Even as the COVID-19 pandemic drove advances in contact tracing and exposure notification systems, user privacy challenges continue to plague otherwise promising approaches to contain contagions. We propose a novel, scalable approach to address privacy in contact tracing that improves utility. We apply passive WiFi scan data using two metrics suitable for estimating contact between users. We support this with real world experimental data captured across a range of environments relevant to contact tracing. To preserve privacy, we leverage properties of truncated cryptographic hashes in an adaptation unique to contact tracing. This hash collision filter allows users to share information about potential contacts with a central server without revealing sensitive information. Using an aggressive threat model, including adversarial users and a malicious server, we share how this technique can improve utility while still providing strong security protections compared to other approaches using, for example, only Bluetooth (BT) or global navigation satellite systems (GNSSs). Finally, we discuss a capability of this approach that allows notification for asynchronous co-location from past contacts.

The Urdu language is used by approximately 200 million people for spoken and written communications on a daily basis. There is a substantial amount of unstructured Urdu textual data that is available worldwide. Data mining techniques can be used to extract meaningful knowledge from such a large, potentially informative source of data. There are many text processing systems available to process unstructured textual data. However, these systems are mostly language specific and developed for a variety of languages such as English, Spanish, Chinese, and so on. Unfortunately, there are not as many language processing resources available for Urdu. Stemming is one of the most important preprocessing steps in the text mining process and its goal is to reduce grammatical words form, e.g., parts of speech, gender, tense, and so on, to their root form. In this work, we have extended the stemming capabilities of our existing pattern-based comprehensive stemming system for Urdu text. In addition to the existing stemming rules in previous work, we introduce novel stemming rules for prefix, and infix stemming. We also optimize the existing suffix removal rules and extend the add character lists for word normalization. These stemming rules are generic and have the ability to generate the stem of Urdu words as well as loan words (words belonging to other languages i.e., Arabic, Persian, Turkish). In the experimental evaluation, we have observed a significant improvement in the overall stemming accuracy of our proposed pattern-based Urud stemmer, which demonstrates the adoptability of the proposed stemming approach for a variety of text-processing applications.

Software defined radios (SDRs) are often used in the experimental evaluation of next-generation wireless technologies. While crowdsourced spectrum monitoring is an important component of future spectrum-agile technologies, there is no clear way to test it in the real world, i.e., with hundreds of users each carrying an SDR while uploading data to a cloud-based controller. Current fully functional SDRs are bulky, with components connected via wires, and last at most hours on a single battery charge. To address these needs, we design and develop a compact, portable, untethered, and inexpensive SDR we callSitara. Our SDR interfaces with a mobile device over Bluetooth 5 and can function standalone or as a client to a central command and control server. It transmits and receives common waveforms, uploads IQ samples or processed receiver data through a mobile device to a server for remote processing and performs spectrum sensing functions. We present results from a user study involving more than 100 participants to evaluate Sitara in a hypothetical large-scale crowdsourced spectrum monitoring application. We also present a comparative analysis of Sitara to related crowdsensing systems with a particular emphasis on the role of incentives and user participation.

Venelin Kovatchev, Phillip Smith, Mark Lee, Rory Devine. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

In this paper we present the first work on the automated scoring of mindreading ability in middle childhood and early adolescence.We create MIND-CA, a new corpus of 11,311 question-answer pairs in English from 1,066 children aged 7 to 14.We perform machine learning experiments and carry out extensive quantitative and qualitative evaluation.We obtain promising results, demonstrating the applicability of state-of-the-art NLP solutions to a new domain and task.

We present LLOCUS, a novel learning-based system that uses mobile crowdsourced RF sensing to estimate the location and power of unknown mobile transmitters in real time, while allowing unrestricted mobility of the crowdsourcing participants. We carefully identify and tackle several challenges in learning and localizing, based on RSS, in such a dynamic environment. We decouple the problem of localizing a transmitter with unknown transmit power into two problems, 1) predicting the power of a transmitter at an unknown location, and 2) localizing a transmitter with known transmit power. LLOCUS first estimates the power of the unknown transmitter and then scales the reported RSS values such that the unknown transmit power problem is transparent to the method of localization. We evaluate LLOCUS using three experiments in different indoor and outdoor environments. We find that LLOCUS reduces the localization error by 17-68% compared to several non-learning methods.

Software-defined radios (SDRs) are often used in the experimental evaluation of next-generation wireless technologies. While crowd-sourced spectrum monitoring is an important component of future spectrum-agile technologies, there is no clear way to test it in the real world, i.e., with hundreds of users each carrying an SDR while uploading data to a cloud-based controller. Current fully functional SDRs are bulky, with components connected via wires, and last at most hours on a single battery charge. To address the needs of such experiments, we design and develop a compact, portable, untethered, and inexpensive SDR we call Sitara. Our SDR interfaces with a mobile device over Bluetooth 5 and can function standalone or as a client to a central command and control server. The Sitara offers true portability: it operates up to one week on battery power, requires no external wired connections and occupies a footprint smaller than a credit card. It transmits and receives common waveforms, uploads IQ samples or processed receiver data through a mobile device to a server for remote processing and performs spectrum sensing functions. Multiple Sitaras form a distributed system capable of conducting experiments in wireless networking and communication in addition to RF monitoring and sensing activities. In this paper, we describe our design, evaluate our solution, present experimental results from multi-sensor deployments and discuss the value of this system in future experimentation.

This paper explores a machine learning process for robotic swarms tasked with a non-trivial problem in restricted environments. The effect of using a semi-stochastic action selector in a learning classifier based behaviour system is examined via adjusting the stochasticity setting. In this study we utilise Greedy Randomised Adaptive Search Procedures, finding some improvement in the ability of the swarm in non-deterministic, partially observable environments, compared to Greedy selection. We also find the swarm performs significantly worse when machine learning is removed. This study also explores an evolutionary process used to optimise the behaviours available to each agent. This evolutionary process is examined in regard to the effect it has on the learning settings. It is found that the evolution reduces the impact of fine-tuning the learning variables. However, fully stochastic selection prevents learning, which impairs the evolution.

Pauses in distributed groupware activity can indicate anything from technical latency through infrastructure failure to a participant's thoughtful contemplation. Unraveling these ambiguities highlights mismatches between unseen off-screen activities and on-screen cursor behaviors. In this paper we suggest that groupware systems have typically been poor at representing off-screen activities, and introduce the concept of display trajectories to bridge the sensor gap between the display and its surrounding space. We consider requirements for display trajectories using the distributed social scientific analysis of video data as an example domain. Drawing on these requirements, we prototype a freeform whiteboard pen tracking and visualization technique around displays using ultrasound. We describe an experiment which inspects the impact of display trajectories on remote response efficiency. Our findings show that visualization of the display trajectory improves participants' ability to coordinate their actions by one second per interaction turn, reducing latency in organizing turn taking by a 'standard maximum' conversation pause.