Current Signal Transduction Therapy - Volume 15, Issue 3, 2020

Objective: In everyday life, more and more people suffer from various diseases. To prefer the best medicine for them, an exact diagnosis is to be done. For example, the Epilepsy patients encounter many challenges because they must take precautionary measures to protect themselves from injury during a sudden occurrence of seizures. Materials and Methods: The investigations of epilepsy can be made analysing Electroencephalogram (EEG) motions to break down the conduct of the cerebrum amid seizures. To find the exact seizure frame in EEG signal is difficult and the overall analysis results is tedious in terms of human error. Results: Hence, there is a need for automatic detection, exact prediction, and classification of EEG waves. Similarly, another potential utilization of EEG signal investigation is in the prediction of epileptic seizures before they occur. This step relieves the patients of anxiety and empowers their guardians. Conclusion: In this study, we first concentrated on seizure discovery and classification issue. Secondly, some bits of knowledge on the complications involved in seizure-management are mentioned. Finally, some suggestions are listed with seizure classifications.

Background: In this paper, the design and computational modeling of microfluidic channel capable of separating platelets and Red Blood Cell (RBC) from the other blood cells are proposed. Materials and Methods: Separation based on their sizes is made possible by utilizing negative dielectrophoretic (n-DEP) force in fusion with drag force. An array of 38º angled electrode separated by 70 μm distance is designed within the microchannel and analyzed for non-uniform electric field distribution. Results and Conclusion: The molecule movement within the microchannel under induced electric field is simulated to demonstrate the separation using the particle trajectories module. A numerical study is performed for the calculation of Clausius Mossotti (CM) factor, n-DEP force and drag force.

Background: Microfluidic technologies are a very challenging area today in the field of biomolecule analysis. This has become feasible with the today’s advanced technologies by designing and fabricating the microfluidic channel. Materials and Methods: Initially, microfluidic channels are used to separate large molecules, where the molecular dimension of the fluidic filter is greater than the gap size. In this work, separation of biomolecules (like RBC, WBC and platelets) that are smaller than the microfluidic filter gap size is demonstrated. Results and Discussion: Due to the curvilinear nature of the spiral, there exists two vortices called dean vortices within the channel and this is influenced by dean flow, centrifugal flow and tubular pinch effect. While flowing a small aliquot of blood in the channel, due to these three effects, molecules attain equilibrium position at one point. The position of equilibrium will be different for different sized biomolecules and this varies with different input velocities. Conclusion: The obtained computational modeling results show how the equilibrium positions influence the separation efficiency of biomolecules in passive based microfluidic filter. Compared with the traditional random nanoporous materials such as gel or polymer monolith, spiral based microfluidic channels can be made precisely to have a pre-determined loop count and Dean Flow number (De).

Background: A topological index of a graph G is a numerical parameter related to G which characterizes its molecular topology. In the field of QSAR and QSPR research, theoretical properties of the chemical compounds and their molecular topological indices such as distance connectivity indices and degree connectivity indices are used to predict the bioactivity of different molecular compounds. Materials and Methods: Such an approach is different from the traditional QSAR methodology, where one employs selected simpler physico-chemical properties to predict biological activities of molecules. In order to obtain the structure-activity relationships in which theoretical and computational methods are necessary to find appropriate representations of the molecular structure of chemical compounds. These representations are realized through the molecular descriptors. Molecular descriptors are numbers containing structural information derived from the structural representation used for molecules under study. Results: A topological index defined on molecular structure G can be considered as a real valued function f :G→ R⁺ which maps each durg molecular structure to certain real numbers. Graphene sheets are composed of carbon atoms linked in hexagonal shapes with each carbon atom covalently bonded to three other carbon atoms. Each sheet of graphene is only one atom thick and each graphene sheet is considered a single molecule. Graphene has the same structure of carbon atoms linked in hexagonal shapes to form carbon nanotubes, but graphene is flat rather than cylindrical. This paper addresses the problem of computing the Wiener , First Zagreb index and Forgotten index of Complementary graphs of graphene sheets, triangular benzenoid graph, circumcoronene molecular graph and nanostar dendrimers. Conclusion: The line graphs were used for modeling amino acid sequences of proteins and of the genetic code. The connected graphs are isomorphic to self complementary graphs. Recently, molecular graphs have proved to be highly useful for drugs activity. Non empirical parameters of chemical structures derived from graph theoretic formalisms are being widely used by many researchers in studies pertaining to molecular design, pharmaceutical drug-design, and environmental hazard assessment of chemicals.

