National Institute of Technology Kurukshetra

Abstract Growing an ensemble of decision trees and allowing them to vote for the most popular class produced a significant increase in classification accuracy for land cover classification. The objective of this study is to present results obtained with the random forest classifier and to compare its performance with the support vector machines (SVMs) in terms of classification accuracy, training time and user defined parameters. Landsat Enhanced Thematic Mapper Plus (ETM+) data of an area in the UK with seven different land covers were used. Results from this study suggest that the random forest classifier performs equally well to SVMs in terms of classification accuracy and training time. This study also concludes that the number of user‐defined parameters required by random forest classifiers is less than the number required for SVMs and easier to define. Acknowledgment The author is grateful for the critical comments of two anonymous referees, whose advice has led to an improvement in the presentation of this paper.

Active learning (AL) attempts to maximize a model’s performance gain while annotating the fewest samples possible. Deep learning (DL) is greedy for data and requires a large amount of data supply to optimize a massive number of parameters if the model is to learn how to extract high-quality features. In recent years, due to the rapid development of internet technology, we have entered an era of information abundance characterized by massive amounts of available data. As a result, DL has attracted significant attention from researchers and has been rapidly developed. Compared with DL, however, researchers have a relatively low interest in AL. This is mainly because before the rise of DL, traditional machine learning requires relatively few labeled samples, meaning that early AL is rarely according the value it deserves. Although DL has made breakthroughs in various fields, most of this success is due to a large number of publicly available annotated datasets. However, the acquisition of a large number of high-quality annotated datasets consumes a lot of manpower, making it unfeasible in fields that require high levels of expertise (such as speech recognition, information extraction, medical images, etc.). Therefore, AL is gradually coming to receive the attention it is due. It is therefore natural to investigate whether AL can be used to reduce the cost of sample annotation while retaining the powerful learning capabilities of DL. As a result of such investigations, deep active learning (DeepAL) has emerged. Although research on this topic is quite abundant, there has not yet been a comprehensive survey of DeepAL-related works; accordingly, this article aims to fill this gap. We provide a formal classification method for the existing work, along with a comprehensive and systematic overview. In addition, we also analyze and summarize the development of DeepAL from an application perspective. Finally, we discuss the confusion and problems associated with DeepAL and provide some possible development directions.

Support vector machines (SVM) are attractive for the classification of remotely sensed data with some claims that the method is insensitive to the dimensionality of the data and, therefore, does not require a dimensionality-reduction analysis in preprocessing. Here, a series of classification analyses with two hyperspectral sensor data sets reveals that the accuracy of a classification by an SVM does vary as a function of the number of features used. Critically, it is shown that the accuracy of a classification may decline significantly (at 0.05 level of statistical significance) with the addition of features, particularly if a small training sample is used. This highlights a dependence of the accuracy of classification by an SVM on the dimensionality of the data and, therefore, the potential value of undertaking a feature-selection analysis prior to classification. Additionally, it is demonstrated that, even when a large training sample is available, feature selection may still be useful. For example, the accuracy derived from the use of a small number of features may be noninferior (at 0.05 level of significance) to that derived from the use of a larger feature set providing potential advantages in relation to issues such as data storage and computational processing costs. Feature selection may, therefore, be a valuable analysis to include in preprocessing operations for classification by an SVM.

