Human activity recognition (HAR) systems attempt to automatically identify and analyze human activities using acquired information from various types of sensors. Although several extensive review papers have already been published in the general HAR topics, the growing technologies in the field as well as the multi-disciplinary nature of HAR prompt the need for constant updates in the field. In this respect, this paper attempts to review and summarize the progress of HAR systems from the computer vision perspective. Indeed, most computer vision applications such as human computer interaction, virtual reality, security, video surveillance and home monitoring are highly correlated to HAR tasks. This establishes new trend and milestone in the development cycle of HAR systems. Therefore, the current survey aims to provide the reader with an up to date analysis of vision-based HAR related literature and recent progress in the field. At the same time, it will highlight the main challenges and future directions.

/pdf/vision-based-human-activity-recognition-a-survey-9vr3o8g5p7.pdf

Vision-based human activity recognition: a survey

The ‘You Only Look Once’ v3 (YOLOv3) method is among the most widely used deep learning-based object detection methods. It uses the k-means cluster method to estimate the initial width and height of the predicted bounding boxes. With this method, the estimated width and height are sensitive to the initial cluster centers, and the processing of large-scale datasets is time-consuming. In order to address these problems, a new cluster method for estimating the initial width and height of the predicted bounding boxes has been developed. Firstly, it randomly selects a couple of width and height values as one initial cluster center separate from the width and height of the ground truth boxes. Secondly, it constructs Markov chains based on the selected initial cluster and uses the final points of every Markov chain as the other initial centers. In the construction of Markov chains, the intersection-over-union method is used to compute the distance between the selected initial clusters and each candidate point, instead of the square root method. Finally, this method can be used to continually update the cluster center with each new set of width and height values, which are only a part of the data selected from the datasets. Our simulation results show that the new method has faster convergence speed for initializing the width and height of the predicted bounding boxes and that it can select more representative initial widths and heights of the predicted bounding boxes. Our proposed method achieves better performance than the YOLOv3 method in terms of recall, mean average precision, and F1-score.

https://www.mdpi.com/2079-9292/9/3/537/pdf

Object Detection Algorithm Based on Improved YOLOv3

Deep learning of artificial neural networks has become the de facto standard approach to solving data analysis problems in virtually all fields of science and engineering. Also in biology and medicine, deep learning technologies are fundamentally transforming how we acquire, process, analyze, and interpret data, with potentially far-reaching consequences for healthcare. In this mini-review, we take a bird's-eye view at the past, present, and future developments of deep learning, starting from science at large, to biomedical imaging, and bioimage analysis in particular.

A bird's-eye view of deep learning in bioimage analysis.

Structural crack detection using deep convolutional neural networks

Video Surveillance plays a pivotal role in today's world. The technologies have been advanced too much when artificial intelligence, machine learning and deep learning pitched into the system. Using above combinations, different systems are in place which helps to differentiate various suspicious behaviors from the live tracking of footages. The most unpredictable one is human behaviour and it is very difficult to find whether it is suspicious or normal. Deep learning approach is used to detect suspicious or normal activity in an academic environment, and which sends an alert message to the corresponding authority, in case of predicting a suspicious activity. Monitoring is often performed through consecutive frames which are extracted from the video. The entire framework is divided into two parts. In the first part, the features are computed from video frames and in second part, based on the obtained features classifier predict the class as suspicious or normal.

Deep Learning Approach for Suspicious Activity Detection from Surveillance Video

Big data applications are consuming most of the space in industry and research area. Among the widespread examples of big data, the role of video streams from CCTV cameras is equally important as other sources like social media data, sensor data, agriculture data, medical data and data evolved from space research. Surveillance videos have a major contribution in unstructured big data. CCTV cameras are implemented in all places where security having much importance. Manual surveillance seems tedious and time consuming. Security can be defined in different terms in different contexts like theft identification, violence detection, chances of explosion etc. In crowded public places the term security covers almost all type of abnormal events. Among them violence detection is difficult to handle since it involves group activity. The anomalous or abnormal activity analysis in a crowd video scene is very difficult due to several real world constraints. The paper includes a deep rooted survey which starts from object recognition, action recognition, crowd analysis and finally violence detection in a crowd environment. Majority of the papers reviewed in this survey are based on deep learning technique. Various deep learning methods are compared in terms of their algorithms and models. The main focus of this survey is application of deep learning techniques in detecting the exact count, involved persons and the happened activity in a large crowd at all climate conditions. Paper discusses the underlying deep learning implementation technology involved in various crowd video analysis methods. Real time processing, an important issue which is yet to be explored more in this field is also considered. Not many methods are there in handling all these issues simultaneously. The issues recognized in existing methods are identified and summarized. Also future direction is given to reduce the obstacles identified. The survey provides a bibliographic summary of papers from ScienceDirect, IEEE Xplore and ACM digital library.

