Vignan University

About: Vignan University is a education organization based out in Guntur, Andhra Pradesh, India. It is known for research contribution in the topics: Control theory & CMOS. The organization has 1138 authors who have published 1381 publications receiving 7798 citations.

Weighted SVMBoost based Hybrid Rule Extraction Methods for Software Defect Prediction

Abstract: The software testing efforts and costs are mitigated by appropriate automatic defect prediction models. So far, many automatic software defect prediction (SDP) models were developed using machine learning methods. However, it is difficult for the end users to comprehend the knowledge extracted from these models. Further, the SDP data is of unbalanced in nature, which hampers the model performance. To address these problems, this paper presents a hybrid weighted SVMBoost-based rule extraction model such as WSVMBoost and Decision Tree, WSVMBoost and Ripper, and WSVMBoost and Bayesian Network for SDP problems. The extraction of the rules from the opaque SVMBoost is carried out in two phases: (i) knowledge extraction, (ii) rule extraction. The experimental results on four NASA MDP datasets have shown that the WSVMBoost and Decision tree hybrid yielded better performance than the other hybrids and WSVM.

Heuristic Scale to Estimate Premature Malaria Parasites: Scope in Microscopic Blood Smear Images

Abstract: Objective: Malaria is one of the epidemic diseases and early detection of malaria symptoms in the patients using the current manual procedures are skeptical, as the diagnosis patterns depends more on the experience of professionals. To overcome the challenges, in this paper we are proposing computer aided model to support in malaria detection at early stages using Microscopic Blood Smear Images analysis using machine learning. Methods/Statistical Analysis: There are many computer aided models that were proposed and adapted in the process of addressing the diagnosis models. Some models like machine learning, image processing, neural network based solutions etc are adapted, which reflects more insights into the process. However, the issue of gaps in accuracy still persists, and the proposed model of Heuristic Scale to Estimate Premature Malaria Parasites Scope (SEMPS) with multi stage processing of the microscopic images of blood smear is processed. Findings: The proposed model is compared with the benchmark models like SVM and Bayesian, the outcome in terms of efficiency of the model is imperative from the results. The proposed model has resulted in more effective and accurate detection of malaria symptoms in the test cases, and the result accuracy is higher than the other two benchmarking models of SVM and Bayesian techniques chosen for comparative analysis. Improvements: The computational complexity of the SEMPS is evinced as linear, where the majority of benchmarking models are found to be up-hard.

NIR luminescence features of Nd3+ ion in lithium antimonite glass system

Abstract: Glasses of the composition 40Li2O‒(60-x)Sb2O3: xNd2O3(x = 0.2, 0.4, 0.6, 0.8 and 1.0 mol%) were synthesized by melt quenching technique. The structural and optical characteristics were investigated as a function of Nd2O3concentration. From the optical absorption spectra J-O intensity parameters (Ωλ, λ = 2,4 and 6) were evaluated; the parameters are found to be in the order: Ω2 > Ω6 > Ω4. The emission spectra recorded at λexc = 808 nm) exhibited three intense bands at 875 nm, 1053 nm and 1328 nm attributed to4F3/2 → 4I9/2,11/2,13/2 transitions, respectively. The intensity of 4F3/2 → 4I11/2 (1.053 μm) emission band is found to be the highest among the three bands. With increasing the concentration of Nd2O3 upto 0.8 mol%, intensity of all emission bands exhibited an increasing trend. Beyond 0.8 mol%, a decrease in the intensity of PL output is observed; this is attributed to concentration quenching losses and increased phonon losses. From emission spectra, various radiative parameters such as transition probability, AR, branching ratio β, and radiative life time, τR, were evaluated for all glass samples. The analysis of the results indicated glasses mixed with 0.8 mol% of Nd3+exhibited the highest efficiency of 1.053 μm emission. The reasons for such high efficiency were further identified using structural analysis of the host glass using IR spectral studies.

Investigation on Rotated Rectangular Slots to Improve the Circular Polarization in Cylindrical Dielectric Resonator Antenna

Abstract: To achieve wideband circular polarization (CP) characteristics, a new structure with a single feeding technique has been proposed. In the proposed CP structure, to excite the cylindrical dielectric resonator (CDR) four asymmetrical rectangular slots are etched on the ground plane, each rectangular slot is rotated by an angle of ( $\theta = 30^{\circ }$ ) with respect to its adjacent slots. The electric fields at each slot are separated by 30° in space with respect to its adjacent slot to create 90° angular separations between the E-field components. Two orthogonal broadside modes ( ${HE}_{11\delta }$ ) are excited inside the cylindrical dielectric resonator antenna (CDRA) independently to obtained CP characteristics. To compare the simulated outcomes with the experimental results, fabrication of the proposed antenna prototype has been done. The measured percentage of bandwidth achieved by the proposed radiator for $\vert \text{S}_{11}\vert $ and CP is 26.73% and 23.59%, respectively, and the whole usable axial ratio (AR) frequency bands overlap the impedance passband of the presented CP structure. The proposed radiator has achieved the maximum gain and radiation efficiency of 3.4 dB and 95% over the operating frequency range of the designed antenna, respectively. The proposed CP DRA has been configured for the WLAN band application.

An intellectual procurement innovation of smart grid power system with wireless communication networks based on machine learning

Abstract: The phased array antenna is one of the most significant applications in fifth-generation mobile networks. It is one of the most important applications in fifth-generation networks. An electric power source that powers the whole application, including the antenna's root, is required. Even with the most outstanding design, if the programme does not have a sound power supply system with minimal packet loss and can't Path find performance, it will be rendered ineffective. When seen from the perspective of the multiplex information, Machine Learning comprises a communication network based on the Internet that transmits information to the control centre via the objects (IOT). To put it another way, the proposed communication infrastructure, via the provision of, and the chance micro-grid state to collect, analyze, and two-way communication link control information, offers the chance to resolve the voltage regulation issues. This cutting-edge communication infrastructure, as well as a suggested state estimation filter focused on improving speed and performance in renewable energy production, are both examples of creative communication infrastructure. Current research is focused on analyzing and enumerating a range of energy abundances in the context of smart grids, which are now in their fifth generation. Rather than concentrating on the future development plan, which should be a problem of illusion, it should concentrate on the composition of the future potential of smart grid communications framework. An in-depth investigation to give evidence to the Machine learning will help intelligent networks in the future conduct a thorough evaluation.