Browsing by Author "Rahul Mishra"

Now showing 1 - 10 of 10

A Federated Learning Approach With Imperfect Labels in LoRa-Based Transportation Systems
(Institute of Electrical and Electronics Engineers Inc., 2023) Ramakant Kumar; Rahul Mishra; Hari Prabhat Gupta
Intelligent Transportation System (ITS) helps to improve vehicle health, driver safety, and passenger comfort. Remotely sharing the information of ITS to train the machine and deep learning models hamper data privacy and generate security threats to the passenger, driver, and vehicle owners. Moreover, sharing the information requires huge networking resources such as high data rate, low latency, and low packet loss. Federated learning provides privacy-preserving model training on the vehicle without sharing the information. However, due to poor annotation mechanisms, federated learning may suffer from imperfect labels. This paper proposes a federated learning approach for ITS that can handle imperfect labels in the datasets of the participants. The approach also uses a Long-Range network to provide communication efficient connectivity. The approach initially estimates class-wise centroids of the datasets at the participants and server and then identifies participants with imperfect labels using similarity scores. Such participants demand the fraction of the correctly annotated dataset at the server to improve performance. We further derive the expression for the optimal fraction of the dataset requested by a participant. We finally verify the effectiveness of the proposed approach using the existing model and publicly available dataset. © 2000-2011 IEEE.
A Model Personalization-based Federated Learning Approach for Heterogeneous Participants with Variability in the Dataset
(Association for Computing Machinery, 2023) Rahul Mishra; Hari Prabhat Gupta
Federated learning is an emerging paradigm that provides privacy-preserving collaboration among multiple participants for model training without sharing private data. The participants with heterogeneous devices and networking resources decelerate the training and aggregation. The dataset of the participant also possesses a high level of variability, which means the characteristics of the dataset change over time. Moreover, it is a prerequisite to preserve the personalized characteristics of the local dataset on each participant device to achieve better performance. This article proposes a model personalization-based federated learning approach in the presence of variability in the local datasets. The approach involves participants with heterogeneous devices and networking resources. The central server initiates the approach and constructs a base model that executes on most participants. The approach simultaneously learns the personalized model and handles the variability in the datasets. We propose a knowledge distillation-based early-halting approach for devices where the base model does not fit directly. The early halting speeds up the training of the model. We also propose an aperiodic global update approach that helps participants to share their updated parameters aperiodically with server. Finally, we perform a real-world study to evaluate the performance of the approach and compare with state-of-the-art techniques. © 2023 Association for Computing Machinery. All rights reserved.
Conservation Agriculture for Soil Health and Carbon Sequestration in the Indian Himalayan Region
(Springer Singapore, 2023) Ashish Rai; Sumit Tripathi; Ayush Bahuguna; Sumit Rai; Jitendra Rajput; Anshu Gangwar; Rajeev Kumar Srivastava; Arvind Kumar Singh; Satish Kumar Singh; Dibyanshu Shekhar; Rahul Mishra; Eetela Sathyanarayana; Supriya Pandey
Mountains the most significant agro-ecosystems that directly or indirectly support human life. The areas surrounding the hills are abundant in biodiversity and have enormous potential for sustaining Indian agriculture. It has been widely recognised that the ecological fragility and sensitivity of the Himalayas to climatic aberrations, topography, peculiar geographical features, and some of the particular identified problems, which may be soil loss, runoff, steep slopes, acidity of soils, and loss of soil nutrients, form it a very distinct region as opposed to plains in terms of socioeconomic situation. Conventional agriculture was one of the best aspects of food production during the green revolution and after India gained its independence for securing food and nutrition through intensive agricultural practices, but on the flip side, it has simultaneous effects on resource degradation and soil biodiversity. The need for food and fodder, an ever-growing population, the preservation of soil biodiversity, declining soil health, climate change, the use of unbalanced fertilisers, and decreased farm profitability all call for a paradigm shift in the agriculture sector. On the other hand, increasing the intensity of the hillside agriculture system without implementing any conservation measures greatly increases the likelihood of disastrous conditions. Conservation agriculture has long been known to improve soil health and sustain agricultural production systems by reducing environmental footprints. Between the atmosphere and the lithosphere, numerous biological and physical processes are regulated by soils. An integral aspect of soil that promotes agricultural sustainability is soil health. However, each measurement of a specific soil health parameter is always tied to a unique set of circumstances. A fundamental concern in maintaining soil health to feed an expanding population is resource conservation. Climate change is a topic of discussion on a worldwide scale in the current globalisation context. The greenhouse effect is best for life but only up to a point beyond which it becomes dangerous. Due to urbanisation, changes in land use, cropping patterns, and other factors, human influences on climate change go beyond the range of natural fluctuation. Climate change in the soil system is significantly influenced by carbon regulation in the soil. The rate of organic matter decomposition is accelerated by an increase in mean annual temperature, which affects aggregate stability, water storage capacity, and nutrient balance— all of which are crucial for healthy soil structure, soil fertility, productivity, and sustainability. In actuality, soil bacteria break down organic materials, but a change in temperature regime may change the microbial population. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.
