R.V. College of Engineering

The Image classification is one of the preliminary processes, which humans learn as infants. The fundamentals of image classification lie in identifying basic shapes and geometry of objects around us. It is a process which involves the following tasks of pre-processing the image (normalization), image segmentation, extraction of key features and identification of the class. The current image classification techniques are much faster in run time and more accurate than ever before, they can be used for extensive applications including, security features, face recognition for authentication and authorization, traffic identification, medical diagnosis and other fields. The idea of image classification can be solved by different approaches. But the machine learning algorithms are the best among them. These algorithms are based on the idea proposed years ago, but couldn't be implemented due to lack of computational power. With the idea of deep learning, the models are trained better and are able to identify different levels of image representation. The convolutional neural networks revolutionized this field by learning the basic shapes in the first layers and evolving to learn features of the image in the deeper layers, resulting in more accurate image classification. The idea of Convolutional neural network was inspired by the hierarchical representation of neurons by Hubel and Wiesel in 1962, their work was based on the study of stimuli of the visual cortex in cat. It was a fundamental breakthrough in the field of computer vision in understanding the working of visual cortex in humans and animals. In this paper feature of an images is extracted using convolution neural network using the concept of deep learning. Further classification algorithms are implemented for various applications.

In this study, cupric oxide (CuO) nanoparticles were synthesized via sonochemical method. The samples were characterized by X-ray diffraction, Fourier transform infrared spectroscopy, scanning electron microscope, and transmission electron microscopy. The spherical CuO nanoparticles were dispersed in sodium hexametaphosphate under sonication (25 kHz) to analyze the particle size distribution and UV absorption spectra. Using these absorption spectra, we further examined the CuO nanoparticle to explore the possibility of using them as a material for applications such as solar cell and textile production.

Deep learning has gained a tremendous influence on how the world is adapting to Artificial Intelligence since past few years. Some of the popular object detection algorithms are Region-based Convolutional Neural Networks (RCNN), Faster-RCNN, Single Shot Detector (SSD) and You Only Look Once (YOLO). Amongst these, Faster-RCNN and SSD have better accuracy, while YOLO performs better when speed is given preference over accuracy. Deep learning combines SSD and Mobile Nets to perform efficient implementation of detection and tracking. This algorithm performs efficient object detection while not compromising on the performance.

Internet of Things (IoT) is an integration of the Sensor, Embedded, Computing, and Communication technologies. The purpose of the IoT is to provide seamless services to anything, anytime at any place. IoT technologies play a crucial role everywhere, which brings the fourth revolution of disruptive technologies after the internet and Information and Communication Technology (ICT). The Research & Development community has predicted that the impact of IoT will be more than the internet and ICT on society, which improves the well-being of society and industries. Addressing the predominant system-level design aspects like energy efficiency, robustness, scalability, interoperability, and security issues result in the use of a potential IoT system. This paper presents the current state of art of the functional pillars of IoT and its emerging applications to motivate academicians and researches to develop real-time, energy-efficient, scalable, reliable, and secure IoT applications. This paper summarizes the architecture of IoT, with the contemporary status of IoT architectures. Highlights of the IoT system-level issues to develop more advanced real-time IoT applications have been discussed. Millions of devices exchange information using different communication standards, and interoperability between them is a significant issue. This paper provides the current status of the communication standards and application layer protocols used in IoT with the detailed analysis. The computing paradigms like Cloud, Cloudlet, Fog, and Edge computing facilitate IoT with various services like data offloading, resource and device management, etc. In this paper, an exhaustive analysis of Edge Computing in IoT with different edge computing architectures and existing status are deliberated. The widespread adoption of IoT in society has resulted in privacy and security issues. This paper emphasizes on analyzing the security challenges, privacy and security threats, conventional mitigation techniques, and further scope for IoT security. The features like fewer memory footprints, scheduling, real-time task execution, fewer interrupt, and thread switching latency of Real-Time Operating Systems (RTOS) enables the development of time critical IoT applications. Also, this review offers the analysis of the RTOS's suitable for IoT with the current status and networking stack. Finally, open research issues in IoT system development are discussed.

Natural fibres will take a major role in the emerging "green" economy based on energy efficiency, the use of renewable materials in polymer products, industrial processes that reduce carbon emissions and recyclable materials that minimize waste. Natural fibres are a kind of renewable resources, which have been renewed by nature and human ingenuity for thousands of years. They are also carbon neutral; they absorb the equal amount of carbon dioxide they produce. These fibers are completely renewable, environmental friendly, high specific strength, non-abrasive, low cost, and bio-degradability. Due to these characteristics, natural fibers have recently become attractive to researchers and scientists as an alternative method for fibers reinforced composites. This review paper summarized the history of natural fibers and its applications. Also, this paper focused on different properties of natural fibers (such as hemp, jute, bamboo and sisal) and its applications which were used to substitute glass fiber.