Background: Image segmentation plays a vital role in clinical study and in diagnosing the stages of diseases. The hospitals are marching towards filmless imaging process in par with digital film technology. Materials and Methods: The paper proposes a novel method based on morphometric segmentation algorithm with Region of Interest (ROI). The core objective is to detect better segmentation of a brain tumor from an MRI image for a clinical study. Results and Conclusion: A set of experiment has been performed for the analysis of the proposed work on several MRI images. The proposed morphometric segmentation method provides better accuracy on segmentation of tumor image from the input MRI image.

Background: A large number of nature-based optimization methods have been proposed to use as efficient tools in scientific studies. Genetic Algorithm (GA), which operates based on human genetical evolution, has been an outstanding mostly used solver in a wide range of applications. This algorithm reflects the process of natural selection where the fittest individuals are selected for reproduction in order to produce offspring of the next generation. Initialization, selection, crossover, and mutation are the main parts of the GA population-based method which enables GA to have a prominent explorative feature. On the other hand, the Teaching Learning Based Optimization algorithm (TLBO) is of great performance during searching for the optimum solution among individuals. Therefore, it is expected that the combination of both algorithms in a certain logical way improves the optimization time. Objective: The study intends to determine ways of improving performance of the TLBO algorithm to solve a complex non-linear problem. Power system studies are one of the most complex problems for analysis. Therefore, a powerful heuristic optimization procedure would have a valuable contribution in solving such problems. In addition, the proposed heuristic algorithm will help scientists to apply the technique to their problems. Materials and Methods: According to the aforementioned explanation, a new efficient optimization approach is proposed which optimizes the parameters of multi-machine power system stabilizers (PSSs). The TLBO algorithm includes two different stages in its main structure, which are aptly called teacher and student stages. The student stage of TLBO is replaced by the genetic algorithm in order to improve the explorative feature of the main TLBO. The PSS parameters are obtained for four PSSs which are connected to four generators. Results: The performance of the proposed stabilizer is compared with other formerly designed stabilizers reported in the literature consisting of multi-band PSSs for two areas four-machine power system. Simulation results demonstrate the effectiveness and robustness of the proposed PSS in damping local and inter-area oscillation modes under various disturbances and confirm its superiority in comparison with the other types of PSSs. Conclusion: A search heuristic method like the genetic algorithm can dramatically improve the performance of meta-heuristic optimization technique. In actuality, the TLBO as a meta-heuristic optimization technique suffers from a direct search of random solutions in its primary stage. Then, the TLBO relinquishes some parts of search space which may restrict the algorithm to find absolute maximums or minimums. In this condition, the GA with a great ability in searching the whole search space effectively improves the TLBO. According to the obtained results, the proposed algorithm, named Genetic-TLBO, obviates the conventional TLBO flaws successfully.

