End Nodes Research Articles

Developing a Grover's quantum algorithm emulator on standalone FPGAs: optimization and implementation

<p>Quantum computing (QC) leverages superposition, entanglement, and parallelism to solve complex problems that are challenging for classical computing methods. The immense potential of QC has spurred explosive interest and research in both academia and industry. However, the practicality of QC based on large-scale quantum computers remains limited by issues of scalability and error correction. To bridge this gap, QC emulators utilizing classical computing resources have emerged, with modern implementations employing FPGAs for efficiency. Nevertheless, FPGA-based QC emulators face significant limitations, particularly in standalone implementations required for low-power, low-performance devices like IoT end nodes, embedded systems, and wearable devices, due to their substantial resource demands. This paper proposes optimization techniques to reduce resource requirements and enable standalone FPGA implementations of QC emulators. We specifically focused on Grover's algorithm, known for its excellent performance in searching unstructured databases. The proposed resource-saving optimization techniques allow for the emulation of the largest possible Grover's algorithm within the constrained resources of FPGAs. Using these optimization techniques, we developed a hardware accelerator for Grover's algorithm and integrated it with a RISC-V processor architecture. We completed a standalone Grover's algorithm-specific emulator operating on FPGAs, demonstrating significant performance enhancements and resource savings afforded by the proposed techniques.</p>

1177Optimized Energy Utilization in Cognitive Radio Networkswith Congestion Control

Various real-time applications can be handled through wireless sensor networks, which consist of a wide range of sensor nodes. A novel congestion control mechanism is proposed on optimized rates for energy-efficient transmissions. To reduce energy consumption across the network, a rate-based congestion control algorithm based on cluster routing is presented. By reducing the end-to-end delay, rate control improves the network life time over a large simulation period. Clustering is initially performed using novel routing algorithms. After that, rate control is implemented using an energy optimization strategy suitable for high packet delivery ratios. Finally, packets are sent with maximum throughput using regionOptimization-driven routing. The simulation is performed on the NS2 simulation platform. Finally, performances are evaluated with respect to average delay in end to end nodes, delivery ratio ofpackets, throughput, energy efficiency, energy consumption and reliability. Novel routing with an energy optimal algorithm (NREOA) reduces energy consumption as the network progresses and a variation of 20% compared with existing protocols.

Networks method of hybrid construction and support of data transmission routes in programmed tools of mobile radio communication based on neural networks

The article proposes a method of hybrid construction and support of data transmission routes in programmable means of mobile radio communication based on neural networks. Taking into account the peculiarities of the operation of mobile radio communication networks and means of communication, the article proposes to intellectualize the processes of managing data flows by using knowledge processing technologies in the construction of a control system. The construction of the control system is based on the use of neural networks, the methodology proposes three main steps of its construction, namely the method of hybrid construction of data transmission routes, the method of maintaining data transmission routes and modeling the process of construction and maintenance of data transmission routes in the network using neural networks. Unlike similar methods, which: are used in stationary communication networks with a small number of end nodes, without the possibility of monitoring the functions of data transmission routes; which are characterized by the absence of a clear decision-making hierarchy and the presence of unpredictability when applied in data transmission systems of mobile radio communication networks; do not take into account the peculiarities of the functioning of mobile radio communications. The proposed technique is able to build data transmission routes, increases the time of network operation and reduces the loading of network channels based on the application of a hybrid structure of neural network construction, by minimizing service traffic in the information direction; selection of the type, number and method of control of data transmission routes; introduction of the hierarchy of the decision-making process for the construction of the data transmission route and the selection of data parameters, taking into account the characteristic features of the use of programmable mobile communication tools to ensure the given quality of network service under different conditions of operation of mobile radio communication tools, using neural networks.

