Search

In this paper, we reviewed the various advanced technologies and methods that could help patients for measuring adherence of patients. There exist intelligent technologies that are available for measuring medication adherence, including medication event monitoring system (MEMS®), smart blister packs, radio frequency identification (RFID) embedded smart drawers, and wisely aware RFID dosage (WARD) system. Utilization of these advanced technologies and systems have aided in enhancing the adherence to a greater extent. For example, MEMS® refers to the electronic cap that counts the number of bottles opened, but it can be employed only with bottles. Smart blisters are pharmaceutical packagings that possess the capability of monitoring when a pill or tablet is taken out of its packing. All those intelligent technologies can help in active monitoring of patients regarding adherence and capable of eradicating various medication errors due to which adherence is affected.

Automating fault detection in communication networks and distributed systems is a challenging process that usually requires the involvement of supporting tools and the expertise of system operators. Automated event monitoring and correlating systems produce event data that is forwarded to system operators for analyzing error events and creating fault reports. Machine learning methods help not only analyzing event data more precisely but also forecasting possible error events by learning from existing faults. This study introduces an automated fault detection system that assists system operators in detecting and forecasting faults. This system is characterized by the capability of exploiting bug knowledge resources at various online repositories, log events and status parameters from the monitored system; and applying bug analysis and event filtering methods for evaluating events and forecasting faults. The system contains a fault data model to collect bug reports, a feature and semantic filtering method to correlate log events, and machine learning methods to evaluate the severity, priority and relation of log events and forecast the forthcoming critical faults of the monitored system. We have evaluated the prototyping implementation of the proposed system on a high performance computing cluster system and provided analysis with lessons learned.

The monitoring of pre-failure movements and their evolution over time is necessary to assess the predisposing and triggering factors. This research focusses on assessing terrain displacements in th...

In recent years, frequent meteorological disasters have caused great concern to people. It is particularly important to timely detect the meteorological events and release early warning information. Most traditional meteorological event detection methods rely on physical sensors, but such practice is usually costly and inflexible. As a new form of lightweight social sensor, social networks make up for the shortcomings of traditional physical sensors. In this paper, we propose a sentence-level feature-based meteorological event detection model to detect 14 types of meteorological events defined by the China Meteorological Administration (CMA) in Sina Weibo. Our joint model consists of two modules: a fine-tuned BERT as the language model and a wide-grained capsule network as the event detection network. The design of our model considers the correlation among meteorological events and achieves the best results on all metrics compared with other baseline models. Moreover, as a practical application, our model has been applied to the meteorological event monitoring platform in the CMA Public Meteorological Service Center to provide online services.

Background Poor adherence to tuberculosis (TB) treatment can result in community transmission and drug resistance. Digital health technologies have been used to enhance adherence to TB medication for proper management, but the cost-effectiveness of this approach remains unclear.Methods We used the real data from the study conducted from April 2014 to December 2020 in Morocco to enhance the adherence to drug-susceptible TB treatment using a smart pillbox with a web-based medication monitoring system, called Medication Event Monitoring Systems (MEMS). We applied a Markov model adding Multi-drug resistant (MDR) TB to evaluate the costs and cost-effectiveness of MEMS, compared to the standard of care (modified directly observed treatment and intervention) from the health perspective. The primary outcome was the incremental cost-effectiveness ratio (ICER) per disability adjusted life-year (DALY) averted. We also performed two-way sensitive analysis between treatment success rate of MEMS and standard of care. Results The average total per-patient health system costs for treating a new TB patient under MEMS versus standard of care were $398.7 and $155.7, respectively. The MEMS strategy would reduce the number of drug-susceptible TB cases by 0.17 and MDR-TB cases by 0.01 per patient over five years. The ICER of MEMS was $434/DALY averted relative to standard of care, and was most susceptible to the TB treatment success rate of both strategies followed by the managing cost of MEMS.Conclusion MEMS is considered cost-effective for managing infectious active TB in Morocco.

The authors propose a Web-Mashup Application Service Framework for Multivariate Time Series Analytics (MTSA) that supports the services of model definitions, querying, parameter learning, model evaluations, data monitoring, decision recommendations, and web portals. This framework maintains the advantage of combining the strengths of both the domain-knowledge-based and the formal-learning-based approaches and is designed for a more general class of problems over multivariate time series. More specifically, the authors identify a general-hybrid-based model, MTSA – Parameter Estimation, to solve this class of problems in which the objective function is maximized or minimized from the optimal decision parameters regardless of particular time points. This model also allows domain experts to include multiple types of constraints, e.g., global constraints and monitoring constraints. The authors further extend the MTSA data model and query language to support this class of problems for the services of learning, monitoring, and recommendation. At the end, the authors conduct an experimental case study for a university campus microgrid as a practical example to demonstrate our proposed framework, models, and language.

Cooperative vehicular cyber physical systems build a group of entities that can accomplish a cooperative task using the distributed control approaches. To this end, such a cooperative task can be coordinated and managed by a distributed control plane that will be able to encapsulate all the required functionality in a layered architecture providing the required interoperability. Here, the authors propose such a distributed control plane that consists of the cooperative awareness layer, thecommunication layer and the distributed control layer. Wireless communications play an important role for the mobility provision, taking into account different constraints in order to provide high reliability and low latency. A simulation environment is considered with a leader–follower control format, where the reliability is evaluated. Further, a distributed safety monitoring approach is devised, given a control diagram and mapping of the events to the different components. The event monitoring relies on the self-triggered approach, where a use case is evaluated to highlight the impact of the input and output delays to the model predictive control component of the overall distributed control diagram including the calculation of the number of triggered events.

