Graph-Based Transfer Learning for Conversational Agents
Aug 1, 2021
Abstract: IEEE 2021 6th International Conference on Communication and Electronics Systems (ICCES) Graphs have proved to be a promising data structure to solve complex problems in various domains. Graphs store data in an associative manner which is analogous to the manner in which humans store memories in the brain. Generathe chatbots lack the ability to recall details revealed by the user in long conversations. To solve this problem, we have used graph-based memory to recall-related conversations from the past. Thus, providing context feature derived from query systems to generative systems such as OpenAI GPT. Using graphs to detect important details from the past reduces the total amount of processing done by the neural network. As there is no need to keep on passingthe entire history of the conversation. Instead, we pass only the last few pairs of utterances and the related details from the graph. This paper deploys this system and also demonstrates the ability to deploy such systems in real-world applications. Through the effective usage of knowledge graphs, the system is able to reduce the time complexity from O(n) to O(1) as compared to similar non-graph based implementations of transfer learning- based conversational agents.
Emotionally Intelligent Artificially Intelligent Virtual Companion
Apr 25, 2020
Abstract: IEEE 2021 6th International Conference on Communication and Electronics Systems (ICCES) The mental health issues of loneliness and depression are two rapidly growing problems in society today. The feeling of being alone is often noted to be an ironic feeling given the almost invasive nature of social networking and mobile platforms today. There is an ever-increasing demand for solutions to help people suffering from these mental health issues. According to government statistics, India needs 13,500 psychiatrists in the country and the nation has only 3,827. Where the country desperately needs 20,250 clinical psychologists, we have only 898. There is also sadly a stigma attached to these problems as Indian society generally looks at people with these problems in a very negative light and outcasts them. AI is a fast-growing phenomenon that has captured the interest of experts from many different fields of study as a way of facilitating complex problem-solving in a way that was not previously possible. This novel solution aims to create artificial intelligence that simulates a lot of the human processes of communication such as establishing long-term relationships with the user, predicting the personality of the user using a model of Mayer’s Briggs and generating responses using Openai-gpt2. The response generation model is trained on the Persona-Chat dataset.
Energy-efficient face recognition authentication system using human detection IoT modules
Apr 5, 2020
Abstract: The application of effective techniques like facial recognition and object detection in the domain of IoT has revolutionized the levels of control and accuracy sensors have had for a variety of purposes. Face recognition modules have established their immense usefulness, and their impact has overweighed most other traditional forms of access control. It remains one of the most secure methods to authenticate human beings to grant them access to restricted areas or systems in an organization. However, this incomparable rise in accuracy comes with a relatively huge price. The algorithms used in facial recognition are complex mathematical functions that are iteratively performed on vast volumes of data continuously. In IoT applications, the embedded systems that run these algorithms are at all times clocked to their maximum processing power, they need not run in cases when there are no humans are present in the vicinity. This is inefficient, especially in systems that need to perform face recognition round-the-clock for authentication. This paper proposes a simple, intuitive and efficient solution to conserve the processor from being clocked to its maximum throughput without compromising on the high level of security that the face recognition algorithm offers.
Smart Home Automation using Computer Vision and Segmented Image Processing
Apr 5, 2019
Abstract: IEEE 8th International Conference on Communication and Signal Processing The objective of this paper is to develop a smart IoT based light control system. Due to negligence and forgetfulness, many instances occur in establishments where the electrical appliances are left turned on even if there no human presence in a room. This is one of the most prominent cases of electricity wastage prevalent in society. Hence there is a need for an intelligent system that can ensure both efficiency and effectiveness. This project combines IoT, Artificial Intelligence and Image Processing which are powerful modern technologies. In this system, object detection methods are used which enable us to control appliances in a specific spatial region. It also uses image processing methods which are more efficient than conventional IR blaster-based home automation systems. conventional IR blasters inevitably come with a fallacy where any and all objects that obstruct the infrared ray trigger whatever response the system was programmed to achieve. These actions that are only meant for actual human beings can now be activated by any object. This produces an undesired result. This paper proposes a system which can efficiently utilize the lighting output and minimize the wastage of electricity by controlling the electrical appliances by detecting changes in the position of the humans in the room.