Search

In the recent era, the utilization of the H.264 encoder has been increasing due to its outstanding performance in video compression. However, compressing video with reduced power is still a challenging issue faced by H.264 encoders. Thus, the proposed study intends to minimize the power consumption of H.264 encoders on FPGA by optimizing the basic components of H.264, thereby enhancing performance. For this purpose, the elements like Motion Estimation, intra-prediction, transform unit and entropy encoder are optimized through the effective schemes introduced in the proposed work. Initially, the Motion Estimation unit can be alternated by optimizing the fundamental components of Block Matching Algorithms. To design the Block Matching Algorithms, the proposed study introduces low-power arithmetic units like an add-one circuit-based Carry SeLect Adder and Sum of Absolute Difference. With the help of these methods, the Block Matching Algorithms has designed, and the Motion Estimation Unit can be effectively optimized. Then, by adopting a comparator-less reusing method, the intra-prediction unit is optimized. Next, the transform unit is optimized by proposing a Steerable Discrete Cosine Transform and finally, the entropy encoders are optimized by combining Golomb and Rice entropy encoders. The proposed study uses the schemes above to improve the efficiency of H.264 encoders on FPGA. The experimental analysis in the proposed study is done using Xilinx software. The simulation results show that the proposed work obtained higher power, LUTs, delay, PSNR, frequency and MSE than other competing methods. [ABSTRACT FROM AUTHOR]

Regular monitoring of blood glucose levels is essential for the management of diabetes and the development of appropriate treatment protocols. The conventional blood glucose (BG) testing have an intrusive technique to prick the finger and it can be uncomfortable when it is a regular practice. Intrusive procedures, such as fingerstick testing has negatively influencing patient adherence. Diabetic patients now have an exceptional improvement in their quality of life with the development of cutting-edge sensors and healthcare technologies. intensive care unit (ICU) and pregnant women also have facing challenges including hyperglycemia and hypoglycemia. The worldwide diabetic rate has incited to develop a wearable and accurate non-invasive blood glucose monitoring system. This research developed an Internet of Things (IoT) - enabled wearable blood glucose monitoring (iGM) system to transform diabetes care and enhance the quality of life. The TTGOT-ESP32 IoT platform with a red and near-infrared (R-NIR) spectral range for blood glucose measurement has integrated into this wearable device. The primary objective of this gadget is to provide optimal comfort for the patients while delivering a smooth monitoring experience. The iGM gadget is 98.82 % accuracy when used after 10 hours of fasting and 98.04 % accuracy after 2 hours of breakfast. The primary objective points of the research were continuous monitoring, decreased risk of infection, and improved quality of life. This research contributes to the evolving field of IoT-based healthcare solutions by streaming real-time glucose values on AWS IoT Core to empower individuals with diabetes to manage their conditions effectively. The iGM Framework has a promising future with the potential to transform diabetes management and healthcare delivery. [ABSTRACT FROM AUTHOR]

Human computer interaction (HCI) systems are increasing due to the demand for non-intrusive methods for communicating with machines. In this research article, vision based hand gesture recognition (HGR) System has been proposed using machine learning. This proposed system consists of three stages: segmentation, feature extraction and classification. The developed system is to be trained and tested using Sebastian Marcel static hand posture database which is available online. Discrete wavelet transform (DWT) along with modified Speed Up Robust Feature extraction technique has been used to extract rotation and scale invariant key descriptors. Then Bag of Word technique is used to develop the fixed dimension input vector that is required for the support vector machine. The classification accuracy of class 2 and class 4 which corresponds to the 'No' and 'grasp' gesture has reached 98%. The overall classification accuracy of the HGR system using SVM classifier is 96.5% with a recognition time of 0.024 s. Due to fast recognition time, this system can be employed in real time gesture image recognition system. Our HGR system addresses the complex background problem and also improves the robustness of hand gesture recognition. [ABSTRACT FROM AUTHOR]

This investigation practices a grey wolf optimization algorithm to optimize the filter coefficients of the two-dimensional wavelet transform to increase the quality of the decompressed image with lossy compression. The reason for the decrease in image quality in wavelet-based compression is nothing more than a quantization error. Our approach reduces the effect of this quantization error by using an adaptive filtering technique with optimization of the wavelet filter coefficients. Experimental results showed that this optimized filter outperforms existing wavelet filters. [ABSTRACT FROM AUTHOR]

