Abstract

Internet of Things (IoT)-based smart factories offer the manufacturing sectors a great opportunity to embrace the fourth industrial revolution (Industry 4.0). The real-time monitoring of manufacturing operations in an Industry 4.0 needs to be ensured by the deployed technologies, like Artificial Intelligence (AI) and Big Data analytics. The overall purpose is to improve the outcomes of the production process. However, Industry 4.0 becomes vulnerable to different potential attacks as the communication takes place via public environments. In this article, an authentication and key agreement method has been suggested to secure the communication that can occur in a Fog-based Industry 4.0 environment. The security proposal provides secure mutual authentication along with key establishment between various smart industrial devices and fog servers, as well as between fog servers and cloud servers. The security analysis and comparative study reveal that the proposed method can mitigate various potential attacks, and it also offers important security and functionality attributes as compared to those for other competing schemes.

Abstract

Denial-of-service (DoS) attacks are a major concern in the field of Internet technology, and they pose a difficult security challenge. Among the different types of DoS attacks, distributed denial-of-service (DDoS) attacks are especially concerning because they can quickly drain the resources of a target, disrupting their computational and communication capabilities without warning. In response to the severity of this problem, various defense strategies have been developed to defend against DDoS attacks. In this paper, a survey on the various DDoS attacks detection schemes is presented. An overview of the DDoS attack methodology is given. The information on different types of DDoS detection methods in SDN environment is also provided. Then a comparative study of different DDoS attack detection schemes is given, which contains the comparisons of different schemes in terms of their advantages, limitations, accuracy values, and time complexity.

Abstract

In the recent past, forest fires have increased due to the changing climate pattern. It is necessary to analyse and quantify various gaseous emissions so as to mitigate their harmful effects on air pollution. Satellite remote sensing data provides an opportunity to study the greenhouse gases in the atmosphere. The multispectral sensor of the Tropospheric Monitoring Instrument (Sentinel-5) is capable of recording the reflectance of wavelengths vital for measuring the atmospheric concentrations of methane, formaldehyde, aerosol, carbon monoxide, etc., at a spatial resolution of 0.01°. The present study utilized the Google Earth Engine (GEE) platform to study the emissions caused by forest fires in four districts of Uttarakhand State of India, which witnessed unprecedented fires in April-May 2021. All the datasets were ingested in GEE, which has the capability to analyse large datasets without the need to download them. The pre-fire period chosen was September 2020; the fire period was February-May 2021, and the post-fire period was June 2021. The variables chosen were aerosol absorbing index (AAI), carbon monoxide (CO) and nitrogen dioxide (NO2). The climate parameter temperature (Moderate Resolution Imaging Spectroradiometer Land Surface Temperature) and precipitation (from Climate Hazards Group InfraRed Precipitation (CHIRPS) Pentad) were also studied for the period mentioned. The results indicate a different trend for emissions in each district. For AAI, maximum emissions were noted in district Nainital

Abstract

Document summarization aims to create a precise and coherent summary of a text document. Many deep learning summarization models are developed mainly for English, often requiring a large training corpus and efficient pre-trained language models and tools. However, English summarization models for low-resource Indian languages are often limited by rich morphological variation, syntax, and semantic differences. In this paper, we propose GAE-ISumm, an unsupervised Indic summarization model that extracts summaries from text documents. In particular, our proposed model, GAE-ISumm uses Graph Autoencoder (GAE) to learn text representations and a document summary jointly. We also provide a manually-annotated Telugu summarization dataset TELSUM, to experiment with our model GAE-ISumm. Further, we experiment with the most publicly available Indian language summarization datasets to investigate the effectiveness of GAE-ISumm on other Indian languages. Our experiments of GAE-ISumm in seven languages make the following observations: (i) it is competitive or better than state-of-the-art results on all datasets, (ii) it reports benchmark results on TELSUM, and (iii) the inclusion of positional and cluster information in the proposed model improved the performance of summaries.

Abstract

The healthcare sector is a very crucial and important sector of any society, and with the evolution of the various deployed technologies, like the Internet of Things (IoT), machine learning and blockchain it has numerous advantages. However, in this section, the data is much more vulnerable than others, because the data is strictly private and confidential, and it requires a highly secured framework for the transmission of data between entities. In this article, we aim to design a blockchain-envisioned authentication and key management mechanism for the IoMT-based smart healthcare applications (in short, we call it SBAKM-HS). We compare the various attributes of the proposed SBAKM-HS and other existing schemes to demonstrate that SBAKM-HS outperforms other existing schemes. The conducted security analysis

Abstract

With the increasing use of Internet of Things (IoT)- enabled drones for various purposes, including photography, de- livery, and surveillance, concerns related to privacy and security have arisen. Drones have the potential to capture sensitive infor- mation, invade privacy, and cause security breaches. Therefore, the need for advanced technology for the automated detection of drones has become crucial. In this paper, we propose an ensemble-based IoT-enabled drones detection scheme (in short, EDDSBS). The presented model is part of a computer vision- based module and uses transfer learning for improved perfor- mance. Transfer learning allows the reuse of pre-trained models and their knowledge in a different but related domain, enabling better performance with less training data. To evaluate the performance of the proposed EDDSBS, we test it on benchmark datasets, including the Drone–vs–Bird Dataset and the UAVDT dataset. The proposed EDDSBS outperforms the existing schemes of drone detection (i.e., in terms of accuracy). The results of the presented scheme demonstrate the potential of deep learning- based technology for automated drone detection in critical areas, such as airports, military bases, and other high-security areas. Thus the paper introduces a comprehensive process methodology for drone detection that can be applied in real-world settings for a sustainable and secure environment, which is required for a safe community