LoRaWAN end device disaggregation and decomposition by means of lightweight virtualization

The LoRaWAN infrastructure has been designed to allow easy implementation of backends in mixed IoT scenario with both on premise and cloud servers. Some very popular providers offer the LoRaWAN backend in the form of SaaS, or the user can install containerized versions of the backends into his/her own servers. In this paper, the containerization of LoRaWAN end node is discussed, addressing different architectures for disaggregating the tasks and decomposing the stack levels from the hardware. Such an analysis leads to the introduction of a new fully virtual end node, that paves the way to innovative use of the LoRaWAN backend. The proposed container-based architecture is then applied to some general IoT use cases, which have been setup using a commercial, industrial-grade, framework for the experimental phase. The experimental evaluation, based on purposely defined metrics, takes into account the latency in transferring data among the different stack level and backend components. The focus is on comparing the performance of the proposed architecture in the diverse use cases, and on giving a clear overview of advantages and disadvantages of the possible choices. For instance, noticeable differences emerged when comparing containerization running directly on Operating System vs. containerization running inside virtual machine. Finally, a discussion about the use of the proposed solution for increasing LoRaWAN capabilities in terms of flexibility and performance (e.g., by means of multiple end nodes leveraging a single radio for redundancy purpose) is carried out.

Substantiation of the methodology for calculation of rope-capacity cylindrical drums of mine hoistmachine

Purpose. To develop a simplified calculation method for the strengthened split cylindrical drums of mine hoisting machines of the TsR-6.75x6.2/1.95 type. To evaluate the application of the method for calculating the drum of a hoisting machine of a complicated design by averaging the elements. The methods. The drum structure of a mine hoisting machine is divided into ten nodes, eight of which include the shell, frontal, rib strengthening and brake discs (end nodes) and two more – the shaftwith hubs and bearing supports. Based on the analysis of the machine's operation, including an assessment of its stiffness under different types of load, simplified models are created for each component. The original drum assemblies are replaced with simplified ones in order to perform a general calculation to determine the maximum axial displacement of the brake disc edges. Findings. Based on the analysis of the mine hoisting machine operation, averaged models of hoist components were developed and axial displacements were successfully calculated for a simplified drum design. The originality. The error of the simplified calculation method, in particular, the method of averaging with increased thickness of the lobes, which allows obtaining more accurate results for complex structures, is estimated Practical implementation. Due to the need to increase the depth of mining, which leads to the need to expand the dimensions of the drum and complicate its design. In this case, the resource intensity of calculating the axial displacement of brake discs increases. This is necessary for the introduction of disc brakes. However, this complicates the use of standard mid-level computer-aided design tools due to the increase in the size of the finite element mesh, which makes its use impractical. The methodology can be used for mine hoisting machines of the following types TsR-6.75x6.2/1.95 with a split drum, 6750 mm in diameter and 6200 mm wide (of which 1950 mm is the interchangeable part), providing accurate calculations of brake disc edge displacements. This approach is particularly useful for use in mid-range software packages such as SolidWorks Simulation, eliminating the need for resource-intensive software.

Unsupervised GAN-Based Intrusion Detection System Using Temporal Convolutional Networks and Self-Attention

Fifth-generation (5G) networks provide connectivity to a massive number of devices and boost a plethora of applications in several different domains. However, the large adoption of connected devices increases attack surfaces and introduces several security threats that can severely damage physical objects and risk people’s lives. Despite existing intrusion detection systems (IDSs), there are still several challenges to be addressed in the detection of cyber-attacks. For instance, while unsupervised IDSs are required to detect zero-day attacks, they usually present high false positive rates. Moreover, most existing IDSs rely on long short-term memory (LSTM) networks to consider time-dependencies among data. However, LSTM networks have recently been shown to present several drawbacks and limitations, which put into question their performance on sequence modeling tasks. Thus, in this paper, we investigate generative adversarial networks (GANs), a promising unsupervised approach to detecting attacks by implicitly modeling systems, and alternatives to LSTM networks to consider temporal dependencies among data. We propose a novel unsupervised GAN-based IDS that uses temporal convolutional networks (TCNs) and self-attention to detect cyber-attacks. The proposed IDS leverages edge computing and is proposed for edge servers, which bring computation resources closer to end nodes. Experiment results show that our proposed IDS can be configured to satisfy different detection rate and detection time requirements. Moreover, they show that our IDS is more accurate and at least 3.8 times faster than two state-of-the-art GAN-based IDSs that are used as baselines.

