Robert Sałat

Accurate fault location in the power transmission line using support vector machine approach

The paper presents a new approach to the location of fault in the high-voltage power transmission line, relying on the application of the support vector machine and frequency characteristics of the measured one-terminal voltage and current transient signals of the system. The extensive numerical experiments performed for location of different kinds of faults of the transmission line have proved very good accuracy of fault location algorithm. The average error of fault location in a 200-km transmission line is below 100 m and the maximum error did not exceed 2 km.

Antiallodynic and antihyperalgesic activity of 3-[4-(3-trifluoromethyl-phenyl)-piperazin-1-yl]-dihydrofuran-2-one compared to pregabalin in chemotherapy-induced neuropathic pain in mice

BACKGROUND Anticancer drugs - oxaliplatin (OXPT) and paclitaxel (PACLI) cause painful peripheral neuropathy activating Transient Receptor Potential (TRP) channels. Here we investigated the influence of 3-[4-(3-trifluoromethyl-phenyl)-piperazin-1-yl]-dihydrofuran-2-one (LPP1) and pregabalin on nociceptive thresholds in neuropathic pain models elicited by these drugs. Pharmacokinetics of LPP1 and its ability to attenuate neurogenic pain caused by TRP agonists: capsaicin and allyl isothiocyanate (AITC) were also investigated. METHODS Antiallodynic and antihyperalgesic effects of intraperitoneally administered LPP1 and pregabalin were tested in the von Frey, hot plate and cold water tests. The influence of LPP1 on locomotor activity and motor coordination was assessed using actimeters and rotarod. Serum and tissue concentrations of LPP1 were measured using the HPLC method with fluorimetric detection. RESULTS In OXPT-treated mice LPP1 and pregabalin dose-dependently reduced tactile allodynia (41-106% and 6-122%, respectively, p<0.01). At the dose of 10mg/kg LPP1 attenuated cold allodynia. In PACLI-treated mice LPP1 and pregabalin reduced tactile allodynia by 12-63% and 8-50%, respectively (p<0.01). Both drugs did not affect cold allodynia, whereas pregabalin (30 mg/kg) attenuated heat hyperalgesia (80% vs. baseline latency time; p<0.01). No motor impairments were observed in LPP1 or pregabalin-treated neuropathic mice in the rotarod test, while severe sedation was noted in the locomotor activity test. LPP1 reduced pain induced by capsaicin (51%; p<0.01) and AITC (41%; p<0.05). The mean serum concentration of LPP1 measured 30 min following i.p. administration was 7904.6 ± 1066.1 ng/ml. Similar levels were attained in muscles, whereas brain concentrations were 62% lower. Relatively high concentrations of LPP1 were also determined in the cerebrospinal fluid and the sciatic nerve. CONCLUSIONS LPP1 and pregabalin reduce pain in OXPT and PACLI-treated mice. This activity of LPP1 might be in part attributed to the inhibition of TRPV1 and TRPA1 channels, but also central mechanisms of action cannot be ruled out.

Analgesic, anticonvulsant and antioxidant activities of 3-[4-(3-trifluoromethyl-phenyl)-piperazin-1-yl]-dihydrofuran-2-one dihydrochloride in mice

Recently we have shown that 3-[4-(3-trifluoromethyl-phenyl)-piperazin-1-yl]-dihydrofuran-2-one dihydrochloride (LPP1) is an antinociceptive and local anesthetic agent in rodents. Below an extended study of the pharmacological activity of LPP1 is described. In vitro LPP1 has no affinity for GABA(A), opioidergic μ and serotonergic 5-HT(1A) receptors. The total antioxidant capacity of LPP1 (1-10mM) measured as ABTS radical cation-scavenging activity showed that LPP1 has dose-dependent antioxidant properties in vitro. Low plasma concentration of this compound detected by means of HPLC method 30min after its intraperitoneal administration suggests a rapid conversion to metabolite(s) which may be responsible for its analgesic and anticonvulsant activities in vivo. In vivo the compounds influence on the electroconvulsive threshold and its activity in the maximal electroshock seizure test (MES) were evaluated. The results demonstrated that LPP1 had an anticonvulsant activity in the MES model (ED(50)=112mg/kg) and at a dose of 50mg/kg was able to elevate the electroconvulsive threshold for 8mA as compared to the vehicle-treated mice. The analgesic activity of LPP1 was investigated in the acetic acid-induced writhing test in two groups of mice: animals with sensory C-fibers ablated, and mice with C-fibers unimpaired. It proved the potent activity of this compound in both groups (approximately 85% as compared to the vehicle-treated mice). The adverse effects of LPP1 were evaluated as acute toxicity (LD(50)=747.8mg/kg) and motor coordination impairments in the rotarod and chimney tests. The results from these tests show that LPP1 at doses higher than 100mg/kg is likely to impair the motor performance of experimental animals. Concluding, LPP1 is an analgesic and anticonvulsant compound which has antioxidant properties in vitro. Further studies are necessary to assess whether the antioxidant activity and the receptor profiling demonstrated in vitro can be confirmed for its metabolite(s) that are formed in vivo.