Background: Environmental health has become a worldwide debating issue among researchers, scientists, and governments. Although fossil fuels have been the greatest energy resources for the human, their consumption leads to injecting greenhouse gases into the air, which can affect the existence of all living species dramatically. In fact, fossil fuels consumption pollutes the environment because of the injection of greenhouse gases which result in global warming. On the other hand, reductions in fossil fuel and drinking water resources have highlighted the importance of energy management and loss reduction in brand-new management strategies and manufacturing methods. Distribution transformers are one of the most used devices in power distribution networks. Hence, it seems to be logical to consider transformer losses as a definitive factor in design and construction procedures. Furthermore, such design procedures require powerful tools to solve complex non-linear equations and find the best solutions in the shortest time. Researchers and scientists have always had a great challenge regarding finding the best solutions for their analysis. In actuality, it is hard to solve complex non-linear problems by means of traditional calculation methods even if a researcher employs a powerful computer. For this reason, metaheuristic optimization algorithms have found great popularity among scientists. These algorithms seek the best solution through a solution pool at an appropriate pace. Therefore, a researcher can save more time and energy in solving an intricate problem. Objective: In this paper, the authors aim to modify the conventional Teaching-Learning Based Optimization (TLBO) algorithm to design an optimum distribution transformer by consideration of the transformer Total Owning Cost (TOC). The TOC consists of operational and initial manufacturing costs of a distribution transformer. The used raw materials affect the manufacturing cost and it would be decreased if the copper and iron volumes are reduced in the construction instruction. However, the operational cost that includes iron and copper losses must not be forgotten in design analysis. Indeed, loss consideration is of great significance to keep energy from frittering away and as a result, protects environmental resources. Materials and Methods: A novel approach based on an optimization technique for distribution transformer design problems is presented in this paper. The entire expenses of a transformer consist of transformer construction and operating costs. In other words, by reducing copper and iron volumes, the initial cost of a transformer will be decreased. Due to the electromagnetic and electrical losses in transformers, the initial cost of a transformer is not its entire design problem and the operating cost must be considered in the design algorithm. Appropriate limits on efficiency, voltage regulation, temperature rise, no-load current and winding fill factor are the constraints on the transformer design problems in the international standards. With respect to these constraints, the transformer designer can minimize the volume of the core and windings. In this paper, the Conditional Teaching-Learning Based Optimization (CTLBO) algorithm determines the appropriate transformer properties, while transformer construction cost and its operating cost are selected as an objective function for optimization method. In order to attain a suitable voltage regulation, transformer impedance is chosen as an optimization constraint. Results: The result of the paper demonstrates the proposed algorithm ability in reducing the Total Owning Cost (TOC) during transformer lifetime, which could be useful for energy distribution companies. In addition, the result analysis proves that the total losses of the transformer are reduced by the proposed approach in comparison to conventional design techniques. Then, more energy will be saved in the power grid when the proposed transformer is utilized in the power network. Conclusion: In this paper, a suitable method to design an optimum distribution transformer is proposed which enables manufacturers to construct their product based on the proposed method. In this way, it can be claimed that not only more money will be saved during the transformer operation, but also the energy consumption will be decreased drastically. Therefore, world resources will remain for future generations.

Background: This paper presents electrical power system comprises many complex and interrelating elements that are susceptible to the disturbance or electrical fault. The faults in electrical power system transmission line (TL) are detected and classified. But, the existing techniques like Artificial Neural Network (ANN) failed to improve the Fault Detection (FD) performance during transmission and distribution. In order to reduce the Power Loss Rate (PLR), Daubechies Wavelet Transform based Gradient Ascent Deep Neural Learning (DWT-GADNL) Technique is introduced for FDin electrical power sub-station. DWT-GADNL Technique comprises three step, normalization, feature extraction and FD through optimization. Initially sample power TL signal is taken. After that in first step, min-max normalization process is carried out to estimate the various rated values of transmission lines. Then in second step, Daubechies Wavelet Transform (DWT) is employed for decomposition of normalized TL signal to different components for feature extraction with higher accuracy. Finally in third step, Gradient Ascent Deep Neural Learning is an optimization process for detecting the local maximum (i.e., fault) from the extracted values with help of error function and weight value. When maximum error with low weight value is identified, the fault is detected with lesser time consumption. DWT-GADNL Technique is measured with PLR, Feature Extraction Accuracy (FEA), and Fault Detection Time (FDT). The simulation result shows that DWT-GADNL Technique is able to improve the performance of FEA and reduces FDT and PLR during the transmission and distribution when compared to state-ofthe- art works. Materials and Methods: An electric power system incorporates production, broadcast and distribution of electric energy. To send the electric power to massive load centers, transmission lines are exploited. The fast growth of electric power systems results in huge number of lines in operation and total length. TL are susceptible to faults in case of lightning, short circuits, mis-operation, human errors, overload, etc. Faults resulted in tiny to long power outages for customers. To protect the reliable power system operations, Fault identification, isolation and localization are imperative. The voltage lessened to minimal value, when fault occurs on TL. FD is an essential problem in power system engineering to minimize the PLR. DWT-GADNL Technique is introduced for FD in TL during transmission and distribution. Results: Power Loss due to the fault occurrence during the transmission and distribution is a common problem in electrical power system. To lessen the PLR, the fault is detected in earlier stage. From the sample transmission line, the features are extracted and the values are calculated. When the observed value is lesser than the actual value, the fault is detected through performing the gradient ascent optimization process in transmission line. In this optimization process, the local maxima are identified to reduce the PLR. At different time instances, PLR gets changed. At instance 3, the PLR of proposed DWTGADNL framework is 12% where the PLR of Fuzzy Logic Based Algorithm and Fault Diagnosis Framework are 27% and 19% respectively. Through comparing all the ten instances, PLR is reduced in GWMD-DE technique by 59% and 40% compared to existing respectively. Conclusion: DWT-GADNL Technique is introduced for FD during transmission and distribution with minimal PLR. Sample power TL signal is taken and min-max normalization process performs the various rated values estimation of transmission lines. DWT decomposes normalized TL signal to different components for feature extraction with higher accuracy. Gradient Ascent Deep Neural Learning detects the local maximum from extracted values with help of error function and weight value. When maximum error with low weight value is identified, the fault is detected with lesser time consumption. The performance of DWT-GADNL technique is tested with the metrics such as PLR, FEA and FDT. With the simulations conducted for all techniques, the proposed DWT-GADNL technique presents better performance on FD during transmission and distribution as evaluated to state-of-the-art works. From simulations results, the DWT-GADNL technique lessens PLR by 50% and enhances FEA by 9% than the existing methods.