Beacon Success Rate versus Gateway Density in Sub-GHz Sensor Networks

Multiple Gateways (GWs) provide network connectivity to Internet of Things (IoT) sensors in a Wide Area Network (WAN). The End Nodes (ENs) can connect to any GW by discovering and acquiring its periodic beacons. This provides GW diversity, improving coverage area. However, simultaneous periodic beacon transmissions among nearby GWs lead to interference and collisions. In this study, the impact of such intra-network interference is analyzed to determine the maximum number of GWs that can coexist. The paper presents a new collision model that considers the combined effects of the Medium Access Control (MAC) and Physical (PHY) layers. The model takes into account the partial overlap durations and relative power of all colliding events. It also illustrates the relationship between the collisions and the resulting packet loss rates. A performance evaluation is presented using a combination of analytical and simulation methods, with the former validating the simulation results. The system models are developed from experimental data obtained from field measurements. Numerical results are provided with Gaussian Frequency Shift Keying (GFSK) modulation. This paper provides guidance on selecting GFSK modulation parameters for low bit-rate and narrow-bandwidth IoT applications. The analysis and simulation results show that larger beacon intervals and frequency hopping help in reducing beacon loss rates, at the cost of larger beacon acquisition latency. On the flip side, the gateway discovery latency reduces with increasing GW density, thanks to an abundance of beacons.

Hybrid Integrated Computing Algorithm for Sustainable Tourism

To avoid destroying the natural environment, we can create tourist paths without disrupting ecological systems or rare places such as rainforests that contain endangered species. Likewise, in sustainable tourism, we should consider visiting national parks or national museums as a way to understand the core values and the meaning of that culture and environment more clearly. In this paper, we consider which points tourists need to avoid or visit for sustainable tourism. We designed an algorithm that can give a path to avoid certain points or to go to a preferred point. If this algorithm does not give any weight, it will give the shortest path from the start to the end, and it can decide which vertices to avoid or travel to. Moreover, it can be used to vary the weights of different positive or negative values to obtain a path to avoid a point or to reach a point. Compared to Dijkstra’s algorithm, we can add a negative weight to the graph and still find the shortest path. In application, it can be used for path schedule decisions. We did not wave the large resources to calculate the walk length. In the usage scenario, users only need to provide the starting node, end node, avoidance point, and facing point to calculate the best path. This algorithm will give a good path for users. At the same time, users can use this algorithm to implement sustainable travel route planning, such as going to museums, avoiding rare environments, etc. So, this algorithm provides a new way to decide the best path. Finally, the experimental results show that the classic algorithms cannot avoid points. In real tourism, tourists can use this algorithm for travel planning to achieve sustainable tourism.

Implementation of LoRa Wireless Communication in Smart Diabetic Shoes Design

Diabetes is a widespread medical condition affecting a substantial portion of the global population. It is a metabolic disorder known as diabetes mellitus, characterized by severe fluctuations in blood glucose levels due to inadequate insulin production in the human body. The effective monitoring of diabetes is of paramount importance to researchers as it holds the potential to enhance the quality of healthcare services. Among the challenges faced by individuals with diabetes, one prevalent issue is the development of ulcers, which can be challenging to detect promptly. Technological advancements offer a promising avenue for cost-effective and continuous monitoring of chronic diseases like diabetes. This study centers on the development of IoT-based intelligent diabetic footwear that incorporates pressure sensors and temperature monitoring for individuals with diabetic feet. In the evaluation of SX1278 (Ra-02) Lora Module communication, deployed at eight different locations, it was observed that two of these points achieved a flawless transmission success rate of 100%. Conversely, the communication failed at points 6 and 7, with a success rate falling below 50%. Some of these failures can be attributed to signal obstructions, including natural elements such as trees and terrain, as well as man-made structures like buildings and machinery workshops, which hinder the efficient transmission of signals from the end node to the gateway. The results of this research provide positive implications in the form of developing IoT-based diabetes shoes that can be applied with alternative Lora communication connections in areas with poor internet signal.

Internet-of-Things framework for scalable end-of-life condition monitoring in remanufacturing

