Dr Nagender Aneja
@ubd.edu.bn
Associate Professor, School of Digital Science
Virginia Tech
Dr. Nagender Aneja is a Collegiate Associate Professor at Bradley Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, Virginia, USA. He has previously worked as a research scholar in the Department of Computer Science at Purdue University, West Lafayette, Indiana. He also has five years of industry experience as an associate IP Lead for the Microsoft Patent Research Services Team at CPA Global India, where he drafted the responses to office actions for US Patent Applications and developed various innovative NLP tools for patent analysis. He is also the founder of ResearchID.
EDUCATION
Ph.D. Computer Engineering
M.E. Computer Technology and Applications
RESEARCH, TEACHING, or OTHER INTERESTS
Computer Science, Artificial Intelligence, Computer Vision and Pattern Recognition, Computer Science Applications
FUTURE PROJECTS
DEEP LEARNING TRAINING WITH LIMITED DATA
Deep learning needs lots of data for training; however, in some industrial applications, the significant amount of data may not be available, limiting the deep learning approach. Modern techniques like transfer learning and generative adversarial networks show some hope to solve this challenge. The objective of the project is to propose new techniques for deep learning training.
Applications Invited
Remote Research Collaboration
DEEP LEARNING SECURITY
Deep-learning networks are susceptible to butterfly effect wherein small alterations in the input data can point to drastically distinctive outcomes, making the deep learning network inherently volatile. Thus, the output of deep learning network may be controlled by altering its input or by adding noise. Research has shown that it is possible to fool the deep learning network by adding an imperceptible amount of noise in the input.
Applications Invited
Remote Research Collaboration
GENERATIVE ADVERSARIAL NETWORKS - REVERSE IMAGE CAPTIONING - TEXT TO IMAGE AND SCALING GAN TRAINING WITH BATCH SIZE
Generative Adversarial Networks may have potential to solve the text-to-image problem, but there are challenges in using GANs for NLP. Image classification have got benefitted with large mini-batches and one of the open question the question https://distill.pub/2019/gan-open-problems/#batchsize is if they can also help to scale GANs
Applications Invited
Remote Research Collaboration
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Sandhya Aneja and Nagender Aneja
IEEE
Browser fingerprinting is the identification of a browser through the network traffic captured during communication between the browser and server. This can be done using the HTTP protocol, browser extensions, and other methods. This paper discusses browser fingerprinting using the HTTPS over TLS 1.3 protocol. The study observed that different browsers use a different number of messages to communicate with the server, and the length of messages also varies. To conduct the study, a network was set up using a UTM hypervisor with one virtual machine as the server and another as a VM with a different browser. The communication was captured, and it was found that there was a $30 \\%-35 \\%$ dissimilarity in the behavior of different browsers.
Pawan Whig, Pavika Sharma, Nagender Aneja, Ahmed A. Elngar, and Nuno Silva
CRC Press
Nishtha Jatana, Mansehej Singh, Charu Gupta, Geetika Dhand, Shaily Malik, Pankaj Dadheech, Nagender Aneja, and Sandhya Aneja
Springer Science and Business Media LLC
Chour Singh Rajpoot, Gajanand Sharma, Praveen Gupta, Pankaj Dadheech, Umar Yahya, and Nagender Aneja
Informa UK Limited
Hassaan Haider Syed, Nagender Aneja, Owais Ahmed Malik, and Mohammed Abdul Rahman Minhaj
IEEE
Traditionally, medical images have been analyzed manually. However, this manual analysis can be subjective, depending on the judgment of radiologists and pathologists, which can result in inconsistency and inefficiency. Computer vision and deep learning models have revolutionized the study and diagnosis of medical images such as X-rays, CT scans, and MRIs. Despite their effectiveness, these models often act as black boxes and are difficult to interpret. In this study, we propose an ensemble of two popular deep learning models, ResNet101 and EfficientNetB7, which not only provide higher classification accuracy for CT scans but also offer superior interpretability. Our ensemble model outperforms the original models in COVID-19 CT scan classification by more than 2%. We compared the performance of three eXplainable AI (XAI) visualization models including GradCAM, Guided-GradCAM, and LIME, against the ground truth data labeled by radiologists. The proposed ensemble method provides better interpretability for the CT scan images compared to the individual models.