Recently, an emerging application field through Twitter messages and algorithmic computation to detect real-time world events has become a new paradigm in the field of data science applications. During a high-impact event, people may want to know the latest information about the development of the event because they want to better understand the situation and possible trends of the event for making decisions. However, often in emergencies, the government or enterprises are usually unable to notify people in time for early warning and avoiding risks. A sensible solution is to integrate real-time event monitoring and intelligence gathering functions into their decision support system. Such a system can provide real-time event summaries, which are updated whenever important new events are detected. Therefore, in this work, we combine a developed Twitter-based real-time event detection algorithm with pre-trained language models for summarizing emergent events. We used an online text-stream clustering algorithm and self-adaptive method developed to gather the Twitter data for detection of emerging events. Subsequently we used the Xsum data set with a pre-trained language model, namely T5 model, to train the summarization model. The Rouge metrics were used to compare the summary performance of various models. Subsequently, we started to use the trained model to summarize the incoming Twitter data set for experimentation. In particular, in this work, we provide a real-world case study, namely the COVID-19 pandemic event, to verify the applicability of the proposed method. Finally, we conducted a survey on the example resulting summaries with human judges for quality assessment of generated summaries. From the case study and experimental results, we have demonstrated that our summarization method provides users with a feasible method to quickly understand the updates in the specific event intelligence based on the real-time summary of the event story.

Risk assessment constitutes the first part within the risk management framework and involves evaluating the importance of a risk, either quantitatively or qualitatively. Risk assessment consists of three steps, namely risk identification, risk estimation and risk evaluation. Nevertheless, the risk management framework also includes a fourth step, i.e., the need for feedback on all the risk assessment undertakings. However, there is a lack of such feedback, which constitutes a serious deficiency in the reduction of environmental hazards at the present time. Risk identification of local or regional hazards involves hazard quantification, event monitoring including early warning systems and statistical inference. Risk identification also involves the development of a database where historical hazard information and hazard effects are included. Similarly, risk estimation involves magnitude–frequency relationships and hazard economic costs. Furthermore, risk evaluation consists of the social consequences of the derived risk and involves cost-benefit analysis and community policy. The objective of this review paper is twofold. On the one hand, it is to address meteorological hazards and extremes within the risk management framework. Analysis results and case studies over Mediterranean ecosystems with emphasis on the wider area of Greece, in the eastern Mediterranean, are presented for each of the three steps of risk assessment for several environmental hazards. The results indicate that the risk management framework constitutes an integrated approach for environmental planning and decision-making. On the other hand, it sheds light on advances and current trends in the considered meteorological and environmental hazards and extreme events, such as tornadoes, waterspouts, hailstorms, heat waves, droughts, floods, heavy convective precipitation, landslides and wildfires, using recorded datasets, model simulations and innovative methodologies.

Summary What is known Currently, medication bottles with an electronic cap are frequently used to measure medication adherence. This system is termed medication event monitoring system (MEMS). To our knowledge, the optimal method to summarize data from MEMS has not yet been determined. Objective Look for best practices on how to quantify adherence data from MEMS. Methods Review of PubMed, Embase and Cochrane databases for the articles on medication adherence with MEMS. Results Of 1493 identified articles, 207 were included in this review. The MEMS cap was used for a median of 3 months (IQR: 4; range: 1 week to 24 months) in various health conditions. Many different outcome measures were used. Most studies computed an adherence score, expressed as the percentage of days on which the correct dose of medication was taken. The threshold to mark people as adherent was most frequently, arbitrarily, set at 80% (range: 67%‐95%). We found no data to support a specific threshold. Discussion Although the commonly used definition of adherence has face validity, we found no validation studies, and not all studies used the same cut‐off for adherence. Ideally, a cut‐off should be defined and validated in the context of the specific drug and its pharmacokinetic and dynamic characteristics, and perhaps other contextual factors, rather than generically. In addition, there was large heterogeneity in the definition of what “correct intake” of medication is. What is new and conclusion Outcome measures for MEMS data lacked standardization, and no demonstrable effort to validate any definition against a relevant clinical outcome is available. Consensus on the definition of adherence is urgently needed., Outcome measures for Medication Event Monitoring System (MEMS) data lacked standardization and no demonstrable effort to validate any definition against a relevant clinical outcome is available. A consensus effort on the definition of adherence is urgently needed.

Sensor nodes in wireless sensor networks (WSNs) are usually battery-operated and resource-constrained. The sensor nodes are often deployed in remote areas where the batteries cannot easily be recharged or replaced. Consequently, power becomes a limited resource in WSNs. Thus, energy consumption of the sensor nodes is among parameters of paramount importance. Subsequently, source location privacy (SLP) routing schemes must be energy-efficient and overall cost-effective. Angle-based routing schemes can cost-effectively protect the SLP. The goal of this study is to propose a new path node offset angle routing algorithm to improve the packet transmission cost of two existing SLP routing schemes. The proposed algorithm considers path node offset angles, arbitrary factors, and contrived regions to compute relatively short but greatly randomized routing paths. The routes offer a reduced number of packet forwarding events in the near-sink region and eventually diminish the packet transmission cost. Performance analysis results verify that the proposed path node offset angle routing algorithm effectively improves the packet transmission cost of the schemes and guarantees strong SLP protection throughout the WSN domain. Furthermore, the routing algorithm is capable of alleviating the energy-hole problem.

