More Like this

1. BatCount: A software program to count moving animals

   https://doi.org/10.1371/journal.pone.0278012  

   Bentley, Ian; Kuczynska, Vona; Eddington, Valerie M.; Armstrong, Mike; Kloepper, Laura N. (March 2023, PLOS ONE)

   Sharma, Lalit Kumar (Ed.)

   One of the biggest challenges with species conservation is collecting accurate and efficient information on population sizes, especially from species that are difficult to count. Bats worldwide are declining due to disease, habitat destruction, and climate change, and many species lack reliable population information to guide management decisions. Current approaches for estimating population sizes of bats in densely occupied colonies are time-intensive, may negatively impact the population due to disturbance, and/or have low accuracy. Research-based video tracking options are rarely used by conservation or management agencies for animal counting due to the perceived training and elevated operating costs. In this paper, we present BatCount, a free software program created in direct consultation with end-users designed to automatically count bats emerging from cave roosts (historical populations 20,000–250,000) with a streamlined and user-friendly interface. We report on the software package and provide performance metrics for different recording habitat conditions. Our analysis demonstrates that BatCount is an efficient and reliable option for counting bats in flight, with performance hundreds of times faster than manual counting, and has important implications for range- and species-wide population monitoring. Furthermore, this software can be extended to count any organisms moving across a camera including birds, mammals, fish or insects. 

   more » « less
2. Leveraging MIMO Transmit Diversity for Channel-Agnostic Device Identification

   Nora Basha, Bechir Hamdaoui (January 2022, IEEE International Conference on Communications)

   The accurate identification of wireless devices is critical for enabling automated network access monitoring and authenticated data communication in large-scale networks; e.g., IoT networks. RF fingerprinting has emerged as a potential solution for device identification by leveraging the transmitter unique manufacturing impairments of the RF components. Although deep learning is proven efficient in classifying devices based on the hardware impairments, trained models perform poorly due to channel variations. That is, although training and testing neural networks using data generated during the same period achieve reliable classification, testing them on data generated at different times degrades the accuracy substantially. To the best of our knowledge, we are the first to propose to leverage MIMO capabilities to mitigate the channel effect and provide a channelresilient device classification. For the proposed technique we show that, for Rayleigh channels, blind partial channel estimation enabled by MIMO increases the testing accuracy by up to 40% when the models are trained and tested over the same channel, and by up to 60% when the models are tested on a channel that is different from that used for training. 

   more » « less
3. On the relationship between predictive coding and backpropagation

   https://doi.org/10.1371/journal.pone.0266102  

   Rosenbaum, Robert (March 2022, PLOS ONE)

   Cymbalyuk, Gennady S. (Ed.)

   Artificial neural networks are often interpreted as abstract models of biological neuronal networks, but they are typically trained using the biologically unrealistic backpropagation algorithm and its variants. Predictive coding has been proposed as a potentially more biologically realistic alternative to backpropagation for training neural networks. This manuscript reviews and extends recent work on the mathematical relationship between predictive coding and backpropagation for training feedforward artificial neural networks on supervised learning tasks. Implications of these results for the interpretation of predictive coding and deep neural networks as models of biological learning are discussed along with a repository of functions, Torch2PC, for performing predictive coding with PyTorch neural network models. 

   more » « less
4. Predicting Software Defect Discovery Incorporating Covariates with Recurrent Neural Networks

   https://doi.org/10.1002/qre.70063  

   Salboukh, Fatemeh; Silva, Priscila; Nagaraju, Vidhyashree; Fiondella, Lance (September 2025, Quality and Reliability Engineering International)

   ABSTRACT Traditional software reliability growth models (SRGM) characterize defect discovery with the Non‐Homogeneous Poisson Process (NHPP) as a function of testing time or effort. More recently, covariate NHPP SRGM models have substantially improved tracking and prediction of the defect discovery process by explicitly incorporating discrete multivariate time series on the amount of each underlying testing activity performed in successive intervals. Both classes of NHPP models with and without covariates are parametric in nature, imposing assumptions on the defect discovery process, and, while neural networks have been applied to SRGM models without covariates, no such studies have been applied in the context of covariate SRGM models. Therefore, this paper assesses the effectiveness of neural networks in predicting the software defect discovery process, incorporating covariates. Three types of neural networks are considered, including (i) recurrent neural networks (RNNs), (ii) long short‐term memory (LSTM), and (iii) gated recurrent unit (GRU), which are then compared with covariate models to validate tracking and predictive accuracy. Our results suggest that GRU achieved better overall goodness‐of‐fit, such as approximately 3.22 and 1.10 times smaller predictive mean square error, and 5.33 and 1.22 times smaller predictive ratio risk in DS1G and DS2G data sets, respectively, compared to covariate models when of the data is used for training. Moreover, to provide an objective comparison, three different proportions for training data splits were employed to illustrate the advancements between the top‐performing covariate NHPP model and the neural network, in which GRU illustrated a better performance over most of the scenarios. Thus, the neural network model with gated recurrent units may be a suitable alternative to track and predict the number of defects based on covariates associated with the software testing process. 

   more » « less
5. Is Pruning Compression?: Investigating Pruning Via Network Layer Similarity

   Blakeney, Cody; Yan, Yan; Zong, Ziliang (March 2020, IEEE Winter Conference on Applications of Computer Vision (WACV ’20))

   Unstructured neural network pruning is an effective technique that can significantly reduce theoretical model size, computation demand and energy consumption of large neural networks without compromising accuracy. However, a number of fundamental questions about pruning are not answered yet. For example, do the pruned neural networks contain the same representations as the original network? Is pruning a compression or evolution process? Does pruning only work on trained neural networks? What is the role and value of the uncovered sparsity structure? In this paper, we strive to answer these questions by analyzing three unstructured pruning methods (magnitude based pruning, post-pruning re-initialization, and random sparse initialization). We conduct extensive experiments using the Singular Vector Canonical Correlation Analysis (SVCCA) tool to study and contrast layer representations of pruned and original ResNet, VGG, and ConvNet models. We have several interesting observations: 1) Pruned neural network models evolve to substantially different representations while still maintaining similar accuracy. 2) Initialized sparse models can achieve reasonably good accuracy compared to well engineered pruning methods. 3) Sparsity structures discovered by pruning models are not inherently important or useful. 

   more » « less