More Like this

1. Predicting Wildlife Trafficking Routes with Differentiable Shortest Paths

   Ferber, A. (May 2023, Part of the Lecture Notes in Computer Science book series (LNCS,volume 13884))

   Cire, A.A. (Ed.)

   Wildlife trafficking (WT), the illegal trade of wild fauna, flora, and their parts, directly threatens biodiversity and conservation of trafficked species, while also negatively impacting human health, national security, and economic development. Wildlife traffickers obfuscate their activities in plain sight, leveraging legal, large, and globally linked transportation networks. To complicate matters, defensive interdiction resources are limited, datasets are fragmented and rarely interoperable, and interventions like setting checkpoints place a burden on legal transportation. As a result, interpretable predictions of which routes wildlife traffickers are likely to take can help target defensive efforts and understand what wildlife traffickers may be considering when selecting routes. We propose a data-driven model for predicting trafficking routes on the global commercial flight network, a transportation network for which we have some historical seizure data and a specification of the possible routes that traffickers may take. While seizure data has limitations such as data bias and dependence on the deployed defensive resources, this is a first step towards predicting wildlife trafficking routes on real-world data. Our seizure data documents the planned commercial flight itinerary of trafficked and successfully interdicted wildlife. We aim to provide predictions of highly-trafficked flight paths for known origin-destination pairs with plausible explanations that illuminate how traffickers make decisions based on the presence of criminal actors, markets, and resilience systems. We propose a model that first predicts likelihoods of which commercial flights will be taken out of a given airport given input features, and then subsequently finds the highest-likelihood flight path from origin to destination using a differentiable shortest path solver, allowing us to automatically align our model’s loss with the overall goal of correctly predicting the full flight itinerary from a given source to a destination. We evaluate the proposed model’s predictions and interpretations both quantitatively and qualitatively, showing that the predicted paths are aligned with observed held-out seizures, and can be interpreted by policy-makers 

   more » « less
2. The reniform body: An integrative lateral protocerebralneuropil complex of Eumalacostraca identified in Stomatopodaand Brachyura

   https://doi.org/10.1002/cne.24788  

   Thoen, Hanne H; Wolff, Gabriella H; Marshall, J; Sayre, Marcel E; Strausfeld, Nicholas J (October 2019, The Journal of comparative neurology)

   Mantis shrimps (Stomatopoda) possess in common with other crustaceans, and with Hexapoda, specific neuroanatomical attributes of the protocerebrum, the most anterior part of the arthropod brain. These attributes include assemblages of interconnected centers called the central body complex and in the lateral protocerebra, situated in the eyestalks, paired mushroom bodies. The phenotypic homologues of these centers across Panarthropoda support the view that ancestral integrative circuits crucial to action selection and memory have persisted since the early Cambrian or late Ediacaran. However, the discovery of another prominent integrative neuropil in the stomatopod lateral protocerebrum raises the question whether it is unique to Stomatopoda or at least most developed in this lineage, which may have originated in the upper Ordovician or early Devonian. Here, we describe the neuroanatomical structure of this center, called the reniform body. Using confocal microscopy and classical silver staining, we demonstrate that the reniform body receives inputs from multiple sources, including the optic lobe's lobula. Although the mushroom body also receives projections from the lobula, it is entirely distinct from the reniform body, albeit connected to it by discrete tracts. We discuss the implications of their coexistence in Stomatopoda, the occurrence of the reniform body in another eumalacostracan lineage and what this may mean for our understanding of brain functionality in Pancrustacea. 

   more » « less
3. The reniform body: An integrative lateral protocerebral neuropil complex of Eumalacostraca identified in Stomatopoda and Brachyura

   H.H. Thoen, G.H. Wolff (October 2019, Journal of comparative neurology)