The complexity of cloud datacenter scenarios poses new challenges in infrastructure management processes such as the impracticality of collecting specific service level events from inside the datacenter infrastructure, and the scalability issues that can appear during event monitoring when thousands of virtual machines have to be polled at a granularity of seconds. Therefore, it would be desirable to provide mechanisms for obtaining these types of events without incurring in the previously described problems. To this end, we propose a generic and scalable method based on the application of deep neural network architectures for predicting service level events using only a reduced number of generic datacenter infrastructure statistics that can be monitored in a scalable way. We demonstrate in a controlled scenario of a real datacenter and using only three variables from a physical machine that it is possible to predict events in real-time and with decent accuracy, without needing to deploy any meter in the end-user equipment. Specifically, we demonstrate this over two service-level events: i) the so-called Noisy Neighbors effect, a harmful situation that appears in physical machines due to the interferences created by the interaction of virtual machines running on them; and ii) the jitter values of a multimedia call running in a virtual machine. We set up a testbed in a real datacenter deploying physical and virtual machines, running a large amount of different experiments for 1000 hours and collecting samples at a 10 seconds granularity in a dataset of 260,000 records. Two different scenarios, in which training and testing data sets contain significant statistical differences, are deployed to demonstrate a better generalization ability of deep models in changing scenarios when compared with traditional Machine Learning techniques. A set of different deep architectures are proposed for both use cases and approximately 4,000 deep models were trained and tested. In both use cases, the best deep models show a good performance when predicting service level events, even if the inputs do not exactly follow the statistical patterns of the data used during training.

With the advancement in the field of Internet-of-Things (IoT), event monitoring applications have rapidly evolved from a simple event data acquisition towards predictive event analytics involving multi-sensory data aggregation in a distributed environment. Existing event monitoring schemes are mainly relying on ine_cient centralized processing mechanism, which may lead to the common single-point of failure for the entire system. In addition, there is no proper method for verifying the event data generated by the monitoring system. In this paper, we present a distributed event monitoring scheme using a Hierarchical Graph Neuron (HGN) distributed pattern recognition algorithm. HGN is a single-cycle learning graph-based recognition scheme that is modelled for in-network deployment. In this work, event data retrieved from multi-sensory IoT devices within a distributed event monitoring network is converted into pattern. To address the event data verification problem, we integrate our proposed scheme with blockchain technology. Combining this IoT event monitoring capabilities with blockchain-based data storage and verification could leads towards a scalable event detection and monitoring model for large-scale network. The results obtained from our simulation shows that the proposed scheme o_ers high event detection accuracy and capable of minimizing the event storage requirements on blockchain network.

Current IoT systems are highly distributed systems that integrate cloud , edge , and fog computing approaches depending on where intelligence and processing capabilities are allocated. This distribution and heterogeneity make development and deployment pipelines very complex and fragmented with multiple delivery endpoints above hardware. This fact prevents rapid development and makes the operation and monitoring of production systems a difficult and tedious task, including cybersecurity event monitoring. The DevSecOps can be defined as a cultural approach to improve and accelerate the delivery of business value by making dev/sec/ops teams’ collaboration effective. This paper focuses on self-service cybersecurity monitoring as an enabler to introduce security practices in a DevOps environment. To that end, we have defined and formalized an activity that supports ‘ Fast and Continuous Feedback from Ops to Dev ’ by providing a flexible monitoring infrastructure so that teams can configure their monitoring and alerting services according to their criteria ( you build, you run, and now you monitor ) to obtain fast and continuous feedback from the operation and thus, better anticipate problems when a production deployment is performed. This activity has been formalized using the Software & Systems Process Engineering Metamodel by OMG and its instantiation is described through a case study that shows the versioned and repeatable configuration of a cybersecurity monitoring infrastructure ( Monitoring as Code ) through virtualization and containerization technology. This self-service monitoring/alerting allows breaking silos between dev, ops, and sec teams by opening access to key security metrics, which enables a sharing culture and continuous improvement.

This paper proposes a distributed energy-efficient algorithm for environmental event detection and monitoring using a mobile wireless sensor network. The mobile sensors could be sensors mounted on vehicles that move in the monitored environment and the mounted sensors collect environmental data. The proposed technique collects the data from the mobile sensors using a mobile sink (e.g. drone). The mobile sink processes the collected to detect and monitor environmental events such as air pollution. The path of the mobile sink affects the accuracy and speed of detecting environmental events. To efficiently detect events, the mobile sink path is shortened and yet all sensed data by the mobile sensors are collected by mobile sink. Therefore, mobile sensors group themselves and then each group selects a group head (GH). The mobile sensors send the sensed data to the their GH, which aggregates the data. To shorten the path of the mobile sink, the proposed method creates a path that passes through the GHs’ locations only. The proposed method uses a space-filling curve to determine the order of GHs along the path of the mobile sink. The mobile sink collects the group’s aggregated data from these GHs. Then, the mobile sink process the collected data to detect the environmental events.

