A mobile service robot is a class of robots that operates in a dynamic environment with other robots and human beings. The service environment is often considered large and unknown, and the robot is expected to operate lifelong. The static path planning system that directly uses maps or explores an unknown environment will work fine if the environment does not change over time. But for a service environment, there can be changes in the environment over time, i.e., new routes can be generated, or old routes are permanently blocked. Considering these facts, it is evident that the path planning system for a service robot should be an artificial intelligence-based system that will be able to plan the path given less or no information about the environment and cope with the environment’s changes for a lifelong. Our work aims at developing a path planning framework using reinforcement learning for a service environment. The proposed path planning algorithm uses a Q-Learning algorithm to learn the paths using a topological map of the environment. The system is trained and tested for two different service environments. The experiment results show that the system can learn and generate efficient routes based on the topological maps with an accuracy of 95%. This artificial intelligence-based framework can extend the path planning system’s capability to adapt to long-term route changes.
The majority of the people in India is dependent on agriculture. Every crop the farmers cultivate has some sort of illness. The most successfully adopted subtropical fruit crop in India is the pomegranate. Pomegranates have the highest economic value of all the fruits. Pomegranate has very little immunity to infection during cultivation, especially in the early stages. As a result, it is particularly susceptible to the sickness. The detection of plant diseases is a beneficial use of image processing. Picture acquisition, picture pre-processing, Image segmentation, feature extraction, object recognition, and classification are all steps within the infection discovery handle.
Visual impairment can have a severe negative effect on a person’s freedom, employment, and daily life. Globally there are at least 2.2 billion individuals who experience some form of visual impairment. Reading, writing, and navigating their environment is challenging for people with visual impairment. A lower quality of life as well as feelings of loneliness and sadness may result from this. There are a variety of deep learning object detection models based on computer vision. In this paper, we aim to integrate MobileNet SSD architecture to develop a navigation system which provides faster and accurate object detection to assist the visually impaired. This project is a mobile-friendly architecture that is lightweight and optimized for embedded and mobile devices with constrained CPU power. In this paper we also designed algorithms which provides direction and distance along with audio output. In the future works, this project can be further modified and implemented in various domains.
This study compares deep learning models such as RNN-LSTM, DenseNet, and ResNet, along with a hybrid model combining SVM, XGBoost, and DTC, for load forecasting in power systems. The results demonstrate the strengths and weaknesses of each approach, with RNN-LSTM capturing temporal patterns effectively, DenseNet and ResNet excelling in feature extraction, and the hybrid model offering a balanced combination of precision and effectiveness. These findings offer valuable insights for power system operators and researchers in selecting suitable load forecasting models.
India is predominantly an agrarian economy. The agricultural industry despite its predominance, is plagued with myriad issues leading to serious consequences. This is a pressing matter, and a multitude of reasons exist for farmers' problems but the primary causes include failure of crops and extreme debt. Apart from the natural factors affecting agriculture, the main challenges faced by a farmer lie in the financial and marketing aspects. The paper aims to develop an application that would serve as a support system to overcome the above problems. The system proposes that the farmers' lease their land to a client for a certain period. During this period, the farmer lets the client take on all the monetary necessities associated with the land. The condition is that the land can only be utilized for harvesting crops and maintenance activities but no other responsibilities like marketing, financing, crop failures, etc. This enables the client to implement his learning and knowledge on agriculture in a realworld, marketing of the yield real-time setup. The farmer is guaranteed a minimum return upon acceptance of the contract and would get to learn new farming techniques from the client without any financial burden. A bidding system is in place for the clients to compete for a farm of their choice. Upon placing a bid, the farmer can view and select the client of their choice and vice versa, in order to go into a mutual agreement. In this way, the contract is established between the two parties. This would serve as an intuitive way to tackle the problem that has been deep-rooted in the farmer's minds and lead them towards the path of progress. Complete transaction model between the farmers and client can be handled using a mobile computing platform using text, image, audio and video along with advisory links for both the parties. A prototype model is created using the android platform based on the above concepts.
