Deep learning is a relatively new branch of machine learning in which computers are taught to recognize patterns in massive volumes of data. It primarily describes learning at various levels of representation, which aids in understanding data that includes text, voice, and visuals. Convolutional neural networks have been used to solve challenges in computer vision, including object identification, image classification, semantic segmentation and a lot more. Object detection in videos involves confirming the presence of the object in the image or video and then locating it accurately for recognition. In the video, modelling techniques suffer from high computation and memory costs, which may decrease performance measures such as accuracy and efficiency to identify the object accurately in real-time. The current object detection technique based on a deep convolution neural network requires executing multilevel convolution and pooling operations on the entire image to extract deep semantic properties from it. For large objects, detection models can provide superior results; however, those models fail to detect the varying size of the objects that have low resolution and are greatly influenced by noise because the features after the repeated convolution operations of existing models do not fully represent the essential characteristics of the objects in real-time. With the help of a multi-scale anchor box, the proposed approach reported in this paper enhances the detection accuracy by extracting features at multiple convolution levels of the object. The major contribution of this paper is to design a model to understand better the parameters and the hyper-parameters which affect the detection and the recognition of objects of varying sizes and shapes, and to achieve real-time object detection and recognition speeds by improving accuracy. The proposed model has achieved 84.49 mAP on the test set of the Pascal VOC-2007 dataset at 11 FPS, which is comparatively better than other real-time object detection models.

In the study of human mobility, gait analysis is a well-recognized assessment methodology. Despite its widespread use, doubts exist about its clinical utility, i.e., its potential to influence the diagnostic-therapeutic practice. Gait analysis evaluates the walking pattern (normal/abnormal) based on the gait cycle. Based on the analysis obtained, various applications can be developed in the medical, security, sports, and fitness domain to improve overall outcomes. Wearable sensors provide a convenient, efficient, and low-cost approach to gather data, while machine learning methods provide high accuracy gait feature extraction for analysis. The problem is to identify gait abnormalities and if present, subsequently identify the locations of impairments that lead to the change in gait pattern of the individual. Proper physiotherapy treatment can be provided once the location/landmark of the impairment is known correctly. In this paper, classification of multiple anatomical regions and their combination on a large scale highly imbalanced dataset is carried out. We focus on identifying 27 different locations of injury and formulate it as a multi-class classification approach. The advantage of this method is the convenience and simplicity as compared to previous methods. In our work, a benchmark is set to identify the gait disorders caused by accidental impairments at multiple anatomical regions using the GaitRec dataset. In our work, machine learning models are trained and tested on the GaitRec dataset, which provides Ground Reaction Force (GRF) data, to analyze an individual’s gait and further classify the gait abnormality (if present) at the specific lower-region portion of the body. The design and implementation of machine learning models are carried out to detect and classify the gait patterns between healthy controls and gait disorders. Finally, the efficacy of the proposed approach is showcased using various qualitative accuracy metrics. The achieved test accuracy is 96% and an F1 score of 95% is obtained in classifying various gait disorders on unseen test samples. The paper concludes by stating how machine learning models can help to detect gait abnormalities along with directions of future work.

The day-by-day advancement of extended reality and its subset technologies, along with effective hardware, is increasing their utilization in various sectors like education, training, sports, and healthcare. Healthcare is one domain of concern. Considering this, the main focus of this paper is on spine surgery. In orthopedic surgery, the main uses of virtual reality (VR) are for education, preoperative planning, and intraoperative use. Yet the training imparted still lags. Orthopedic training committees in North America and Europe have endorsed the use of virtual reality for educational purposes. Spinal surgery is one of the main focuses where virtual reality (VR) is applied. In the past, open techniques and instruments that could be seen in real time were used to perform spine surgery. Significant advancements in minimally invasive spine (MIS) surgery have been made. Virtual reality (VR) has been used in preoperative contexts for spine surgery. This paper delves into the applications of augmented reality (AR), virtual reality (VR), and mixed reality (MR) in spinal surgery, emphasizing their potential in education, training, and surgical settings. Specifically, we focus on procedures like pedicle screw placement, cervical spine, and deformity correction, where AR augments surgical precision and information accessibility. The primary objective is to provide a comprehensive framework for evaluating the clinical benefits of AR–VR-enabled spinal surgery technology and propose a viable business model catering to diverse stakeholders, including patients, hospitals, research centers, and technology adopters.

Clustering is regarded as one of the significant task in data mining which deals with primarily grouping of similar data. To cluster large data is a point of concern. Hadoop is a software framework which deals with distributed processing of huge amount of data across clusters of commodity computers using MapReduce programming model. MapReduce allows a kind of parallelization for solving a problem involving large data sets using computing clusters and is also an attractive mean for data clustering involving large datasets. Mahout, a scalable machine learning library is an approach to Fuzzy K-mean clustering which runs on a Hadoop. This paper focuses on studying the performance of different datasets using Fuzzy K-mean clustering in MapReduce on Hadoop. Experimental results depict the execution time of the approach on a multi-node Hadoop cluster which is build using Amazon Elastic Cloud Computing(Amazon EC2).

In recent years, face detection has achieved considerable attention in the field of computer vision using traditional machine learning techniques and deep learning techniques. Deep learning is used to build the most recent and powerful face detection algorithms. However, partial face detection still remains to achieve remarkable performance. Partial faces are occluded due to hair, hat, glasses, hands, mobile phones, and side-angle-captured images. Fewer facial features can be identified from such images. In this paper, we present a deep convolutional neural network face detection method using the anchor boxes section strategy. We limited the number of anchor boxes and scales and chose only relevant to the face shape. The proposed model was trained and tested on a popular and challenging face detection benchmark dataset, i.e., Face Detection Dataset and Benchmark (FDDB), and can also detect partially covered faces with better accuracy and precision. Extensive experiments were performed, with evaluation metrics including accuracy, precision, recall, F1 score, inference time, and FPS. The results show that the proposed model is able to detect the face in the image, including occluded features, more precisely than other state-of-the-art approaches, achieving 94.8% accuracy and 98.7% precision on the FDDB dataset at 21 frames per second (FPS).

MapReduce is one of the most popular programming model for big data analysis in Distributed and Parallel Computing Environment. It is used for implementing parallel applications. With the growing development of mobile Internet and cloud computing, the issues related to big data have been a matter of concern in both industry and academy. There are several platforms for users to develop their applications based on MapReduce framework such as Hadoop. Hadoop is a free, Java-based programming framework that supports the processing of large data sets in a distributed computing environment. This paper discusses various MapReduce applications like Wordcount, Pi, TeraSort, Grep in Cloud based Hadoop. We have shown experimental results of these applications on Amazon EC2 using two types of Ubuntu instances. In this paper, performance of above application has been shown with respect to execution time and number of nodes. We find in our research study that as the number of nodes increases the execution time decreases and performance increases.