WSN consists of a number of nodes and base stations and is used for event monitoring in various fields such as war situations, forest fires, and home networks. WSN sensor nodes are placed in fields that are difficult for users to manage. It is therefore vulnerable to attackers, and attackers can use false nodes or MAC injection attacks through the hijacked nodes to reduce the lifetime of the network or trigger false alarms. In order to prevent such attacks, several security protocols have been proposed, and all of them have been subjected to MAC-dependent validation, making it impossible to defend against false report attacks in extreme attack circumstances. As attacks have recently become more diverse and more intelligent, WSNs require intelligent methods of security. Based on the report information gathered from the base station, the proposed method provides a technique to prevent attacks that may occur where all MAC information is damaged by carrying out verification of a false report attack through the machine learning based prediction model and the evaluation function.

Extreme events have long been underestimated in the extent to which they shape the surface of our planet, our environment, its ecological integrity, and the sustainability of human society. Extreme events are by definition rarely observed, of significant impact and, as a result of their spatiotemporal range, not always easily predicted. Extremes may be short-term catastrophic events such as tsunamis, or long-term evolving events such as those linked to climate change; both modify the environment, producing irreversible changes or regime shifts. Whatever the driver that triggers the extreme event, the damages are often due to a combination of several processes and their impacts can affect large areas with secondary events (domino effect), whose effects in turn may persist well beyond the duration of the trigger event itself. Early studies of extreme events were limited to opportunistic approaches: observations were made within the context of naturally occurring events with high societal impact. Given that climate change is now moving us out of a relatively static climate regime during the development of human civilization, extreme events are now a function of underlying climate shifts overlain by catastrophic processes. Their impacts are often due to synergistic factors, all relevant in understanding process dynamics; therefore, an integrated methodology has become essential to enhance the reliability of new assessments and to develop strategies to mitigate societal impacts. Here we summarize the current state of extreme event monitoring in the marine system, highlighting the advantages of a multidisciplinary approach using Research Infrastructures for providing the temporal and spatial resolution required to monitor Earth processes and enhance assessment of associated impacts.

Background: This study was designed to monitor the short-term (up to 12 weeks) use and safety of quetiapine (Seroquel) extended release (XL) and quetiapine immediate release (IR) prescribed to patients with a clinical diagnosis of schizophrenia, and/or manic episodes associated with bipolar disorder by psychiatrists under normal conditions of use. Methods: A Specialist Cohort Event Monitoring (SCEM) study was conducted in England February 2010–April 2013. This observational cohort study recruited patients prescribed quetiapine XL within the secondary care setting by psychiatrists. A reference cohort of quetiapine IR users was also recruited. Baseline and 12 week observational data were collected from psychiatrists who abstracted information from medical records onto bespoke questionnaires. Data were collected on demographics, indication, past medical history, prescribing information and events of interest. Summary descriptive statistics were calculated. Results: The final cohort consisted of 869 eligible patients; 646 XL users and 223 IR users. The majority of XL and IR users were female (56.2% and 55.6%, respectively), with a median age of 40 (interquartile range [IQR]: 29, 49) and 39 (IQR: 28, 50) years, respectively. The most frequent indication for treatment was Manic episodes associated with Bipolar Affective disorder (53.4% XL and 49.8% IR). Median index dose was 200 mg/day (IQR: 100, 300) for XL users and 50 mg/day (IQR: 50, 100) for IR users, while median final maintenance dose was 400mg/day (IQR: 250, 600) and 300 mg/day (IQR: 100, 400), respectively. The most frequently reported event of interest in both cohorts was sedation ( n = 151, 23.9% XL cohort and n = 49, 23.0% IR cohort). Conclusion: Utilisation of quetiapine XL appeared to be in line with prescribing guidelines in terms of dose, and commonly reported events of interest were in concordance with the known safety profile. Overall, this SCEM study provided important information on the safety and utilisation of quetiapine XL in the secondary care setting in England.

Multi-pedestrian tracking in aerial imagery has several applications such as large-scale event monitoring, disaster management, search-and-rescue missions, and as input into predictive crowd dynamic models. Due to the challenges such as the large number and the tiny size of the pedestrians (e.g., 4 x 4 pixels) with their similar appearances as well as different scales and atmospheric conditions of the images with their extremely low frame rates (e.g., 2 fps), current state-of-the-art algorithms including the deep learning-based ones are unable to perform well. In this paper, we propose AerialMPTNet, a novel approach for multi-pedestrian tracking in geo-referenced aerial imagery by fusing appearance features from a Siamese Neural Network, movement predictions from a Long Short-Term Memory, and pedestrian interconnections from a GraphCNN. In addition, to address the lack of diverse aerial pedestrian tracking datasets, we introduce the Aerial Multi-Pedestrian Tracking (AerialMPT) dataset consisting of 307 frames and 44,740 pedestrians annotated. We believe that AerialMPT is the largest and most diverse dataset to this date and will be released publicly. We evaluate AerialMPTNet on AerialMPT and KIT AIS, and benchmark with several state-of-the-art tracking methods. Results indicate that AerialMPTNet significantly outperforms other methods on accuracy and time-efficiency., ICPR 2020

International audience; Poor medication adherence remains frequent in schizophrenia. The present study examined the efficacy of two month-long pilot interventions using the Medication Event Monitoring System (MEMS®). Thirty-three outpatients at high risk for relapse were randomized to receive a smartphone-based intervention, a nurse-based intervention, or treatment as usual. All patients then used the MEMS® to objectively measure medication adherence over six months. No differences were observed in adherence measures or relapse rates across the three groups. When using electronic medication monitoring as an objective measure of adherence, easily-implemented interventions may not significantly improve adherence in patients at high risk for relapse.

