Search

One of the most difficult challenges of multimedia transmission during the last two decades has been the retrieval of degraded or missing regions of images and videos while maintaining satisfactory perceptual accuracy. The objective is to retrieve lost data by using the similarity between frames. Usually, error concealment (EC) schemes depend on replacing incorrect data with data that are identical to the initial. This is possible because video contains a high degree of self-similarity. This research focuses on applying an EC approach in transform-domain video sequences. To conduct EC on films, they must first be translated to frames and then transformed using one of the available transformations into frequency-domain images. Using successive frames, it is possible to recover lost or incorrect data from images. Intra-coded frames (I-frames) may be used to recreate lost knowledge in predictive (P-frames) and bidirectional predictive frames (B-frames). I-frame knowledge that has been lost may be restored using previous intra-coded frames. The use of wavelet error concealment generated more precise results than the other techniques. In this study, it was discovered that covering faults in the density sector with wavelets produces more reliable results than the other techniques.

The growth of internet era leads to a major transformation in a storage of data and accessing the applications. One such new trend that promises the endurance is the Cloud computing. Computing resources offered by the Cloud includes the servers, networks, storage, and applications, all as services. With the advent of Cloud, a single application is delivered as a metered service to numerous users, via an Application Programming Interface (API) accessible over the network. The services offered via the Cloud are such as the infrastructure, software, platform, database and web services. The main motivation of this application model is to provide computationally secure key generation to protect the data via encryption. This key generation in the cryptography process falls into three categories in this research work. In the first part, SVM based encryption service model is constructed for which the key generation is from the conventional encryption operation mode with some improvements. To make the process more complex, the optimization techniques are taken into account for the key generation in descendant two methods application model that acts computationally more secure specifically for Cloud environment. The results of security analysis confirm the effectiveness of the proposed application model withstands potentially against various attacks such as Chosen Cipher Attack, Chosen Plain text Attack indistinguishable attacks for files. In case of images, it resists well against statistical and differential attacks. Comparative Analysis shows evidence of the efficiency of the developed pioneering application model quality and strength compared with that of the existing services.

Due to the wide acceptance of White Blood Cells (WBCs) in disease diagnosis, detection and classification of WBC are hot topic. Existing methodologies have some drawbacks such as significant degree of error, higher accuracy, time bound and higher misclassification rate. A WBCs detection and classification called, Jenks Optimized Logistic Convolutional Neural Network (JO-LCNN) method has proposed. Initally, Eulers Principal Axis is used as a convolution model to obtain a rotation invariant form of image by differentiating the background and RBCs, then eliminating them which leaves only the WBCs. By eliminating the wanton features, inherent features are detected contributing to minimum misclassification rate. According to above, Jenks Optimization function is used as a pooling model to obtain feature map for lower resolution. Therefore JO-LCNN is used for removing tiny objects in image and complete nuclei. Finally, Multinomial Logistic classifier is used to classify five types of classes by means of loss function and updating weight according to the loss function, therefore classifying with higher accuracy rate. Using LISC database for WBCs with different parameters as classification accuracy, false positive rate and time complexity are performed. Result shows that JO-LCNN, efficiently improves accuracy with less time, misclassification rate than the state-of-art methods.

Gesture recognition is a type of perceptual computing user interface that allows computers to capture and interpret human gestures as commands. Gestures are generally the movement of the hands which is a form of non-verbal communication. We use gestures as input to control devices or applications or websites. By using the gestures, we directly open or manipulate the website for the users. When the user uses the gesture, the system captures the gesture and compares it with the stored gesture data. If the gesture matches the data, then the required website will be manipulated. These gestures are widely helpful for the people who are blind and unable to type. The main objective of the project is to deliver user friendly access to the web contents. The vision based technology of hand gesture recognition is an important part of human-computer interaction (HCI), thus stepping into the path of future and our project is one such kind of stepping stone. Our project really concerns the people who are not able to search contents on the web through text search. We provide an improvisable solution where it paves a way for research and development.

Blood analysis is regarded as the one of the most predominant examinations in medicine field to obtain patient physiological state. A significant process in the classification of white blood cells (WBC) is blood sample analysis. An automatic system that is potential of identifying WBC aids the physicians in early disease diagnosis. In contrast to previous methods, thus resulting in trade-off among computational time (CT) and performance efficiency, an interpolative Leishman-stained multi-directional transformation invariant deep classification (LSM-TIDC) for WBC is presented. LSM-TIDC method discovers possibilities of interpolation and Leishman-stained function, because they require no explicit segmentation, and yet they eliminated false regions for several input images. Next, with the preprocessed images, optimal and relevant features are extracted by applying multi-directional feature extraction. To identify and classify blood cells, a system is developed via the implementation of transformation invariant model for extraction of nucleus and subsequently performs classification through convolutional and pooling characteristics. The proposed method is evaluated by extensive experiments on benchmark database like blood cell images from Kaggle. Experimental results confirm that LSM-TIDC method significantly captures optimal and relevant features and improves the classification accuracy without compromising CT and computational overhead.

Terahertz radiation has drawn enormous attention in recent times due to its various application possibilities. This chapter reviews various emerging trends and well-established technologies in Terahertz biomedical. Due to its extraordinary sensing capabilities, non-invasive, non-ionizing properties, sensitive instrumentations for spectroscopy and imaging, Terahertz has found various biomedical sensing applications from biomolecules, proteins to cells and tissues. This chapter highlights terahertz device engineering, system technologies, range of materials, aiming at various biomedical applications. It also includes emerging topics such as terahertz biomedical imaging, pattern recognition and tomographic reconstruction by machine learning and artificial intelligence, for possible biomedical imaging applications.