   Mantis shrimps (Stomatopoda) possess in common with other crustaceans, and with Hexapoda, specific neuroanatomical attributes of the protocerebrum, the most anterior part of the arthropod brain. These attributes include assemblages of interconnected centers called the central body complex and in the lateral protocerebra, situated in the eyestalks, paired mushroom bodies. The phenotypic homologues of these centers across Panarthropoda support the view that ancestral integrative circuits crucial to action selection and memory have persisted since the early Cambrian or late Ediacaran. However, the discovery of another prominent integrative neuropil in the stomatopod lateral protocerebrum raises the question whether it is unique to Stomatopoda or at least most developed in this lineage, which may have originated in the upper Ordovician or early Devonian. Here, we describe the neuroanatomical structure of this center, called the reniform body. Using confocal microscopy and classical silver staining, we demonstrate that the reniform body receives inputs from multiple sources, including the optic lobe's lobula. Although the mushroom body also receives projections from the lobula, it is entirely distinct from the reniform body, albeit connected to it by discrete tracts. We discuss the implications of their coexistence in Stomatopoda, the occurrence of the reniform body in another eumalacostracan lineage and what this may mean for our understanding of brain functionality in Pancrustacea. 

   more » « less
4. Convergent evolution of optic lobe neuropil in Pancrustacea

   Nichola J. Strausfeld, Brianna Olea-Rowe (March 2021, Arthropod structure development)

   A prevailing opinion since 1926 has been that optic lobe organization in malacostracan crustaceans and insects reflects a corresponding organization in their common ancestor. Support for this refers to malacostracans and insects both possessing three, in some instances four, nested retinotopic neuropils beneath their compound eyes. Historically, the rationale for claiming homology of malacostracan and insect optic lobes referred to those commonalities, and to comparable arrangements of neurons. However, recent molecular phylogenetics has firmly established that Malacostraca belong to Multicrustacea, whereas Hexapoda and its related taxa Cephalocarida, Branchiopoda, and Remipedia belong to the phyletically distinct clade Allotriocarida. Insects are more closely related to remipedes than are either to malacostracans. Reconciling neuroanatomy with molecular phylogenies has been complicated by studies showing that the midbrains of remipedes share many attributes with the midbrains of malacostracans. Here we review the organization of the optic lobes in Malacostraca and Insecta to inquire which of their characters correspond genealogically across Pancrustacea and which characters do not. We demonstrate that neuroanatomical characters pertaining to the third optic lobe neuropil, called the lobula complex, may indicate convergent evolution. Distinctions of the malacostracan and insect lobula complexes are sufficient to align neuroanatomical descriptions of the pancrustacean optic lobes within the constraints of molecular-based phylogenies. 

   more » « less
5. An audio‐based risky flight detection framework for quadrotors

   https://doi.org/10.1049/csy2.12105  

   Liu, Wansong; Liu, Chang; Sajedi, Seyedomid; Su, Hao; Liang, Xiao; Zheng, Minghui (January 2024, IET Cyber-Systems and Robotics)

   Abstract Drones have increasingly collaborated with human workers in some workspaces, such as warehouses. The failure of a drone flight may bring potential risks to human beings' life safety during some aerial tasks. One of the most common flight failures is triggered by damaged propellers. To quickly detect physical damage to propellers, recognise risky flights, and provide early warnings to surrounding human workers, a new and comprehensive fault diagnosis framework is presented that uses only the audio caused by propeller rotation without accessing any flight data. The diagnosis framework includes three components: leverage convolutional neural networks, transfer learning, and Bayesian optimisation. Particularly, the audio signal from an actual flight is collected and transferred into time–frequency spectrograms. First, a convolutional neural network‐based diagnosis model that utilises these spectrograms is developed to identify whether there is any broken propeller involved in a specific drone flight. Additionally, the authors employ Monte Carlo dropout sampling to obtain the inconsistency of diagnostic results and compute the mean probability score vector's entropy (uncertainty) as another factor to diagnose the drone flight. Next, to reduce data dependence on different drone types, the convolutional neural network‐based diagnosis model is further augmented by transfer learning. That is, the knowledge of a well‐trained diagnosis model is refined by using a small set of data from a different drone. The modified diagnosis model has the ability to detect the broken propeller of the second drone. Thirdly, to reduce the hyperparameters' tuning efforts and reinforce the robustness of the network, Bayesian optimisation takes advantage of the observed diagnosis model performances to construct a Gaussian process model that allows the acquisition function to choose the optimal network hyperparameters. The proposed diagnosis framework is validated via real experimental flight tests and has a reasonably high diagnosis accuracy. 

   more » « less