The worldwide generation of waste electrical and electronic equipment is continuously growing, with electric vehicle batteries reaching their end-of-life having become a key concern for both the environment and human health in recent years. In this context, the proliferation of Internet of Things standards and data ecosystems is advancing the feasibility of data-driven condition monitoring and remanufacturing. This is particularly desirable for the end-of-life recovery of high-value equipment towards sustainable closed-loop production systems. Low-Power Wide-Area Networks, despite being relatively recent, are starting to be conceived as key-enabling technologies built upon the principles of long-range communication and negligible energy consumption. While LoRaWAN is considered the open standard with the highest level of acceptance from both industry and academia, it is its random access protocol (Aloha) that limits its capacity in large-scale deployments to some extent. Although time-slotted scheduling has proved to alleviate certain scalability limitations, the constrained nature of end nodes and their application-oriented requirements significantly increase the complexity of time-slotted network management tasks. To shed light on this matter, a multi-agent network management system for the on-demand allocation of resources in end-of-life monitoring applications for remanufacturing is introduced in this work. It leverages LoRa’s spreading factor orthogonality and network-wide knowledge to increase the number of nodes served in time-slotted monitoring setups. The proposed system is validated and evaluated for end-of-life monitoring where two representative end-node distributions were emulated, with the achieved network capacity improvements ranging from 75.27% to 249.46% with respect to LoRaWAN’s legacy operation. As a result, the suitability of different agent-based strategies has been evaluated and a number of lessons have been drawnaccording to different application and hardware constraints. While the presented findings can be used to further improve the explainability of the proposed models (in line with the concept of eXplainable AI), the overall framework represents a step forward in lightweight end-of-life condition monitoring for remanufacturing.

Inhibitory influence of supply chain digital transformation on bullwhip effect feedback difference

PurposeThis paper breaks through the limitations of the research on bullwhip effect in the traditional supply chain, extends the research perspective to digital supply chain and discusses the weakening effect of digital supply chain on bullwhip effect by comparing the overall performance of the two.Design/methodology/approachThis paper starts with the weakening mechanism of supply chain digitization on bullwhip effect, builds bullwhip effect models of traditional supply chain and digital supply chain, respectively, simulates the influence of supply chain digitization transformation on bullwhip effect by using Matlab software and analyzes the causes of bullwhip effect in supply chain led by T company and the digitization process.FindingsFirstly, digitization can reduce bullwhip effect in multi-level supply chain by reducing information feedback deviation. Second, digital transformation is conducive to improving the overall performance of the supply chain. Third, government incentives can promote the digital transformation of supply chain and inhibit bullwhip effect.Research limitations/implicationsAlthough the study considers the heterogeneous subject -- the government's incentive effect on digital transformation and information sharing – it does not include the influence of the end node in the supply chain, that is the consumer. In addition, this paper only analyzes and discusses the bullwhip effect on the amplification of demand, without considering the situation that the market contraction will lead to the reduction of demand.Practical implicationsThis paper considers the distortion degree and delay degree of information feedback, carries out quantitative analysis of bullwhip effect, builds the bullwhip effect model of traditional supply chain and digital supply chain, uses Matlab software to analyze the difference of the influence of supply chain digital transformation on bullwhip effect suppression and puts forward the corresponding control strategy.Social implicationsThe research shows that digital transformation can reduce the bullwhip effect in multi-layer supply chain by reducing the information feedback deviation, which is conducive to improving the overall supply chain performance, and government support can accelerate the digital transformation of supply chain to a certain extent.Originality/valueFirst, break through the limitations of traditional supply chain research, expand the research perspective to digital supply chain and discuss the weakening effect of digital supply chain on bullwhip effect by comparing the overall performance of the two. Second, quantify the bullwhip effect through information feedback bias and provide an analysis method for the weakening of the bullwhip effect. Third, the driving role of the government in the digital transformation of the supply chain is considered in the study, so that the model is more close to the actual situation of enterprise operation.

Exploration of transferable deep learning-aided radio frequency fingerprint identification systems

Radio frequency fingerprint identification (RFFI) shows great potential as a means for authenticating wireless devices. As RFFI can be addressed as a classification problem, deep learning techniques are widely utilized in modern RFFI systems for their outstanding performance. RFFI is suitable for securing the legacy existing Internet of Things (IoT) networks since it does not require any modifications to the existing end-node hardware and communication protocols. However, most deep learning-based RFFI systems require the collection of a great number of labelled signals for training, which is time-consuming and not ideal, especially for the IoT end nodes that are already deployed and configured with long transmission intervals. Moreover, the long time required to train a neural network from scratch also limits rapid deployment on legacy IoT networks. To address the above issues, two transferable RFFI protocols are proposed in this paper leveraging the concept of transfer learning. More specifically, they rely on fine-tuning and distance metric learning, respectively, and only require only a small amount of signals from the legacy IoT network. As the dataset used for transfer is small, we propose to apply augmentation in the transfer process to generate more training signals to improve performance. A LoRa-RFFI testbed consisting of 40 commercial-off-the-shelf (COTS) LoRa IoT devices and a software-defined radio (SDR) receiver is built to experimentally evaluate the proposed approaches. The experimental results demonstrate that both the fine-tuning and distance metric learning-based RFFI approaches can be rapidly transferred to another IoT network with less than ten signals from each LoRa device. The classification accuracy is over 90%, and the augmentation technique can improve the accuracy by up to 20%.

