the topology of the network grows through the formation of the link. the connection between two nodes in a social network indicates a confidence in terms of the similarity of some activities. Generally, a new link in the social network is created from different perspectives such as familiarity, cohesiveness, geographical locations etc. The concept of the link in the social network has been utilized to discover the hidden meaning of different fields such as e-commerce, bioinformatics and information retrieval. The prediction of a new link between two nodes in the social network is normally accomplished based on the nature of the topology and the similarity function among the nodes is defined with the help of the number of common friends. In this paper, we propose two link prediction algorithms: Local Link Prediction Algorithm and Global Link prediction by taking into consideration of user's activities as well as the common friends. We apply two formulas called correlation based cScore and influential score based iScore to measure the similarity between the two predicted nodes. Finally, we analyze the performance of the proposed algorithms by using DBLP, PPI, PB, and USAir data sets and the experimental result attests that our link predicted algorithm outperforms over the existing algorithms.
Description:
Intelligent Electronic Devices (IEDs) diagnose faults and traffic issues of data packets in a reliable and efficient manner in a substation environment. These devices determine abnormal system condition, wide area disturbances offering greater flexibility to the operator in terms of condition monitoring and diagnostics. In a distribution system, end user get multiple faults in the network and one such nuisance disruption of power on a faulty feeder results in sympathetic tripping. Sympathetic tripping occurs during high load conditions causing entire protection system to spuriously trip due to an out of section fault. Occurrence of such faults could be attributed to load unbalance in the distribution feeders, delayed voltage recovery conditions, voltage swell/sag in the feeders etc. Usually, this phenomenon occur when loads containing low inertia rotating equipment are connected to distribution feeders. In this paper, an Optimized Network Engineering Tool (OPNET) is used to simulate, mitigate faults attributed to Sympathetic Tripping in a laboratory environment.
Description:
Pulsed Eddy Current (PEC) sensors possess proven functionality in measuring ferromagnetic material thickness. However, most commercial PEC service providers as well as researchers have investigated and claim functionality of sensors on homogeneous structural steels (steel grade Q235 for example). In this paper, we present design steps for a PEC sensing set-up to measure thickness of cast iron, which is unlike steel, is a highly inhomogeneous and non-linear ferromagnetic material. The setup includes a PEC sensor, sensor excitation and reception circuits, and a unique signal processing method. The signal processing method yields a signal feature which behaves as a function of thickness. The signal feature has a desirable characteristic of being lowly influenced by lift-off. Experimental results show that the set-up is usable for Non-destructive Evaluation (NDE) applications such as cast iron water pipe assessment.
Description:
Pulsed Eddy Current (PEC) sensors possess proven functionality in measuring ferromagnetic material thickness. However, most commercial PEC service providers as well as researchers have investigated and claim functionality of sensors on homogeneous structural steels (steel grade Q235 for example). In this paper, we present design steps for a PEC sensing set-up to measure thickness of cast iron, which is unlike steel, is a highly inhomogeneous and non-linear ferromagnetic material. The setup includes a PEC sensor, sensor excitation and reception circuits, and a unique signal processing method. The signal processing method yields a signal feature which behaves as a function of thickness. The signal feature has a desirable characteristic of being lowly influenced by lift-off. Experimental results show that the set-up is usable for Non-destructive Evaluation (NDE) applications such as cast iron water pipe assessment.
Description:
Intentional Controlled Islanding (ICI) is the last protective measure that must be adopted in power systems to prevent forming unstable islands with load-generation imbalance power. If conventional protective schemes fail to save the power system against wide-area blackout, some cutsets are selected to keep the system operating while feeding essential loads. This paper investigates the effect of the number of partitions on the dynamic performance of controlled islanding and proposes a unified algorithm to identify the coherent generators, optimal cutsets, and timing of islanding in online applications. The algorithm provides an islanding solution with minimum power flow disruption while each island contains coherent groups of generators. The concept of Centre of Inertia (COI) referred angles of generators has been used to determine the critical timing of islanding. Different scenarios in NE 39-bus and IEEE 118-bus test systems were simulated in PowerFactory that led to instability in the power system, and then controlled islanding schemes with a different number of partitions were applied to create stable islands. To better demonstrate the shortcomings of the existing clustering techniques, the effect of the number of required islands on transient stability of controlled islanding and the necessity of devising an automatic method to recognise the number of islands is discussed.