Object Detection algorithms find application in various fields such as defence, security, and healthcare. In this paper various Object Detection Algorithms such as face detection, skin detection, colour detection, shape detection, target detection are simulated and implemented using MATLAB 2017b to detect various types of objects for video surveillance applications with improved accuracy. Further, various challenges and applications of Object Detection methods are elaborated.

We propose a method for estimating depth from images captured with a real aperture camera by fusing defocus and stereo cues. The idea is to use stereo-based constraints in conjunction with defocusing to obtain improved estimates of depth over those of stereo or defocus alone. The depth map as well as the original image of the scene are modeled as Markov random fields with a smoothness prior, and their estimates are obtained by minimizing a suitable energy function using simulated annealing. The main advantage of the proposed method, despite being computationally less efficient than the standard stereo or DFD method, is simultaneous recovery of depth as well as space-variant restoration of the original focused image of the scene.

Metal-organic framework (MOF) of Ni-MOF, Co-MOF, and Ni/Co-MOF were synthesized by a facile hydrothermal method using Trimesic acid as structure directing linker. The physico-chemical properties of the synthesized MOFs were characterized by P-XRD (powder X-ray diffraction), FT-IR (fourier transform infrared spectroscopy), SEM-EDS (scanning electron microscopy/energy-dispersive X-ray spectroscopy), HR-TEM (high-resolution transmission tlectron microscope) and BET (Brunner Emmett Teller) surface area techniques. The supercapacitance performance of these MOFs were studied by electroanalytical techniques such as cyclic voltammetry (CV), chronopotentiometry (CP) and electrochemical impedance spectroscopy (EIS). Amongst the MOFs investigated, Ni/Co-MOF exhibited highest specific capacitance (C _s ) of 2041 F g ^−1 at a scan rate of 2 mV s ^−1 and 980 F g ^−1 at a current density of 2.5 A g ^−1 . Ni/Co-MOFs delivered a maximum energy density (ED) of 55.7 W h Kg ^−1 at a corresponding power density (PD) of 1 K W kg ^−1 and maximum PD of 9.8 K W kg ^−1 at an ED of 41.6 W h Kg ^−1 . An outstanding supercapacitance performance with superior columbic efficiency of 98.4% and capacitive retention of 73% after 5000 cycles marks this material as potential candidate for supercapacitors (SCs). A comparative electrochemical study of these MOFs were made in three electrode system, further electrochemical performance was corelated with their physico-chemical properties.

Global climatic changes and increased carbon footprints provided the main impetus for the decrease in the use of fossil fuels for electricity generation and transportation. Matured manufacturing technologies of solar PV panels and on-shore and off-shore windmills have brought down the cost of generation of electricity using solar energy on par with conventional fossil fuel. Initially, solar and wind power generation was envisioned for microgrids, serving small local communities. However, advancements in power electronics have now facilitated large solar and wind farms to be integrated with main power grids. In this context, hosting capacity, which is the amount of distributed energy resources a grid can accommodate, without significant infrastructure up-gradation, has gained importance. In determining the hosting capacity at a particular location, the uncertainties of wind and solar power generation play a role. Effective forecasting models using time-series weather data can be built to predict wind and solar power generation. This forecast is essential to ensure proper grid operation and control when renewable energy sources are already installed. The forecast is also useful in the planning stages for investment decisions and distribution system planning. While long-term forecasts are rarely needed for the operation of integrated grids, accurate short-term predictive models are necessary for scheduling. This paper presents an extensive review of various forecast models available in the literature. The study mainly focuses on the short-term forecast, providing a critical review of the duration of data used in each model and a synoptic comparison of their performance indices.

Diagnosis and treatment of ailments require that precise information be obtained through various modalities of medical images such as Computed Tomography (CT), Positron Emission Tomography (PET), and Magnetic Resonance Imaging (MRI) etc. Often these techniques give some information regarding the ailment which is incomplete and ambiguous. In this scenario, image fusion gains utmost importance as the overall quality of scans can be improved. Thus, fusing various multi – modality medical images into a distinct image with more detailed anatomical information and high spectral information is highly desired in clinical diagnosis. In this work, MRI and PET images are preprocessed along with enhancing the quality of the input images which are degraded and non-readable due to various factors by using spatial filtering techniques like Gaussian filters. The enhanced image is then fused based on Discrete Wavelet Transform (DWT) for brain regions with different activity levels. The system showed around 80-90% more accurate results with reduced color distortion and without losing any anatomical information in comparison with the existing techniques in terms of performance indices including Average Gradient (AG) and Spectral Discrepancy (SD), when tested on three datasets - normal axial, normal coronal and Alzheimer's brain disease images.