Open Artificial Intelligence (AI) published an AI chatbot tool called ChatGPT at the end of November 2022. Generative Pre-trained Transformer (GPT) architecture is the foundation of ChatGPT. On the internet, ChatGPT has been rapidly growing. This chatbot enables users to discuss with the AI by inputting prompts, and it is based on OpenAI’s language model. Although ChatGPT is fantastic and produces exciting results for writing tales, poetry, songs, essays, and other things, it has certain restrictions. Users may ask the bot questions, and it will reply with pertinent, convincing subjects and replies. ChatGPT has now risen to the top of several academic agendas. Administrators create task teams and hold institution-wide meetings to react to the tools, with most of the advice being to adopt this technology. This paper briefs about the ChatGPT and its need. Further, various Progressive Work Flow Processes of the ChatGPT Tool are stated diagrammatically. Specific features and capabilities of the ChatGPT Support System are studied in this paper. Finally, we identified and discussed the significant roles of ChatGPT in the current scenario. The neural language models that form the foundation of character AI have been developed from the bottom up with talks in mind. This technology implies that the programme uses deep learning methods to analyse and produce text. The model “understands” the subtleties of human-produced natural language using vast amounts of data from the internet. • Open Artificial Intelligence (AI) published an AI chatbot tool called ChatGPT at the end of November 2022. • This paper briefs about ChatGPT and its need in the current scenario. • Progressive Work Flow Processes of the ChatGPT tool are diagrammatically stated. • Specific features and capabilities of the ChatGPT support system are elaborated in this paper. • Paper identified and discusses the significant roles of ChatGPT in the current scenario.

Nanotechnology has extensive application as nanomedicine in the medical field. Some nanoparticles have possible applications in novel diagnostic instruments, imagery and methodologies, targeted medicinal products, pharmaceutical products, biomedical implants, and tissue engineering. Today treatments of high toxicity can be administered with improved safety using nanotechnology, such as chemotherapeutic cancer drugs. Further, wearable gadgets can detect crucial changes in vital signs, cancer cell conditions, and infections that are genuinely happening in the body. We anticipate these technologies to provide doctors with considerably much better direct access to critical data on the reasons for changes in the signs of life or illness because of the technological presence at the source of the problem. Biomedicine can be utilised for therapies with predictive analytics and artificial intelligence. For carrying out this study, relevant papers on Nanotechnology in the medical field from Scopus, Google scholar, ResearchGate, and other research platforms are identified and studied. The study discusses different types of Nanoparticles used in the medical field. This paper discusses nanotechnology applications in the medical field. The class, features, and characteristics of Nanotechnology for medicine are also briefed. Scientists, governments, civil society organisations, and the general public will need to collaborate across sectors to assess the significance of nanotechnology and guide its advancement in various fields. The current research includes several possible Nanotechnology uses in the medical field. As a result, the study provides a brief and well-organised report on nanotechnology that should be valuable to researchers, engineers, and scientists for future research projects.

Energy storage plays crucial role to complete global and economical requirements of human beings. Supercapacitor act as promising candidate for energy storage applications due to its astonishing properties like - high power density, remarkable crystallinity, large porosity, elongated life-cycle, exceptional chemical & thermal stability, framework diversity and high specific surface area. The current review article embraces the history along with the difference of supercapacitors with fuel cells, capacitors, and batteries and detailed explanation of fabrication of supercapacitors i.e. proper selection of electrode and electrolyte material, separator and current collector. As a supercapacitor electrode material, several carbon-based materials, metal-oxides, and metal–organic frameworks have been briefly mentioned here. The current review article also discusses the supercapacitor components and various types of electrolytes. Electrochemical characterization techniques such as Cyclic Voltammetry (CV), Galvanostatic Charge Discharge (GCD) and Electrochemical Impedance Spectroscopy (EIS) are also briefly discussed here. Furthermore, this article outlines the current issues as well as potential solutions for upcoming time period.