Event monitoring is an essential application of Smart City platforms. Real-time monitoring of gully and drainage blockage is an important part of flood monitoring applications. Building viable IoT sensors for detecting blockage is a complex task due to the limitations of deploying such sensors in situ. Image classification with deep learning is a potential alternative solution. However, there are no image datasets of gullies and drainages. We were faced with such challenges as part of developing a flood monitoring application in a European Union-funded project. To address these issues, we propose a novel image classification approach based on deep learning with an IoT-enabled camera to monitor gullies and drainages. This approach utilises deep learning to develop an effective image classification model to classify blockage images into different class labels based on the severity. In order to handle the complexity of video-based images, and subsequent poor classification accuracy of the model, we have carried out experiments with the removal of image edges by applying image cropping. The process of cropping in our proposed experimentation is aimed to concentrate only on the regions of interest within images, hence leaving out some proportion of image edges. An image dataset from crowd-sourced publicly accessible images has been curated to train and test the proposed model. For validation, model accuracies were compared considering model with and without image cropping. The cropping-based image classification showed improvement in the classification accuracy. This paper outlines the lessons from our experimentation that have a wider impact on many similar use cases involving IoT-based cameras as part of smart city event monitoring platforms.

An efficient routing using a virtual backbone (VB) network is one of the most significant improvements in the wireless sensor network (WSN). One promising method for selecting this subset of network nodes is by finding the minimum connected dominating set (MCDS), where the searching space for finding a route is restricted to nodes in this MCDS. Thus, finding MCDS in a WSN provides a flexible low-cost solution for the problem of event monitoring, particularly in places with limited or dangerous access to humans as is the case for most WSN deployments. In this paper, we proposed an adaptive scatter search (ASS-MCDS) algorithm that finds the near-optimal solution to this problem. The proposed method invokes a composite fitness function that aims to maximize the solution coverness and connectivity and minimize its cardinality. Moreover, the ASS-MCDS methods modified the scatter search framework through new local search and solution update procedures that maintain the search objectives. We tested the performance of our proposed algorithm using different benchmark-test-graph sets available in the literature. Experiments results show that our proposed algorithm gave good results in terms of solution quality.

Distributed Stream Processing Systems (DSPSs) are among the currently most emerging topics in data management, with applications ranging from real-time event monitoring to processing complex dataflow programs and big data analytics. The major market players in this domain are clearly represented by Apache Spark and Flink, which provide a variety of frontend APIs for SQL, statistical inference, machine learning, stream processing, and many others. Yet rather few details are reported on the integration of these engines into the underlying High-Performance Computing (HPC) infrastructure and the communication protocols they use. Spark and Flink, for example, are implemented in Java and still rely on a dedicated master node for managing their control flow among the worker nodes in a compute cluster. In this paper, we describe the architecture of our AIR engine, which is designed from scratch in C++ using the Message Passing Interface (MPI), pthreads for multithreading, and is directly deployed on top of a common HPC workload manager such as SLURM. AIR implements a light-weight, dynamic sharding protocol (referred to as "Asynchronous Iterative Routing"), which facilitates a direct and asynchronous communication among all client nodes and thereby completely avoids the overhead induced by the control flow with a master node that may otherwise form a performance bottleneck. Our experiments over a variety of benchmark settings confirm that AIR outperforms Spark and Flink in terms of latency and throughput by a factor of up to 15; moreover, we demonstrate that AIR scales out much better than existing DSPSs to clusters consisting of up to 8 nodes and 224 cores., 16 pages, 6 figures, 15 plots

This paper presents a Cybersecurity Framework for end-to-end IoT Platforms called DRAFT. It is developed in response to rising number of Cyberattacks against IoT applications and services. The framework is composed of a risk assessment framework, a Security Incident and Event Monitoring (SIEM) tool, and a Cyberattack resilient framework. DRAFT framework has been integrated into an end-to-end IoT Platform and has been tested using five known and simulated Cyberattacks using the Fed4FIRE+ federated testbeds. The results obtained show that the proposed Cybersecurity framework is capable of increasing Cyberattack resilience of the IoT Platform under test., © 2020 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

Critical infrastructure monitoring is one of the most important applications of a smart city. The objective is to monitor the integrity of the structures (e.g., buildings, bridges) and detect and pinpoint the locations of possible events (e.g., damages, cracks). Regarding today's complex structures, collecting data using wireless sensor data over extensive vertical lengths creates enormous challenges. With a direct BS deployment, a big amount of data will accumulate to be relayed to the BS. As a result, traditional models and schemes developed for health monitoring are largely challenged by low-cost, quality-guaranteed, and real-time event monitoring. In this article, we propose BigReduce, a cloud based health monitoring application with an IoT framework that could cover most of the key infrastructures of a smart city under an umbrella and provide event monitoring. To reduce the burden of big data processing at the BS and enhance the quality of event detection, we integrate real-time data processing and intelligent decision making capabilities with BigReduce. Particularly, we provide two innovative schemes for health event monitoring so that an IoT sensor can use them locally; one is a big data reduction scheme, and the other is a decision making scheme. We believe that BigReduce will result in a remarkable performance in terms of data reduction, energy cost reduction, and the quality of monitoring.