/pdf/intelligent-video-surveillance-a-review-through-deep-4u0qpijyy7.pdf

Intelligent video surveillance: a review through deep learning techniques for crowd analysis

A cryptographic system uses two dissimilar keys — a public key known to all and a private key known only to the receiver of the message. Encryption of the data uses public key while decryption uses both public and private keys. So in this method all parties need a key pair for conversing with any other interactive parties. RSA is a generally known asymmetric cryptography algorithm. Modified RSA is the improved version of RSA, enhancing better security. To advance the security of RSA, this paper is proposing a new cryptography algorithm called Binary RSA Encryption Algorithm (BREA). In BREA, the security is further improved by converting the cipher text which is encrypted by MREA into binary code format. The first section of this paper is the introduction and second section contains the literature survey of various modifications of RSA. Section three describes about the Modified RSA Encryption Algorithm that we have selected. The fourth section is details about the Binary RSA Encryption Algorithm (BREA). The fifth section is the comparison between RSA, MREA, and BREA. The sixth section is the conclusion and seventh section is the References.

Binary RSA encryption algorithm

Security in web pages is one of the crucial problems nowadays. Web technologies are advancing with the boost in the digital world and changing requirements. Even though web applications can provide efficiency in storing and managing a large amount of information, certain security issues can pose threat to information assurance. Those security issues, vulnerabilities that mainly include SQL injection, cross-site scripting etc can be prevented using the security scanners currently available. A web vulnerability scanner detects potential security vulnerabilities in web pages by accessing the web page through the front end. They provide the proficiency of detecting errors early. Meanwhile, they have some limitations. Overcoming the limitations still existing to a certain extent, several new techniques can perform far better. The paper consists of two main sections, the first section dealing with existing techniques of vulnerability testing and second section on a new and faster method which employs machine learning techniques for detecting security vulnerabilities.

Web Scanning: Existing Techniques and Future

Efficient searching and quality services are offered by prevailing infrastructure of Peer-to-Peer(P2P)networks. P2P applications are more and more wide spreading with good scope. Though the advantages are still existing the P2P system is vulnerable to some security issues. One of the important issues that threatens the subsistence of P2P system is freeriding. Freeriders are peers(nodes) which only utilize the system but not contribute anything to the system. Freeriders affect the system in a drastic manner. Freeriders mainly download the contents without uploading anything. So the contents will be concentrated in few peers and that will increase the congestion and reduce the quality of the system. This reduces the popularity of the system. This paper compares different approaches for managing freeriders and finally a solution is suggested which is an extension to existing protocol known as BARTERCAST and the enhancement is done through Q-learning. Application of reinforcement learning approach in BARTERCAST results in more accurate results.

Enhancement of BARTERCAST Using Reinforcement Learning to Effectively Manage Freeriders

The widespread usage of peer to peer (P2P) system is visible in all major application areas like, file sharing , high performance computing, P2P TV, P2P IP TV etc. Conversely, the foremost confront in the growth of P2P system is the dearth of an efficient scheme to handle malicious and mysterious nodes. The QoS factor of the system will be deeply reduced by freeriders. To facilitate the augmentation, the system should be able to trim down the influence of malicious nodes with a feasible, proficient and scalable reputation model. Trust value computation among peers outline the basis of reputation model. This paper recommends a hybrid reputation model through federation of peers having analogous function. The grouping of peers having analogous function is introduced to reduce the unnecessary searching. The competence of the model can be augmented by the application of following methods. Application of election algorithm with suggested modification is a solution to central point failure. The ring structure formation of peers having analogues function reduces the search time through the network. In addition to that the behavior prediction of peers is made more accurate using the Markov chain.

G. Sreenu

Papers

Intelligent video surveillance: a review through deep learning techniques for crowd analysis

Binary RSA encryption algorithm

Web Scanning: Existing Techniques and Future

Enhancement of BARTERCAST Using Reinforcement Learning to Effectively Manage Freeriders

A Hybrid Reputation Model through Federation of Peers Having Analogous Function