Description:
The modern wireless technology exploiting the full potential of 5G IoT is the future for healthcare sector. In the healthcare sector, the 5G technology will maximize the performance and will reduce the chances of damage to the patient by providing careful and advance activity monitoring scenarios. We have proposed the idea of monitoring different body posture in Huntington disease by exploiting the low cost wireless devices operating at 4.8 GHz frequency. The system captures the wireless channel information for three body motions and classification of these motions was performed by using support vector machine. The SVM used 10 time-domain features for the classification process by using three main kernel functions, such as, Linear, Polynomial and Radial basis function. The system minimizes all the external noise by using the microwave absorbing materials. This increases the performance and feasibility of sensing body motions.
Description:
Every IPv6-enabled device connected and communicating over the Internet forms the Internet of things (IoT) that is prevalent in society and is used in daily life. This IoT platform will quickly grow to be populated with billions or more objects by making every electrical appliance, car, and even items of furniture smart and connected. The 5th generation (5G) and beyond networks will further boost these IoT systems. The massive utilization of these systems over gigabits per second generates numerous issues. Owing to the huge complexity in large-scale deployment of IoT, data privacy and security are the most prominent challenges, especially for critical applications such as Industry 4.0, e-healthcare, and military. Threat agents persistently strive to find new vulnerabilities and exploit them. Therefore, including promising security measures to support the running systems, not to harm or collapse them, is essential. Nature-inspired algorithms have the capability to provide autonomous and sustainable defense and healing mechanisms. This paper first surveys the 5G network layer security for IoT applications and lists the network layer security vulnerabilities and requirements in wireless sensor networks, IoT, and 5G-enabled IoT. Second, a detailed literature review is conducted with the current network layer security methods and the bio-inspired techniques for IoT applications exchanging data packets over 5G. Finally, the bio-inspired algorithms are analyzed in the context of providing a secure network layer for IoT applications connected over 5G and beyond networks.
Description:
Every IPv6-enabled device connected and communicating over the Internet forms the Internet of things (IoT) that is prevalent in society and is used in daily life. This IoT platform will quickly grow to be populated with billions or more objects by making every electrical appliance, car, and even items of furniture smart and connected. The 5th generation (5G) and beyond networks will further boost these IoT systems. The massive utilization of these systems over gigabits per second generates numerous issues. Owing to the huge complexity in large-scale deployment of IoT, data privacy and security are the most prominent challenges, especially for critical applications such as Industry 4.0, e-healthcare, and military. Threat agents persistently strive to find new vulnerabilities and exploit them. Therefore, including promising security measures to support the running systems, not to harm or collapse them, is essential. Nature-inspired algorithms have the capability to provide autonomous and sustainable defense and healing mechanisms. This paper first surveys the 5G network layer security for IoT applications and lists the network layer security vulnerabilities and requirements in wireless sensor networks, IoT, and 5G-enabled IoT. Second, a detailed literature review is conducted with the current network layer security methods and the bio-inspired techniques for IoT applications exchanging data packets over 5G. Finally, the bio-inspired algorithms are analyzed in the context of providing a secure network layer for IoT applications connected over 5G and beyond networks.
Description:
In order to save time and cost, many disease gene prediction methods have been proposed in recent years. However, the traditional network model uses a binary relationship to represent the relationship between different proteins or gene molecules and phenotypes, which leads to the loss of information. Recently, hypergraph shows that it can overcome this loss of information to some extent and preserve the multivariate relationship, so we transformed the disease gene prediction problem into the problem of ranking the multivariate-relationship object. In this paper, we propose a method of Heterogeneous Probabilistic Hypergraph Ranking (HPHR) to predict disease genes. Firstly, fix a graph centroid for each hyperedge and according to different associations, and add other nodes related to the graph centroid to hyperedges with a certain probability. Then transform the problem of predicting disease genes into the problem of ranking heterogeneous objects, and the candidate genes are sorted by hypergraph ranking. The method is then applied to the integrated disease gene network. Compared with other prediction methods achieved better results, which was verified by this experiment.
Description:
News media often contain reports that raise doubt related to policing operations. We examine the question of how to improve policing integrity during the execution of search warrants and provide an outline for law enforcement search warrants and digital forensic analysis procedures. Existing techniques for improving the integrity of search warrants are reviewed, limitations are noted, and we propose an Advanced Forensic Evidence System (AFES) to address these limitations.AFES provides an immutable record and biometric authentication of the officers present during the execution of a search warrant, time and location, video recording, seizure record, contemporaneous notes, and photographs. AFES records digital evidence items, imaging details, evidence hashes, provides an access control system, and an immutable record of access to all stored items. AFES uses a permissioned distributed ledger prototype, called Scrybe, developed under NSF aegis, to ensure evidence seizure integrity. Scrybe is run as multiple blockchain instances at law enforcement, prosecution, judicial, and defence organisations to ensure that an immutable record is maintained.
