The benefits of the Internet of Medical Things (IoMT) in providing seamless healthcare to the world are at the forefront of technological advancement. However, security concerns of any IoMT systems are high since they threaten to compromise personal information of patients and can even cause health hazards. Researchers are exploring the use of various techniques to ensure a high level of security of IoMT systems. One key concern is that the computing power of any Internet of Things (IoT) device is relatively low, hence mechanisms that require low computational power are appropriate for designing Intrusion Detection Systems (IDS). In this research work, a blockchain IDS coalition is proposed for securing IoMT networks and devices. The blockchain ledger is compact and uses less processing resources. Additionally, the ledger requires less communication overhead. The cryptographic hashes in the suggested architecture ensure complete data secrecy and integrity between parties who are trusted and those who are untrustworthy. Peer-to-peer networks in both central and cluster networks are also included in this work for complete decentralization. The proposed model can counter various attacks, including Denial of Service (DoS), anonymity attacks, impersonation attacks, Man-In-The-Middle (MITM), and Cross-Site Scripting (XSS). The proposed method achieved an F1- score as high as 100% and reported an AUC value of over 99%.

Neural style transfer is used as an optimization technique that combines two different images – a content image and a style reference image – to produce an output image that retains the appearance of the content image but has been modified to match the actual style of the style reference image. This is achieved by fine-tuning the output image to match the style reference images and the statistics for both content and style in the content image. These statistics are extracted from the images using a convolutional network. Primitive models such as WCT were improved upon by models such as PhotoWCT, whose spatial and temporal limitations were improved upon by Deep Photo Style Transfer. Eventually, wavelet transforms were introduced to perform photorealistic style transfer. A wavelet-corrected transfer based on whitening and colouring transforms, i.e., WCT 2 , was proposed that allowed the preservation of core content and eliminated the need for any post-processing steps and constraints. A model called Domain-Aware Universal Style Transfer also came into the picture. It supported both artistic and photorealistic style transfer. This study provides an overview of the neural style transfer technique. The recent advancements and improvements in the field, including the development of multi-scale and adaptive methods and the integration of semantic segmentation, are discussed and elaborated upon. Experiments have been conducted to determine the roles of encoder-decoder architecture and Haar wavelet functions. The optimum levels at which these can be leveraged for effective style transfer are ascertained. The study also highlights the contrast between VGG-16 and VGG-19 structures and analyzes various performance parameters to establish which works more efficiently for particular use cases. On comparing quantitative metrics across Gatys, AdaIN, and WCT, a gradual upgrade was seen across the models, as AdaIN was performing 99.92 percent better than the primitive Gatys model in terms of processing time. Over 1000 iterations, we found that VGG-16 and VGG-19 have comparable style loss metrics, but there is a difference of 73.1 percent in content loss. VGG-19, however, is displaying a better overall performance since it can keep both content and style losses at bay.

The open and unreliable environment of drones could make data transfer and authentication challenging. Given the proliferation of drone applications, the Internet of Drones (IoD) represents a promising phenomenon to enhance flight reliability and security. IoD has recently acquired pace due to its exceptional flexibility in numerous challenging circumstances. Furthermore, the incorporation of drones holds the potential to enhance many network systems’ performance metrics, such as throughput, scalability, connection, and latency. Regardless of its diverse domain, IoD is susceptible to malicious attacks owing to the wireless medium’s inherent unreliability. Drone communication can be made secure, reliable, and affordable by utilizing blockchain (BC) concepts that can be used to develop security mechanisms for addressing IoD’s shortcomings. This article reviews emerging BC-powered schemes, focusing on their application in drone communication, authentication, and security. Our study explores various drone applications and intricacies associated with BC-based drone technology. By leveraging BC concepts, security mechanisms can mitigate IoD’s shortcomings. Unlike previous works, this survey offers a detailed examination of BC applications in drone technology. The research includes a thorough investigation into current IoD challenges and proposes insightful recommendations to fortify its security framework. Additionally, we conduct experiments on the runtime of consensus algorithms, providing a detailed comparison along with various security models. An analysis of recent work shows diverse approaches in BC for IoD, with a comparative study aimed at mitigating challenges. An overview of machine learning in IoD along with insightful research recommendations are also given that provide ways to improve IoD’s security.

