Login to your account
Don’t have an account?
Create a Free Account
R-badged Articles 
MOPO-LSI: An open-source multi-objective portfolio optimization library for sustainable investments
Financial portfolio optimization is a process of selecting the optimal combination of assets to achieve a specific investment objective. Traditional portfolio optimization may only maximize returns and minimize risks, and ignore social responsibility or sustainability in financial investments. In this paper, we release MOPO-LSI which is a mutli-objective portfolio optimization library for sustainable investments. More specifically, MOPO-LSI additionally considers Environmental, Social and Governance (ESG) factors as objectives to be optimized in financial portfolio, where investors’ assets can be well allocated to mutual funds towards the improvements in sustainable development and practices.pFedDef: Characterizing evasion attack transferability in federated learning
Federated learning jointly trains a model across multiple clients, leveraging information from all of them. However, client models are vulnerable to attacks during training and testing. We introduce the pFedDef library, which analyzes and addresses the issue of adversarial clients performing internal evasion attacks at test time to deceive other clients. pFedDef characterizes the transferability of internal evasion attacks for different learning methods and analyzes the trade-off between model accuracy and robustness to these attacks.Smart Meter Synthetic Data Generator development in python using FBProphet
Data-science is a key component of modern science since it fuels AI, ML and data analytics, etc. As the electrical grid has been modernized into a smart grid, it has also become increasingly dependent on data science to monitor and control grid activity. Realistic data is essential to evaluating the algorithm’s workability but it is difficult to obtain real smart meter data due to strict privacy and security policies of many countries. In this paper, using the prophet library, we code and develop a prediction-based Synthetic Data Generator GUI, which generate the synthetic data sets.Anomaly Detection, Classification and Identification Tool (ADCIT)
The Anomaly Detection, Classification and Identification Tool (ADCIT) is an open source Matlab and Python code used for detection, classification and identification of anomalies in power system state estimation. Outputs of weighted least squares (WLS) and extended Kalman filter (EKF) state estimators, developed in Matlab, are used as inputs for machine learning algorithms developed in Python. The ADCIT can address hard anomaly cases; for example, it can detect and classify the case when load is abruptly changed at multiple nodes simultaneously, or when false data injection attack targets multiple states at the same time.hiscovid for visualizing and identifying when policymakers made mistakes against COVID-19
There are two types of policy outcome analysis tools: snapshot tool and time-series tool. hiscovid is a time-series policy outcome scoring tool of COVID-19 policies by country where the daily cumulative population mortality is used for scoring the outcomes of COVID-19 country policies to visualize and identify when policymakers made mistakes. hiscovid allows policymakers to observe the progress and transition of scores over time to learn lessons from the past decision-making mistakes for correcting the current policies to reduce unnecessary deaths.FluxPAW: A standalone software to calculate flux-based plant available water
Soil water contents at field capacity (FC), the limiting point (LP), and the wilting point (WP) delimit the fractions of soil water availability, the plant available water (PAW). FC is primarily a function of soil hydraulic properties, whereas LP and WP depend on soil, plant, and atmospheric conditions. The difference between FC and WP is called total available water, whereas FC minus LP is the readily available water. The flux-based method (FBM) predicts PAW from unsaturated soil water flow, rooting characteristics, and atmospheric water demand.Parallel Sparse Computation Toolkit
This paper presents a new software framework for solving large and sparse linear systems on current hybrid architectures, from small servers to high-end supercomputers, embedding multi-core CPUs and Nvidia GPUs at the node level. The framework has a modular structure and is composed of three main components, which separate basic functionalities for managing distributed sparse matrices and executing some sparse matrix computations involved in iterative Krylov projection methods, eventually exploiting multi-threading and CUDA-based programming models, from the functionalities for setup and application of different types of one-level and multi-level algebraic preconditioners.Swaragram: A software toolbox for musical feature of Indian music
We present a melodic musical feature and a toolbox preferable for Indian classical music that incorporates tonic information and micro-tonic scales (Shruti). The Chromagram feature, widely used for computational analysis in Western music, inspired our feature’s methodology. The feature’s performance is evaluated for Raag Identification and is comparable to other approaches on the same dataset. We also present a few applications of the toolbox.TS-Evolutionary_Prototyping: A Python module for finding the prototype in large sets of time series