We developed a Multinomial Nave Bayes Classifier to categorize the microblog posts into five types according to the text content of posts.Different types of information had significantly different propagation patterns in terms of scale and topological features.Social media users exhibited significantly different interaction patterns for different types of information at different stages. Social media has been playing an increasingly important role in information publishing and event monitoring in emergencies like natural disasters. The propagation of different types of information on social media is critical in understanding the reaction and mobility of social media users during natural disasters. In this research, we analyzed the dynamic social networks formed by the reposting (retweeting) behaviors in Weibo.com (the major microblog service in China) during Yiliang Earthquake. We developed a Multinomial Nave Bayes Classifier to categorize the microblog posts into five types based on the content, and then characterized the information propagation patterns of the five types of information at different stages after the earthquake occurred. We found that the type of information has significant influence on the propagation patterns in terms of scale and topological features. This research revealed the important role of information type in the publicity and propagation of disaster-related information, thus generated data-driven insights for timely and efficient emergency management using the publicly available social media data.

Applications face additional latency when they launch or access a disk to load data into the memory. In this paper, a user-level disk prefetching framework, called iFetcher, is introduced to hide this delay in Linux-based operating systems. This employs an inode-notification ( inotify ) application programming interface (API), which provides an efficient method of tracing operations in a Linux file system, and reports these events to applications in real time. During an initial training run, iFetcher traces the pattern with which data are read by an application. Subsequently, it searches the areas directly ahead of passages where it is requested that a lot of data are read, and locates events that can be used to trigger preloading. When the application is run again and a trigger event is reported (by the inotify API), the corresponding data are read into the page cache prior to actual demand. iFetcher has a low overhead, because disk reads are only need to be monitored during training. Furthermore, it does not require any modifications to the Linux kernel, because it runs at the user level. Five benchmark applications were run on a PC using a solid-state drive, and results demonstrated that iFetcher reduced the launch times by up to 41% and post-launch data loading times by up to 9%.

Monitoring agents are deployed in distributed network environments to collect data and report events to a central coordinator. A widespread event is defined as an event that is observed by all monitoring agents simultaneously. Identifying widespread events can assist in detecting problems, such as cyberattacks, network malfunctions, and abnormal usages. However, detecting widespread events is challenging and a significant communication overhead can be incurred, because every monitoring agent must report any observed event to a central coordinator. In this paper, we study the problem of detecting widespread events accurately. Our proposed schemes can significantly reduce communication overhead and achieve perfect detection accuracy, which was not achieved by any previous studies. The new schemes can also identify generalized widespread events, defined as events observed by more than a predefined number of monitoring agents.

This paper investigates the operation inspection and anomaly diagnosis of transformers in substations, and carries out an application study of artificial intelligence-based sound recognition technology in transformer discharge diagnosis to improve the timeliness and diagnostic capability of intelligent monitoring of substation equipment operation. In this study, a sound parameterization technology in the field of sound recognition is used to implement automatic discharge sound detections. The sound samples are pre-processed and then Mel-frequency cepstrum coefficients (MFCCs) are extracted as features, which are used to train Gaussian mixture models (GMMs). Finally, the trained GMMs are used to detect discharge sounds in the place of transformers in substations. The test results demonstrate that the audio anomaly detection based on MFCCs and GMMs can be used to effectively recognize anomalous discharge in the high scenario of transformers.

The substantial increase in the usage of wireless sensor networks (WSNs) encourages to develop data clustering in event monitoring applications. Many centralized algorithms with single objective optimization are employed to solve this problem. However privacy, security and technical constraints are key issues in traditional centralized approach. Moreover, many WSN applications like condition monitoring and target tracking require more than three objectives for effective partitioning of dataset. This paper proposes many-objective whale optimization algorithm to handle robust distributed clustering in WSN. Initially, a swarm based many-objective whale optimization (MaOWOA) is discussed where reference point based leader selection method is utilized in updating the solutions instead of grid based leader selection as in multi-objective approach. This method gives better convergence and diversity. The simulation result of proposed approach is evaluated on many-objective DTLZ test problems against existing many-objective methods which is faster in terms of simulation time and gives competitive results in terms of generational distance (GD), inverse generational distance (IGD), spacing (SP) and hyper volume difference (HVD). Further, the encouraging results of the proposed MaOWOA are applied to perform robust distributed clustering in WSNs which is termed as distributed many-objective clustering using whale optimization algorithm (DMaOWOA). In this approach, a weight based method is incorporated to detect and remove the outliers and diffusion method of cooperation is used for distributed clustering. The proposed DMaOWOA is tested on one synthetic and three practical WSN datasets. It is observed that DMaOWOA based clustering performs up to 6% and 8% improvement in terms of Silhouette index as compared to particle swarm optimization based many-objective distributed clustering (DMaOPSO) and distributed K-Means (DK-Means) clustering algorithm, respectively.