Abstract

Drought is a natural hazard due to the lack of water availability in terms of precipitation and the consequent shortage of streamflow and soil moisture affecting the socioeconomics of a country. Although drought impacts on water quantity in terms of precipitation, streamflow, and soil moisture are widely recognized, the impacts on water quality are less known. Specifically, hydrological drought is observed to be impacted by climate change, which in turn probably increased the frequency and intensity of low river flows, affecting the water quality. Hydrological drought in combination with high water temperatures may deteriorate river water quality. This study analyzes hydrological drought impacts on river water quality for a peninsular river system, the Tunga-Bhadra River in India. A drought assessment has been done over the Tunga-Bhadra River Basin with a keen focus on studying the impact of hydrological drought on the water quality by observing the behavior of water quality parameters between the drought period and the reference years. The impact of hydrological drought on water quality during a drought period was assessed by calculating the Standardized Precipitation Index (SPI) and Streamflow Drought Index (SDI) for the studied period from June 1, 2005, to May 31, 2017. A statistical analysis has been done to study the significance of the impact on the water quality over the river basin. Time series of water quality parameters were investigated at three monitoring stations during the common drought period, occurring in the year 2013. A total amount of five water quality parameters were involved in the analysis: water temperature, pH, dissolved oxygen (DO), biochemical oxygen demand (BOD), and nitrates. The behavioral changes of the parameters were studied, analyzed, and justified. An increase in river water temperature (3.4°C) with a decrease in discharge (25%) have resulted in lower DO (0.3 mg/l) values during the drought year of 2013 compared to the 2012 reference period along with the Bhadravathi station along the Bhadra River. A decrease in discharge during drought events along with an increase in river water temperature under an increase of air temperature resulted in the lowering of oxygen saturation concentrations and decrease in DO levels. The results indicate deterioration of river water quality of the Tunga-Bhadra River during drought, with respect to high water temperatures, reduction in dilution

Abstract

Text-based VQA aims at answering questions by reading the text present in the images. It requires a large amount of scene-text relationship understanding compared to the VQA task. Recent studies have shown that the question-answer pairs in the dataset are more focused on the text present in the image but less importance is given to visual features and some questions do not require understanding the image. The models trained on this dataset predict biased answers due to the lack of understanding of visual context. For example, in questions like "What is written on the signboard?", the answer predicted by the model is always "STOP" which makes the model to ignore the image. To address these issues, we propose a method to learn visual features (making V matter in TextVQA) along with the OCR features and question features using VQA dataset as external knowledge for Text-based VQA. Specifically, we combine the TextVQA dataset and VQA dataset and train the model on this combined dataset. Such a simple, yet effective approach increases the understanding and correlation between the image features and text present in the image, which helps in the better answering of questions. We further test the model on different datasets and compare their qualitative and quantitative results.

Abstract

We present Continuous Volumetric Embeddings (ConVol-E), a novel robust representation for dense correspondence-matching across RGB images of different human subjects in arbitrary poses and appearances under non-rigid deformation scenarios. Unlike existing representations [8], [14], ConVol-E captures the deviation from the underlying parametric body model by choosing suitable anchor/key points on the underlying parametric body surface and then representing any point in the volume based on its euclidean relationship with the anchor points. It allows us to represent any arbitrary point around the parametric body (clothing details, hair, etc.) by an embedding vector. Subsequently, given a monocular RGB image of a person, we learn to predict per-pixel ConVol-E embedding, which carries a similar meaning across different subjects and is invariant to pose and appearance, thereby acting as a descriptor to establish robust dense correspondences across different images of humans. We empirically evaluate our proposed embedding using a novel metric and show superior performance compared to the state-of-the-art for the task of in-the-wild dense correspondence matching across different subjects, camera views, and appearance.

Abstract

Growing interest in conversational agents promote two- way human-computer communications involving asking and answering visual questions have become an active area of research in AI. Thus, generation of visual question- answer pair(s) becomes an important and challenging task. To address this issue, we propose a weakly-supervised vi- sual question answer generation method that generates a relevant question-answer pairs for a given input image and associated caption. Most of the prior works are supervised and depend on the annotated question-answer datasets. In our work, we present a weakly supervised method that synthetically generates question-answer pairs procedurally from visual information and captions. The proposed method initially extracts list of answer words, then does near- est question generation that uses the caption and answer word to generate synthetic question. Next, the relevant question generator converts the nearest question to rele- vant language question by dependency parsing and in-order tree traversal, finally, fine-tune a ViLBERT model with the question-answer pair(s) generated at end. We perform an exhaustive experimental analysis on VQA dataset and see that our model significantly outperform SOTA methods on BLEU scores. We also show the results wrt baseline models and ablation study