In this work, an environmental benign, sugarcane juice (SCJ) was applied as an eco-friendly stabilizing agent to synthesize copper oxide nanoparticles (CuO NPs). To produce CuO NPs, 2, 5 and 10 ml of juice were added during the synthesis. The produced CuO NPs were characterized using FTIR, which confirmed the transformation of functional groups through Cu–O. The XRD analysis confirmed the monoclinic crystalline structure and purity of the material. SEM images confirm the nanoparticles formation. Quantitative estimation of Cu, O and C present in samples were carried out by EDS. Square, rectangular, cubic cylindrical and spherical shaped particles observed from the TEM micrographs. Furthermore, Micro-raman and X-ray photoelectron spectroscopy (XPS) were taken to assure the formation of CuO NPs. The results revealed that the SCJ is a good stabilizing agent which reduces the size of particles significantly at higher concentrations and altered shapes to spherical. Hence, it sugarcane juice could be applied as a green stabilizing agent to fabricate the CuO NPs. Antibacterial activity of CuO NPs was assessed against some pathogenic bacteria.

Big data analytics and processing require complex architectures and sophisticated techniques for extracting useful information from the accumulated information. Visualizing the extracted data for real-time solutions is demanding in accordance with the semantics and the classification employed by the processing models. This article introduces fuzzy-optimized data management (FDM) technique for classifying and improving coalition of accumulated information based semantics and constraints. The dependency of the information is classified on the basis of the relationships modeled between the data based on the attributes. This technique segregates the considered attributes based on similarity index boundaries to process complex data in a controlled time. The performance of the proposed FDM is analyzed using a real-time weather forecast dataset consisting of sensor data (observed) and image data (captured). With this dataset, the functions of FDM such as input semantics analytics and classification based on similarity are performed. The metrics classification and processing time and similarity index are analyzed for the varying data sizes, classification instances, and dataset records. The proposed FDM is found to achieve 36.28% less processing time for varying classification instances, and 12.57% high similarity index.

Speech impaired people use hand based gestures to communicate. Unfortunately, the vast majority of the people are not aware of the semantics of these gestures. In a attempt to bridge the same, we propose a real time hand gesture recognition system based on the data captured by the Microsoft Kinect RGB-D camera. Given that there is no one to one mapping between the pixels of the depth and the RGB camera, we used computer vision techniques like 3D contruction and affine transformation. After achieving one to one mapping, segmentation of the hand gestures was done from the background noise. Convolutional Neural Networks (CNNs) were utilised for training 36 static gestures relating to Indian Sign Language (ISL) alphabets and numbers. The model achieved an accuracy of 98.81% on training using 45,000 RGB images and 45,000 depth images. Further Convolutional LSTMs were used for training 10 ISL dynamic word gestures and an accuracy of 99.08% was obtained by training 1080 videos. The model showed accurate real time performance on prediction of ISL static gestures, leaving a scope for further research on sentence formation through gestures. The model also showed competitive adaptability to American Sign Language (ASL) gestures when the ISL models weights were transfer learned to ASL and it resulted in giving 97.71% accuracy.

The primitive machine learning algorithms that are present break down each problem into small modules and solve them individually. Nowadays requirement of detection algorithm is to work end to end and take less time to compute. Real-time detection and classification of objects from video records provide the foundation for generating many kinds of analytical aspects such as the amount of traffic in a particular area over the years or the total population in an area. In practice, the task usually encounters slow processing of classification and detection or the occurrence of erroneous detection due to the incorporation of small and lightweight datasets. To overcome these issues, YOLO (You Only Look Once) based detection and classification approach (YOLOv2) for improving the computation and processing speed and at the same time efficiently identify the objects in the video records. The classification algorithm creates a bounding box for every class of objects for which it is trained, and generates an annotation describing the particular class of object. The YOLO based detection and classification (YOLOv2) use of GPU (Graphics Processing Unit) to increase the computation speed and processes at 40 frames per second.

This research paper looks into a state of the art tool for interactive packet manipulation named Scapy which is written in Python language; detail out some vital commands, strengths and weakness, protocols supported, usage explained with snapshots, tracking packets being sent and received using wireshark and scope of future integration with newer protocols. The research paper, tries to give a brief introduction and readable usage and applications using the Scapy tool.