In recent days, total hip arthroplasty (THP) become a very victorious process which relieve the pain and enhances its functioning. The main motive of the paper is to design and assess a synergic deep learning (SDL) for learning and predicting various metrics like duration of stay (DOS), discharge disposition (DD) and inpatient expenses for THA. The next motive is to develop a patient specific payment (PSP) model reporting the complexity level of the patient. By the use of 15 preoperative parameters from 78,335 THA patients for osteoarthritis from National Inpatient Sample and OME databases, the prediction of DOS, DS and inpatient expenses takes place. A set of two evaluation parameters namely accuracy and receiver operating characteristic curve is used for experimentation. In addition, a predictive uncertainty is employed. All patient refined comorbidity cohort for establishing the PSP model. The presented SDL model exhibited better learning with high trustworthiness, receptiveness, and validity in its prediction outcome. The presented model can be applied for the implementation of PSP model for tiered payments depending upon the case complexities. [ABSTRACT FROM AUTHOR]

The modern world uses digital data invariably and the advent of smart phones and cameras add to images and communicating through images in social media is a very common happening due to the exposure to internet and the economical availability of data. Moreover, people explore the web for much news and on different topics. They feel satisfied to look into image type info than textual information. So, image retrieval is paramount nowadays and it is very much useful in many societal and defence applications. The methods used for retrieval started through text based and query based is popularly used now. The content based retrieval uses many stages, approaches, technologies, algorithms etc. It is intended to provide a broad perspective about CBIR in this work. Moreover, the computational and time complexities involved during retrieval relies on the performance of the entire system. One of the aspects that can improve the precision is the reduction of semantic gap. Taking this as the base, we have explored a literature and presented the points related to various points including relevance feedback so as to enable other researchers to carry out experimental work on the suggested areas. [ABSTRACT FROM AUTHOR]

In the MANET, mobile nodes have restricted energy level, so it is very difficult to proceed the communication in a stable manner. The restricted energy level of the node causes poor lifetime of network. These mobile nodes are unrelated with each other, so very difficult to maintain the routing process. The optimized routing only focuses on packet success but does not focus the packet transmission latency, causes the load. A few nodes uses maximum energy causes the network fold down. So, Proposed Improved multi objective data transmission (IMD) technique is applied to balance the load. This technique forwards data in multiple flow manners to various paths. This scheme uses the node for routing process has similar energy node. The conventional route selection algorithm is constructed for data packets are transmitted to different addresses may pursue dissimilar paths. The dissimilar paths are many paths which activities are varied. Every individual path having similar energy nodes, these will manage the overload during communication period. This minimize packet loss rate, and energy consumption, also improves the packet delivery ratio. [ABSTRACT FROM AUTHOR]

The dependency on computers and machines have progressively increased in the past few years and hence human interaction with computers is one of the most actively researched area in science. Many Hand Gesture Recognition (HGR) systems have been developed and they continue to evolve, where in which the gesture interaction becomes smoother and smarter. Gesture recognition is usually implemented in three phases- gesture segmentation, feature extraction and gesture classification, and it's important that the processes involved in these stages are chosen appropriately such that the misrecognition rate will be kept to a minimum. This paper has proposed a novel algorithm that combines 2D-Discrete Wavelet Transform along with Speed Up Robust Feature (SURF) extraction technique to achieve a robust HGR system that is rotation and scale invariant. The proposed method has achieved an overall classification accuracy of 96.9% with the Radial Basis Function Neural Network (RBFNN) classifier. [ABSTRACT FROM AUTHOR]

