We show that pretrained acoustic embeddings classify elephant vocalisations at a level approaching that of end-to-end supervised neural networks, without any fine-tuning of the embedding model. This result is of practical importance because annotated bioacoustic data are scarce and costly to obtain, leaving conventional supervised approaches prone to overfitting and to poor generalisation under domain shift. A broad range of embedding models drawn from general audio, speech, and bioacoustic domains is evaluated, all of which are either out-of-domain (containing no bioacoustic data) or out-of-species (containing no elephant call data). The embedding networks themselves remain fixed; only the lightweight downstream classifiers, which include a linear model and several small neural networks, are trained. Among the models considered, Perch 2.0 achieves the best cross-validated classification performance, attaining AUCs of 0.849 on African bush elephant (Loxodonta africana) calls and 0.936 on Asian elephant (Elephas maximus) calls, with Perch 1.0 close behind. The best-performing system is within 2.2 % of an end-to-end supervised elephant call classification system. A layerwise analysis
We consider a generalization of the so-called elephant random walk by introducing multiple elephants moving along the integer line, $\mathbb{Z}$. When taking a new step, each elephant considers not only its own previous steps but also the past steps of other elephants. The dynamics of "who follows whom" are governed by a directed graph, where each vertex represents an elephant, and the edges indicate that an elephant will consider the past steps of its in-neighbour elephants when deciding its next move. In other words, this model involves a collection of reinforced random walks evolving through graph-based interactions. We briefly investigate the first- and second-order asymptotic behaviour of the joint walks and establish connections with other network-based reinforced stochastic processes studied in the literature. We show that the joint walk can be expressed as a stochastic approximation scheme. In certain regimes, we employ tools from stochastic approximation theory to derive the asymptotic properties of the joint walks. Additionally, in a specific regime, we use better techniques to establish a strong invariance principle and a central limit theorem with improved rates compare
In this paper, we study the number of moves in a multidimensional elephant random walk with stops. We establish several convergence results for the number of moves, including the law of large numbers and the law of iterated logarithm. Using a martingale approach, we study the multidimensional elephant random walk with random step sizes. For this model, we obtain several almost sure convergence results for the number of moves, including the law of large numbers, the quadratic strong law, the law of iterated logarithm and the central limit theorem. Similar convergence results are derived for the multidimensional elephant random walk with random step sizes.
Detecting elephants through seismic signals is an emerging research topic aimed at developing solutions for Human-Elephant Conflict (HEC). Despite the promising results, such solutions heavily rely on manual classification of elephant footfalls, which limits their applicability for real-time classification in natural settings. To address this limitation and build on our previous work, this study introduces a classification framework targeting resource-constrained implementations, prioritizing both accuracy and computational efficiency. As part of this framework, a novel event detection technique named Contextually Customized Windowing (CCW), tailored specifically for detecting elephant footfalls, was introduced, and evaluations were conducted by comparing it with the Short-Term Average/Long-Term Average (STA/LTA) method. The yielded results show that the maximum validated detection range was 155.6 m in controlled conditions and 140 m in natural environments. Elephant footfall classification using Support Vector Machine (SVM) with a Radial Basis Function (RBF) kernel demonstrated superior performance across multiple settings, achieving an accuracy of 99% in controlled environments,
The logarithmic spiral is observed as a common pattern in several living beings across kingdoms and species. Some examples include fern shoots, prehensile tails, and soft limbs like octopus arms and elephant trunks. In the latter cases, spiraling is also used for grasping. Motivated by how this strategy simplifies behavior into kinematic primitives and combines them to develop smart grasping movements, this work focuses on the elephant trunk, which is more deeply investigated in the literature. We present a soft arm combined with a rigid robotic system to replicate elephant grasping capabilities based on the combination of a soft trunk with a solid body. In our system, the rigid arm ensures positioning and orientation, mimicking the role of the elephant's head, while the soft manipulator reproduces trunk motion primitives of bending and twisting under proper actuation patterns. This synergy replicates 9 distinct elephant grasping strategies reported in the literature, accommodating objects of varying shapes and sizes. The synergistic interaction between the rigid and soft components of the system minimizes the control complexity while maintaining a high degree of adaptability.
We consider a two-elephant walking model in which the elephants interact dynamically. At each time step, each elephant determines its next move randomly based on its partner's past movements. We show that the asymptotic behavior of the elephants mainly depends on the sign and the absolute value of the product of their reinforcement parameters. In various regimes, we establish the law of large numbers and the central limit theorem. Our proofs are based on a connection to the random recursive trees and employ stochastic approximation techniques and martingale methods.