Predictive models for determining the sale price of houses in cities like Bengaluru is still remaining as more challenging and tricky task. The sale price of properties in cities like Bengaluru depends on a number of interdependent factors. Key factors that might affect the price include area of the property, location of the property and its amenities. In this research work, an analytical study has been carried out by considering the data set that remains open to the public by illustrating the available housing properties in machine hackathon platform. The data set has nine features. In this study, an attempt has been made to construct a predictive model for evaluating the price based on the factors that affect the price. Modeling explorations apply some regression techniques such as multiple linear regression (Least Squares), Lasso and Ridge regression models, support vector regression, and boosting algorithms such as Extreme Gradient Boost Regression (XG Boost). Such models are used to build a predictive model, and to pick the best performing model by performing a comparative analysis on the predictive errors obtained between these models. Here, the attempt is to construct a predictive model for evaluating the price based on factors that affects the price.

Present investigation was focused on the effect of strain rate and lay-up configuration on tensile and flexural behaviour of four combinations of fiber metal laminates. Tensile and flexural tests were conducted on universal test machine as per standards. The result shows that the tensile strength increased with increasing strain rate. However the flexural strength decreased with increasing strain rate. Both tensile and flexural strength are maximum for carbon based FML structures, minimum for glass based FML and hybrid FML structure lies between them. The observations on both tensile and flexural failure mechanisms deduced from a microscopic study of the fractured specimens are presented.

Rapid increase in volume and types of solid and hazardous waste due to continuous economic growth, urbanization and industrialization, is becoming a burgeoning problem for national and local governments to ensure effective and sustainable management of waste. It is estimated that in 2006 the total amount of municipal solid waste generated globally reached 2.02 billion tones, representing a 7% annual increase since 2003 (Global Waste Management Market Report 2007). The segregation, handling, transport, and disposal of waste needs to be properly managed to minimize the risk to the health and safety of patients, the public, and the environment. The economic value of waste is best realized when it is segregated. Currently, there is no such system of segregation of dry, wet and metallic wastes at the household level. This paper proposes an Automated Waste Segregator (AWS) which is a cheap, easy to use solution for a segregation system for household use, so that it can be sent directly for processing. It is designed to sort the refuse into metallic waste, wet waste and dry waste. The AWS employs parallel resonant impedance sensing mechanism to identify metallic items, and capacitive sensors to distinguish between wet and dry waste. Experimental results show that the segregation of waste into metallic, wet and dry waste has been successfully implemented using the AWS.

This research aimed to assess the fitness of fiber collected from the bark of Acacia concinna (AC) plant for composite reinforcement. Chemical analysis report exposed that ACF has the cellulose and hemicellulose content of 59.43 wt. % and 12.78 wt. %, respectively. Different chemical compositions and relevant functional groups existing in the ACF were identified thought the Fourier Transform-Infrared (FTIR) Analysis. Crystallinity index (27.5%) and crystalline size (4.17 nm) of the ACF were calculated by the X-ray diffraction analysis. Surface of the ACF was investigated with the aid of Scanning electron microscope (SEM) and Atomic force microscope (AFM). Comparatively higher thermal stability (225°C), kinetic activation energy (69.33 KJ/mol) and lower density (1365 kg/m3) of ACF are the required assets for reinforcement in the polymer matrix.

Dispersion of functional inorganic nano-fillers like TiO2 within polymer matrix is known to impart excellent photobactericidal activity to the composite. Epoxy resin systems with Ag+ ion doped TiO2 can have combination of excellent biocidal characteristics of silver and the photocatalytic properties of TiO2. The inorganic antimicrobial incorporation into an epoxy polymeric matrix was achieved by sonicating laboratory-made nano-scale anatase TiO2 and Ag-TiO2 into the industrial grade epoxy resin. The resulting epoxy composite had ratios of 0.5–2.0 wt% of nano-filler content. The process of dispersion of Ag-TiO2 in the epoxy resin resulted in concomitant in situ synthesis of silver nanoparticles due to photoreduction of Ag+ ion. The composite materials were characterized by DSC and SEM. The glass transition temperature (Tg) increased with the incorporation of the nanofillers over the neat polymer. The materials synthesized were coated on glass petri dish. Anti-biofilm property of coated material due to combined release of biocide, and photocatalytic activity under static conditions in petri dish was evaluated against Staphylococcus aureus ATCC6538 and Escherichia coli K-12 under UV irradiation using a crystal violet binding assay. Prepared composite showed significant inhibition of biofilm development in both the organisms. Our studies indicate that the effective dispersion and optimal release of biocidal agents was responsible for anti-biofilm activity of the surface. The reported thermoset coating materials can be used as bactericidal surfaces either in industrial or healthcare settings to reduce the microbial loads.