A5000027012- Building Energy and Comfort Optimization
- Privacy-Preserving Technologies in Data
- Air Quality Monitoring and Forecasting
- Anomaly Detection Techniques and Applications
- Smart Grid Energy Management
- Human Mobility and Location-Based Analysis
- Data Stream Mining Techniques
- Network Security and Intrusion Detection
- Time Series Analysis and Forecasting
- Internet Traffic Analysis and Secure E-voting
- IoT and Edge/Fog Computing
- Context-Aware Activity Recognition Systems
- IoT-based Smart Home Systems
- Traffic Prediction and Management Techniques
- Data Quality and Management
- Green IT and Sustainability
- Adversarial Robustness in Machine Learning
- Neural Networks and Applications
- Energy Load and Power Forecasting
- Smart Agriculture and AI
- Data Management and Algorithms
- Mobile Crowdsensing and Crowdsourcing
- Advanced Database Systems and Queries
- Gene expression and cancer classification
- Biomedical Text Mining and Ontologies
Universidad de Murcia
2016-2024
Information Technologies Institute
2022
Centre for Research and Technology Hellas
2022
The application of Machine Learning (ML) techniques to the well-known intrusion detection systems (IDS) is key cope with increasingly sophisticated cybersecurity attacks through an effective and efficient process. In context Internet Things (IoT), most ML-enabled IDS approaches use centralized where IoT devices share their data centers for further analysis. To mitigate privacy concerns associated approaches, in recent years Federated (FL) has attracted a significant interest different...
The recent technological advances and their applications to agriculture provide leverage for the new paradigm of smart agriculture. Remote sensing can help optimize resources, making more ecological, increasing productivity helping farmers anticipate events that could not otherwise be avoided. Considering losses caused by anomalies such as diseases, weeds pests account 20-40 % overall agricultural productivity, a successful research effort in this area would breakthrough In paper, we propose...
This paper presents the main foundations of big data applied to smart cities. A general Internet Things based architecture is proposed be different cities applications. We describe two scenarios analysis. One them illustrates some services implemented in campus University Murcia. The second one focused on a tram service scenario, where thousands transit-card transactions should processed. Results obtained from both show potential applicability this kind techniques provide profitable cities,...
Federated learning (FL) has attracted significant interest given its prominent advantages and applicability in many scenarios. However, it been demonstrated that sharing updated gradients/weights during the training process can lead to privacy concerns. In context of Internet Things (IoT), this be exacerbated due intrusion detection systems (IDSs), which are intended detect security attacks by analyzing devices' network traffic. Our work provides a comprehensive evaluation differential...
Considering that the largest part of end-use energy consumption worldwide is associated with buildings sector, there an inherent need for conceptualization, specification, implementation, and instantiation novel solutions in smart buildings, able to achieve significant reductions through adoption efficient techniques active engagement occupants. Towards design such solutions, identification main consuming factors, trends, patterns, along appropriate modeling understanding occupants' behavior...
Misbehavior detection represents a key security approach in vehicular scenarios to identify attacks that cannot be detected by traditional cryptographic mechanisms. In this context, the application of Machine Learning (ML) techniques has been widely considered increasingly sophisticated misbehavior attacks. However, most proposed approaches are based on centralized settings, which could pose privacy issues, as well an increased latency leading severe consequences environment where real-time...
The factors affecting the penetration of certain diseases such as COVID-19 in society are still unknown. Internet Things (IoT) technologies can play a crucial role during time crisis and they provide more holistic view reasons that govern outbreak contagious disease. understanding will be enriched by analysis data related to phenomena, this collected using IoT sensors. In paper, we show an integrated solution based on serve opportunistic health acquisition agents for combating pandemic...
The arrival of the Internet Things (IoT) paradigm has opened door to a variety services for building users. Considering long-lasting issue high energy use by buildings and low-energy literacy, it is tempting this new technology increasing literacy This paper shows results study performed in two pilot with real users that have interacted series educational interventions encourage them timed personalised way reduce their consumption. aimed at reducing consumption close follow-up intervention...
This work presents how to proceed during the processing of all available data coming from smart buildings generate models that predict their energy consumption. For this, we propose a methodology includes application different intelligent analysis techniques and algorithms have already been applied successfully in related scenarios, selection best one depending on value selected metric used for evaluation. result depends specific characteristics target building data. Among reference...
Energy efficiency is in the interest of everyone, from individuals to governments, since it yields economical savings, reduces greenhouse gas emissions and alleviates energy poverty. Buildings are one largest consumers primary attaining their is, therefore, an important goal. The Internet Things currently provides vast amounts data that can be used extract knowledge all kinds, including regarding prediction. This has motivated us test wether prior information on physics building heat...
Internet of Things (IoT) enables the seamless integration sensors, actuators, and communication devices for real-time applications. IoT systems require good quality sensor data in order to make decisions. However, values are often missing from collected owing faulty a loss during communication, interference, measurement errors. Considering spatiotemporal nature uncertainty by we propose new framework with which impute utilizing Bayesian maximum entropy (BME) as convenient means estimate...
Abstract The current cost that energy represents is crucial in a field like climate control which has high demands, therefore its reduction must be prioritized. expansion of ICT and IoT come with an extensive deployment sensors computation infrastructure creating opportunity to analyze optimize management. Data on building internal external conditions essential for developing efficient strategies order minimize consumption while maintaining users’ comfort inside. We here present dataset...
Given that the global water system is deteriorating and supply demand are very dynamic, smart ways to improve management needed so it becomes more efficient extend services provided citizens leading cities. One of many related problems can be addressed by Internet Things anomaly detection in consumption. The analysis data collected meters will help personalize feedback customers, prevent waste detect alarming situations. Water consumption considered as a time series. Time series an old topic...
Human activities and city routines follow patterns. Transfer learning can help achieve scalable solutions toward the realization of smart cities accounting for similarities between regions, domains, activities. In this study, we propose a transfer learning-based framework buildings to test hypothesis in energy-related problems. Our has two major components: network creation transferable predictive model. order create that groups sharing characteristics, evaluated strategies: novel clustering...
Electricity is currently the most important energy vector in domestic sector and industry. Unlike fuels, electricity hard expensive to store. This creates need of precise coupling between generation demand. In addition, transmission lines electric power be sized for a given maximum power, overloading them may result blackout or electrical accidents. For these reasons, consumption forecasting vital. The time scale depends on who interested such prediction. Grid operators have predict demand...
Due to the rapid development of Internet Things (IoT) and consequently, availability more IoT data sources, mechanisms for searching integrating sources become essential leverage all relevant improving processes services. This paper presents search framework IoTCrawler. The IoTCrawler is not only another framework, it a system systems which connects existing solutions offer interoperability overcome fragmentation. In addition its domain-independent design, features layered approach, offering...
The massive collection of data via emerging technologies like the Internet Things (IoT) requires finding optimal ways to reduce observations in time series analysis domain. IoT require aggregation methods that can preserve and represent key characteristics data. In this paper, we propose a segmentation algorithm adapts unannounced mutations (i.e., drifts). splits streams into blocks groups them square matrices, computes Discrete Cosine Transform (DCT), quantizes them. information is...