Artificial Reaching and Feeding Hand
Robotic arms are designed for helping disabled people. The main function of the robotic arm is feeding food and drinks for disabled people. Nowadays there are so many robotic arms available in our market. These arms are more expensive because they use high-level technologies like sensing brain signals of arms and perform the task according to this. These expensive products are not affordable by common people. We are introducing this light weight portable robotic arm for feeding disabled people in affordable price. The ultimate aim of this proposed methodology is to assist the persons with movement disorder who need the help of someone to feed themselves. The proposed methodology comprises of four servo motors, one arduino controller and one usb camera. By detecting the eye blinking of the user, the operation will be initiated. The required height will be obtained by detecting the lip area of the user with the help of usb camera fixed on the robotic arm. Arduino uno is programmed in such a way to co-ordinate the required movements of the arm. The desirable robotic arm position is accomplished by the rotation of servo motors. The assistive feeding device has a gripper which can hold a spoon or a cup according to the written program. The motors will rotate in both directions to take the meals and drinks and feed to the user.
Published by: Amarnath V., Ashif C. M., Aryatheertha A. P., S. Dinesh
Author: Amarnath V.
Paper ID: V8I2-1351
Paper Status: published
Published: May 2, 2022
Sentiment classification with the BERT procedure based on deep learning
The need for Sentiment classification is a critical step in determining how people feel about a product, service, or issue. To solve the sentiment categorization problem, many natural language processing models have been developed. The majority of them, however, have concentrated on binary sentiment categorization. In this study, we tackle the fine-grained sentiment categorization task using BERT, a powerful deep learning model. Experiments show that without complicated architecture, our model outperforms other popular models in this job. In the process, we also demonstrate the utility of transfer learning in natural language processing.
Published by: P. Susmitha, V. Swetha, S. Udaya, K. Anusha, P. Nagendra
Author: P. Susmitha
Paper ID: V8I2-1346
Paper Status: published
Published: May 2, 2022
Solar Inverter with Wireless Home Automation System
Increasing energy demand,high oil prices and concerns about environmental impacts are driving the development of renewable energies such as wind,solar,sea,biomass and geothermal. Solar energy is one among the foremost developed renewable energy sources . In our project, we will create a solar inverter that converts solar energy into electrical energy. This energy is used to charge the battery and simultaneously power the home lightning system and the sockets that charge multiple appliances. Home lightning systems that consist of Arduino circuits that help enable wireless operation.
Published by: Yukta Sawant, Kunal Pathare, Rakesh Patel, Sahil Sane, Sachin Shinde, Dr. Prashant Deshmukh
Author: Yukta Sawant
Paper ID: V8I2-1335
Paper Status: published
Published: May 2, 2022
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
