Environmental sensing is becoming an important segment across the geographical globe even beyond. That can be important tool for primary alarming indicator for saving millions of lives in the world. Impact of sensing devices is playing key role in understanding; as a result, we stand a better chance of improving and keeping our impact to a minimum. The obvious benefits of environmental monitoring include pollution reduction, occupational disease reduction, and also minimizing the impact of human activities. Perhaps, the biggest advancement that environmental sensing will make in the future is that smart sensors will be implemented in order to monitor the natural gas infrastructure. Here, we will be discussing some of the most innovative ways in which smart sensors are used to reduce the strain on the environment.

Center for Environmental Sciences & Engineering

Smart Nanostructure Materials and Sensor Technology

<a href="https://doi.org/10.1007/978-981-19-2685-3_6">Environmental Impact of Sensing Devices</a>

The present study utilized earth observation Sentinel5P TROPOMI (TROPOspheric Monitoring Instrument) data for monitoring submarine volcanic activities. The world has seen a sequence of abrupt volcanic eruptions within one-month duration i.e., on 20th December 2021, 13th January 2022 and 15th January 2022. This caused the emissions of natural gaseous pollutants such as Sulphur Dioxide (SO2), Hydrogen Sulphide (H2S) and ash particles. Atmospheric SO2, AAI (Absorbing Aerosol Index) and Cloud fraction data are retrieved from the TROPOMI onboard the Copernicus Sentinel5P European Space Agency satellite. Results confirmed the increased concentration of SO2 column density after 20th December, and it was observed to be 0.002 mol/m2, the highest concentration during the period of study. Generally, SO2 concentration stays within 0.001 mol/m2 or less. Concentration was seen increasing after the first eruption and reached maximum after 15th January 2022 eruption to a level up to 0.002 mol/ m2. Similar outcomes were observed for AAI for the chosen site. AAI values increased to 25,000 fold (AAI values of 1.25) during the first eruption and increased to 29,000 fold on 15th January 2022 after eruptions (AAI values of 1.45) as compared AAI values of 0.005 or negative AAI values before eruptions. A cloud fraction of value 1 is observed during this time, along with the top most cloud height at 14,233.16 m (14.23 kms) above the crater of the volcano (maximum estimation limit by S5P). These values are higher as compared to isolated islands, as there are no other sources of emissions at surrounding environment. The outcomes support the role of Earth Observation datasets for disaster monitoring and management plans for mitigation. © 2022 Informa UK Limited, trading as Taylor &amp; Francis Group

Remote Sensing Letters

Highlighting the Role of Earth Observation Sentinel5P TROPOMI in monitoring volcanic eruptions: A Report on Hunga Tonga, a Submarine Volcano

Recent years have been witnessing significant developments in research in human action recognition based on skeleton data. The graphical representation of the human skeleton, available with the dataset, provides opportunity to apply Graph Convolutional Networks (GCN), to avail efficient analysis of deep spatial-temporal information from the joint and skeleton structure. Most of the current works in skeleton action recognition use the temporal aspect of the video in short-term sequences, ignoring the long-term information present in the evolving skeleton sequence. The proposed long-term Spatio-temporal Contrastive Learning framework for Skeleton Action Recognition uses an encoder-decoder module. The encoder collects deep global-level (long-term) information from the complete action sequence using efficient self-supervision. The proposed encoder combines knowledge from the temporal domain with high-level information of the relative joint and structure movements of the skeleton. The decoder serves two purposes: predicting the human activity and predicting skeleton structure in the future frames. The decoder primarily uses the high-level encodings from the encoder to anticipate the action. For predicting skeleton structure, we extract an even deeper correlation in the Spatio-temporal domain and merge it with the original frame of the video. We apply a contrastive framework in the frame prediction part so that similar actions have similar predicted skeleton structure. The use of the contrastive framework throughout the proposed model helps achieve exemplary performance while employing a self-supervised aspect to the model. We test our model on the NTU-RGB-D-60 dataset and achieve state-of-the-art performance. The codes related to this work are available at: \url{https://github.com/AnshulRustogi/Long-Term-Spatio-Temporal-Framework}.

World University root node

Computer Science and Engineering

(SoE) School of Engineering

IJCNN

Long-term Spatio-temporal Contrastive Learning framework for Skeleton Action Recognition

SNU Management

Physics

Shiv Nadar University

(SoNS) School of Natural Sciences

Shiv Nadar University is a comprehensive, multidisciplinary, research-focused, and student-centric University offering a full range of academic programs at the undergraduate, postgraduate and doctoral level. With state-of-the-art infrastructure, the University comprises of academic wings, sophisticated labs, international standard sports facilities, amphitheaters, auditorium, conference rooms and smart classrooms. The University&rsquo;s goal is to become internationally recognized for the quality of its research and creative endeavors and their applicability to improving quality of life, generating new insights and expanding the boundaries of human knowledge creativity. Committed to excellence in teaching, research and service, the University aims to serve the higher education needs of India and the world beyond.