Artificial Intelligence (AI)-based ChatGPT developed by OpenAI is now widely accepted in several fields, including education. Students can learn about ideas and theories by using this technology while generating content with it. ChatGPT is built on State of the Art (SOA), like Deep Learning (DL), Natural Language Processing (NLP), and Machine Learning (ML), an extrapolation of a class of ML-NLP models known as Large Language Model (LLMs). It may be used to automate test and assignment grading, giving instructors more time to concentrate on instruction. This technology can be utilised to customise learning for kids, enabling them to focus more intently on the subject matter and critical thinking ChatGPT is an excellent tool for language lessons since it can translate text from one language to another. It may provide lists of vocabulary terms and meanings, assisting students in developing their language proficiency with resources. Personalised learning opportunities are one of ChatGPT’s significant applications in the classroom. This might include creating educational resources and content tailored to a student’s unique interests, skills, and learning goals. This paper discusses the need for ChatGPT and the significant features of ChatGPT in the education system. Further, it identifies and discusses the significant applications of ChatGPT in education. Using ChatGPT, educators may design lessons and instructional materials specific to each student’s requirements and skills based on current trends. Students may work at their speed and concentrate on the areas where they need the most support, resulting in a more effective and efficient learning environment. Both instructors and students may profit significantly from using ChatGPT in the classroom. Instructors may save time on numerous duties by using this technology. In future, ChatGPT will become a powerful tool for enhancing students’ and teachers’ experience.

Summary Understanding of any computing environment requires familiarity with its underlying technologies. Internet of Things (IoT), being a new era of computing in the digital world, aims for the development of large number of smart devices that would support a variety of applications and services. These devices are resource‐constrained, and the services they would provide are going to impose specific requirements, among which security is the most prominent one. Therefore, in order to comprehend and conform these requirements, there is a need to illuminate the underlying architecture of IoT and its associated elements. This comprehensive survey focuses on the security architecture of IoT and provides a detailed taxonomy of major challenges associated with the field and the key technologies, including Radio Frequency Identification (RFID) and Wireless Sensor Networks (WSN), that are enabling factors in the development of IoT. The paper also discusses some of the protocols suitable for IoT infrastructure and open source tools and platforms for its development. Finally, a brief outline of major open issues, along with their potential solutions and future research directions, is given.

Generative Pretrained Transformer, often known as GPT, is an innovative kind of Artificial Intelligence (AI) which can produce writing that seems to have been written by a person. OpenAI created this AI language model called ChatGPT. It is built using the GPT architecture and is trained on a large corpus of text data to respond to natural language inquiries that resemble a person’s requirements. This technology has lots of applications in healthcare. The need for accurate and current data is one of the major obstacles to adopting ChatGPT in healthcare. GPT must have access to precise and up-to-date medical data to provide trustworthy suggestions and treatment options. It might be accomplished by ensuring that the data used by GPT is received from reliable sources and that the data is updated regularly. Since sensitive medical information would be involved, it will also be crucial to consider privacy and security issues while utilising GPT in the healthcare industry. This paper briefs about ChatGPT and its need for healthcare, its significant Work Flow Dimensions and typical features of ChatGPT for the Healthcare domain. Finally, it identified and discussed significant applications of ChatGPT for healthcare. ChatGPT can comprehend the conversational context and provide contextually appropriate replies. Its effectiveness as a conversational AI tool makes it useful for chatbots, virtual assistants, and other applications. However, we see many limitations in medical ethics, data interpretation, accountability and other issues related to the privacy. Regarding specialised tasks like text creation, language translation, text categorisation, text summarisation, and creating conversation systems, ChatGPT has been pre-trained on a large corpus of text data, and somewhat satisfactory results can be expected. Moreover, it can also be utilised for various Natural Language Processing (NLP) activities, including sentiment analysis, part-of-speech tagging, and named entity identification.

In spite of various gains, cloud computing has got few challenges and issues including dynamic resource scaling and power consumption. Such affairs cause a cloud system to be fragile and expensive. In this paper we address both issues in cloud datacenter through workload prediction. The workload prediction model is developed using long short term memory (LSTM) networks. The proposed model is tested on three benchmark datasets of web server logs. The empirical results show that the proposed method achieved high accuracy in predictions by reducing the mean squared error up to 3.17 x 10-3.

