scispace - formally typeset
Search or ask a question
Author

Deeksha

Bio: Deeksha is an academic researcher from National Institute of Technology, Hamirpur. The author has contributed to research in topics: Word2vec & Vocabulary. The author has co-authored 2 publications.
Topics: Word2vec, Vocabulary, SQL, Relational database

Papers
More filters
Book ChapterDOI
05 Sep 2020
TL;DR: A thorough study of making of an efficient surveillance system along with a feature of automatically informing the owner about the suspicious movement, finding that faster RCNN is much accurate than the other conventional methods.
Abstract: The present document represents a thorough study of the making of an efficient surveillance system along with a feature of automatically informing the owner about the suspicious movement. In this moving world, normally people are suffering from the availability of time, so if any crime has happened at the site, it will take many days of searching for finding the actual presence of criminals, and thus a good chance for those burglars to flee away to protect themselves. For making the task possible, chose Python as the weapon for this battle and used different efficient techniques like COCO dataset for getting labeled and annotated images, LabelImg for making the annotation set of images, TensorFlow, object detection API for object detection and faster RCNN for training as faster RCNN has shown the highest accuracy for the COCO dataset so far. The owner can be informed in two ways: Either send a message to him via mail or phone or call at the time of suspicious image capturing. Here, both of these cases are used: For mail, the task is done via SMTP and for phone calls Twilio is used which provides us registered phone no. and can make both outbound and inbound calls. After using all the mentioned things and making the model in a way described above, it was found that faster RCNN is much more accurate than the other conventional methods. The results have been very well as RCNN show 86.7% accuracy and 100% has come out with the informing module as there simply the mail will be sent to the one whose mail is given in the code and the same is for Twilio calling.

2 citations

Book ChapterDOI
05 Sep 2020
TL;DR: In this paper, a web application has been developed that can check the subjective answers written by the students with the same efficiency as in the case of manual checking by the teachers, using this software, teachers can set the question paper and students can take their examination by getting their answers checked simultaneously.
Abstract: In a world where technology has grown to be a mega thing impacting the lives of mankind to a greater extent, a common man is still having huge difficulty in adapting the available technical solutions immediately. There are so many basic tasks that are performed in the day-to-day lives of people which take a lot of effort and time and can be automated with the help of technology but still, and humans are more prone to do them manually. One such example is taking subjective examinations by students and then evaluation of the answer sheets manually by the teachers. So, to ease the process of subjective answer checking, a web application has been developed that can check the subjective answers written by the students with the same efficiency as in the case of manual checking by the teachers. Using this software, teachers can set the question paper and students can take their examination by getting their answers checked simultaneously. The model’s development is settled with the Word2Vec skip-gram model, Natural Language ToolKit (NLTK) modules, and Flask Python framework, whereas all the data have been stored in the form of relational database tables which are inserted and fetched through the SQL queries. The Word2Vec skip-gram model is used to make the vocabulary of terms and to find their corresponding word embeddings (feature vectors). The paper proposes the development of a model that will make a time-consuming and tiresome task like manual answer checking as effortless as possible.

1 citations


Cited by
More filters
Book ChapterDOI
01 Jan 2023
TL;DR: In this article , the authors investigated the factors that influence teachers' acceptance of e-teaching by asking respondents to fill out questionnaires, conduct interviews, collect relevant information, and analyze the data obtained.
Abstract: The education process, which includes teachers and students, as well as the teaching environment in general, has drawn the attention of the education process due to desirable characteristics such as the educational function, which is distinguished by evolution in its performance methods, scalability, coherence, cost savings, and efficiency. Over the last several decades, e-teaching has varied from the traditional education style, where teachers encounter many difficulties while implementing the traditional education style. Researchers have arrived at conclusions regarding the variables that influence teachers’ acceptance of e-teaching by asking respondents to fill out questionnaires, conduct interviews, collect relevant information, and analyze the data obtained. In addition, colleges and universities have been searching for innovative ways to make education readily available to learners and make teaching easier for teachers. Despite the great importance of e-teaching in Iraq to support higher education and human development in contemporary ways, the implementation of e-teaching resists multiple challenges in Iraq. The proposed work can summarize these challenges as the few lecturers and trainers who provide training courses in preparing electronic lectures, information and communications technology infrastructure, electronic lectures and educational materials, tutors, and technical expertise. This paper aimed to identify factors determining the effect of activating e-teaching in Iraq. The research will elaborate on the concept of e-teaching in Iraq and discuss its importance and impacts with significant emphasis on Iraq. The current work concludes that e-teaching in Iraq has made meaningful progress in three universities.
Proceedings ArticleDOI
08 Feb 2023
TL;DR: In this paper , the authors proposed a model to build an intelligent automation and security system that would provide state-of-the-art security such as intruder detection, fire and gas detection, Vibration and Sound Detection, live feed, and many smart home features such as Plant Monitoring, Temperature Monitoring, Appliance control, and Voice control features.
Abstract: The rise of IoT has been playing a very important role in every aspect of our everyday lives in a world where modern technology is developing quickly. With the smart features inherited from automation, it has played a crucial role in the home automation and security industries and significantly facilitated our way of life. Wi-Fi-based wireless home automation is designed and implemented to manage devices with built-in security and protection systems. The modern lifestyle of individuals calls for everything that this home automation provides. The main intent of this work is to allow the user to easily operate their house from any of its corners. One of the main concerns for homes in the Modern World is the threat of property intrusion and burglary. New technologies such as the Internet of things have provided us with the perfect solution to tackle this problem. The objective of this proposed model is to build an Intelligent Automation and Security System that would provide state-of-the-art security such as intruder detection, Fire and Gas Detection, Vibration and Sound Detection, live feed, and many smart home features such as Plant Monitoring, Temperature Monitoring, Appliance control, and Voice control features.
Proceedings ArticleDOI
08 Feb 2023
TL;DR: In this article , the authors proposed an Intelligent Automation and Security System that would provide state-of-the-art security such as intruder detection, fire and gas detection, Vibration and Sound Detection, live feed, and many smart home features such as Plant Monitoring, Temperature Monitoring, Appliance control, and Voice control features.
Abstract: The rise of IoT has been playing a very important role in every aspect of our everyday lives in a world where modern technology is developing quickly. With the smart features inherited from automation, it has played a crucial role in the home automation and security industries and significantly facilitated our way of life. Wi-Fi-based wireless home automation is designed and implemented to manage devices with built-in security and protection systems. The modern lifestyle of individuals calls for everything that this home automation provides. The main intent of this work is to allow the user to easily operate their house from any of its corners. One of the main concerns for homes in the Modern World is the threat of property intrusion and burglary. New technologies such as the Internet of things have provided us with the perfect solution to tackle this problem. The objective of this proposed model is to build an Intelligent Automation and Security System that would provide state-of-the-art security such as intruder detection, Fire and Gas Detection, Vibration and Sound Detection, live feed, and many smart home features such as Plant Monitoring, Temperature Monitoring, Appliance control, and Voice control features.