Recent advances in emerging technologies have given birth to a new type of networks called Internet of Things (IoT). The emergence of IoT has led practitioners to envision networking a large number of sensors for event monitoring, data collection and filtering. Due to the use of wireless technologies, a secure communication is strongly needed to protect valuable information. Secure group communication is one of the most significant requirements for IoT applications. This employs a group rekeying mechanism for a secure and efficient delivery of data. In this paper, we present a new efficient and scalable rekeying protocol for wireless communicating things. This protocol uses O ( log 2 n 3 ) memory complexity, improving significantly the literature works, where n is the network size. Simulation results show that our protocol has better performances than existing works in several criteria.

The paper presents a new, innovative approach of programming of autonomous behavior of reactive metering systems. The presented method is based on safely timed automata defined by UPPAAL team. This modeling language is extended with event monitoring, utility functions for asynchronous operations invocation and supervising capabilities. Additionally, appropriate metering operations querying principle for metering systems is proposed. Finally, a new method of timed automata systems simulation is presented. This method is based on the principle of random interleaving of automata execution order and probabilities balancing in order to ensure fairness of automata execution. Advantages of presented methods as well as their basic principles are summarized and demonstrated on a case study of AMM network data concentrator. On this case study, it is shown, that proposed methods allow to effortlessly define the autonomous behavior of a data concentrator in the understandable and easily modifiable way, thus they lack major disadvantages of the currently used approach.

Background Simplicity of regimen is known to be an important determinant of medication adherence and using single-pill combination (SPC) in hypertension treatment resulted in better adherence and persistence than free-equivalent combination. However, this finding has been studied only in dual-component antihypertensive treatments and in observational studies using medication possession ratio as an index of adherence. Medication event monitoring system (MEMS) is considered to be the gold standard in estimating medication adherence. Purpose To investigate the superiority in adherence of triple-component SPC compared to equivalent two-pill regimen using MEMS Methods This is a multi-center open-label randomized controlled trial. Inclusion criteria were hypertensive patients whose clinic blood pressure is not adequately controlled (systolic >140 mmHg or diastolic >90 mmHg) with combination antihypertensive regimen comprising two of three classes (angiotensin receptor blocker, calcium channel blocker and thiazide diuretics) for at least 4 weeks. Eligible patients were randomized either to single-pill (triple-component SPC, olmesartan/amlodipine/ hydrochlorothiazide 20/5/12.5 mg) or two-pill (dual-component SPC + one free pill, olmesartan/hydrochlorothiazide 20/12.5 mg + amlodipine 5 mg) groups and maintained for 12 weeks. Medications were dispensed in MEMS. Primary outcomes were the difference of percentage of dose taken (PDT) and percentage of days with prescribed dose taken correctly (PDTc) between single- and two-pill therapy, calculated from MEMS data. Results From 8 hospitals, 146 hypertensive patients were randomized into single- and two-pill groups. Final analysis was done in 65 and 66 patients in each group from which adherence index could be obtained. Baseline clinical characteristics of the two groups were not different. The single-pill group had significantly higher PDT and PDTc compared to the two-pill group. (median (25–75 percentile) (%), PDT 95.1 (87.9 - 100.0) vs 91.2 (79.8 - 96.5); PDTc 93.1 (79.8 - 96.5) vs 91.3 (70.7 - 96.4), p = both 0.04, by Wilcoxon rank sum test) Percent dose taken Conclusion Single-pill combination of triple-component antihypertensive regimen showed superior adherence compared to equivalent two-pill therapy. Reducing pill burden by using SPC is a relevant strategy to enhance the adherence to multi-drug antihypertensive therapy. Acknowledgement/Funding Daiichi-Sankyo

Cyber security operations centre (CSOC) is a horizontal business function responsible primarily for managing cyber incidents, in addition to cyber-attack detection, security monitoring, security incident triage, analysis and coordination. To monitor systems, networks, applications and services the CSOC must first on-board the systems and services onto their security monitoring and incident management platforms. Cyber Onboarding (a.k.a. Onboarding) is a specialist technical process of setting up and configuring systems and services to produce appropriate events, logs and metrics which are monitored through the CSOC security monitoring and incident management platform. First, logging must be enabled on the systems and applications, second, they must produce the right set of computing and security logs, events, traps and messages which are analysed by the detection controls, security analytics systems and security event monitoring systems such as SIEM, and sensors etc.; and further, network-wide information e.g. flow data, heartbeats and network traffic information are collected and analysed, and finally, threat intelligence data are ingested in real-time to detect, or be informed of threats which are out in the wild. While setting up a CSOC could be straightforward, unfortunately, the ‘people’ and ‘process’ aspects that underpin the CSOC are often challenging, complicated and occasionally unworkable. In this paper, CSOC and Cyber Onboarding are thoroughly discussed, and the differences between SOC vs SIEM are explained. Key challenges to Cyber Onboarding are identified through the reframing matrix methodology, obtained from four notable perspectives – Cyber Onboarding Perspective, CSOC Perspective, Client Perspective and Senior Management Team Perspective. Each of the views and interests are discussed, and finally, recommendations are provided based on lessons learned implementing CSOCs for many organisations – e.g. government departments, financial institutions and private sectors.

