More Like this

1. Phylogeny and classification of Odonata using targeted genomics

   https://doi.org/https://doi.org/10.1016/j.ympev.2021.107115  

   Bybee, S.M. (July 2021, Molecular phylogenetics and evolution)
2. Verification and Validation of AI Systems Using Explanations

   https://doi.org/10.1609/aaaiss.v4i1.31774  

   Mahmud, Saaduddin; Saisubramanian, Sandhya; Zilberstein, Shlomo (November 2024, Proceedings of the AAAI Symposium Series)

   Verification and validation of AI systems, particularly learning-enabled systems, is hard because often they lack formal specifications and rely instead on incomplete data and human subjective feedback. Aligning the behavior of such systems with the intended objectives and values of human designers and stakeholders is very challenging, and deploying AI systems that are misaligned can be risky. We propose to use both existing and new forms of explanations to improve the verification and validation of AI systems. Toward that goal, we preseant a framework, the agent explains its behavior and a critic signals whether the explanation passes a test. In cases where the explanation fails, the agent offers alternative explanations to gather feedback, which is then used to improve the system's alignment. We discuss examples of this approach that proved to be effective, and how to extend the scope of explanations and minimize human effort involved in this process. 

   more » « less
3. Detection and Tracking of Drone Swarms using LiDAR

   Abir, Tasnim; Le, Vu; Kuantama, Endrowednes; Gupta, Pranjol; Copley, Austin; Dawes, Judith; Islam, Mohammad; Han, Richard; Nguyen, Phuc (June 2025, ACM MobiSys 2025)

   This paper introduces LiSWARM, a low-cost LiDAR system to detect and track individual drones in a large swarm. LiSWARM provides robust and precise localization and recognition of drones in 3D space, which is not possible with state-of-the-art drone tracking systems that rely on radio-frequency (RF), acoustic, or RGB image signatures. It includes (1) an efficient data processing pipeline to process the point clouds, (2) robust priority-aware clustering algorithms to isolate swarm data from the background, (3) a reliable neural network-based algorithm to recognize the drones, and (4) a technique to track the trajectory of every drone in the swarm. We develop the LiSWARM prototype and validate it through both in-lab and field experiments. Notably, we measure its performance during two drone light shows involving 150 and 500 drones and confirm that the system achieves up to 98% accuracy in recognizing drones and reliably tracking drone trajectories. To evaluate the scalability of LiSWARM, we conduct a thorough analysis to benchmark the system’s performance with a swarm consisting of 15,000 drones. The results demonstrate the potential to leverage LiSWARM for other applications, such as battlefield operations, errant drone detection, and securing sensitive areas such as airports and prisons. 

   more » « less
4. Interpolation and Denoising of Graph Signals Using Plug-and-play Admm

   https://doi.org/10.1109/ICASSP.2019.8682282  

   Yazaki, Yoshinao; Tanaka, Yuichi; Chan, Stanley H. (May 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP))
5. Identification and Classification of Electronic Devices Using Harmonic Radar

   https://doi.org/10.1109/DCOSS-IoT58021.2023.00050  

   Perez, Beatrice; Pierson, Timothy J; Mazzaro, Gregory; Kotz, David (September 2023, IEEE)

   Smart home electronic devices invisibly collect, process, and exchange information with each other and with remote services, often without a home occupants' knowledge or consent. These devices may be mobile or fixed and may have wireless or wired network connections. Detecting and identifying all devices present in a home is a necessary first step to control the flow of data, but there exists no universal mechanism to detect and identify all electronic devices in a space. In this paper we present ICED (Identification and Classification of Electronic Devices), a system that can (i) identify devices from a known set of devices, and (ii) detect the presence of previously unseen devices. ICED, based on harmonic radar technology, collects measurements at the first harmonic of the radar's transmit frequency. We find that the harmonic response contains enough information to infer the type of device. It works when the device has no wireless network interface, is powered off, or attempts to evade detection. We evaluate performance on a collection of 17 devices and find that by transmitting a range of frequencies we correctly identify known devices with 97.6% accuracy and identify previously unseen devices as ‘unknown’ with 69.0% balanced accuracy. 

   more » « less