Support Vector Machine for soft fault location in electrical circuits

The paper is concerned with the application of Support Vector Machine (SVM) to the fault location in the analog electrical circuits. The recognition of fault is based on the measurements of the accessible terminal voltage and current of the network at the set of frequencies. The SVM network is applied as the recognizing system and as the classifier. The important feature of the proposed solution is its high accuracy and great speed of operation. Once the network has been trained, the recognition of fault is achieved immediately, irrespective of the size of the circuit. Thus the solution is suited for real time applications for fault location in electrical circuits. The numerical results of recognition of faulty elements in two different structures of electrical filters are presented and discussed in the paper.

The effect of GABA transporter 1 (GAT1) inhibitor, tiagabine, on scopolamine-induced memory impairments in mice

BACKGROUND GABAergic neurotransmission is involved in long-term potentiation, a neurophysiological basis for learning and memory. On the other hand, GABA-enhancing drugs may impair memory and learning in humans and animals. The present study aims at investigating the effect of GAT1 inhibitor tiagabine on memory and learning. METHODS Albino Swiss (CD-1) and C57BL/6J mice were used in the passive avoidance (PA), Morris water maze (MWM) and radial arm water maze (RAWM) tasks. Scopolamine (1mg/kg ip) was applied to induce cognitive deficits. RESULTS In the retention trial of PA scopolamine reduced step-through latency as compared to vehicle-treated mice, and pretreatment with tiagabine did not have any influence on this effect. In MWM the results obtained for vehicle-treated mice, scopolamine-treated group and combined scopolamine+tiagabine-treated mice revealed variable learning abilities in these groups. Tiagabine did not impair learning in the acquisition trial. In RAWM on day 1 scopolamine-treated group made nearly two-fold more errors than vehicle-treated mice and mice that received combined scopolamine and tiagabine. Learning abilities in the latter group were similar to those of vehicle-treated mice in the corresponding trial block on day 1, except for the last trial block, during which tiagabine+scopolamine-injected mice made more errors than control mice and the scopolamine-treated group. In all groups a complete reversal of memory deficits was observed in the last trial block of day 2. CONCLUSIONS The lack of negative influence of tiagabine on cognitive functions in animals with scopolamine-induced memory impairments may be relevant for patients treated with this drug.

Estimation of tensile strength of ductile iron friction welded joints using hybrid intelligent methods

Abstract A hybrid intelligent method for evaluation of near optimal settings of friction welding process parameters of ductile iron was presented. The optimization of welding parameters was carried out in automatic cycle with the use of support vector regression (SVR), genetic algorithm (GA) and imperialist competitive algorithm (ICA). The method suggested was used to determine welding process parameters by which the desired tensile strength was obtained in the friction welding of ductile iron. The highest tensile strength (TS) of 256.93 MPa was obtained using SVR plus GA method for the following friction welding parameters: heating force 40 kN, heating time 300 s and upsetting force 10.12 kN. The samples were welded by friction and subjected to the tensile strength test. The optimized values obtained by means of these hybrid techniques were compared with the experimental results. The application of hybrid intelligent methods allowed to increase the tensile strength joints from 211 to 258 MPa for the friction welder ZT–14 type.

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.

Fault location in transmission line using hybrid neural network

The paper presents the application of self‐organizing neural network for the location of the fault in the transmission line and estimation of the parameter of the faulty element. The location of fault is done on the basis of the measurement of some node voltages of the line and appropriate preprocessing it to enhance the differences between different faults. The hybrid neural network is used to solve the problem. The self‐organizing layer of this network is used as the classifier. The output postprocessing MLP structure realizes the association of the place of the fault and its parameter with the measured set of node voltages. The results of computer experiments are given in the paper and discussed.

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.

Modeling analgesic drug interactions using support vector regression: A new approach to isobolographic analysis

BACKGROUND Modeling drug interactions is important for illustrating combined drug actions and for predicting the pharmacological and/or toxicological effects that can be obtained using combined drug therapy. AIM In this study, we propose a new and universal support vector regression (SVR)-based method for the analysis of drug interactions that significantly accelerates the isobolographic analysis. METHODS Using SVR, a theoretical model of the dose-effect relationship was built to simulate various dose ratios of two drugs. Using the model could then rapidly determine the combinations of doses that elicited equivalent effects compared with each drug used alone. RESULTS The model that was built can be used for any level of drug effect and can generate classical isobolograms to determine the nature of drug interactions (additivity, subadditivity or synergy), which is of particular importance in the case of novel compounds endowed with a high biological activity for which the mechanism of action is unknown. In addition, this method is an interesting alternative allowing for a meaningful reduction in the number of animals used for in vivo studies. CONCLUSIONS In a mouse model of toxic peripheral neuropathy induced by a single intraperitoneal dose of oxaliplatin, the usefulness of this SVR method for modeling dose-effect relationships was confirmed. This method may also be applicable during preliminary investigations regarding the mechanism of action of novel compounds.