Praveen Kaushik

Human walking is a very challenging task and always requires rigorous practice. It is a learning process that involves the complex coordination of the brain and lower limbs. The bipedal robots that mimic the human morphological structure to produce human similar walking, are not capable of producing an efficient walk. Due to walking challenges and structural differences, a robot cannot walk like a human being. In this research, to achieve the aforementioned objective to produce a human similar walk, human lower extremity activities are considered to understand walking behaviour. The experiment involves different walking styles on different terrains. To capture the learning process of bipedal robot locomotion, a deep learning‐based ensemble classifier is introduced for human lower activities recognition. To understand the learning process seven different walking activities are considered for analysis purposes. An Inertial measurement unit (IMU) is used as a wearable device due to its small form factor and unobtrusive nature to capture the walking movement of different lower limbs joints. Three public datasets viz. mHealth, OU‐ISIR similar action and HAPT inertial sensor data sets are considered for this study. To classify the activities, 2 different deep learning models namely convolutional neural network (CNN) and long short‐term memory (LSTM) are used. To generalize the results, an ensemble of different classifiers is implemented. The Classifier has reported accuracy of 99.25%, 88.48% and 97.44%, respectively, on the aforementioned data sets. This work can be utilized for elderly subjects' postural stability, rehabilitation of patients post‐stroke and trauma, generation of robot walk trajectories in cluttered environment and reconstruction of impaired walking.

Focused Crawler collects domain specific web page from the internet. However, the performance of focused web crawler depends upon the multidimensional nature of the web page. This paper presents a comprehensive analysis of recent web page classifiers for focused crawlers and also explores the impact of web-based feature in collaboration with web classifier. It also evaluates the performance of classification technique such as Support vector machine, Naive Bayes, Linear Regression and Random Forest over web page classification. Along with that it examines the impact of web feature i.e. anchor text, Page content and link over web page classification. Finally the paper yield interesting result about the collective response of web feature and classification technique for web page classification as a relevant class and irrelevant class.

Denoising of medical image modalities is one among the foremost basic issues in medical image process. Medical modalities such as ultrasound images suffer from multiplicative speckle noise. This noise consequently reduces the contrast of ultrasound images and adversely affects the other medical image processing tasks such as medical image registration, image super-resolution, and image segmentation. Therefore, one of the important objectives of any denoising algorithm is to attenuate the speckle noise effectively and also preserve the significant medical details in the denoised image. The main focus of this paper is the reduction of speckle noise for ultrasound images using various similarity measures in non-local framework. Through exhaustive experiments conducted on real ultrasound images, B-mode and simulated synthetic images demonstrate that, the Square chord and Chi-square distance-based similarity measures are the most effective similarity measure used in non-local framework for denoising of ultrasound images.

Designing an efficient filtering technique is an ill-posed problem especially for image affected from high density of noise. The majority of existing techniques suffer from edge degradation and texture distortion issues. Therefore, in this paper, an efficient weighted nuclear norm minimization (NNM)-based filtering technique to preserve the edges and texture information of filtered images is proposed. The proposed technique significantly improves the quantitative improvements on the low rank approximation of nonlocal self-similarity matrices to deal with the overshrink problem. Extensive experiments reveal that the proposed technique preserves edges and texture details of filtered image with lesser number of visual artifacts on visual quality. The proposed technique outperforms the existing techniques over the competitive filtering techniques in terms of structural similarity index metric (SSIM), peak signal-to-noise ratio (PSNR) and edge preservation index (EPI).

Intrusion detection system(IDS) is a preventing measure against different harmful cyber-attacks. It has a key role in securing our information and communication technology system. As the internet evolved, the dynamic growth of network traffic data generated which become a challenge for traditional machine learning algorithms. Performance of a classifier solely depends on feature selection and classifier. Traditional machine learning algorithms can't perform well with huge network traffic dataset. So ML algorithms are not optimistic. In this paper, we implemented Convolution neural network(CNN-1D) for NIDS(Network Intrusion detection system) on NSL-KDD benchmark dataset. CNN automatically fetch network traffic features from the dataset. in this paper, we trained our model 500 epoch. We also compared performance of different ML(machine learning) algorithms & DL(deep learning) approaches with our CNN-1D approach with metrics of AC (accuracy), DR (detection rate) and FAR (False alarm rate).

Due to limited buffer space available at routers, the packets in the Internet gets lost or dropped, especially when the network is congested. Automatic repeat request (ARQ), is an error-control method that uses acknowledgments and timeouts to decide retransmission of messages to achieve reliable data transmission. However, the re-transmission of a lost packet further increases the congestion in the network, and hence the end-to-end delay of other coexisting flows. This paper aims at improving the performance of ARQ schemes by introducing a lightweight re-transmission mechanism called LW-ARQ based on the concept of caching of packets at intermediate routers that are indented to be dropped. To evaluate the performance of proposed LW-ARQ scheme, we chose to implement it over TCP protocol considering that TCP has become a de-facto transport layer protocol standard for the Internet. However, the proposed LW-ARQ scheme can be integrated with any protocol that uses either stop-and-wait or sliding window based ARQ scheme to handle packet losses. On analyzing the results obtained by performing simulations, we found that the proposed LW-ARQ scheme improves the average end-to-end delay performance of the TCP protocol.

Recent researches show mobility and Transmission Range (TR) has impact on the Quality of Service (QoS) performance of the Intelligent Transportation System (ITS). Impact of mobility and TR on expected transmission's probability of success (P _s ) and contention (P _c ) may be the cause behind QoS improvement. This article analyzes direct impact of mobility and TR on P _s and P _c in ITS; for same this article proposes a new algorithm and methodology. The obtained result confirms that mobility has very less impact whereas TR has significant impact on P _s and P _c .