More Like this

1. Globally Aware Contextual Embeddings for Named Entity Recognition in Social Media Streams

   Satadisha Saha Bhowmick; Eduard C. Dragut; Weiyi Meng (April 2023, ICDE)

   An important task for Information Extraction from Microblogs is Named Entity Recognition (NER) that extracts mentions of real-world entities from microblog messages and meta-information like entity type for better entity characterization. A lot of microblog NER systems have rightly sought to prioritize modeling the non-literary nature of microblog text. These systems are trained on offline static datasets and extract a combination of surface-level features – orthographic, lexical, and semantic – from individual messages for noisy text modeling and entity extraction. But given the constantly evolving nature of microblog streams, detecting all entity mentions from such varying yet limited context in short messages remains a difficult problem to generalize. In this paper, we propose the NER Globalizer pipeline better suited for NER on microblog streams. It characterizes the isolated message processing by existing NER systems as modeling local contextual embeddings, where learned knowledge from the immediate context of a message is used to suggest seed entity candidates. Additionally, it recognizes that messages within a microblog stream are topically related and often repeat mentions of the same entity. This suggests building NER systems that go beyond localized processing. By leveraging occurrence mining, the proposed system therefore follows up traditional NER modeling by extracting additional mentions of seed entity candidates that were previously missed. Candidate mentions are separated into well-defined clusters which are then used to generate a pooled global embedding drawn from the collective context of the candidate within a stream. The global embeddings are utilized to separate false positives from entities whose mentions are produced in the final NER output. Our experiments show that the proposed NER system exhibits superior effectiveness on multiple NER datasets with an average Macro F1 improvement of 47.04% over the best NER baseline while adding only a small computational overhead. 

   more » « less
2. Demo:Towards the Development of a Differentially Private Lightweight and Scalable Blockchain for IoT Conference Paper · November 2019 with 22 Reads 

   Abdur R. Shahidx, Niki Pissinou (November 2019, 16th IEEE International Conference on Mobile Ad-Hoc and Smart Systems (MASS))

   In this work, we demonstrate the design and implementation of a novel privacy-preserving blockchain for the resource-constrained Internet of Things (IoT). Blockchain, by design, ensures trust, provides built-in integrity of information and security of immutability in an IoT system without the need of a centralized entity. However, its slow transaction rate, lack of transaction privacy, and high resource consumption are three of the major hindrances to the practical realization of blockchain in IoT. While directed acyclic graphs (DAG)-based blockchain variants (e.g., hashgraph) improve the transaction rate, the other two problems remain open. To this end, we designed and constructed the prototype of a blockchain by utilizing the benefits of high transaction rate and miner-free transaction validation process from hashgraph. The proposed blockchain, coined as PrivLiteChain, implements the concept of local differential privacy to provide transaction privacy and temporal constraint to the lifecycle of the blockchain to make it lightweight. 

   more » « less
3. Model-Based Trust Assessment for Internet of Things Networks

   Adams, Stephen; Beling, Peter A; Greenspan, Steven; Velez-Rojas, Maria; Mankovski, Serge (January 2018, 2018 17th IEEE International Conference On Trust, Security And Privacy In Computing And Communications/12th IEEE International Conference On Big Data Science And Engineering (TrustCom/BigDataSE))

   Trust in data collected by and passing through Internt of Things (IoT) networks is paramount. The quality of decisions made based on this collected data is highly dependent upon the accuracy of the data. Currently, most trust assessment methodologies assume that collected data follows a stationary Gaussian distribution. Often, a trust score is estimated based upon the deviation from this distribution. However, the underlying state of a system monitored by an IoT network can change over time, and the data collected from the network may not consistently follow a Gaussian distribution. Further, faults that occur within the estimated Gaussian distribution may go undetected. In this study, we present a model-based trust estimation system that allows for concept drift or distributions that can change over time. The presented methodology uses data-driven models to estimate the value of the data produced by a sensor using the data produced by the other sensors in the network. We assume that an untrustworthy piece of data falls in the tails of the residual distribution, and we use this concept to assign a trust score. The method is evaluated on a smart home data set consisting of temperature, humidity, and energy sensors. 

   more » « less
4. Harnessing the Power of Repetition Structure in Ultra-Narrowband IoT

   https://doi.org/10.1109/SPAWC53906.2023.10304468  

   Peppas, Spyridon; Karakasis, Paris A; Sidiropoulos, Nicholas D; Cabric, Danijela (September 2023, IEEE)

   NA (Ed.)

   In this paper, we present a method for decoding uplink messages in Internet of Things (IoT) networks that employ packet repetition. We focus on the Sigfox protocol, but our approach is applicable to other IoT protocols that employ message repetition. Our approach endeavors to enhance the reliability of message capture as well as the error rate performance at the base station. To achieve this goal, we propose a novel technique that capitalizes on the unique features of the IoT network’s uplink transmission structure. Through simulations, we demonstrate the effectiveness of our method in various scenarios, including single-user and multi-user setups. We establish the resilience of our approach under higher system loads and interference conditions, showcasing its potential to improve IoT network performance and reliability even when a large number of devices operates over limited spectrum. Our findings reveal the potential of the proposed method as a promising solution for enabling more dependable and energy-efficient communication in IoT Low Power Wide Area Networks. 

   more » « less
5. IGaaS: An IoT Gateway-as-a-Service for On-demand Provisioning of IoT Gateways

   https://doi.org/10.1109/WF-IoT48130.2020.9221225  

   Aminul Hoque, Mohammad; Hossain, Mahmud; Hasan, Ragib (June 2020, 2020 IEEE 6th World Forum on Internet of Things (WF-IoT))

   null (Ed.)

   The widespread adoption of the Internet of Things (IoT) devices has increased its popularity and usage in diverse dimensions, including smart city, home, healthcare, and vehicles. The pervasiveness of the number of IoT devices that operate in low power and lossy network leads to performance issues. An excessive amount of IoT devices that operate with a fixed number of gateways reduce the quality of service (QoS) due to the increased latency of routing messages between the source and destination sensors. In this paper, we propose an IoT Gateway as a Service (IGaaS) that enables on-demand provisioning of IoT Gateways to maintain and improve QoS in an IoT system with a significant number of sensors. The IGaaS allows both the stationary and mobile gateways to be provisioned on-demand. The mobile devices, such as smartphones and drones, provide gateway services in exchange for incentives. The IGaaS supports both the upscale and downscale of IoT gateways depending on various metrics and requirements. The experimental results show that the IGaaS improves the QoS in terms of latency and power consumption. 

   more » « less