Banoth SeethaRamulu

The automatic prediction of daily human activities like walking, running, cooking, and office work is called Human Activity Recognition (HAR). The medical industry can greatly benefit from it, especially those working with the elderly, personal health care aides, those keeping patient records for reference in the future, etc. A HAR system can take (a) video or still images of people doing things, or (b) data showing the human body's motions as they do those things gathered from sensors in smart devices (accelerometers, gyroscopes, etc.), smart homes, eldercare, and the Internet of Things (IoT). The suggested HAR applications heavily rely on the latest developments in AI approaches, such as optimisation algorithms from Deep Learning (DL) and Swarm Intelligence (SI). Here, we use open-source data from wearable sensors to construct a reliable HAR system that combines DL and SI. A method for light feature extraction called Residual Bidirectional Long Short-Term Memory (Res-BiLSTM) has been developed. Based on the Marine Predator Algorithm (MPA), we presented novel feature selection approaches to choose the best collection of features. Using three publicly available HAR datasets from the UCI machine learning repository, we assess the performance of the suggested model. We evaluate the suggested model against different DL architectures that have recently been suggested as solutions to the HAR problem. The proposed model surpasses other state-of-the-art approaches in terms of accuracy 96.92%, precision of 95.45%, recall of 94.07%, and F1 score of 96.15% on all three datasets. The suggested approach outperforms several reported results in robustness and activity detection. As well as adapting activity aspects, it has fewer parameters and improved accuracy.

The industries and factories that produce goods which are always in demand require good amount of productivity, with small delays even can result in supply crunches. Most of the factories do not have smart machinery which can predict the breakdowns of the machines used and save time for better productivity because of the cost they come with. With a Predictive Maintenance system using machine learning on the edge this can save both time and cost of the factories and at the same time give better and quick results compared to cloud systems. In this paper we discuss on how the machine learning models can fit in a micro controller and run inference on it and predict results without requiring it to connect to a cloud system. We have emulated a washing machine to be a factory equipment and ran the system in it with its monitored data for predictions.

The growth of internet and network technologies has been increasing day by day.With the increase of these technologies, attacks and intrusions are also increasing. The prevention of these attacks has become an task. Intrusion Detection System (IDS) provides prevention against these attacks. Data Mining and Machine Learning techniques are used for IDS to reduce error rate and to improve accuracy and detection rate. In this paper, we proposed a novel Artificial Neural Network (ANN) classifier using Back propagation algorithm to model IDS. ANN is widely used supervised classifier for IDS. The performance of our model is evaluated by conducting experiments on KYOTO data set which is refined version of KDD99 data set. Empirical results show that proposed model is efficient with high detection rate and accuracy.

Cloud Computing is an emerging technology now a days , where cloud is most preferable when there is data backup, storage and data distribution service with low cost. But cloud is semi honest in nature due to not reveled storage and security structure thus while storing and sharing cloud data , its suppose to honest and secured. When data owners outsource their data in secured manner system should assure the security, data integrity and confidentiality. Here we noticed secure access controlling is the prime objective for sensitive data management.in this regards we have been used ABE (Attribute based encryption) for the above objective. This paper concentrates on secure storage and sharing system.