Time series analysis has become one of the basic building blocks for the technological fields of science and engineering. Therefore, there are a large number of software tools that encompass the preparation of the data, the performance of a large number of processing tasks with the data, the generation of datasets and finally the implementation of the necessary evaluation techniques. Of particular importance within the above tasks is the prototyping or summarisation of sets of time series as they have direct application in the resolution of clustering problems.MoreThanSentiments: A text analysis package
Text mining on a large corpus of data has gained utility and popularity over recent years owing to advancements in information retrieval and machine learning methods. However, popular text mining software packages mainly focus on either sentiment analysis or semantic meaning extraction, requiring pretraining on a large corpus of text data. In comparison, MoreThanSentiments provides computation of newer text attribution measures, including boiler score, specificity, redundancy, and hard info, which have been proposed in accounting analytics literature.DFLER: Drone Flight Log Entity Recognizer to support forensic investigation on drone device
DFLER is an open-source CLI-based tool developed using Python and supported by a fine-tuned BERT model to perform named entity recognition on drone flight log data, specifically the log messages. This model is hosted on the HuggingFace platform to make it publicly available and accessible. The tool expects decrypted DJI flight log files as input and generates a forensic report in a PDF containing a forensic timeline highlighting parts of the mentioned entities in the log messages. The generated file is an attachment to a complete forensic report and helps forensic investigators pinpoint critical events on the constructed forensic timeline.An R package for percentile-based control charts: pbcc
Although the percentile-based control charts are very effective with guaranteed in-control and out-of-control run lengths in statistical process control, they still lack algorithmic and (especially) software support. The proposed percentile-based control charts (pbcc) software tool fills this gap. This software is freely available and implements the recent work on individual as well as joint percentile-based control charts.PL-kNN: A Python-based implementation of a parameterless k -Nearest Neighbors classifier
This paper presents an open-source implementation of PL-kNN, a parameterless version of the k -Nearest Neighbors algorithm. The proposed model, developed in Python 3.6, was designed to avoid the choice of the k parameter required by the standard k -Nearest Neighbors technique. Essentially, the model computes the number of nearest neighbors of a target sample using the data distribution of the training set. The source code provides functions resembling the Scikit-learn methods for fitting the model and predicting the classes of the new samples.KSDSLD — A tool for keystroke dynamics synthesis & liveness detection
Keystroke dynamics is a behavioral biometrics modality that employs the characteristic typing patterns of users to verify their identity, generally as a part of a multifactor authentication scheme. Naïve implementations of keystroke dynamics verification are susceptible to presentation attacks with synthesized samples, leveraging partial or complete knowledge of the legitimate users’ typing patterns to forge accurate imitations of their behavior. The companion article has presented several novel methods for the synthesis of forged keystroke dynamics samples given one or more authentic samples of free text by the legitimate user, and a liveness detection method that employs the latter as adversaries to train a classification model, which can distinguish human-written samples from synthetic forgeries.ODE4ViTRobustness: A tool for understanding adversarial robustness of Vision Transformers
Understanding the adversarial robustness of Vision Transformers (ViTs) has long been needed since the vulnerability of neural networks hinders their use of it. We present an approach that decomposes the network into submodules and calculates the maximal singular value for each module w.r.t. input, which is a good indication of adversarial robustness. To understand whether Multi-head Self-Attention (MSA) in ViTs contributes to its adversarial robustness, we replace the module with convolutional layers with our decomposing method and conclude that MSA has limited power to defend against adversarial attacks.scorecovid for scoring individual country COVID-19 policies in the world
There are two types of policy analysis tools: snapshot tool and time-series tool. scorecovid is a snapshot tool to score individual COVID-19 policies in the world and sort a list of scores. The population mortality rate is used for evaluating the outcomes of COVID-19 country policies. The lower the score, the less the COVID-19 deaths. The lower the score, the better the policy. The scorecovid tool is intended for poorly scored countries to learn good strategies from countries with excellent scores where scorecovid attracted 15192 users worldwide.SyReC Synthesizer: An MQT tool for synthesis of reversible circuits
Reversible circuits form the backbone for many promising emerging technologies such as quantum computing, low power/adiabatic design, encoder/decoder devices, and several other applications. In the recent years, the scalable synthesis of such circuits has gained significant attention. In this work, we present the SyReC Synthesizer, a synthesis tool for reversible circuits based on the hardware description language SyReC. SyReC allows to describe reversible functionality at a high level of abstraction.LiBEIS : A software tool for broadband electrochemical impedance spectroscopy of lithium-ion batteries