Vehicular Ad hoc Networks (VANETs) that are considered as a subset of Mobile Ad hoc Networks (MANETs) can be applied in the field of transportation especially in Intelligent Transportation Systems (ITS). The routing process in these networks is a challenging task due to rapid topology changes, high vehicle mobility and frequent disconnection of links. Therefore, developing an efficient routing protocol that satisfies restriction of delay and minimum overhead is faced with many difficulties and limitations. Also, the detection of malicious vehicles is a significant task in VANETs. To address these issues, using Unmanned Aerial Vehicles (UAVs) can be helpful to cope with these limitations. In this paper, operation of UAVs in ad hoc mode and their cooperation with vehicles in VANETs are studied to help in the process of routing and detection of malicious vehicles. A routing protocol named VRU is proposed that includes two distinct ways of routing of data: (1) delivering packets of data between vehicles with the help of UAVs using a protocol named VRU_vu, and (2) routing packet of data between UAVs using a protocol named VRU_u. The NS-2.35 simulator under Linux Ubuntu 12.04 is utilized in order to appraise the performance of VRU routing components in an urban scenario. Also, VanetMobiSim generator of mobility and MobiSim are used to produce the motions of vehicles and to produce the motions of UAVs, respectively. The performance analysis displays that VRU protocol can improve the packet delivery ratio by 16% and detection ratio by 7% compared to other reviewed routing protocol. Also, VRU protocol decreases end-to-end delay by an average of 13% and overhead by 40%.

The possibility of substituting natural fine aggregate with industrial by-products such as waste foundry sand and bottom ash offers technical, economic and environmental advantages which are of great importance in the present context of sustainability in the construction sector. The study investigated the effect of waste foundry sand and bottom ash in equal quantities as partial replacement of fine aggregates in various percentages (0–60%), on concrete properties such as mechanical (compressive strength, splitting tensile strength and flexural strength) and durability characteristics (rapid chloride penetration and deicing salt surface scaling) of the concrete along with microstructural analysis with XRD and SEM. The results showed that the water content increased gradually from 175 kg/m3 in control mix (CM) to 238.63 kg/m3 in FB60 mix to maintain the workability and the mechanical behavior of the concrete with fine aggregate replacements was comparable to that of conventional concrete except for FB60 mix. The compressive strength was observed to be in the range of 29–32 MPa, splitting tensile strength in the range of 1.8–2.46 MPa, and flexural strength in the range of 3.95–4.10 MPa on the replacement of fine aggregates from 10% to 50% at the interval of 10%. Furthermore, it was observed that the greatest increase in compressive, splitting tensile strength, and flexural strength compared to that of the conventional concrete was achieved by substituting 30% of the natural fine aggregates with industrial by-product aggregates. The inclusion of waste foundry sand and bottom ash as fine aggregate does not affect the strength properties negatively as the strength remains within limits except for 60% replacement. The morphology of the formations arising as a result of the hydration process was not observed to change in the concrete with varying percentages of waste foundry sand and bottom ash.

The demand of electric energy is increasing globally, and the fact remains that the major share of this energy is still being produced from the traditional generation technologies. However, the recent trends, for obvious reasons of environmental concerns, are indicating a paradigm shift towards distributed generation (DG) incorporating renewable energy resources (RERs). But there are associated challenges with high penetration of RERs as these resources are unpredictable and stochastic in nature, and as a result, it becomes difficult to provide immediate response to demand variations. This is where energy storage systems (ESSs) come to the rescue, and they not only can compensate the stochastic nature and sudden deficiencies of RERs but can also enhance the grid stability, reliability, and efficiency by providing services in power quality, bridging power, and energy management. This paper provides an extensive review of different ESSs, which have been in use and also the ones that are currently in developing stage, describing their working principles and giving a comparative analysis of important features and technical as well as economic characteristics. The wide range of storage technologies, with each ESS being different in terms of the scale of power, response time, energy/power density, discharge duration, and cost coupled with the complex characteristics matrices, makes it difficult to select a particular ESS for a specific application. The comparative analysis presented in this paper helps in this regard and provides a clear picture of the suitability of ESSs for different power system applications, categorized appropriately. The paper also brings out the associated challenges and suggests the future research directions.

