The sudden surge in the fuel cost and increase in environmental impact causes a reduction in electricity generation through conventional energy sources. The power system is moving towards the incorporation of distributed energy resources (DERs) into the existing microgrid (MG). Distributed generation (DG), storage system and geographically scattered loads forms a MG. The stochasticity and unpredictable output associated with DGs may create imbalance in supply and demand. Further, the unexpected peak loads on the system mayjeopardize the system reliability. Hence, proper energy management system is obligatory for peak reduction so as to maintain the power balance. One of the emerging and efficient energy management techniques is demand response. While incorporating demand response, a part of curtailed loads i.e., shiftable loads at peak loads should be re-distributed to other off-peak hours where the load demand and electricity offer price is less. The re-distribution of loads at non-peak hours eventually increases the market clearing price (MCP). Increment in MCP mostly effects the inelastic loads as they cannot shift their schedule from one horizon to another since they are must run loads and of on/off in nature. In this context, the present work focuses on optimal rescheduling of the redistributed loads that doesn’t impact much MCP and operational cost (OC) of the MG much and should able to maintain the dynamic balance between supply and demand. A cost-based method was employed in which grey wolf optimization (GWO) algorithm is used to optimize the OC of the MG.
Birdwatching or Birding is observing or watching the birds which is found to be one of the serene activities to do in daily life. But recognizing the bird species is hard for humans as it requires a bit of support from the bird book. Also, in the olden days, many ornithologists and researchers faced hardships in detecting bird species and learning about the different patterns of bird species. We have developed an Arduino-based system that performs automatic bird species recognition. This system will be helpful for ornithologists, researchers, and other enthusiasts to learn about the existence of different bird species in a given geographical region. This system is developed using Arduino Uno, PIR Motion Sensor, and an ESP-32 camera. When the motion is detected, the ESP-32 camera captures the image and uploads the image to Google Drive. The images in Google Drive can be given to the trained deep learning models to predict the name of the bird species. To develop the deep learning model, we have used a Kaggle data set that consists of 450 bird species images of which 70,626 training images, 22500 test images, and 2250 validation images.
This paper discusses the clinical chatbot which could examine the contamination and deliver essential insights regarding the contamination previous to counseling a specialist. To lower the healthcare charges and similarly increase openness to clinical facts the clinical chatbot is constructed. Certain chatbots pass approximately as clinical reference books, which facilitates the affected person to discover approximately their contamination and assists with running on their fitness. The person can accomplish the real gain of a chatbot simply while it is able to examine all forms of infections and deliver essential data. In later sections of the paper, a doctor appointment system software is also discussed that is integrated with the chatbot so that the specialist which is recommended by medical chatbot can be easily visited at the mutually agreed time of both specialist and patient. Such an appointment system has its own advantages like it reduces the waiting time of the patient, patients can choose the appointment time in keeping with their desire additionally to be had and booked slots are proven in powerful graphical person interface.
In this paper, we have implemented a novel unsupervised graph-based algorithm for Hindi Word Sense Disambiguation. For disambiguation, we perform a random walk on graph created for each instance. The nodes in the graph are various senses of the words appearing in the context of ambiguous word. The edge weights are assigned using semantic similarity between pair of nodes. We compare two path-based similarity measures. The experimental investigations suggest that a Leacock-Chodrow similarity measure performs better than Shortest path measure. We observed an accuracy of 72.09% averaged over all the instances of five Polysemous nouns.
Mobility impairments and difficulties are a problem faced by a significant portion of the population. The statistics on differently abled people and the mobility aids can benefit a great deal for governmental institutions in areas such as policy-making and infrastructure development. This paper proposes an automated process for the detection and identification of people who use mobility aids. The YOLO (You Only Look Once) algorithm is used to train the dataset. The performance metrics and the feasibility of the algorithm are being discussed. The primary aim of this paper is to help improve the facilities made for differently people in public places by the detection and analysis of the different kinds of mobility aids that people use and how it affects movement in a public place. The model detects and classifies each person in the image as differently abled or not, and if found to be differently abled, it finds out the type of the mobility aid used and the number of differently abled people in each class as well.