Electrochemical impedance spectroscopy (EIS) is a fundamental tool used in numerous research fields and applications. In particular, EIS is commonly employed for studying and monitoring lithium-ion batteries, to ensure their safe and efficient operation. The LiBEIS software tool computes EIS data by processing the voltage and current time series acquired from a battery under test, which is excited with a broadband current signal. Furthermore, LiBEIS performs fitting of the EIS data to an equivalent circuit model, which is often employed in practice to analyse the behaviour of the battery.CalcPlotAnomaly: A set of functions in MATLAB for the computation and plotting of anomalies of oceanographic and meteorological parameters
CalcPlotAnomaly is a set of source code functions implemented in MATLAB and compatible with Octave, these functions are used for the computation of oceanographic (physical and biogeochemical), and meteorological parameter anomalies that are used by geoscientists and decision-makers. They use as input time-ordered data from observed data (in situ, satellite, or radar) and interannual model outputs (raw data, analysis, or reanalysis). These anomalies can be computed over the whole period, by months or seasons.IDS-ML: An open source code for Intrusion Detection System development using Machine Learning
Due to the expansion and development of modern networks, the volume and destructiveness of cyber attacks are continuously increasing. Intrusion Detection Systems (IDSs) are essential techniques for maintaining and enhancing network security. IDS-ML is an open-source code repository written in Python for developing IDSs from public network traffic datasets using traditional and advanced Machine Learning (ML) algorithms. With optimized ML models, the IDSs developed in the repository can identify various types of cyber-attacks to protect modern networks.Libra: A modular software library for quantum nonadiabatic dynamics
Libra is a versatile open-source software that implements a multitude of community-developed methods and computational workflows for nonadiabatic and quantum dynamics calculations, such as trajectory surface hopping or Ehrenfest dynamics, discrete variable representation or trajectory-guided wavepacket propagation schemes, and more. Through interfaces with electronic structure codes for excited state calculations, Libra enables modeling quantum nonadiabatic processes in extended atomistic systems.CyberSignature: A user authentication tool based on behavioural biometrics
Behavioural biometrics, such as the way people type on computer keyboard and/or move the cursor are almost impossible to steal. This paper presents CyberSignature1, a tool that uses behavioural biometrics to create unique digital identities that can be used during online card transactions to distinguish legitimate users from fraudsters. The tool is implemented in Python, with a machine learning algorithm at its core. It receives user input data entries from a graphical user interface, similar to an online payment form, and transforms them into unique digital identities.DCF: Disparity computing framework for stereo vision systems
Disparity maps are vital components of stereo vision systems as they encode the displacement of two or more images. However, previous works provide only a few implementation details, suggest processing steps that are not very well defined, and the software design is rarely discussed. Conversely, DCF applies the main components of a stereo vision system and integrates them to promote disparity map construction. As a result, DCF algorithms can be parameterized or executed with previously defined configurations.Simultaneous Botnet Dataset Generator: A simulation tool for generating a botnet dataset with simultaneous attack characteristic
A botnet attack must be handled appropriately, such that botnet detection models have been developed, whose performance is supported by datasets obtained through recording actual network traffic or simulations. Nevertheless, the available datasets only show particular characteristics. In the real environment, botnet attacks can coincide with same networks, recorded in different intrusion detectors. Thus, a dataset representing simultaneous botnet attacks is essential. This paper proposes a simulation software for botnet activity modeling with simultaneous characteristics, performed by extracting sporadic and periodic activities of botnet attacks.MMFT Droplet Simulator: Efficient Simulation of Droplet-based Microfluidic Devices
Microfluidic devices have found many great applications in medicine, (bio-)chemistry, pharmacology, etc. Unfortunately, their design process is still in its infancy, and frequently results in a costly and time-consuming “trial-and-error” approach, where designs are derived by hand. In order to prevent this, design automation methods and simulation tools can be utilized that aid designers during the whole design phase. In this article, we present such a simulation tool that allows to simulate the behavior of droplet-based microfluidic devices and, by this, allows to validate the functionality of the device, even before the first prototype is fabricated.
The content on this site is intended for healthcare professionals.
Copyright © 2023 Elsevier Inc. except certain content provided by third parties.
