Classification of time series data plays a critical role across various domains, enabling pattern recognition and trend prediction. Traditional methods like Dynamic Time Warping (DTW) have been widely used to measure similarity between time series, but there are challenges related to computational complexity and sensitivity to noise. The conventional DTW approach, with its quadratic time complexity, can be inefficient for large datasets, and some implementations may struggle with noise and local variations. To overcome these limitations, a novel method called Graph-Theoretic Dynamic Time Warping (GT-DTW) is proposed. GT-DTW represents each time series as a graph, applies DTW on the graph representations and calculates the distances between different time series based on these graph representations. This approach provides a robust and computationally efficient method for time series classification, and experimental results show that GT-DTW provides better results when compared with conventional methods on the benchmark datasets from the UCR time series database. GT-DTW also demonstrates enhanced effectiveness in situations where time series share fundamental similarities, yet are affected by intricate transformations, noise, inconsistencies in length, and localized distortions.

As our world becomes increasingly urbanized, smart cities are leading the way in using technology to create more efficient, connected, and sustainable environments. However, amidst all the talk of connectivity and smartness, it’s crucial not to lose sight of one of the most basic human needs: access to nature in cities. This research describes a novel open-source framework for investigating the availability and accessibility of green recreation spaces using open-source data and statistical analytic approaches. The framework includes a comprehensive set of tools for data extraction, processing, analysis, and visualization, thereby enabling reproducible geospatial research. We test our framework on five international cities: Medellin, Milan, Chicago, Singapore, and Mumbai. Through geospatial analysis and statistical modeling of data sourced from OpenStreetMaps, we explore and comprehend the characteristics and distribution of spatial accessibility related to green recreation spaces in five cities. We find significant clustering of green recreation spaces in all these cities, indicating that a majority of such spaces are located in close proximity to each other within small areas. Our findings also shed light on the potential implications of unequal distribution of green recreation spaces for the health and well-being of city residents and highlight the need for policies and initiatives that promote equitable access to green recreation spaces in smart cities.

Cities around the world are struggling with environmental pollution. The conventional monitoring approaches are not effective for undertaking large-scale environmental monitoring due to logistical and cost-related issues. The availability of low-cost and low-power Internet of Things (IoT) devices has proved to be an effective alternative to monitor the ambient environment. Such systems have opened up environment monitoring opportunities to researchers and citizens while simultaneously confronting them with challenges like sensor accuracy, accumulation of large data sets, and data analysis, which itself is a formidable task that requires extensive computational resources and technical expertise. To address this challenge, a social, open-source, and citizen-centric IoT (Soc-IoT) framework is proposed that combines tools for real-time environmental sensing with an intuitive data analysis and visualization application. Soc-IoT has two main components: (1) CoSense Unit – a resource-efficient, portable and modular environment monitoring device intended for citizen sensing and complementing official environment monitoring infrastructure, and (2) exploreR – an intuitive cross-platform data analysis and visualization application that offers a comprehensive set of tools for systematic analysis of sensor data without any coding requirement. Developed as a proof-of-concept framework to monitor the environment at scale, Soc-IoT aims to promote environmental resilience and open innovation by reducing technological barriers.