The Internet of Things (IoT) paradigm plays a vital role for improving smart city applications by tracking and managing city processes in real-time. One of the most significant issues associated with smart city applications is solid waste management, which has a negative impact on our society’s health and the environment. The traditional waste management process begins with waste created by city residents and disposed of in garbage bins at the source. Municipal department trucks collect garbage and move it to recycling centers on a fixed schedule. Municipalities and waste management companies fail to keep up with outdoor containers, making it impossible to determine when to clean them or when they are full. This work proposes an IoT-enabled solid waste management system for smart cities to overcome the limitations of the traditional waste management systems. The proposed architecture consists of two types of end sensor nodes: PBLMU (Public Bin Level Monitoring Unit) and HBLMU (Home Bin Level Monitoring Unit), which are used to track bins in public and residential areas, respectively. The PBLMUs and HBLMUs measure the unfilled level of the trash bin and its location data, process it, and transmit it to a central monitoring station for storage and analysis. An intelligent Graphical User Interface (GUI) enables the waste collection authority to view and evaluate the unfilled status of each trash bin. To validate the proposed system architecture, the following significant experiments were conducted: (a) Eight trash bins were equipped with PBLMUs and connected to a LoRaWAN network and another eight trash bins were equipped with HBLMUs and connected to a Wi-Fi network. The trash bins were filled with wastes at different levels and the corresponding unfilled levels of every trash bin were monitored through the intelligent GUI. (b) An experimental setup was arranged to measure the sleep current and active current contributions of a PBLMU to estimate its average current consumption. (c) The life expectancy of a PBLMU was estimated as approximately 70 days under hypothetical conditions.

Real-world data streams pose a unique challenge to the implementation of machine learning (ML) models and data analysis. A notable problem that has been introduced by the growth of Internet of Things (IoT) deployments across the smart city ecosystem is that the statistical properties of data streams can change over time, resulting in poor prediction performance and ineffective decisions. While concept drift detection methods aim to patch this problem, emerging communication and sensing technologies are generating a massive amount of data, requiring distributed environments to perform computation tasks across smart city administrative domains. In this article, we implement and test a number of state-of-the-art active concept drift detection algorithms for time series analysis within a distributed environment. We use real-world data streams and provide critical analysis of results retrieved. The challenges of implementing concept drift adaptation algorithms, along with their applications in smart cities, are also discussed.

A Smart Campus is a miniature of a Smart City with a more demanding framework that enables learning, social interaction and creativity. To ensure a Smart Campus uninterruptible secure operation, a key requirement is that daily routines and activities are performed protected in an environment monitored unobtrusively by a robust surveillance system. The various components that compose such an environment, buildings, labs, public spaces, smart lighting, smart parking, or even smart traffic lights, require us to focus on surveillance systems, and recognize which detection activities to establish. In this paper, we perform a comparative assessment in the area of surveillance systems for Smart Campuses. A proposed taxonomy for IoT-enabled Smart Campus unfold five research dimensions: (1) physical infrastructure; (2) enabling technologies; (3) software analytics; (4) system security; and (5) research methodology. By applying this taxonomy and by adopting a weighted scoring model on the surveyed systems, we first present the state-of-the-art, and then we make a comparative assessment and classify the systems. We extract valuable conclusions and inferences from this classification, providing insights and directions towards required services offered by surveillance systems for Smart Campus.

Willingness to invest in renewable energy sources (RES) is predictable under data mining classification methods. Data was collected from the area of Evia in Greece via a questionnaire survey by using a sample of 360 respondents. The questions focused on the respondents’ perceptions and offered benefits for wind energy, solar photovoltaics (PVs), small hydro parks and biomass investments. The classification algorithms of Bayesian Network classifier, Logistic Regression, Support Vector Machine (SVM), C4.5, k-Nearest Neighbors (k-NN) and Long Short Term Memory (LSTM) were used. The Bayesian Network classifier was the best method, with a prediction accuracy of 0.7942. The most important variables for the prediction of willingness to invest were the level of information, the level of acceptance and the contribution to sustainable development. Future studies should include data on state incentives and their impact on willingness to invest.