Current status of available techniques for removal of heavy metal contamination in the river ecosystem
(Elsevier, 2022) Rahul Mishra; Aman Kumar; Ekta Singh; Sunil Kumar; Vinod Kumar Tripathi; Santosh K. Jha; Sushil K. Shukla
Heavy metal contamination in river ecosystem is a worldwide problem that is of great environmental concern. These heavy metals concentration in river water has expanded rapidly over the last few decades. As indicated by a Central Water Commission study, India’s 42 rivers have at least two heavy metals in excess of the safe limit. Ganga, India’s National River, has been found to be polluted with five heavy metals, namely Fe, Ni, Cu, Cr and Pb. Other than Ganga, more concentrations of these metals were found in Arkavathi, Orsang, Rapti, Sabarmati, Saryu, and Vaitarna. Moreover, it is of more concern because they disturb the ecological stability of river ecosystems due to its long-term negative influences. Consequently, concentrations of toxic metals have increased at alarming rates in grains and vegetables grown in contaminated soils. Because of its toxicity, non-biodegradability, and bioaccumulation it poses a serious threat to humans and the environment. Membrane filtration, reverse osmosis, chemical precipitation, charcoal/activated carbon adsorption, phytoremediation and biosorption have been widely used techniques for treatment of wastewater. The present chapter attempts to provide the status of these techniques and scenario of river ecosystems with respect to heavy metal contamination. © 2022 Elsevier Inc. All rights reserved.
Eco-efficiency tool for urban solid waste management system: A case study of mumbai, india
(Springer Science and Business Media Deutschland GmbH, 2021) Ekta Singh; Aman Kumar; Rahul Mishra; Sunil Kumar
Carbon emissions in urban solid waste treatment are a main cause for the change in climate which, according to the United Nations Environment Program (UNEP), accounts for almost 5% of ozone-depleting substances worldwide. The gases and fluids that are being released cause many ecological effects like environmental change and acidification particularly in the major metropolitan cities in India like Mumbai. Therefore, managing the solid waste properly is one of the major concerns of almost all the cities in India. The aim of the present study is to analyse the eco-efficiency for managing urban solid waste in Mumbai region. The assessment model is developed on the basis of adapting Eco-Efficiency Analysis (Eco-Eff) methodology that helps in the formulation of solid waste management (SW) criteria. Life Cycle Assessment (LCA) has been considered for portraying and recognizing proficient techniques and proposing improvement criteria for appropriate treatment of these wastes. The ecological profile of both i.e the original situation and the virtual (proposed improvement measures) were compared all together to identify the net benefits connected with the changed inputs. This evaluation framework is useful for the assessment of system alternatives and adapting the changes for decision-making. The model was implemented in the context of Mumbai which explicitly tackles sustainability in its organizational strategic plan. The development of the model depends on an adaptation of the technique that would allow a comparison of the proposed key objectives with the available data on solid waste management. This technique showed the overall decrease in environmental impact utilizing profitable strategies as the major objective towards improving waste management. The segregation proportion and the techniques utilized for treatment are key markers of optimization steps. Comparing the intervals with the prior efficiency of the system and the proposed performance, it is finally concluded whether the eco-efficiency score obtained is neutral or good. On the basis of the assessment of the performance of the optimization measure proposed, it is quite possible that its value would demonstrate a better management of solid waste being generated in this area. © Springer Nature Singapore Pte Ltd 2021.