Advanced Neural Networks are widely used to recognize multi-modal conversational speech with significant improvements in accuracy automatically. Significantly, Convolutional Neural sheets have retreated cutting-edge performance in Automatic Voice Recognition (AVR) recently more appropriately in English; however, the Hindi language has not been explored and examined well on AVR systems. The work in this article has exposed a three-layered two-dimensional Sequential Convolutional neural architecture. The Sequential Conv2D is an end-to-end system that can instantaneously exploit speech signal spectral and temporal structures. The network has been trained and tested on different cepstral features such as Frequency and Time variant-Mel-Filters, Gamma-tone Filter Cepstral Quantities, Bark-Filter band Coefficients, and Spectrogram features of speech structures. The experiment was performed on two low-resourced speech command datasets; Hindi with 27,145 Speech Keywords developed by TIFR and 23,664 (1-s utterances) of English speech commands by Google TensorFlow and AIY English Speech Commands. The experimental outcome showed that the model achieves significant performance of Convolutional layers trained on spectrograms with 91.60% accuracy, compared to that achieved in other cepstral feature labels for English speech. However, the model achieved an accuracy of 69.65% for Hindi audio words in which bark-frequency cepstral coefficients features outperformed spectrogram features.

The exponential growth of the Internet of Everything (IoE), in recent times, has revealed many underlying security vulnerabilities of the nodes forming IoE networks. The extension of conventional security protocol to these devices has been greatly complicated by the prevalence of restricted computational hardware and limited battery life. Modern learning-based algorithms have shown the potential to secure the IoE networks without undue duress on the nodes’ limited capabilities. In this article, a machine learning-based architecture has been proposed to identify malicious and benign nodes in an IoE network operating with big data. A novel approach for the cooperation of XGBoost and deep learning models along with a genetic particle swarm optimization (GPSO) algorithm to discover the optimal architectures of individual machine learning models has been proposed. Through simulations, it is shown that GPSO-based learning algorithms provide reliable, robust, and scalable solutions. The proposed model significantly outperforms other security protocols in the classification of malicious and benign nodes forming an IoE network.

Internet of everything (IoE) has the power of reforming the healthcare sector - various medical devices, hardware, and software applications that are interconnected, tendering a massive volume of data. The huge interconnected medical-based network is prone to significant malicious attacks that can modify the medical data being communicated and transferred. IoE permits dynamic two-way communication and empowers the network with intellect, sophisticated data handling, caching, and allocation mechanisms. In this paper, an improvement in the conventional variable-sized detector generation for healthcare - IVD-IMT algorithm under Artificial Immune System (AIS) based Intrusion Detection System (IDS) capable of handling enormous data generated by the IoE medical network is proposed. Algorithm efficiency is dependent on two performance metrics - detection rate and false alarm rate. The input parameters were tuned using synthetic datasets and then tested over the NSL-KDD dataset. The research lays emphasis on lowering the false alarm rate without compromising on the detection rate.

Social Media has been growing and has provided the world with a platform to opine, debate, display, and discuss like never before. It has a major influence in research areas that analyze human behavior and social groups, and the phenomenon of social interactions is even being used in areas such as Internet of Things. This constant stream of data connecting individuals and organizations across the globe has had a tremendous impact on the functioning of society and even has the power to sway elections. Despite having numerous benefits, social media has certain issues such as the prevalence of fake news, which has also led to the rise of the hate speech phenomenon. Due to lax security throughout these social media platforms, these issues continue to exist without any repercussions. This leads to cyberbullying, defamation, and presents grave security concerns. Even though some work has been done independently on native scripts, hate speech detection, and code-mixed data, there exists a lack of academic work and research in the area of detecting hate speech in transliterated code-mixed data and in-text containing native language scripts. Research in this field is inhibited greatly due to the multiple variations in grammar and spelling and in general a lack of availability of annotated datasets, especially when it comes to native languages. This article comes up with a method to automate hate speech detection in code-mixed and native language text. The article presents an architecture containing a Tabnet classifier-based model trained on features extracted using MuRIL from transliterated code-mixed textual data. The article also shows that the same model works well on features extracted from text in Devanagari despite being trained on transliterated data.

Abstract Authentication is one of the foremost pillars in the Internet of Things (IoT) security that authenticates the identity of a device or a person with the help of a unique identification number. If authentication is compromised then an intruder can gain access and launch a variety of attacks on the network. The world of IoT devices is benefiting us in many ways, but the vulnerability of becoming a victim of cybercrime is also increasing at a rapid pace. This research paper proposes an authentication‐based solution for designing a secure communication network to ensure safe access to data and stop attackers from any unauthorized access to various IoT applications using cryptography and cloud computing. The proposed work is then compared with other popular cryptosystems such as Secure Internet of Things (SIT), Data Encryption Standard (DES) and Blowfish. LEOBAT is simulated using MATLAB and proves to be a fast and efficient authentication technique.