The monitoring of the indoor air quality against the presence of contaminant sources is of paramount importance since it directly influences the occupants’ comfort, productivity, health and safety. Various approaches exist in the literature for monitoring and controlling the building environment. However, there is an identified lack of automated tools for evaluating, testing and comparing such approaches. This paper presents COMOB (COntaminat MOnitoring in Buildings), a developed MATLAB toolbox for sensor placement and contaminant monitoring in buildings. Specifically, the COMOB toolbox realizes an offline sensor placement procedure for positioning the contaminant sensors inside the building, such that the harmful effects due to a possible airborne contaminant event are minimized. In addition, an online contaminant monitoring approach is also implemented for detecting and isolating contaminant events in the building interior. Besides the aforementioned algorithms, the modularity of the COMOB toolbox facilitates the implementationof various other algorithms related to air-quality monitoring in buildings. In particular, the COMOB toolbox is able to generate multiple airflow and contaminant concentration data-sets by varying the building parameters; thus enabling the comprehensive and systematic evaluation and testing of the developed algorithms. Finally, the functionalities of the COMOB toolbox are demonstrated through a case-study corresponding to a real building model. COMOB is released under an open-source license, and is available at https://github.com/KIOS-Research/COMOB-Toolbox.

Event monitoring and detection in real-time systems is crucial. Protecting users' data while reporting an event in almost real-time will increase the level of this challenge. In this work, we adopt the strong notion of differential privacy to private stream counting for event detection with the aim of minimizing false positive and false negative rates as our utility metrics.

Trust management of the Internet of Connected Vehicles has been a hot topic in recent years with the rapid development of UGV technologies. However, existing resolutions based on trustworthiness verification among vehicles make the traffic event transmission quite inefficient. In this article, we assume that the deployed roadside units (RSUs) can provide efficient communication between any pair of RSU and vehicle and propose vehicle cash (Vcash), a reputation framework for identifying denial of traffic service, to resolve the trustworthiness problem in the application level of the Internet of Connected Vehicles. In our reputation framework, every vehicle communicates with the RSU directly for traffic event verification, and spreads verified traffic event notification. We borrow the idea of market trading, and set up trading rules to restrict the malicious vehicle’s spread of false message, and to encourage vehicles to contribute to the traffic event monitoring and verification. To evaluate the effectiveness of our reputation framework, we conduct a simulation experimental. Our experiment results indicate that our proposal manages to avoid bogus event spread, and a vehicle in our framework has to contribute to the traffic event detection to normally employ the traffic service.

Copyright © 2019 Torre, Cary, Borges, Ferreira, Alarcão, Leufkens, Costa and Martins. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms., Introduction: Intensive monitoring (IM) is one of the methods of post-marketing active surveillance based upon event monitoring, which has received interest in the current medicines regulatory landscape. For a specific period of time, IM involves primary data collection and is actively focused on gathering longitudinal information, mainly safety, since the first day of drug use. Objectives: To describe IM systems and studies' data published over 11-years period (2006-2016). Specifically, we reviewed study population/event surveillance, methodological approaches, limitations, and its applications in the real-world evidence generation data. Methods: We completed a systematic search of MEDLINE and EMBASE to identify studies published from 2006 to 2016, that used IM methodology. We extracted data using a standardized form and results were analyzed descriptively. The methodological quality of selected studies was assessed using the modified Downs and Black checklist. Results: From 1,400 screened citations, we identified 86 papers, corresponding to 69 different studies. Seventy percent of reviewed studies corresponded to established IM systems, of which, more than half were prescription event monitoring (PEM) and modified-PEM. Among non-established IM systems, vaccines were the most common studied drugs (n = 14). The median cohort size ranged from 488 (hospitals) to 10,479 (PEM) patients. Patients and caregivers were the event data source in 39.1% of studies. The mean overall quality score was similar between established and non-established IM. Conclusions: Over the study period, IM studies were implemented in 26 countries with different maturity levels of post-marketing surveillance systems. We identified two major limitations: only 20% of studies were conducted at hospital-level, which is a matter of concern, insofar as healthcare systems are facing a lack of access to new medicines at ambulatory care level. Additionally, IM access to data of drug exposure cohorts, either at identification or at follow-up stages, could somehow constitute a barrier, given the complexity of managerial, linkable, and privacy data issues., The publication fee was supported by the Center for Health Evaluation and Research (CEFAR), National Association of Pharmacies, Lisbon, Portugal.

Wireless smart sensors (WSS) have been proposed as an effective means to reduce the high cost of wired structural health monitoring systems. However, many damage scenarios for civil infrastructure involve sudden events, such as strong earthquakes, which can result in damage or even failure in a matter of seconds. Wireless monitoring systems typically employ duty cycling to reduce power consumption, hence, they will miss such events if they are in power-saving sleep mode when the events occur. This paper develops a demand-based WSS to meet the requirements of sudden event monitoring with minimal power budget and low response latency, without sacrificing high-fidelity measurements or risking a loss of critical information. In the proposed WSS, a programmable event-based switch is implemented utilizing a low-power trigger accelerometer, the switch is integrated in a high-fidelity sensor platform. Particularly, the approach can rapidly turn on the WSS upon the occurrence of a sudden event and seamlessly transition from low-power acceleration measurement to high-fidelity data acquisition. The capabilities of the proposed WSS are validated through laboratory and field experiments. The results show that the proposed approach is able to capture the occurrence of sudden events and provide high-fidelity data for structural condition assessment in an efficient manner.