Argument Mining (AM) involves identifying and extracting Argumentative Components (ACs) and their corresponding Argumentative Relations (ARs). Most of the prior works have broken down these tasks into multiple sub-tasks. Existing end-to-end setups primarily use the dependency parsing approach. This work introduces a generative paradigm-based end-to-end framework argTANL. argTANL frames the argumentative structures into label-augmented text, called Augmented Natural Language (ANL). This framework jointly extracts both ACs and ARs from a given argumentative text. Additionally, this study explores the impact of Argumentative and Discourse markers on enhancing the model’s performance within the proposed framework. Two distinct frameworks, Marker-Enhanced argTANL (ME-argTANL) and argTANL with specialized Marker-Based Fine-Tuning, are proposed to achieve this. Extensive experiments are conducted on three standard AM benchmarks to demonstrate the superior performance of the ME-argTANL.

Video analytics plays a crucial role in the development of smart estates and cities. Applications such as garbage dumping detection, lift monitoring, safety surveillance, etc. rely on video analytics, and require fast response time. Traditional cloud-based systems are ill-suited for these applications due to their limitations in handling large volume of video data with low latency. In contrast, the IoT-Edge-Cloud paradigm is better suited for such applications, but it presents challenges such as system heterogeneity, and resource allocation and orchestration. There is a need for an efficient platform for distributed video stream processing where resource orchestration and scalability aspects are tailored to smart estate applications.In this paper, we present ViEdge, an edge-based platform for video analytics applications in smart estates. It is highly adaptable and scalable, making it ideal for various deployments in such environments. Our implementation of ViEdge utilizes Kubernetes (K8s) for resource management and orchestration, and Apache Storm for distributed video stream processing. To study ViEdge’s customization capabilities, we evaluated its performance on a heterogeneous edge testbed. We observed increased latency in Apache Storm when integrated with Kubernetes, affecting overall application performance. However, by developing a heuristic-based scheduler, we demonstrate that ViEdge effectively reduces end-to-end latency and enhances frame processing rates.

The rapid growth of Internet-of- Things (IoT) systems demands higher throughput to process sensor data. Existing data processing platforms use simple heuristics for task placement, which perform poorly. We proposed a Permutation-based Task Placement Optimizer (PTPO) that constructs a set of valid task placement permutations to formulate a mixed-integer linear programming problem. PTPO enables efficient real-time task placement for multiple dynamic applications. Our study highlights three key design factors: joint consideration of compute and network constraints, accurate profiling of resource needs, and fine-grained splitting of tasks across nodes. We demonstrate more than 80% throughput gain compared to state-of-the-art schemes using real-world IoT Applications.

Urban air pollution is a major problem in many cities globally. Prolonged exposure to particulate matter in the air is harmful to health. Government agencies and industries use expensive EPA-rated Air Quality Monitoring Systems (AQMS) with specialized and expensive instruments. However, the air quality data provided by agencies is based on delayed averages and is region-based. The AirQ platform is a smart and cost-effective solution for air quality monitoring. The AirQ device is portable, low-cost and provides real-time and location-specific air quality data. It supports wireless data communication technologies including WiFi, 4G, Bluetooth, LoRa, etc. We have developed an ontology-based backend to support data management and the implementation of smart data analytics algorithms. The real-time air quality data and alerts are provided by the AirQ Dashboard and Smartphone App. The AirQ platform can be used to build large-scale and high-density air quality monitoring networks for Smart Cities, with devices deployed at many locations such as schools, childcare centers, hospitals, community centers, bus stops, parks, etc.

Conventional IoT infrastructure deployments require complex configurations and management at the sensor devices, gateway and the backend levels. We have developed a smart ontology-driven IoT platform which can significantly improve the scalability and efficiency of the deployment and management of large-scale IoT infrastructures. The platform provides a unified ontology management layer across the sensor devices, IoT gateway and IoT backend. It also provides a virtualization-based IoT gateway which supports the interoperability of sensor devices with heterogeneous network protocols.