Impact of network load for anomaly detection in software-defined networking
(Springer, 2020) Ashish Gupta; Bharat Didwania; Gaurav Singh; Hari Prabhat Gupta; Rahul Mishra; Tanima Dutta
Software-Defined Networking (SDN) introduces a new network paradigm for separating the control plane and data plane. The control plane manages the packet flow in the data plane of the network. The anomaly detection in the context of SDN is to identify potentially harmful traffic. If an anomaly occurs because of malicious packets in SDN, inspecting the payload of packets is an effective way to recognize abnormal traffic. In this paper, we consider different bandwidths and topologies of the network for the detection of an anomaly in SDN. We also evaluate the performance of the SDN on the same network. We have implemented different tree topologies on OpenFlow controller using Mininet network emulator. We considered OpenFlow messages as a performance metric for evaluating the performance of the network with different tree topologies. © Springer Nature Singapore Pte Ltd. 2020.
Microbes and compost: an emerging role in climate resilience agriculture
(Elsevier, 2024) Ashish Rai; Rahul Mishra; Abhik Patra; Arvind Kumar Singh; Sachin Sharma; A. Arvind; Ayush Bahuguna; Sumit Rai; Jitendra Rajput; Anshu Gangwar; Shankar Jha; Sumit Kumar Tripathi; Rajeev Kumar Srivastava; Dibyanshu Shekhar; Satish Kumar Singh; Tejaswini Kapil; Ram Babu Sharma; Supriya Rai
Microbes and their metabolic activity are crucial for a healthy and functioning soil. The rhizosphere, where plant roots and microbes mingle, is a bustling hub for nutrient cycling, energy flow, and microbial activity. Sustainable farming prioritizes nurturing these rhizospheric processes. Biofertilizers, including symbiotic and nonsymbiotic microbial partnerships, plant growth-promoting microbes, and arbuscular mycorrhizal collaborations, all play diverse roles in soil health and plant growth. Some microbes like Pseudomonas spp., Bacillus spp., and Streptomyces spp. help convert insoluble phosphorus into plant available forms. Composting, is another sustainable process, transforms organic waste into valuable compost, a dual-action fertilizer and soil amendment. Microbes decompose organic matter in compost, turning it into a stable, plant-friendly material. This aerobic process breaks down easy-to-digest molecules, generating CO2 and more durable substances. Composting effectively manages organic waste, reusing nutrients, reducing volume and moisture, and breaking down harmful organics plus, intricate humic-like chemicals form, boosting soil health. Thus, understanding and nurturing the vibrant microbial world in the rhizosphere through sustainable practices like biofertilizers and composting is key to healthy soil and a thriving future for farming. © 2025 Elsevier Inc. All rights reserved.
Monitoring of land use/land cover changes by the application of gis for disposal of solid waste: A case study of proposed smart cities in bihar
(Springer Science and Business Media Deutschland GmbH, 2021) Aman Kumar; Ekta Singh; Rahul Mishra; Sunil Kumar
Disposal of solid waste has turned into a severe issue in major urban areas in India nowadays. Most of the municipalities have failed to solve such a situation. A major statement of the issue is the normal sights of wastes that regularly undermine the streets closed due to traffic. The appearance of the cities along with the well-being of the people residing there is highly influenced by the risk presented by this situation. Waste disposal issues continue to rise due to improper collection of the waste and its processing/disposal following the rules in place. In some cases, the issue could be followed to absence of an appropriate site for transfer and treatment of these wastes. The solid waste disposal depends upon the selection of proper site and numerous other issues like sustainability and social acceptance. The objective of this paper is to show how GIS is utilized in finding a proper site for the disposal of wastes. It illustrates the spatio-temporal dynamics of land use/land cover changes of proposed smart cities of the state of Bihar namely Biharsharif, Patna, Muzaffarpur and Bhagalpur. These studies exhibit the current situation of solid waste management in these cities of Bihar although numerous components are necessary while choosing a site for proper disposal of municipal solid waste being generated, communication routes, land use/land cover and geomorphological changes. All these features have been consolidated in this study to choose the fundamental site that meets the specific conditions. In general, map layers are determined, and final outputs clearly indicate appropriate site for the disposal of solid waste. LANDSAT-TM and DEM images used in this study and their results are overlapped with the inferred layer of the built-up area and the final disposal site. It also provides comprehensive monitoring of key performance measurements, mainly due to the identification of factors connecting diagnostic and improvement steps. Based on the case study, a quality analysis could be carried out and its principles shown in the solid waste management (SWM) practice. The obtained results clearly show all the favourable locations that can be possibly used as the best suitable area for the proper disposal of solid waste being generated in these areas. It is therefore concluded that the performance assessment of SWM is an important element in ensuring compliance and implementing the sustainability strategy plan. © Springer Nature Singapore Pte Ltd 2021.
