Multilevel inverter had been paid a lot of attention from the academia and research community in recent times due to its role in high and medium power applications. In this paper, a detailed survey is made on the recently designed multilevel inverter to find the suitability of the inverters for particular applications. Research is performed on various types of multilevel inverters such as: Symmetric, asymmetric, hybrid and modularized multilevel inverter in order to identify the issues in generating more levels at the output. A summary of various issues in multilevel inverter with reduced switch count is provided, so that a novel topology of multilevel inverter can be designed in future. Further, an 81-level switched ladder multilevel inverter using unidirectional and bidirectional switches is designed. Simulation work is carried out using Matlab/Simulink in order to validate the performance of the inverter with change in resistive load and impedance load. The output of the 81-level inverter is fed to a 110 V, 186.5 W single phase induction motor in order to study the characteristics, further speed control of motor is performed by varying the input voltage of the motor and the results are presented.

In this paper, an attempt is made to improve the performance of permanent magnet DC (PMDC) motor using third order sliding mode control. From the derived mathematical modelling for buck converter fed permanent magnet DC motor, expressions for both classical sliding surface (CSS) and proportional integral derivative sliding surface (PIDSS) with the third order sliding mode control is derived and compared analytically. Simulation work is done for PI controller, sliding mode control (SMC), third order CSS and third order PIDSS by using Matlab/Simulink to validate the performance of the above said controllers under no-load condition and various load torque conditions such as: constant load torque, frictional load torque, fan type load torque, propeller type load torque and undefined load torque. Experimental results are obtained with PMDC motor to validate the proposed control method for various speeds with different constant load torque conditions. Comparisons are carried out both in simulation and real time for PI controller, SMC, CSS and PIDSS based on the speed settling time and steady state error. Satisfactory results are obtained and presented in this paper.

A brain tumor is a lethal neurological disease that affects the average performance of the brain and can be fatal. In India, around 15 million cases are diagnosed yearly. To mitigate the seriousness of the tumor it is essential to diagnose at the beginning. Notwithstanding, the manual evaluation process utilizing Magnetic Resonance Imaging (MRI) causes a few worries, remarkably inefficient and inaccurate brain tumor diagnoses. Similarly, the examination process of brain tumors is intricate as they display high unbalance in nature like shape, size, appearance, and location. Therefore, a precise and expeditious prognosis of brain tumors is essential for implementing the of an implicit treatment. Several computer models adapted to diagnose the tumor, but the accuracy of the model needs to be tested. Considering all the above mentioned things, this work aims to identify the best classification system by considering the prediction accuracy out of Alex-Net, ResNet 50, and Inception V3. Data augmentation is performed on the database and fed into the three convolutions neural network (CNN) models. A comparison line is drawn between the three models based on accuracy and performance. An accuracy of 96.2% is obtained for AlexNet with augmentation and performed better than ResNet 50 and Inception V3 for the 120th epoch. With the suggested model with higher accuracy, it is highly reliable if brain tumors are diagnosed with available datasets.

Aerial image-based target object detection has several glitches such as low accuracy in multi-scale target detection locations, slow detection, missed targets, and misprediction of targets. To solve this problem, this paper proposes an improved You Only Look Once (YOLO) algorithm from the viewpoint of model efficiency using target box dimension clustering, classification of the pre-trained network, multi-scale detection training, and changing the screening rules of the candidate box. This modified approach has the potential to be better adapted to the positioning task. The aerial image of the unmanned aerial vehicle (UAV) can be positioned to the target area in real-time, and the projection relation can convert the latitude and longitude of the UAV. The results proved to be more effective; notably, the average accuracy of the detection network in the aerial image of the target area detection tasks increased to 79.5%. The aerial images containing the target area are considered to experiment with the flight simulation to verify its network positioning accuracy rate and were found to be greater than 84%. This proposed model can be effectively used for real-time target detection for multi-scale targets with reduced misprediction rate due to its superior accuracy.

In recent years, human action recognition is modeled as a spatial-temporal video volume. Such aspects have recently expanded greatly due to their explosively evolving real-world uses, such as visual surveillance, autonomous driving, and entertainment. Specifically, the spatio-temporal interest points (STIPs) approach has been widely and efficiently used in action representation for recognition. In this work, a novel approach based on the STIPs is proposed for action descriptors i.e., Two Dimensional-Difference Intensity Distance Group Pattern (2D-DIDGP) and Three Dimensional-Difference Intensity Distance Group Pattern (3D-DIDGP) for representing and recognizing the human actions in video sequences. Initially, this approach captures the local motion in a video that is invariant to size and shape changes. This approach extends further to build unique and discriminative feature description methods to enhance the action recognition rate. The transformation methods, such as DCT (Discrete cosine transform), DWT (Discrete wavelet transforms), and hybrid DWT+DCT, are utilized. The proposed approach is validated on the UT-Interaction dataset that has been extensively studied by past researchers. Then, the classification methods, such as Support Vector Machines (SVM) and Random Forest (RF) classifiers, are exploited. From the observed results, it is perceived that the proposed descriptors especially the DIDGP based descriptor yield promising results on action recognition. Notably, the 3D-DIDGP outperforms the state-of-the-art algorithm predominantly.