Introduction: Segmentation and recognition of text from the scene image are a challenging task due to blurred, low-resolution and small sized image. Materials and Methods: Innovative methods have been proposed to address this problem and to recognize the text from the natural scene image. The acquired image is pre-processed by the YUV channel conversion technique and the Y channel image is converted to a gray scale image. Connected Component Based Text Segmentation Algorithm (CCBTSA) and MSER methods are used for segmentation and recognition of text using Optical Character Recognition (OCR). GLCM and FOS features are extracted from the segmented region. The Template matching algorithm is used to extract the text character from the bounding box of the segmented image. Results and Conclusion: Trained SVM classifier is used to classify the image containing text and non-text region. Performances are analyzed based on the recall rate, precision, accuracy, and Fmeasure. From the experimental results, the accuracy of the proposed classifier was obtained as 95%.

Background: Depression is the most underestimated and widespread health condition among people in developing countries. Depression levels among Indian population are rapidly increasing. It can be attributed to work pressure, social challenges, addiction to social media, adoption of the western culture and several other reasons. Indians’ depression levels are as high as 36 percent and shockingly this number is the highest in the world. Objective: What makes this even more alarming is the fact that WHO projects depression to be the second leading cause of disability worldwide by2020. Materials and Methods: This work focuses on Machine learning based Depression prediction by utilizing different brain wave frequency bands. It is carried out by askingthe universal standard Patient Health Questionnaire (PHQ.9) to subjects which are related to respective emotions. Neurosky’s Mind Wave Head kit is connected to the forehead (of subject) and 86 sample values are recorded. Total 85 Samples are trained, whereas 1 data is tested. Results: The MANOGLANISTARA- android App has been designed which sends the Emotional Wellness output (depressed/normal) to the subject via email. This provides the basis of analysis as to whether the subject is suffering from depression or not. Customization of the medication and treatment to such subjects can be initiated by the doctors. In this work, the MATLAB SVM based Depression prediction model is developed by evaluating the data built from Mindwave kit and standard PHQ.9 questionnaire. Work is also extended by using Orange Toolbox for classification of depressed/ normal subjects. Conclusion: In Orange toolbox, Prediction, ROC Analysis and Confusion Matrix are evaluated for different classifiers such as SVM, Naïve Bayes, Classification tree, Random forest and CN2 Rule Inducer. Accuracy, Precision, Sensitivity and Specificity is computed for all the abovementioned classifiers. CN2 Rule Inducer classifier gave higher accuracy of 0.9418, sensitivity 0.9778, Specificity 0.9736 and Precision 0.9778.