This work proposes an innovative infrastructure of secure scenario which operates in a wireless-mobile 6G network for managing big data (BD) on smart buildings (SBs). Count on the rapid growth of telecommunication field new challenges arise. Furthermore, a new type of wireless network infrastructure, the sixth generation (6G), provides all the benefits of its past versions and also improves some issues which its predecessors had. In addition, relative technologies to the telecommunications filed, such as Internet of Things, cloud computing (CC) and edge computing (EC), can operate through a 6G wireless network. Take into account all these, we propose a scenario that try to combine the functions of the Internet of Things with CC, EC and BD in order to achieve a Smart and Secure environment. The major purpose of this work is to create a novel and secure cache decision system (CDS) in a wireless network that operates over an SB, which will offer the users safer and efficient environment for browsing the Internet, sharing and managing large-scale data in the fog. This CDS consisted of two types of servers, one cloud server and one edge server. In order to come up with our proposal, we study related cache scenarios systems which are listed, presented, and compared in this work.

Wearable Inertial sensors have revolutionised the way kinematics analysis is performed in sports. This paper aims to present a comprehensive review of the literature related to the use of wearable inertial sensors for performance analysis in various games. Kinematics analysis using wearable sensors can provide real-time feedback to the players about their adopted techniques in their respective sports and thus help them to perform efficiently. This article reviews the key technologies (IMU sensors, communication technology, data fusion and data analysis techniques) that enable the implementation of wearable sensors for performance analysis in sports. The review focuses on research papers, commercial sports sensors and 3D motion tracking products to provide a holistic and systematic categorisation & analysis of the wearable sensors in sports. The review identifies the importance of sensors classification, applications and performance parameters in sports for structured analysis. The survey also reviews the technology concerning sensor architecture, network and communication protocols, covers various data fusion algorithms and their accuracy while throwing light on essential performance matrices for an athlete. This review paper will assist both end-users and the researchers to have a comprehensive glimpse of the wearable technology pertaining to designing sensors and solutions for athletes in different sports.

Abstract Microgrid with hybrid renewable energy sources is a promising solution where the distribution network expansion is unfeasible or not economical. Integration of renewable energy sources provides energy security, substantial cost savings and reduction in greenhouse gas emissions, enabling nation to meet emission targets. Microgrid energy management is a challenging task for microgrid operator (MGO) for optimal energy utilization in microgrid with penetration of renewable energy sources, energy storage devices and demand response. In this paper, optimal energy dispatch strategy is established for grid connected and standalone microgrids integrated with photovoltaic (PV), wind turbine (WT), fuel cell (FC), micro turbine (MT), diesel generator (DG) and battery energy storage system (ESS). Techno-economic benefits are demonstrated for the hybrid power system. So far, microgrid energy management problem has been addressed with the aim of minimizing operating cost only. However, the issues of power losses and environment i.e., emission-related objectives need to be addressed for effective energy management of microgrid system. In this paper, microgrid energy management (MGEM) is formulated as mixed-integer linear programming and a new multi-objective solution is proposed for MGEM along with demand response program. Demand response is included in the optimization problem to demonstrate it’s impact on optimal energy dispatch and techno-commercial benefits. Fuzzy interface has been developed for optimal scheduling of ESS. Simulation results are obtained for the optimal capacity of PV, WT, DG, MT, FC, converter, BES, charging/discharging scheduling, state of charge of battery, power exchange with grid, annual net present cost, cost of energy, initial cost, operational cost, fuel cost and penalty of greenhouse gases emissions. The results show that CO 2 emissions in standalone hybrid microgrid system is reduced by 51.60% compared to traditional system with grid only. Simulation results obtained with the proposed method is compared with various evolutionary algorithms to verify it’s effectiveness.