Neurological manifestations of COVID-19: a systematic review and meta-analysis of proportions
(Springer-Verlag Italia s.r.l., 2020) T.T. Favas; Priya Dev; Rameshwar Nath Chaurasia; Kamlesh Chakravarty; Rahul Mishra; Deepika Joshi; Vijay Nath Mishra; Anand Kumar; Varun Kumar Singh; Manoj Pandey; Abhishek Pathak
Background: Coronaviruses mainly affect the respiratory system; however, there are reports of SARS-CoV and MERS-CoV causing neurological manifestations. We aimed at discussing the various neurological manifestations of SARS-CoV-2 infection and to estimate the prevalence of each of them. Methods: We searched the following electronic databases; PubMed, MEDLINE, Scopus, EMBASE, Google Scholar, EBSCO, Web of Science, Cochrane Library, WHO database, and ClinicalTrials.gov. Relevant MeSH terms for COVID-19 and neurological manifestations were used. Randomized controlled trials, non-randomized controlled trials, case-control studies, cohort studies, cross-sectional studies, case series, and case reports were included in the study. To estimate the overall proportion of each neurological manifestations, the study employed meta-analysis of proportions using a random-effects model. Results: Pooled prevalence of each neurological manifestations are, smell disturbances (35.8%; 95% CI 21.4–50.2), taste disturbances (38.5%; 95%CI 24.0–53.0), myalgia (19.3%; 95% CI 15.1–23.6), headache (14.7%; 95% CI 10.4–18.9), dizziness (6.1%; 95% CI 3.1–9.2), and syncope (1.8%; 95% CI 0.9–4.6). Pooled prevalence of acute cerebrovascular disease was (2.3%; 95%CI 1.0–3.6), of which majority were ischaemic stroke (2.1%; 95% CI 0.9–3.3), followed by haemorrhagic stroke (0.4%; 95% CI 0.2–0.6), and cerebral venous thrombosis (0.3%; 95% CI 0.1–0.6). Conclusions: Neurological symptoms are common in SARS-CoV-2 infection, and from the large number of cases reported from all over the world daily, the prevalence of neurological features might increase again. Identifying some neurological manifestations like smell and taste disturbances can be used to screen patients with COVID-19 so that early identification and isolation is possible. © 2020, Fondazione Società Italiana di Neurologia.
Transforming Large-Size to Lightweight Deep Neural Networks for IoT Applications
(Association for Computing Machinery, 2023) Rahul Mishra; Hari Gupta
Deep Neural Networks (DNNs) have gained unprecedented popularity due to their high-order performance and automated feature extraction capability. This has encouraged researchers to incorporate DNN in different Internet of Things (IoT) applications in recent years. However, the colossal requirement of computation, energy, and storage of DNNs make their deployment prohibitive on resource-constrained IoT devices. Therefore, several compression techniques have been proposed in recent years to reduce the energy, storage, and computation requirements of the DNN. These techniques have utilized a different perspective for compressing a DNN with minimal accuracy compromise. This encourages us to comprehensively overview DNN compression techniques for the IoT. This article presents a comprehensive overview of existing literature on compressing the DNN that reduces energy consumption, storage, and computation requirements for IoT applications. We divide the existing approaches into five broad categories - network pruning, sparse representation, bits precision, knowledge distillation, and miscellaneous - based upon the mechanism incorporated for compressing the DNN. The article discusses the challenges associated with each category of DNN compression techniques and presents some prominent applications using IoT in conjunction with a compressed DNN. Finally, we provide a quick summary of existing work under each category with the future direction in DNN compression. © 2023 Association for Computing Machinery.