Search

Deep neural network (DNN) based computer-aided breast tumor diagnosis (CABTD) method plays a vital role in the early detection and diagnosis of breast tumors. However, a Brightness mode (B-mode) ultrasound image derives training feature samples that make closer isolation toward the infection part. Hence, it is expensive due to a meta-heuristic search of features occupying the global region of interest (ROI) structures of input images. Thus, it may lead to the high computational complexity of the pre-trained DNN-based CABTD method. This paper proposes a novel ensemble pre-trained DNN-based CABTD method using global- and local-ROI-structures of B-mode ultrasound images. It conveys the additional consideration of a local-ROI-structures for further enhancing the pre-trained DNN-based CABTD method’s breast tumor diagnostic performance without degrading its visual quality. The features are extracted at various depths (18, 50, and 101) from the global and local ROI structures and feed to support vector machine for better classification. From the experimental results, it has been observed that the combined local and global ROI structure of small depth residual network ResNet18 (0.8 in %) has produced significant improvement in pixel ratio as compared to ResNet50 (0.5 in %) and ResNet101 (0.3 in %), respectively. Subsequently, the pre-trained DNN-based CABTD methods have been tested by influencing local and global ROI structures to diagnose two specific breast tumors (Benign and Malignant) and improve the diagnostic accuracy (86%) compared to Dense Net, Alex Net, VGG Net, and Google Net. Moreover, it reduces the computational complexity due to the small depth residual network ResNet18, respectively [ABSTRACT FROM AUTHOR]

Potholes are the major causes of road accidents. There is no proper maintenance in the local areas and reporting is done manually .The model is designed to be installed in a vehicle to report the potholes using Image Processing with the help of Raspberry-Pi. This is achieved using various image processing edge detection algorithms using Open CV software in python language. Edge detection techniques have been applied by the combination of various morphological filtering techniques using the combination of various smoothing filters. [ABSTRACT FROM AUTHOR]

These days the Medical services sector has driven science and information such that it is influenced by innovations based on wireless-detecting nodes. Patients are going up against a risky condition of unexpected passing in view of the heart issues and attack which is an immediate aftereffect of the nonexistence of good clinical care to patients at the necessary time. Our designed system brings into play the sensors that allow the recognition of the pulse of an individual using the heartbeat detection whether or not the person is at home. The sensor is then interfaced with a microcontroller that licenses checking of pulse readings along with oxygen levels and directs them over the web. The individual may calibrate the upper limit and lower limit of a heartbeat. After the process is done, the framework begins verifying, and it updates about the patient's pulse and oxygen level status over the web utilizing the MQTT convention and cautions the specialists just as concerned clients. On the off chance that anytime the individual signs in for checking the system, in the same manner, it shows the live pulse of the patient. Along these lines, concerning may screen pulse rate along with oxygen level from anywhere and the client can be rescued without any delay [ABSTRACT FROM AUTHOR]

In Internet of Things (IoT), there are many applications involved one among which is smart city. Smart city involves maintaining activities of the traffic system, CCTV surveillance camera which kept in many locations to monitor the abnormal activities, human movement detection, energy measurement etc. Among which, surveillance camera plays major role in security purpose. Basically, in smart city camera is kept on and it stores the entire situation happening around the environment which results in major challenge in the storage management and security level. To avoid this criteria, in this paper it conveys a scheme which enable CCTV surveillance system to store only when there is detection of any movement of human and occurring of any abnormal event in city. A new approach is performed in modifying the Advanced Encryption Standard method for smart city which is IoT based system. The main aim of this cryptography is to maintain the storage management efficiently and also it provides lesser execution time by providing less weight age in processing an image than other cryptography mechanism. [ABSTRACT FROM AUTHOR]

In this paper, we consider a multiple-input-multiple-output system employing orthogonal space time block codes over a generalized fading model, namely, $$\eta - \mu$$ fading distribution. Simplified closed-form expressions for the probability density function and cumulative distribution function of the proposed system under absolute SNR scheduling have been derived in this paper. More specifically, new analytical expressions for average bit error rate and average channel capacity are derived for two cases: (a) independent and identically distributed (i.i.d) fading links and (b) independent and non-identically distributed (i.ni.d) fading links. Numerical evaluation shows improvement in system performance for various values of $$\eta$$ in format 1 with increase in the (a) number of users ( U), (b) number of transmit antennas ( n ), and (c) number of receive antennas ( n ). The proposed mathematical analysis is verified using MATLAB numerical results which demonstrate the accuracy of theoretical approach. [ABSTRACT FROM AUTHOR]