We study the gambler's ruin problem for the Elephant Random Walk, focusing on escape time from a symmetric interval of the form $\{-N, \ldots, N\}$. As our main result, we derive tight exponential bounds for the tail of this escape time. We then illustrate the usefulness of such bounds by proving that, in the diffusive regime, the Elephant's average behavior mirrors that of the traditional symmetric random walk: the expected escape time grows quadratically with $N$.
The interaction between elephants and their environment has profound implications for both ecology and conservation strategies. This study presents an analytical approach to decipher the intricate patterns of elephant movement in Sub-Saharan Africa, concentrating on key ecological drivers such as seasonal variations and rainfall patterns. Despite the complexities surrounding these influential factors, our analysis provides a holistic view of elephant migratory behavior in the context of the dynamic African landscape. Our comprehensive approach enables us to predict the potential impact of these ecological determinants on elephant migration, a critical step in establishing informed conservation strategies. This projection is particularly crucial given the impacts of global climate change on seasonal and rainfall patterns, which could substantially influence elephant movements in the future. The findings of our work aim to not only advance the understanding of movement ecology but also foster a sustainable coexistence of humans and elephants in Sub-Saharan Africa. By predicting potential elephant routes, our work can inform strategies to minimize human-elephant conflict, effectively
In this report, we introduce the elephant random walk on the triangular lattice over $R^2$ incorporating directions by extending the model developed in \cite{baur2016elephant}. We study the behavior of the walk by finding the appropriate scaling limits. This model was studied as a part of my Master of Statistics, 2018 final year dissertation at Indian Statistical Institute, Kolkata.
The goal of this paper is to investigate the asymptotic behavior of the multidimensional elephant random walk with stops (MERWS). In contrast with the standard elephant random walk, the elephant is allowed to stay on his own position. We prove that the Gram matrix associated with the MERWS, properly normalized, converges almost surely to the product of a deterministic matrix, related to the axes on which the MERWS moves uniformly, and a Mittag-Leffler distribution. It allows us to extend all the results previously established for the one-dimensional elephant random walk with stops. More precisely, in the diffusive and critical regimes, we prove the almost sure convergence of the MERWS. In the superdiffusive regime, we establish the almost sure convergence of the MERWS, properly normalized, to a nondegenerate random vector. We also study the self-normalized asymptotic normality of the MERWS.
Human-wildlife conflict challenges conservation worldwide, which requires innovative management solutions. We developed a prototype Agent-Based Model (ABM) to simulate interactions between humans and solitary bull Asian elephants in the Periyar-Agasthyamalai complex of the Western Ghats in Kerala, India. The main challenges were the complex behavior of elephants and insufficient movement data from the region. Using literature, expert insights, and field surveys, we created a prototype behavior model that incorporates crop habituation, thermoregulation, and aggression. We designed a four-step calibration method to adapt relocation data from radio-tagged elephants in Indonesia to model elephant movements in the model domain. The ABM's structure, including the assumptions, submodels, and data usage are detailed following the Overview, Design concepts, Details protocol. The ABM simulates various food availability scenarios to study elephant behavior and environmental impact on space use and conflict patterns. The results indicate that the wet months increase conflict and thermoregulation significantly influences elephant movements and crop raiding. Starvation and crop habituation inten
This paper is concerned with a stochastic linear-quadratic leader-follower differential game with elephant memory. The model is general in that the state equation for both the leader and the follower includes the elephant memory of the state and the control, which are part of the diffusion term. Under certain assumptions, the state feedback representation of the open-loop Stackelberg strategy is derived by introducing two Riccati equations and a special matrix-valued equation. Finally, theoretical results are illustrated by means of an example concerning a dynamic advertising problem with elephant memory.
Cortisol, corticosterone and aldosterone activate full-length glucocorticoid receptor (GR) from elephant shark, a cartilaginous fish belonging to the oldest group of jawed vertebrates. Activation by aldosterone a mineralocorticoid, indicates partial divergence of elephant shark GR from the MR. Progesterone activates elephant shark MR, but not elephant shark GR. Progesterone inhibits steroid binding to elephant shark GR, but not to human GR. Deletion of the N-terminal domain (NTD) from elephant shark GR (Truncated GR) reduced the response to corticosteroids, while truncated and full-length elephant shark MR had similar responses to corticosteroids. Chimeras of elephant shark GR NTD fused to MR DBD+LBD had increased activation by corticosteroids and progesterone compared to full-length elephant shark MR. Elephant shark MR NTD fused to GR DBD+LBD had similar activation as full-length elephant shark MR, indicating that activation of human GR by the NTD evolved early in GR divergence from the MR.