Abstract Sepsis is a severe life‐threatening disease, which is the body's extreme reverberation to any virus leading to failed organs, damaged tissue, or death. It requires accurate and efficient real‐time detection. Continuous and potent monitoring of patient health data can be useful in predicting the potential risks the patient might be exposed to, based on their recent history of medical records. Machine learning models have proven to be a significant approach in performing accurate and precise predictions, especially in the medical field. In this paper, a smart network with a long short term memory (LSTM) based model at its heart is proposed for early prediction of Sepsis for patients admitted in the ICU. The network operates on time series data and predicts the probability of a patient developing sepsis based on the historical medical data of the patient. It comprises Internet of Things based devices which have proven to be impactful in the areas of acquiring continuous and real‐time data in the healthcare field. In this paper, an architecture for early prediction and monitoring Sepsis with minimized latency through LSTM network is proposed by designing a decentralized prediction model in a fog‐based environment. The model had an accuracy of 95.1% after the last epoch with validation accuracy as 95%. The receiver operating characteristic curve area was reported as 0.864 for testing data with an accuracy of 95.1%. The model was not over‐fitted since the validation accuracy was significantly close to the training accuracy of the model.

There has been an asymmetric shift toward harnessing cloud-based technologies as the world focuses on shifting operations remotely. Data security for remote operations is crucial for the protection and preservation of critical infrastructure. Furthermore, there has been an emerging trend to integrate IoT-based devices with the expanding cloud infrastructure. In this work, mobile cloud-based infrastructure is considered where contact opportunities are developed in an opportunistic manner so as to facilitate efficient data forwarding and secure process handling. A probabilistic framework is proposed that facilitates data routing between the nodes and local cloud in an IoT network coupled with a multitier trust and encryption scheme for secure data delivery in the cloud-based IoT network. The proposed scheme is evaluated with simulations over two data sets against attack resilience and routing efficiency-based performance metrics, comparing to standard protocols, such as PRoPHET, MaxProp, ProWait, and TCAFE, which displays the enhancement in operations of Sec-CIoT.

In opportunistic networks, the path connecting two nodes is not continuous at any time instant. In such an environment, routing is an extremely taxing word owing to the ever‐changing nature of the network and random connections between nodes. Routing in such networks is done by a store carry forward mechanism, in which local information is used to make opportunistic routing decisions. In this study, the authors present a novel dynamic and intelligent self‐learning routing protocol that is an improvement of the history‐based routing protocol for opportunistic (HiBOp) networks. The proposed method presents a novel solution for the estimation of average latency between any two nodes, which is used along with reinforcement learning to dynamically learn the nodes' interactions. Simulation results on a real mobility trace (INFOCOM 2006) show that latency‐aware reinforced routing for opportunistic network applied to HiBOp outperforms the original HiBOp protocol by 14.4% in terms of delivery probability, 15% in terms of average latency and 34.7% in terms of overhead ratio.

Routing in Opportunistic Internet of Things Network (OppIoT) is an involved problem, because the network is intermittently connected and source to destination end-to-end paths are non-existent. Moreover, Machine Learning (ML) has recently achieved great success in multiple domains and is now being applied to automate routing in Opportunistic Networks (OppNets) which are similar in characteristics to OppIoT, through protocols such as MLProph and KNNR. In this paper, we utilize cascade learning, a form of ensemble based ML, for improved routing in OppIoT. Through simulations we show that our proposed protocol called Cascaded Machine Learning based routing protocol (CAML), outperforms existing ML based protocols (MLProph and KNNR), and traditional well-performing protocols (HBPR and PRoPHET), on a wide range of performance metrics including message delivery probability, average hop count, packets dropped and network overhead ratio.

In an Opportunistic Network (Oppnet), the transmission of messages between mobile devices is achieved in a store-carry-and-forward fashion since nodes store the incoming messages in their buffer and wait until a suitable next hop node is encountered that can carry the message closer to the destination. In such environment, due to the delay-tolerant nature of the network, designing a routing protocol is a challenge. This paper proposes a novel routing protocol called Encounter and Distance based Routing (EDR), which utilizes the so-called forward parameter to determine the next hop selection. This parameter is calculated by taking into account the number of encounters and the distance of each node in the network with respect to a particular destination. Simulation results are provided, showing the superiority of EDR over the History based Prediction for Routing (HBPR) protocol and the ProWait protocol, chosen as benchmark schemes, in terms of hop count, messages dropped, and average latency.

In Opportunistic Networks (OppNets), the existence of an end-to-end connected path between the sender and the receiver is not possible. Thus routing in this type of networks is different from the traditional Mobile Adhoc Networks (MANETs). MANETs assume the existence of a fixed route between the sender and the receiver before the start of the communication and till its completion. Routes are constructed dynamically as the source node or an intermediate node can choose any node as next hop from a group of neighbors assuming that it will take the message closer to the destination node or deliver to the destination itself. In this paper, we proposed a novel History Based Prediction Routing (HBPR) protocol for infrastructure-less OppNets which utilizes the behavioral information of the nodes to find the best next node for routing. The proposed protocol was compared with the Epidemic routing protocol. Through simulations it was found that the HBPR performs better in terms of number of messages delivered and the overhead ratio than the Epidemic protocol.