Abstract With fast-growing technology, online social networks (OSNs) have exploded in popularity over the past few years. The pivotal reason behind this phenomenon happens to be the ability of OSNs to provide a platform for users to connect with their family, friends, and colleagues. The information shared in social network and media spreads very fast, almost instantaneously which makes it attractive for attackers to gain information. Secrecy and surety of OSNs need to be inquired from various positions. There are numerous security and privacy issues related to the user’s shared information especially when a user uploads personal content such as photos, videos, and audios. The attacker can maliciously use shared information for illegitimate purposes. The risks are even higher if children are targeted. To address these issues, this paper presents a thorough review of different security and privacy threats and existing solutions that can provide security to social network users. We have also discussed OSN attacks on various OSN web applications by citing some statistics reports. In addition to this, we have discussed numerous defensive approaches to OSN security. Finally, this survey discusses open issues, challenges, and relevant security guidelines to achieve trustworthiness in online social networks.

Abstract The emergence of the Internet of Things (IoT) concept as a new direction of technological development raises new problems such as valid and timely identification of such devices, security vulnerabilities that can be exploited for malicious activities, and management of such devices. The communication of IoT devices generates traffic that has specific features and differences with respect to conventional devices. This research seeks to analyze the possibilities of applying such features for classifying devices, regardless of their functionality or purpose. This kind of classification is necessary for a dynamic and heterogeneous environment, such as a smart home where the number and types of devices grow daily. This research uses a total of 41 IoT devices. The logistic regression method enhanced by the concept of supervised machine learning (logitboost) was used for developing a classification model. Multiclass classification model was developed using 13 network traffic features generated by IoT devices. Research has shown that it is possible to classify devices into four previously defined classes with high performances and accuracy (99.79%) based on the traffic flow features of such devices. Model performance measures such as precision, F-measure, True Positive Ratio, False Positive Ratio and Kappa coefficient all show high results (0.997–0.999, 0.997–0.999, 0.997–0.999, 0–0.001 and 0.9973, respectively). Such a developed model can have its application as a foundation for monitoring and managing solutions of large and heterogeneous IoT environments such as Industrial IoT, smart home, and similar.

Due to the outbreak of COVID-19, the Internet of Medical Things (IoMT) has enabled the doctors to remotely diagnose the patients, control the medical equipment, and monitor the quarantined patients through their digital devices. Security is a major concern in IoMT because the Internet of Things (IoT) nodes exchange sensitive information between virtual medical facilities over the vulnerable wireless medium. Hence, the virtual facilities must be protected from adversarial threats through secure sessions. This article proposes a lightweight and physically secure mutual authentication and secret key establishment protocol that uses physical unclonable functions (PUFs) to enable the network devices to verify the doctor's legitimacy (user) and sensor node before establishing a session key. PUF also protects the sensor nodes deployed in an unattended and hostile environment from tampering, cloning, and side-channel attacks. The proposed protocol exhibits all the necessary security properties required to protect the IoMT networks, like authentication, confidentiality, integrity, and anonymity. The formal AVISPA and informal security analysis demonstrate its robustness against attacks like impersonation, replay, a man in the middle, etc. The proposed protocol also consumes fewer resources to operate and is safe from physical attacks, making it more suitable for IoT-enabled medical network applications.

Deep learning methods, e.g., convolutional neural networks (CNNs) and Recurrent Neural Networks (RNNs), have achieved great success in image processing and natural language processing especially in high level vision applications such as recognition and understanding. However, it is rarely used to solve information security problems such as attack detection studied in this paper. Here, we move forward a step and propose a novel multi-channel intelligent attack detection method based on long short term memory recurrent neural networks (LSTM-RNNs). To achieve high detection rate, data preprocessing, feature abstraction, and multi-channel training and detection are seamlessly integrated into an end-to-end detection framework. Data preprocessing provides high-quality data for subsequent processing, then different types of features are extracted from the processed data. Multi-channel processing is used to generate classifiers by training neural networks with different types of features, which preserve attack features of input vectors and classify the attack from normal data. With the results of the classifier's attack detection, we introduce a voting algorithm to decide whether the input data is an attack or not. Experimental results validate that the proposed attack detection method greatly outperforms several attack detection methods that use feature detection and Bayesian or SVM classifiers.