MIT-World Peace University (MIT-WPU) is a top educational institute located in Pune, India. It is recognized within&nbsp;UGC under Government of Maharashtra Act No. XXXV 2017.&nbsp;

It is part of the MIT group of institutions (established in 1983) which covers 10+ campuses across India and has more than 50,000+ students enrolled across various disciplines at a given point of time. The institute houses 15 schools ranging from Engineering &amp; Technology, Design, Pharmacy, Commerce, Governance among others. It offers undergraduate, postgraduate and PhD programs among different disciplines.&nbsp;

&nbsp;

MIT World Peace University

School of Computer Engineering & Technology

Industrial production is pushed on by the constantly changing market requests and global competition. To keep up with these demands and thrive in a furiously competitive market, rapid advances in current manufacturing technologies are required. Automation is the trendsetter among the technologies currently in operation. To aid in the development of production methods, the idea proposed is predictive maintenance and asset tracking. Predictive maintenance is a revolution in the way machines that are in continuous operation can be constantly monitored to detect an anomaly before it blows up into a full-fledged problem. The device is kept under constant monitoring and readings of different parameters, for example, temperature and vibrations are tabbed. Any reading that strays from the regular pattern could indicate a flaw in the device. By predicting this, downtime for maintenance can be reduced. Asset tracking is another revolutionary method to speed up efficiency in the industrial sector. Using different technologies like Wireless Sensor Networks (WSNs), the assets and their locations can be viewed using a remote device. The benefit of the same lies in the fact that often an asset whose location is unknown, wastes production time of the team by unnecessarily having to look for it. Ultimately, the idea is to implement these technologies using the modern concepts of Machine Learning, Data Visualization, Cloud Computing and the Internet of Things. This paper provides a brief introduction to the architecture of such a system followed by a detailed rundown of the above methodologies for real-time applications. © 2020 IEEE.

World University root node

Engineering and Technology

2020 International Conference for Emerging Technology, INCET 2020

Cloud-based asset monitoring and predictive maintenance in an industrial IoT system

Wireless Sensor Networks (WSNs) are key enablers for IoT and pervasive computing paradigm. While devices are being seamlessly enabled with connection and communication capabilities, exploring techniques to quantify and improve quality has gathered significance. This work explores quality of a Data Aggregation Tree (DAT) in sensor networks. DATs are building blocks for data collection in WSNs. In this work Quality of Experience (QoE) and Quality of Service (QoS) of DATs is evaluated using data aggregation ratio $$\alpha $$ and generated data $$\delta $$ respectively. An algorithm Quality Aware Data Aggregation Tree (QADAT) to construct a quality aware DAT is proposed. QADAT adapts the DAT to network and user expectation dynamics. Simulation results show the effectiveness of the proposed algorithm and demonstrates quality awareness through DAT adaptability.

Lecture Notes on Data Engineering and Communications Technologies

Quality Aware Data Aggregation Trees in Sensor Networks

Proper utilization of wireless sensor networks (WSNs) has direct impact on various application developed using it in our daily life. In the past years wireless sensor network is popular area of research due to its applicability in different real scenario like border surveillance, fire detection, underwater application, IoT, body area network, irrigation system. The large number of nodes cooperatively performs a specific task. The nodes work in hazardous environment where human intervention is not possible. The battery power is limited, so proper clustering helps to maintain the network life significantly. There is wide variety of methods to perform clustering. This paper presents general classification of state-of-art clustering schemes.

2020 11th International Conference on Computing, Communication and Networking Technologies, ICCCNT 2020

A survey on clustering in wireless sensor network

Control \& Cybernetics

A survey of big data classification strategies.

International Journal of Pure and Applied Mathematics

Machine Learning for Data Aggregation in Wireless Sensor Networks : A Survey Machine Learning for Data Aggregation in WSN : A Survey

Gallium Nitride (GaN) high power amplifiers become very popular in recent years for RF and microwave applications. There is huge interest in design and development of GaN high power amplifiers. In certain microwave applications GaN power amplifiers have already replaced conventional travelling wave tube amplifiers (TWTAs). This paper summarizes about different power devices and semiconductor technologies used for power amplification with emphasis on GaN technology. Various advantages of GaN power amplifiers with other power amplifier technologies are addressed. Often used performance improvement techniques in solid state power amplifiers (SSPAs) for microwave applications are discussed. This paper also describes some examples of GaN high electron mobility transistor (HEMT) power amplifier for microwave applications.