Description:
Banking Malware, has become a popular and ever more prevalent mechanism to monetise malware development. Since the development of the Zeus malware kit in 2007, the frequency and complexity of banking malware has been increasing. Developing a good understanding of the operation of a malware family is a first step in the reverse engineering required to create tools to extract the malware configuration, which is used in the remediation of malware infrastructure. This reverse engineering process in recent years has become increasingly challenging. This manuscript provides a brief summary of the reverse engineering of banking malware families over a two year period and emphasises the anti-analysis techniques employed by the authors of six families of banking malware. The manuscript presents this analysis, and examines trends in the development of these anti-analysis techniques.
Description:
This paper employs detectability ideas to decide uniform global asymptotic stability (UGAS) of the trivial solution for a class of switched nonlinear time-varying systems when the trivial solution is uniformly globally stable. Using the notion of limiting behaviors of the state, output, and switching signals, the concept of a limiting zeroing-output solution is introduced. This leads to a definition of weak zero-state detectability (WZSD) that can be used to check UGAS, (uniformly for a set of switched signals). En route to establish this, a number of new stability results are derived. For example, under appropriate conditions, it is feasible to decide UGAS even when the switching signal does not satisfy an averaged dwell-time condition. It is also shown that WZSD of the original switched system can be verified by detectability conditions of much simpler auxiliary systems. Moreover, UGAS can be guaranteed without requiring that in each allowable system (without switching), the trivial solution is attractive. The effectiveness of the proposed concept is illustrated by a few examples including a switched semi-quasi-Z-source inverter.
Description:
Extremum seeking control (ESC) is a data-driven optimization technique that can steer a dynamic plant toward an extremum of an unknown but measurable input to steady-state output. In the context of networked control systems, a new implementation method for ESC inspired by the well-known Luus-Jaakola algorithm is proposed. The main motivation is to minimize the communication burden associated with the search phase of ESC. In the proposed method, the controller only requires a notification of a change registered at the sensor, rather than the full information available at the sensor. This event-based approach leads to sporadic packet transmission. In addition, the proposed method is able to directly account for constraints while seeking the desired extremum. The constraints may be of the inequality or equality type. The algorithm's behavior is illustrated on a networked water pump control system.
Description:
Vibrational control seeks to stabilize an unstable system by judiciously injecting a state-free high-frequency dither. This article presents some robustness properties of vibrational control with respect to additive disturbances in a nonlinear system. We assume that, without disturbances, the appropriately averaged system is regionally asymptotically stable. Using perturbation techniques, our first result shows that the stabilization realized through vibrational control is robust with respect to additive disturbances of sufficiently small amplitude. Indeed, the perturbed system of vibrational control has a robustness feature similar to input-to-state stability in a local region. In the case of periodic disturbances, our second result indicates that vibrational control naturally dampens disturbances of sufficiently high frequency, which allows for relatively high amplitude disturbances. A tight bound for the effect of such periodic disturbances on the ultimate deviation of states from the desired equilibrium is presented. Simulation results from a planar manipulator support the theoretic analysis.
Description:
Evaluating progress throughout a patient's rehabilitation episode is critical for determining the effectiveness of the selected treatments and is an essential ingredient in personalised and evidence-based rehabilitation practice. The evaluation process is complex due to the inherently large human variations in motor recovery and the limitations of commonly used clinical measurement tools. Information recorded during a robot-assisted rehabilitation process can provide an effective means to continuously quantitatively assess movement performance and rehabilitation progress. However, selecting appropriate motion features for rehabilitation evaluation has always been challenging. This paper exploits unsupervised feature learning techniques to reduce the complexity of building the evaluation model of patients' progress. A new feature learning technique is developed to select the most significant features from a large amount of kinematic features measured from robotics, providing clinically useful information to health practitioners with reduction of modeling complexity. A novel indicator that uses monotonicity and trendability is proposed to evaluate kinematic features. The data used to develop the feature selection technique consist of kinematic data from robot-aided rehabilitation for a population of stroke patients. The selected kinematic features allow for human variations across a population of patients as well as over the sequence of rehabilitation sessions. The study is based on data records pertaining to 41 stroke patients using three different robot assisted exercises for upper limb rehabilitation. Consistent with the literature, the results indicate that features based on movement smoothness are the best measures among 17 kinematic features suitable to evaluate rehabilitation progress.