Algorithm for ensuring the minimum power consumption of the end node in the LoRaWAN network

Algorithm for ensuring the minimum power consumption of the end node in the LoRaWAN network

Distributed economic forecasting system and its application in rural revitalization

AbstractCompared with the city, the rural area is large and the associated population disperses. Therefore, it needs to design a distributed scheme to collect and analysis the economic data. The federated learning can handle the economic data from different rural areas to protect primal economic data. This paper utilizes federated learning for economic forecasting which plays a very important role in rural revitalization. The proposed economic forecasting system consists of two parts: end nodes and cloud center. An end node is deployed in a village. The economic data of village is encrypted and villages only can communicate with other using encrypted data to avoid the leakage of primal data. The cloud center utilizes federated learning to jointly optimize the models in end nodes. During the processing of optimization, the transition between cloud center and end nodes is encrypted as well. The distributed economic forecasting system is evaluated on real data and achieves the expected results.

Design of an Autonomous IoT Node Powered by a Perovskite-Based Wave Energy Converter

Abstract This paper presents the results of experimental research focused on wave energy harvesting and its conversion to power Internet of Things (IoT) devices. The harvesting and conversion process was performed using a wave energy converter (WEC) consisting of a lead zirconate titanate piezoelectric ceramic perovskite material and a prototype power electronic circuit. The designed WEC was considered as a power supply for an end node device (END) of an IoT network. The END consisted of a long-range radio module and an electronic paper display. A set of physical experiments were carried out, and the results confirmed that an energy surplus was supplied by WEC compared to the energy consumed by the END. Hence, the proposed scheme was experimentally validated as a convenient solution that could enable the autonomous operation of an IoT device. The use case presented here for the proposed WEC was analysed for selected sea areas on the basis of wave statistics. The novelty of this paper arises from an investigation that confirms that WECs can significantly contribute to the development of wireless and mobile IoT communication powered by freely available sea wave energy.

Unveiling LoRa's Oceanic Reach: Assessing the Coverage of the Azores LoRaWAN Network from an Island.

In maritime settings, effective communication between vessels and land infrastructure is crucial, but existing technologies often prove impractical for energy-sensitive IoT applications, like deploying sensors at sea. In this study, we explore the viability of a low-power, cost-effective wireless communication solution for maritime sensing data. Specifically, we conduct an experimental assessment of the Azorean Long Range Wide Area Network (LoRaWAN) coverage. Our tests involve positioning the gateway at the island's highest point and installing end nodes on medium-sized fishing vessels. Through measurements of received signal strength indicator (RSSI), signal-to-noise ratio (SNR), and lines of sight (LOS), we showcase the potential of LoRaWAN transmissions to achieve communication distances exceeding 130 km in a LOS-free scenario over the ocean. These findings highlight the promising capabilities of LoRaWAN for reliable and long-range maritime communication of sensing data.

An Efficient Adaptive Data-Link-Layer Architecture for LoRa Networks

LoRa is one of the most popular low-power wireless network technologies for implementation of the Internet of Things, with the advantage of providing long-range communication, but lower data rates, when compared with technologies such as Zigbee or Bluetooth. LoRa is a single-channel physical layer technology on top of which LoRaWAN implements a more complex multi-channel network with enhanced functionalities, such as adaptive data rate. However, LoRaWAN relies on expensive hardware to support these functionalities. This paper proposes a LoRa data-link-layer architecture based on a multi-layer star network topology that adapts relevant LoRa parameters for each end node dynamically taking into account its link distance and quality in order to balance communication range and energy consumption. The developed solution is comprised of multiple components, including a LoRa parameter calculator to help the user to configure the network parameters, a contention-free MAC protocol to avoid collisions, and an adaptive spreading factor and transmission power mechanism. These components work together to ensure a more efficient use of the chosen ISM band and end node resources, but with low-cost implementation and operation requirements.