Keratin composites enable animals to hike with hooves, fly with feathers, and sense with skin. These distinct functions arise from variations in the underlying properties and microscale arrangement of this natural polymer. One well-studied example is mammalian whiskers, elongated keratin rods attached to tactile skin structures that extend the animal's sensory volume. Here, we investigate the non-actuated whiskers that cover Asian elephant (Elephas maximus) trunks and find they are geometrically and mechanically tailored to facilitate tactile perception by encoding contact location in vibrotactile signal amplitude and frequency. Elephant whiskers emerge from armored trunk skin and shift from a thick, circular, porous, stiff root to a thin, ovular, dense, soft point. This smooth transition enables interaction with widely varying substrates, reduces wear, and increases the vibrotactile signal information generated during contact. The functionally graded geometry, porosity, and stiffness of elephant whiskers tune the neuromechanics of trunk touch, facilitating highly dexterous manipulation.
African elephants are vital to their ecosystems, but their populations are threatened by a rise in human-elephant conflict and poaching. Monitoring population dynamics is essential in conservation efforts; however, tracking elephants is a difficult task, usually relying on the invasive and sometimes dangerous placement of GPS collars. Although there have been many recent successes in the use of computer vision techniques for automated identification of other species, identification of elephants is extremely difficult and typically requires expertise as well as familiarity with elephants in the population. We have built and deployed a web-based platform and database for human-in-the-loop re-identification of elephants combining manual attribute labeling and state-of-the-art computer vision algorithms, known as ElephantBook. Our system is currently in use at the Mara Elephant Project, helping monitor the protected and at-risk population of elephants in the Greater Maasai Mara ecosystem. ElephantBook makes elephant re-identification usable by non-experts and scalable for use by multiple conservation NGOs.
We study how conditioning on the first $k$ steps, which we think of as training, affects the long-term behavior of the Elephant Random Walk. When the elephant is conditioned to be at position $k$ at time $k$, the first return time to the origin scales as $k^{(4-4p)/(3-4p)}$ in the diffusive regime, and grows exponentially in the critical regime. We loosely interpret this as a measurement of the rate at which the elephant forgets its training.
This research represents a pioneering application of automated pose estimation from drone data to study elephant behavior in the wild, utilizing video footage captured from Samburu National Reserve, Kenya. The study evaluates two pose estimation workflows: DeepLabCut, known for its application in laboratory settings and emerging wildlife fieldwork, and YOLO-NAS-Pose, a newly released pose estimation model not previously applied to wildlife behavioral studies. These models are trained to analyze elephant herd behavior, focusing on low-resolution ($\sim$50 pixels) subjects to detect key points such as the head, spine, and ears of multiple elephants within a frame. Both workflows demonstrated acceptable quality of pose estimation on the test set, facilitating the automated detection of basic behaviors crucial for studying elephant herd dynamics. For the metrics selected for pose estimation evaluation on the test set -- root mean square error (RMSE), percentage of correct keypoints (PCK), and object keypoint similarity (OKS) -- the YOLO-NAS-Pose workflow outperformed DeepLabCut. Additionally, YOLO-NAS-Pose exceeded DeepLabCut in object detection evaluation. This approach introduces a n
Elephant random walk is a special type of random walk that incorporates the memory of the past to determine its future steps. The probability of this walk taking a particular step (+1 or -1) at a time point, conditioned on the entire history, depends on a linear function of the proportion of steps of that type till that time point. In this work, we consider a generalization of the elephant random walk where we investigate how the dynamics of the random walk will change if we replace this linear function with a generic map satisfying some analytic conditions. We propose a new model, called the multidimensional generalized elephant random walk, that includes several variants of elephant random walk in one and higher dimensions and generalizations thereof. Using tools from the theory of stochastic approximation, we derive the asymptotic behavior of our model leading to newer results on the phase transition boundary between diffusive and non-diffusive regimes. In the process, we extend some results on one-dimensional stochastic approximation process, which can be of independent interest. We also mention a few open problems in this context.
We establish stable functional central limit theorems for scaled elephant random walks in the diffusive, critical, and superdiffusive cases using the martingale approach.
Motivated by the previous results by Coletti-de Lima-Gava-Luiz (2020) and Shiozawa (2022), we study the fluctuation of the dynamic elephant random walk in the superdiffusive case with a strong elephant component. Applying the martingale convergence theorem, we prove the Central Limit Theorem and the Law of Iterated Logarithm, where a random drift is subtracted from the process considered.