Image caption generator using CNN and LSTM
The realm of technology in the field of AI is progressing rapidly these days. Many research-based projects have been carried out and are still being carried out, thanks to this advancement. Many studies have been done in the field of AI, and image caption creation is also a component of this research that is based on deep learning. There are a variety of activities that must be completed during the image captioning process, including identifying the items in the photographs, determining their semantic link, and translating the backdrop scene into the relevant phrases. The picture's information is generated automatically in artificial intelligence, which also includes computer vision and natural language processing. In order to assess the model's fluency and accuracy, the flickr8k dataset of 8000 photographs is used to describe the images. This shows that the model is appropriately captioning the photos.
Published by: Julu Basnet, Supriya Kumari, Mohit Rathore, Dipanshu
Author: Julu Basnet
Paper ID: V8I2-1280
Paper Status: published
Published: May 2, 2022
Analysis of Marital Rape as an Exemption
Marital rape is an issue that reflects the socio-cultural conditioning of marriage in a manner that leads to gender disparity in the essential aspect of decision-making that forms the basis for every individual's existence. Women experience the dark side of marital relations, subjecting themselves to the gender roles instilled in them by society. In India, women are subject to veritable societal and cultural expectations. The patriarchal roots of society have viewed women as instruments to fulfill familial expectations rather than their expectations about her life. Such an idea is perceived as a norm even in today's world, despite advancements seen in various aspects of gender studies. India indeed has granted equality to women in social, political, and economic spheres. There is hidden hypocrisy within the social realm as these advancements do not influence gender equality in various households. The paper aims to delve into socio-legal aspects of the issue of marital rape. The initial section of the article gives an insight into the philosophical dimension of the problem, which offers veritable views from philosophers. This enables us to think from some realms of morality and ethics in a more specialized manner. The second section deals with some of the prevalent justifications restricting the criminalization of this primitive social norm. The author has also attempted to decipher the validity of such explanations by various societies and governments in pertinence to the issue's intensity. The subsequent section offers a brief description of the backward and arbitrary nature of 'consent.' The author questions the narrow approach towards understanding the concept of 'consent, an essential character binding a marriage. The following section delves into the legal aspects of such an exception, offering a detailed description of the legal lacunae posed by such an exception. This section explains the contradictory nature of the legal exception with the Constitution, which is the supreme law of the land. The succeeding area puts forth a psychological understanding of the victims of this inhumane form of violence through the theory of 'learned helplessness.' The paper's final section lays an account of the prevalence of the issue in rural and urban areas, respectively.
Published by: Shradha Alanghat
Author: Shradha Alanghat
Paper ID: V8I3-1139
Paper Status: published
Published: May 2, 2022
Recognition of objects in Adverse Weather conditions using Dual Subnet Network in Comparison with CNN Network
The purpose of this Research work is to Detect objects in Adverse weather conditions using Dual Subnet Network and comparing it with CNN network. Object detection algorithms based on convolutional neural networks have been intensively explored and successfully implemented in numerous computer vision applications during the last half-decade. However, due to poor visibility, recognising things in rainy weather remains a considerable challenge. In this study, we introduce an unique dual-subnet network (DSNet) that can be trained end-to-end and jointly perform three tasks: visibility improvement, object categorization, and object localisation, to handle the object identification problem in the presence of fog. By incorporating two subnetworks: detection and restoration, DSNet achieves complete performance enhancement. RetinaNet is used as a backbone network (also known as a detection subnet) for learning to categorise and find objects. The restoration subnet shares feature extraction layers with the detection subnet and uses a feature recovery (FR) module to improve visibility. Our DSNet outperformed many state-of-the-art object detectors and combination models between dehazing and detection methods while maintaining a high speed, obtaining 50.84 percent mean average precision (mAP) on a synthetic foggy dataset that we composed and 41.91 percent mAP on a public natural foggy dataset (Foggy Driving dataset).
Published by: K. Pavan Kumar, K. Bhanu Teja, B. Deepa, M. Sagar, C. Venkata Sai Rakesh, I. Suneetha Rani
Author: K. Pavan Kumar
Paper ID: V8I2-1344
Paper Status: published
Published: April 30, 2022
Advancement in Multimedia Information System Security
A multimedia communication system enables multimedia data's generation, storage, management, distribution, receiving, consuming, editing, sharing, and so on. In such systems, there are various security issues, which must be considered such as eavesdropping, intrusion, forgery, piracy and privacy, etc. Until now, various security solutions for multimedia communication systems have been reported, while few works have surveyed the latest research advances. This paper gives a thorough review to multimedia information system security. It introduces a general architecture of multimedia information system, and investigates some security issues in multimedia information systems. It reviews the latest security solutions such as Digital Rights Management (DRM), confidentiality protection, ownership protection, traitor tracing, secure multimedia distribution based on watermarking, forgery detection, copy detection, privacy-preserving data mining, secure user interface, intrusion detection and prevention. Moreover, the paper presents some hot research topics such as Trusted Computing, steganography, security in network or service convergence, security of content sharing in social networks, privacy-preserving data processing, multimedia forensics and intelligent surveillance in multimedia information system security. It is expected to benefit readers by providing the latest research progress, advising some research directions and giving a list of references about multimedia system security.
Published by: Pranav Sanjay Patil
Author: Pranav Sanjay Patil
Paper ID: V8I2-1342
Paper Status: published
Published: April 30, 2022
Efficacy of a topical ayurvedic preparation (Zandu ultra power balm) – relief from cold and associated symptoms
Zandu Ultra Power Balm is a topical ayurvedic preparation that contains various active ingredients such as Menthol, Gaultheria oil, clove oil, cajeput oil, ajwan satva, etc. This present study attempts to support the product claims made by the above-mentioned (OTC) product for cold and pain relief. Consenting adults (n=30) who were experiencing cold and related symptoms were enrolled in a prospective open-label, phase 4 study. Each of them was provided 1 bottle of the product for the study (7 days) and asked to answer questions regarding product efficacy on a visual analog scale. The scores were traced on days 0, 2, 4, and 6. Subjects observed an effective reduction in cold and congestion over 2 days and a reduction of headache and backache due to cold over 6 days (p <0.001). Conclusion: Zandu Ultra Power Balm works effectively as a remedy for cold and its associated symptoms.
Published by: G. Gandhimathi
Author: G. Gandhimathi
Paper ID: V8I2-1271
Paper Status: published
Published: April 27, 2022
Efficacy of ayurvedic oil (Advanced Emami Kesh King Scalp and Hair Medicine Ayurvedic Oil ) – Hair growth, hair fall reduction and dandruff protection
Advanced Emami Kesh King Scalp and Hair Medicine Ayurvedic Oil contains potent extracts of various herbs such as Manjistha, Nagkesara, Brahmi, Bhringaraja, etc. This present study attempts to support the claims made by the above mentioned ayurvedic oil for hair growth, hair fall reduction and protection from dandruff. Consenting adults (n=30) who were experiencing hair fall and dandruff issues were enrolled in a prospective open-label, phase 4 study. Each of them was provided 2 bottles of the product for the study (60 days) and asked to answer questions regarding product efficacy on a visual analogue scale. The scores were traced on days 0, 15, 30 and 60. Subjects observed an effective reduction in hair fall over 15 days and improvement in hair growth and dandruff signs over 60 days (p <0.001). Conclusion: Advanced Emami Kesh King Scalp and Hair Medicine Ayurvedic Oil works effectively for hair fall and dandruff issues
Published by: Dr. G. Gandhimathi
Author: Dr. G. Gandhimathi
Paper ID: V8I2-1277
Paper Status: published
Published: April 27, 2022
