Support Vector Machine for soft fault location in electrical circuits

Black box modeling of PIDs implemented in PLCs without structural information: a support vector regression approach

In this report, the parameters identification of a proportional–integral–derivative (PID) algorithm implemented in a programmable logic controller (PLC) using support vector regression (SVR) is presented. This report focuses on a black box model of the PID with additional functions and modifications provided by the manufacturers and without information on the exact structure. The process of feature selection and its impact on the training and testing abilities are emphasized. The method was tested on a real PLC (Siemens and General Electric) with the implemented PID. The results show that the SVR maps the function of the PID algorithms and the modifications introduced by the manufacturer of the PLC with high accuracy. With this approach, the simulation results can be directly used to tune the PID algorithms in the PLC. The method is sufficiently universal in that it can be applied to any PI or PID algorithm implemented in the PLC with additional functions and modifications that were previously considered to be trade secrets. This method can also be an alternative for engineers who need to tune the PID and do not have any such information on the structure and cannot use the default settings for the known structures.

The application of support vector regression for prediction of the antiallodynic effect of drug combinations in the mouse model of streptozocin-induced diabetic neuropathy

Drug interactions are an important issue of efficacious and safe pharmacotherapy. Although the use of drug combinations carries the potential risk of enhanced toxicity, when carefully introduced it enables to optimize the therapy and achieve pharmacological effects at doses lower than those of single agents. In view of the development of novel analgesic compounds for the neuropathic pain treatment little is known about their influence on the efficacy of currently used analgesic drugs. Below we describe the preliminary evaluation of support vector machine in the regression mode (SVR) application for the prediction of maximal antiallodynic effect of a new derivative of dihydrofuran-2-one (LPP1) used in combination with pregabalin (PGB) in the streptozocin-induced neuropathic pain model in mice. Based on SVR the most effective doses of co-administered LPP1 (4mg/kg) and PGB (1mg/kg) were predicted to cause the paw withdrawal threshold at 6.7g in the von Frey test. In vivo for the same combination of doses the paw withdrawal was observed at 6.5g, which confirms good predictive properties of SVR.

New approach to predicting proconvulsant activity with the use of Support Vector Regression

Antiepileptic drugs are commonly used for many therapeutic indications, including epilepsy, neuropathic pain, bipolar disorder and anxiety. Accumulating data suggests that many of them may lower the seizure threshold in men. In the present paper we deal with the possibility of using Support Vector Regression (SVR) to forecast the proconvulsant activity of compounds exerting anticonvulsant activity in the electroconvulsive threshold test in mice. A new approach to forecast this drug-related toxic effect by means of the support vector machine (SVM) in the regression mode is discussed below. The efficacy of this mathematical method is compared to the results obtained in vivo. Since SVR investigates the anticonvulsant activity of the compounds more thoroughly than it is possible using animal models, this method seems to be a very helpful tool for predicting additional dose ranges at which maximum anticonvulsant activity without toxic effects is observed. Good generalizing properties of SVR allow to assess the therapeutic dose range and toxicity threshold. Noteworthy, this method is very interesting for ethical reasons as this mathematical model enables to limit the use of living animals during the anticonvulsant screening process.