Decision from Experience Behavior Modeling (DEBM): an open-source Python package for developing, evaluating, and visualizing behavioral models.

The last decade was characterized by an emphasis on enhancing reproducibility and replicability in the social sciences. To contribute to these efforts within the decision-making research field, we introduce DEBM (Decision from Experience Behavior Modeling) – an open-source Python package. The main goal of DEBM is to serve as a central colloberative pool of models and methods in the decision from experience domain. Specifically, it provides a convenient “playground” for developing models or experimenting with existing ones. DEBM includes many features such as multiprocessing, parameter estimation, visualization, and more. In this paper we cover the basic functionality of DEBM by simulating behavior using an existing model and given parameters, and recovering these parameters using grid search.

Hyperparameter tuning for multi-label classification of feedbacks in online courses

In this work, we propose the extension of a methodology for the multi-label classification of feedback according to the Hattie and Timperley feedback model, incorporating a hyperparameter tuning stage. It is analyzed whether the incorporation of the hyperparameter tuning stage prior to the execution of the algorithms support vector machines, random forest and multi-label k-nearest neighbors, improves the performance metrics of multi-label classifiers that automatically locate the feedback generated by a teacher to the activities sent by students in online courses on the Blackboard platform at the task, process, regulation, praise and other levels proposed in the feedback model by Hattie and Timperley. The grid search strategy is used to refine the hyperparameters of each algorithm. The results show that the adjustment of the hyperparameters improves the performance metrics for the data set used.

Malware Detection Using Ensemble N-gram Opcode Sequences

Conventional approaches to tackling malware attacks have proven to be futile at detecting never-before-seen (zero-day) malware. Research however has shown that zero-day malicious files are mostly semantic-preserving variants of already existing malware, which are generated via obfuscation methods. In this paper we propose and evaluate a machine learning based malware detection model using ensemble approach. We employ a strategy of ensemble where multiple feature sets generated from different n-gram sizes of opcode sequences are trained using a single classifier. Model predictions on the trained multi feature sets are weighted and combined on average to make a final verdict on whether a binary file is malicious or benign. To obtain optimal weight combination for the ensemble feature sets, we applied a grid search on a set of pre-defined weights in the range 0 to 1. With a balanced dataset of 2000 samples, an ensemble of n-gram opcode sequences of n sizes 1 and 2 with respective weight pair 0.3 and 0.7 yielded the best detection accuracy of 98.1% using random forest (RF) classifier. Ensemble n-gram sizes 2 and 3 obtained 99.7% as best precision using weight 0.5 for both models.

Forecasting public bicycle rental demand using an optimized eXtreme Gradient Boosting model

The rational distribution of public bicycle rental fleets is crucial for improving the efficiency of public bicycle programs. The accurate prediction of the demand for public bicycles is critical to improve bicycle utilization. To overcome the shortcomings of traditional algorithms such as low prediction accuracy and poor stability, using the 2011–2012 hourly bicycle rental data provided by the Washington City Bicycle Rental System, this study aims to develop an optimized and innovative public bicycle demand forecasting model based on grid search and eXtreme Gradient Boosting (XGBoost) algorithm. First, the feature ranking method based on machine learning models is used to analyze feature importance on the original data. In addition, a public bicycle demand forecast model is established based on important factors affecting bicycle utilization. Finally, to predict bicycle demand accurately, this study optimizes the model parameters through a grid search (GS) algorithm and builds a new prediction model based on the optimal parameters. The results show that the optimized XGBoost model based on the grid search algorithm can predict the bicycle demand more accurately than other models. The optimized model has an R-Squared of 0.947, and a root mean squared logarithmic error of 0.495. The results can be used for the effective management and reasonable dispatch of public bicycles.

Parsimonious Optimization of Multitask Neural Network Hyperparameters

Neural networks are rapidly gaining popularity in chemical modeling and Quantitative Structure–Activity Relationship (QSAR) thanks to their ability to handle multitask problems. However, outcomes of neural networks depend on the tuning of several hyperparameters, whose small variations can often strongly affect their performance. Hence, optimization is a fundamental step in training neural networks although, in many cases, it can be very expensive from a computational point of view. In this study, we compared four of the most widely used approaches for tuning hyperparameters, namely, grid search, random search, tree-structured Parzen estimator, and genetic algorithms on three multitask QSAR datasets. We mainly focused on parsimonious optimization and thus not only on the performance of neural networks, but also the computational time that was taken into account. Furthermore, since the optimization approaches do not directly provide information about the influence of hyperparameters, we applied experimental design strategies to determine their effects on the neural network performance. We found that genetic algorithms, tree-structured Parzen estimator, and random search require on average 0.08% of the hours required by grid search; in addition, tree-structured Parzen estimator and genetic algorithms provide better results than random search.

Effective Passive Multitarget Localization Using Maximum Likelihood

Localization of multiple targets is a challenging task due to immense complexity regarding data fusion received at the sensors. In this context, we propose an algorithm to solve the problem for an unknown number of emitters without prior knowledge to address the data fusion problem. The proposed technique combines the time difference of arrival (TDOA) and frequency difference of arrival (FDOA) measurement data fusion which further uses the maximum likelihood of the measurements received at each sensor of the surveillance region. The measurement grids of the sensors are used to perform data association. The simulation results show that the proposed algorithm outperforms the multipass grid search and further effectively eliminated the ghost targets created due to the fusion of measurements received at each sensor. Moreover, the proposed algorithm reduces the computational complexity compared to other existing algorithms as it does not use repeated steps for convergence or any biological evolutions. Furthermore, the experimental testing of the proposed technique was executed successfully for tracking multiple targets in different scenarios passively.