Software Impacts最新文献

alPCA is a software coded in R and designed to automatically combine predictions from a collection of individual forecasting methods that integrate it. It employs three categories of weights derived from the PCA scores, and decision rules to determine the optimal combination of these methods. alPCA serves as an automated component within the artificial intelligence toolkit for monthly time series processing with the objective of obtaining the best forecast.

Most websites and applications are hosted on a public or private cloud. In-house deployments also require dealing with system resources. Researchers have started considering resources utilized by application workloads to estimate and reduce application running costs. RAW-HF (Resource Availability & Workload aware Hybrid Framework) framework tries to analyze two types of resource utilization; (1) System Resource Utilization and (2) Resource Utilized by each Query task. The RAW-HF code tries to provide a lightweight solution to monitor & analyze the system and DBMS process resource utilization. It filters the required data in real time to find available resources and allocate query-specific resources based on their complexity by utilizing less than 2% CPU resources.

DNNs are widely used for complex tasks like image and signal processing, and they are in increasing demand for implementation on Internet of Things (IoT) devices. For these devices, optimizing DNN models is a necessary task. Generally, standard optimization approaches require specialists to manually fine-tune hyper-parameters to find a good trade-off between efficiency and accuracy. In this paper, we propose OptDNN, a software that employs innovative and automatic approaches to determine optimal hyper-parameters for pruning, clustering, and quantization. The models optimized by OptDNN have a smaller memory footprint, faster inference time, and a similar accuracy to the original models.

Search engine data is a prime source of insights on information-seeking behaviour and such information is instrumental for the scientific study of human culture and behaviour. The gtrendsAPI R software package aims to facilitate programmatic access to data available from the Google Trends API. Here, I introduce the functions available through this software package and provide worked examples of how to use it. I also discuss some the potential research applications and caveats of this software and the data available through it.

Neural Gas Principal Component Analysis (NGPCA) is an online clustering algorithm. An NGPCA model is a mixture of local PCA units and combines dimensionality reduction with vector quantization. Recently, NGPCA has been extended with an adaptive learning rate and an adaptive potential function for accurate and efficient clustering of high-dimensional and non-stationary data streams. The algorithm achieved highly competitive results on clustering benchmark datasets compared to the state of the art. Our implementation of the algorithm was developed in MATLAB and is available as open source. This code can be easily applied to the clustering of stationary and non-stationary data.

License Plate Recognition (LPR) sensors often fail to detect vehicles or to identify all plate numbers correctly. This noise results in missing digits or an incomplete route of a vehicle, for example, missing one node (LPR camera) in the route. Addressing these issues, RouteRecoverer creates the route followed by a vehicle while efficiently recovering absent LPR plate digits, and filling gaps in routes. For example, when a vehicle is detected by LPR A and C, with the only route between them being B, our tool seamlessly retrieves the missing information, improving the data output.

SPHMPS 1.0, developed within a Lagrangian framework, offers a robust solution for modeling multi-structure collision problems involving large plastic deformation and inherent thermal effects. Utilizing its innovative algorithm, SPHMPS 1.0 emerges as a versatile tool for researchers in the field of fluid-rigid-elastic structure interactions. By providing a comprehensive framework tailored to address these complex phenomena, SPHMPS 1.0 facilitates reproducible, extendable, and efficient research endeavors. Implemented in Fortran, its flexible algorithm ensures adaptability to a wide range of applications requiring solutions for fluid-rigid-elastic structure interaction problems.

LATTIN is a Python-based tool for Lagrangian atmospheric moisture and heat tracking. It can read input data from the Lagrangian FLEXPART and FLEXPART-WRF models. Features include parallel reading of atmospheric parcel trajectories and user custom threshold criteria. It complements and improves existing tools by including several tracking approaches and also by its non-dependence on the horizontal resolution of the input or output grid. LATTIN provides a compact tool for Lagrangian atmospheric moisture and heat tracking, which will support a wide range of research to understand future changes in the hydrological cycle and extreme temperature events.

This paper presents a user-friendly version of Persistent Homology (PH) graph code to model financial market structures and changes. By leveraging Topological Data Analysis (TDA), the code offers an effective approach for analyzing high-dimensional stock data, enabling the identification of persistent topological features indicative of market changes. The code’s potential applications in financial stability prediction, investment strategy development, and educational advancement are discussed. This contribution aims to facilitate the adoption of PH techniques in finance, promising significant implications for academic research and practical market analysis.

This paper presents user-friendly code for the implementation of a loss function for neural network time series models that exploits the topological structures of financial data. By leveraging the recently-discovered presence of topological features present in financial time series data, the code offers a more effective approach for creating forecasting models for such data given the fact that it allows neural network models to not only learn temporal patterns of the data, but also topological patterns. This paper aims to facilitate the adoption of the loss function proposed by Souto and Moradi (2024a) in financial time series by practitioners and researchers.