Recently, Content-based medical image retrieval (CBMIR) systems enable fast diagnosis via the assessment of the visual information in medical application. Most of the state-of-the-art CBMIR systems facing few issues: computationally expensive due to the usage of high dimensional feature vectors and complex classifier/clustering approaches. The reasons behind this are, inability to properly handle the "semantic gap" and the high intra-class versus inter-class variability problem of the medical image database (like radiographic image database). This yields a crucial demand for developing computationally efficient and highly effective retrieval system. For this purpose, the present study proposed an efficient retrieval system which has a four-fold: First, pre-processing and Feature extraction of input image using canonical correlation analysis (CCA). By this approach extracted the feature in both pixel and feature domains and examined more rigorously. Second, applied Fuzzy C means clustering of pixel intensity values as features based on the singular value decomposition. Through this can grouping, the image based on the pixel intensity value. Third, deep convolutional neural network with SVM classifier which makes implementable and requires only a compact feature vector representation of the stored database image with their class levels during retrieval. Finally evaluated the performance based on the measure of Mean Average Precision, Correct rate (CR), Error rate (ER), Accuracy. The classification results and learned features are used for the purpose of retrieving the medical images in a database. The proposed retrieval system performs better than the traditional approach in terms of measuring average value of precision, recall, f-measure and accuracy 95.9%, 94.96%, 95.37% and 95.798% respectively. The suggested approach is best suited towards retrieving the medical images for various part of the body. [ABSTRACT FROM AUTHOR]

Mobile Adhoc network is a network, which has advances of dynamic topology, mobility of nodes and congestion control. It is also an infrastructure less networks. This paper "Congestion control and packet Recovery for cross layer approach" is proposed. Traffic of packets occurred due to congestion and contention problems are reduced in datalink layer and transport layer. Also ensuring that, the superior performance of congestion is a challenging model due to changes in link layer contentions, topological changes and characteristic of wireless channel. The features of this model were localized packet recovery, deterministic, ability to trade of efficiency and peer to peer recovery. It can retrieve the missing packets by storing the copy of packet. Also by assigning priority order to the packets, data traffic congestion rate of higher and lower priority packets are maintained. This will develop the high priority flow to get desired access to the medium and its flow rate of low priority is adjusted, in order to have high flow rate of higher priority. Therefore the overall performance gives the better result than existing method. The simulation of CCPRCLA is verified using ns2 simulator, then graph and experimental results are discussed. [ABSTRACT FROM AUTHOR]

Mg, Mn dual doped ZnS quantum dots (QDs) have been synthesized via co-precipitation method. XRD results revealed that the dual doped ZnS QDs have a cubic structure without forming secondary phase. The particle size was ranged in ~ 2 nm. TEM study portrayed particle assembly and its agglomeration. The scanning electron microscope (SEM) study showed the surface smoothening on samples for Mg addition. Fourier transform infra-red (FTIR) and energy dispersive x-ray (EDX) analysis evidenced the substitution of Mg into Mn:ZnS QDs. UV–visible studies showed that absorption peak intensity was increased and redshifted, shortening of band-gap with increasing Mg doping concentration. A weak UV emission and strong red emission were received from the photoluminescence (PL) investigations. The electrochemical analysis showed a better electrical property for Mg = 2% concentration. Since Mg = 2% doping ratio offers better optical absorption, PL emission, catalytic properties, these materials shall be selected as a suitable candidate for solar and optoelectronic device applications. [ABSTRACT FROM AUTHOR]

Nowadays, cloud storage services increased the popular for data storage in the cloud and retrieve from any location without any time limitations. In recent days one of the most important demands required in cloud is secured data transmission in un-trusted cloud applications. Due to user's data security, the encrypted data is stored in cloud server to protect from unauthorized users. Existing methods offer either data transformation efficiency or security. They fail to maintain end to end security during massive transformations. However, existing methods are not capable of solving the key complexity and avoiding key secrecy disclosure. The main objective of this study is to design and develop a secured efficient data forwarding algorithm for increasing the security level. It is developed specially for untrusted cloud environment. In order to provide a better solution, an efficient framework is proposed for forwarding and retrieving the content in the untrusted cloud environment. Proposed system implements dual privacy for reliable data transmission in an untrusted cloud environment. It develops efficient secret key exposure to minimize the key complexity during data transmission. SEDFA is used for one to many communications as a public key used for encryption and decryption. This scheme provides reliable data transmission between the data owner and end user in untrusted Cloud Environment. Proposed mechanisms minimized the data encryption time, decryption time and improved the communication cost. Based on experimental results, SEDFA reduces the communication cost 5%, encryption time (ET), 2 s, decryption time (DT) 0.5 s. [ABSTRACT FROM AUTHOR]