International Journal of Advanced Science and Technology

Review of GaN HEMT High Power Amplifiers for Microwave Applications

Segmentation of knee joint is an instrumental task in a medical fraternity during knee osteoarthritis (KOA) progression. In general, it is a primary concern to segment, detect and extract the defects from knee magnetic resonance images (MRI). Conventionally, this process is carried out manually in clinical practice but it is time consuming and observer dependent. It is a big challenge to segment cartilage manually from MRI, as cartilage structure has inadequate image contrast and complex tissue structure. Currently, semiautomatic and automatic methods are used to overcome this limitation. In the proposed method, we present a segmentation approach for the extraction of bone and cartilage from MRI. Here, in this paper we perform preprocessing for image enhancement and noise removal of knee MR image using Gaussian blur and block matching 3D method. Larger bones in the knee joint are segmented first to perform reliable cartilage segmentation. Hence distance regularization level set evolution (DRLSE) is used for bone extraction successively followed by cartilage segmentation. Further, the performance of the proposed method is analyzed on a variety of knee MR images and experimental results demonstrated the improvement in accuracy compared to existing approaches. In conclusion, it is observed that the proposed technique improves significant performance with consistency and robustness during the segmentation process. © Springer Nature Singapore Pte Ltd. 2020.

Advances in Intelligent Systems and Computing

Segmentation of knee bone using MRI

Correctness of data and efficient mechanisms for data security, while transferring the file to and from Cloud, are of paramount importance in today's cloud-centric processing. A mechanism for correctness and efficient transfer of data is proposed in this article. While processing users request data, a set of attributes are defined and checked. States with attributes at different levels are defined to prevent unauthorized access. Security is provided while storing the data using a chunk generation algorithm and verification of chunks using lightweight Third-Party Auditor (TPA). TPA uses digital signatures to verify user's data that are generated by RSA with MD5 algorithms. The metadata file of generated chunks is encrypted using a modified AES algorithm. The proposed method prevents unauthorized users from accessing the data in the cloud environment, in addition to maintaining data integrity. Results of the proposed cloud security model implementation are discussed.

International Journal of Knowledge and Systems Science(IJKSS)

Achieving Cloud Security Using a Third Party Auditor and Preserving Privacy for Shared Data Over a Public Cloud

In this paper, a new local feature, called, Salient Wavelet Feature with Histogram of Oriented Gradients (SWFHOG) is introduced for human action recognition and behaviour analysis. In the proposed approach, regions having maximum information are selected based on their entropies. The SWF feature descriptor is formed by using the wavelet sub-bands obtained by applying wavelet decomposition to selected regions. To improve the accuracy further, the SWF feature vector is combined with the Histogram of Oriented Gradient global feature descriptor to form the SWFHOG feature descriptor. The proposed algorithm is evaluated using publicly available KTH, Weizmann, UT Interaction, and UCF Sports datasets for action recognition. The highest accuracy of 98.33% is achieved for the UT interaction dataset. The proposed SWFHOG feature descriptor is tested for behaviour analysis to identify the actions as normal or abnormal. The actions from SBU Kinect and UT Interaction dataset are divided into two sets as Normal Behaviour and Abnormal Behaviour. For the application of behaviour analysis, 95% recognition accuracy is achieved for the SBU Kinect dataset and 97% accuracy is obtained for the UT Interaction dataset. Robustness of the proposed SWFHOG algorithm is tested against Camera view angle change and imperfect actions using Weizmann robustness testing datasets. The proposed SWFHOG method shows promising results as compared to earlier methods.

Fulltext

International Journal of Advanced Computer Science and Applications

A Novel Human Action Recognition and Behaviour Analysis Technique using SWFHOG

Machine learning has gained tremendous attention from researchers recently. It has wide applications in tasks such as prediction and classification. Current work focuses on the effective detection of the personality of social network users. Personality is a combination of one’s thinking and behavior. Having knowledge about personality of a person has many applications in real world such as varied recommendation systems or HR departments. Personality of a person can be better understood by interacting with him/her. Predicting personality using social media is a new approach where direct interaction with people can be eliminated and accurate predictions can be built. Although different machine learning methods have been used by researchers recently for the task of prediction, the use of Ensembles has not been explored. Current work focuses on advanced classifiers such as XGBoost and Ensemble for prediction. Experimentation on the real-time Twitter dataset indicates high accuracy of 82.59% with an Ensemble. These results are encouraging for future research. © 2020, Springer Nature Singapore Pte Ltd.