Machine learning decision tree models for multiclass classification of common malignant brain tumors using perfusion and spectroscopy MRI data.

To investigate the contribution of machine learning decision tree models applied to perfusion and spectroscopy MRI for multiclass classification of lymphomas, glioblastomas, and metastases, and then to bring out the underlying key pathophysiological processes involved in the hierarchization of the decision-making algorithms of the models. From 2013 to 2020, 180 consecutive patients with histopathologically proved lymphomas (n = 77), glioblastomas (n = 45), and metastases (n = 58) were included in machine learning analysis after undergoing MRI. The perfusion parameters (rCBVmax, PSRmax) and spectroscopic concentration ratios (lac/Cr, Cho/NAA, Cho/Cr, and lip/Cr) were applied to construct Classification and Regression Tree (CART) models for multiclass classification of these brain tumors. A 5-fold random cross validation was performed on the dataset. The decision tree model thus constructed successfully classified all 3 tumor types with a performance (AUC) of 0.98 for PCNSLs, 0.98 for GBM and 1.00 for METs. The model accuracy was 0.96 with a RSquare of 0.887. Five rules of classifier combinations were extracted with a predicted probability from 0.907 to 0.989 for that end nodes of the decision tree for tumor multiclass classification. In hierarchical order of importance, the root node (Cho/NAA) in the decision tree algorithm was primarily based on the proliferative, infiltrative, and neuronal destructive characteristics of the tumor, the internal node (PSRmax), on tumor tissue capillary permeability characteristics, and the end node (Lac/Cr or Cho/Cr), on tumor energy glycolytic (Warburg effect), or on membrane lipid tumor metabolism. Our study shows potential implementation of machine learning decision tree model algorithms based on a hierarchical, convenient, and personalized use of perfusion and spectroscopy MRI data for multiclass classification of these brain tumors.

Experimental Study on the New Type of Connecting Nodes of Prefabricated Stairs Using Flexible Grouting Material

In recent years, prefabricated buildings have been developing positively in China. Prefabricated concrete stairs are widely used in prefabricated concrete buildings because of their quick construction, convenient handling, reduced cost, and premium appearance. They also have promising application potential in cast-in-place concrete structures and steel buildings. The stairs are important escape routes during earthquakes and play the role of “safety islands.” Therefore, the study on the seismic performance of connecting nodes of prefabricated concrete stairs is significant. For a new flexible-hinge connecting node of the prefabricated stairs with flexible grouting material (FGM), the low-frequency cyclic loading test is carried out in this paper to study the stress performance of the end nodes of the stairs under in-plane and out-of-plane low-frequency cyclic loading. The results show that the new flexible-hinge connecting nodes of the prefabricated concrete stairs have moderate bearing capacity and stiffness, which can mitigate the effect of diagonal bracing under small and medium earthquakes and dissipate energy to a certain extent.

Predicted connectivity pathways between grizzly bear ecosystems in Western Montana

Habitat and corridor mapping are key components of many conservation programs. Grizzly bear populations in the continental US are fragmented and connectivity among federal recovery areas is a conservation goal. Building on recent work, we modeled movements to predict areas of connectivity, using integrated step selection functions (iSSFs) developed from GPS-collared grizzly bears (F = 46, M = 19) in the Northern Continental Divide Ecosystem (NCDE). We applied iSSFs in a >300,000 km2 area including the NCDE, Cabinet–Yaak (CYE), Bitterroot (BE), and Greater Yellowstone (GYE) Ecosystems. First, we simulated directed movements (randomized shortest paths with 3 levels of exploration) between start and end nodes across populations. Second, we simulated undirected movements from start nodes in the NCDE, CYE, or GYE (no predetermined end nodes). We summarized and binned results as classes 1 (lowest relative predicted use) – 10 (highest relative predicted use) and evaluated predictions using 127 outlier grizzly bear locations. Connectivity pathways were primarily associated with mountainous areas and secondarily with river and stream courses in open valleys. Values at outlier locations indicated good model fit and mean classes at outlier locations (≥7.4) and Spearman rank correlations (≥0.87) were highest for undirected simulations and directed simulations with the highest level of exploration. Our resulting predictive maps can facilitate on-the-ground application of this research for prioritizing habitat conservation, human-bear conflict mitigation, and transportation planning. Additionally, our overall modeling approach has utility for myriad species and conservation applications.