The effect of traffic congestion has a major impact on the loss of time in an emergency. Smart traffic management systems utilize sensors, GPS, and automation to monitor and direct the traffic inspector to reduce congestion. Nowadays there is a detrimental flaw in traffic management, especially in an emergency. In metropolitan areas, the average distance from an emergency department, is 3.6miles, this distance can be easily covered in mere minutes, but due to heavy traffic congestion, there is always a delay in reaching out to the nearest hospital which leads to increase in death rate. The main objective of this project is to decrease the travelling time of the ambulance. It enriches users with prior information about traffic local convenience real time running information which reduced the travelling time of the commuters and enhances the survival rate. Implementation, the app is going to be used by Ambulance drivers and traffic inspectors. Ambulance driver builds his profile by entering his details such as Vehicle Number, name etc., Similarly, the traffic inspector will build his profile by entering the route details in which he's currently working on. In an emergency, a driver needs to select a route in which way he's going to travel to the hospital. And the traffic inspectors in the corresponding route gets an alert and the traffic inspector will be able to track the ambulance location and clear the traffic and make the way for the ambulance accordingly in prior.

Aim: Further to our reports on chip-integrable uncooled terahertz microbolometer arrays, compatible with medium-scale semiconductor device fabrication processes, the possibility of the development of chip-integrable medical device is proposed here. Methods: The concept of graphene-based nanopatch antennas with design optimization by the finite element method (FEM) is explored. The high-frequency structure simulator (HFSS) utilized fine FEM solver for analyzing empirical mode decomposition preprocessing and for modeling and simulating graphene antennas. Results: Graphene nanopatch antennas exhibited tunable features with varying patch dimensions and dependence on substrate material permittivity. Conclusion: This work implements reconfigurable graphene nanopatch antenna compatible with terahertz microbolometer arrays. This design concept further develops on-chip medical devices for possible screening of cancer cell with terahertz image processing.

One of the most important and difficult research fields is newborn jaundice grading. The mitotic count is an important component in determining the severity of newborn jaundice. The use of principal component analysis (PCA) feature selection and an optimal tree strategy classifier to produce automatic mitotic detection in histopathology images and grading is given. This study makes use of real-time and benchmark datasets, as well as specific approaches for detecting jaundice in newborn newborns. According to research, the quality of the feature may have a negative impact on categorization performance. Additionally, compressing the classification method for exclusive main properties can result in a classification performance bottleneck. As a result, identifying appropriate characteristics for training the classifier is required. By combining a feature selection method with a classification model, this is possible. The major outcomes of this study revealed that image processing techniques are critical for predicting neonatal hyperbilirubinemia. Image processing is a method of translating analogue images to digital formats and manipulating them. The primary goal of medical image processing is to collect information useful for disease detection, diagnosis, monitoring, and therapy. Image datasets can be used to validate the performance of newborn jaundice detection. When compared to conventional approaches, it offers results that are accurate, quick, and time efficient. Accuracy, sensitivity, and specificity, which are common performance indicators, were also predictive.

This paper highlights the prospect of design and development of a terahertz medical screening system, giving an overview of existing devices, systems, for THz spectroscopy and imaging of biological samples (e.g., cell, tissue imaging or screening). Considering the non-ionizing nature of THz waves along with its reasonable soft-tissue sensitivity, terahertz instrumentation has opened up possibilities for medical screening devices. Some THz imaging systems presently use raster scanning for calculation of image region of interest. Here, a particular system is proposed as a medical screening device and factors like signal-to-noise ratio, image resolution, image contrast, etc., have been described and correlated with relevant clinical results for exploring possible prospects in medical applications of terahertz waves.

With the progress of cloud computing, more users are attracted by its strong and cost-effective computation potentiality. Nevertheless, whether Cloud Service Providers can efficiently protect Cloud Users data confidentiality (DC) remains a demanding issue. The CU may execute several applications with multicast needs. In Cloud different techniques were used to provide DC with multicast necessities. In this work, we aim at ensuring DC in the cloud. This is achieved using a two-step technique, called Fat Tree Data Confidential Recurrent Neural Network (FT-DCRNN) in a cloud environment. The first step performs the construction of Fat Tree based on Multicast model. The aim to use Fat Tree with Multicast model is that the multicast model propagates traffic on multiple links. With the Degree Restrict Multicast Fat Tree construction algorithm using a reference function, the minimum average between two links is measured. With these measured links, multicast is said to be performed that in turn improves the throughput and efficiency of cloud service. Then, with the objective of providing DC for the multi-casted data or messages, DCRNN model is applied. With the Non-linear Recurrent Neural Network using Logistic Activation Function, by handling complex non-linear relationships, average response time is said to be reduced.

This article describes with Shunt Active Power Filter (SAPF) for compensation of reactive Power (P), current harmonics. An ADALINE based neural network current estimator can control the SAPF to maintain sinusoidal source currents and unity Power Factor (PF). The three-phase (III-Phase) load currents are sensed and measured by Least Mean Square(LMS) algorithm based on ADALINE, the weights obtained with the help of online calculation, and then these weights are multiplied with the help of unit vector, which gives the fundamental frequency of Load Currents (LC). The DC link voltage (V) of the V Source Converter, maintained at a constant value, and it can work as the SAPF, and various simulation results are presented under the steady-state conditions using the PI controller. The switching action of VSC is performed using Hysteresis Current Control based on pulse width modulation, which makes the source currents should follow the reference source currents. The MATLAB based simulation results and implementation results are obtained to determine the efficacy of the SAPF with ADALINE based neural network control for load compensation. SAPF system meets IEEE Standard 519 recommended harmonic standards for different rated nonlinear loads under balanced supply conditions.