Description:
Predictive Maintenance Management in an industry can play a pivotal role in asset management and revenue generation. This work proposes a data-driven-based multi classifier model for implementing predictive maintenance to simultaneously reduce the downtime and idle time of the machines in a manufacturing plant. A case study of the plant comprising of 100 machines has been done to identify the early prediction of failure, its nature, and the attributing cause. Gradient Boosting Tree Classifier and Random Forest Classifier machine learning algorithms have been used to develop the models for fault prediction. A comparative analysis of results obtained using these methods has also been done. Random Forest Classifier outperforms Gradient Boost tree classifier in all evaluation parameters - accuracy, precision and recall.
Description:
Intentional controlled islanding (ICI) is the last resort to split an endangered power system into smaller islands to prevent blackout. New lines that are planned by transmission expansion planning (TEP) can affect the stability of islands during ICI. In this paper, an ICI-TEP method is proposed to improve the stability of islands by more efficient planning of transmission assets. Moreover, by developing a criterion for the frequency of center of inertia (COI) in each island, the frequency deviations of generators from the COI frequency are minimized to result in more stable islands. The proposed ICI-TEP, incorporating AC network representation, is modeled as mixed-integer linear programming and quadratic convex problems ensuring tractability. A Benders decomposition strategy is also proposed to solve the problem. Results of testing the proposed ICI-TEP method on IEEE 39-bus and 300-bus test systems confirm its effectiveness, compared to conventional TEP, in terms of coping with sever disturbances by creating more stable islands with a lower load shedding.
Description:
With the increasing number of renewable generations, the prospects of long-distance bulk power transmission impels the expansion of point-to-point High Voltage Direct Current (HVDC) grid to an emerging Multi-terminal high-voltage Direct Current (MTDC) grid. The DC grid protection with faster selectivity enhances the operational continuity of the MTDC grid. Based on the reactor voltage gradient (RVG), this paper proposes a fast and reliable fault identification technique with precise discrimination of internal and external DC faults. Considering the voltage developed across the modular multilevel converter (MMC) reactor and DC terminal reactor, the RVG is formulated to characterise an internal and external DC fault. With a window of four RVG samples, the fault is detected and discriminated by the proposed main protection scheme amidst a period of five sampling intervals. Depending on the reactor current increment, a backup protection scheme is also proposed to enhance the protection reliability. The performance of the proposed scheme is validated in a four-terminal MTDC grid. The results under meaningful fault events show that the proposed scheme is capable to identify the DC fault within millisecond. Moreover, the evaluation of the protection sensitivity and robustness reveals that the proposed scheme is highly selective for a wide range of fault resistances and locations, higher sampling frequencies, and irrelevant transient events. Furthermore, the comparison results exhibit that the proposed RVG method improves the discrimination performance of the protection scheme and thereby, proves to be a better choice for future DC fault identification.
Description:
With the increasing number of renewable generations, the prospects of long-distance bulk power transmission impels the expansion of point-to-point High Voltage Direct Current (HVDC) grid to an emerging Multi-terminal high-voltage Direct Current (MTDC) grid. The DC grid protection with faster selectivity enhances the operational continuity of the MTDC grid. Based on the reactor voltage gradient (RVG), this paper proposes a fast and reliable fault identification technique with precise discrimination of internal and external DC faults. Considering the voltage developed across the modular multilevel converter (MMC) reactor and DC terminal reactor, the RVG is formulated to characterise an internal and external DC fault. With a window of four RVG samples, the fault is detected and discriminated by the proposed main protection scheme amidst a period of five sampling intervals. Depending on the reactor current increment, a backup protection scheme is also proposed to enhance the protection reliability. The performance of the proposed scheme is validated in a four-terminal MTDC grid. The results under meaningful fault events show that the proposed scheme is capable to identify the DC fault within millisecond. Moreover, the evaluation of the protection sensitivity and robustness reveals that the proposed scheme is highly selective for a wide range of fault resistances and locations, higher sampling frequencies, and irrelevant transient events. Furthermore, the comparison results exhibit that the proposed RVG method improves the discrimination performance of the protection scheme and thereby, proves to be a better choice for future DC fault identification.