Shafkat Islam, Nagender Aneja, Ruy De Oliveira, Sandhya Aneja, Bharat Bhargava, Jason Hamlet, and Chris Jenkins
IEEE
Over the years, space systems have evolved considerably to provide high-quality services for demanding applications such as navigation, communication, and weather forecast. Modern space systems rely on extremely fast commercially available off-the-shelf (COTS) processing units, with built-in GPU, DSP, and FPGA in light-weight, energy-efficient hardware. Since such devices are not necessarily designed with security features as a priority, there must be an adaptive controller to protect this mission-critical space system from potential malicious attacks, such as memory leaks, packet drops, algorithmic trojans, and so on. These attacks can lead the system to substantial inefficiency or complete failure. Considering the hardware diversity in current space systems, we propose a framework to explore both diversity and redundancy not only of hardware but also of software to make the overall system fault-tolerant. Our approach deploys mechanisms for monitoring and orchestrating actions of redundancy, diversity, and randomization to render the system resilient unpredictably dynamic, and optimize efficiency as much as possible during abnormalities. Yet, we use rule-based and adaptive engines to keep track of the various computing units to learn the best strategies to take when the system is under attack. The robustness of our approach lies in the fact that it makes the system highly unpredictable to potential attackers and tolerates attacks to some extent, which is crucial for any mission-critical application.
Priyanka Sharma, Pankaj Dadheech, Nagender Aneja, and Sandhya Aneja
Institute of Electrical and Electronics Engineers (IEEE)
Agriculture contributes a significant amount to the economy of India due to the dependence on human beings for their survival. The main obstacle to food security is population expansion leading to rising demand for food. Farmers must produce more on the same land to boost the supply. Through crop yield prediction, technology can assist farmers in producing more. This paper’s primary goal is to predict crop yield utilizing the variables of rainfall, crop, meteorological conditions, area, production, and yield that have posed a serious threat to the long-term viability of agriculture. Crop yield prediction is a decision-support tool that uses machine learning and deep learning that can be used to make decisions about which crops to produce and what to do in the crop’s growing season. It can decide which crops to produce and what to do in the crop’s growing season. Regardless of the distracting environment, machine learning and deep learning algorithms are utilized in crop selection to reduce agricultural yield output losses. To estimate the agricultural yield, machine learning techniques: decision tree, random forest, and XGBoost regression; deep learning techniques - convolutional neural network and long-short term memory network have been used. Accuracy, root mean square error, mean square error, mean absolute error, standard deviation, and losses are compared. Other machine learning and deep learning methods fall short compared to the random forest and convolutional neural network. The random forest has a maximum accuracy of 98.96%, mean absolute error of 1.97, root mean square error of 2.45, and standard deviation of 1.23. The convolutional neural network has been evaluated with a minimum loss of 0.00060. Consequently, a model is developed that, compared to other algorithms, predicts the yield quite well. The findings are then analyzed using the root mean square error metric to understand better how the model’s errors compare to those of the other methods.
Wang Xin Hui, Nagender Aneja, Sandhya Aneja, and Abdul Ghani Naim
Elsevier BV
Kavita Sheoran, Arpit Bajgoti, Rishik Gupta, Nishtha Jatana, Geetika Dhand, Charu Gupta, Pankaj Dadheech, Umar Yahya, and Nagender Aneja
Institute of Electrical and Electronics Engineers (IEEE)
Nagender Aneja, Sandhya Aneja, and Bharat Bhargava
Hindawi Limited
WiFi and private 5G networks, commonly referred to as P5G, provide Internet of Things (IoT) devices the ability to communicate at fast speeds, with low latency and with a high capacity. Will they coexist and share the burden of delivering a connection to devices at home, on the road, in the workplace, and at a park or a stadium? Or will one replace the other to manage the increase in endpoints and traffic in the enterprise, campus, and manufacturing environments? In this research, we describe IoT device testbeds to collect network traffic in a local area network and cyberspace including beyond 5G/6G network traffic traces at different layers. We also describe research problems and challenges, such as traffic classification and traffic prediction by the traffic traces of devices. An AI-enabled hierarchical learning architecture for the problems above using sources like network packets, frames, and signals from the traffic traces with machine learning models is also presented.
Ajay Kumar Bansal, Virendra Swaroop Sangtani, Pankaj Dadheech, Nagender Aneja, and Umar Yahya
Informa UK Limited
Sandhya Aneja, Nagender Aneja, and Ponnurangam Kumaraguru
IAES International Journal of Artificial Intelligence Institute of Advanced Engineering and Science
<span>Media news are making a large part of public opinion and, therefore, must not be fake. News on web sites, blogs, and social media must be analyzed before being published. In this paper, we present linguistic characteristics of media news items to differentiate between fake news and real news using machine learning algorithms. Neural fake news generation, headlines created by machines, semantic incongruities in text and image captions generated by machine are other types of fake news problems. These problems use neural networks which mainly control distributional features rather than evidence. We propose applying correlation between features set and class, and correlation among the features to compute correlation attribute evaluation metric and covariance metric to compute variance of attributes over the news items. Features unique, negative, positive, and cardinal numbers with high values on the metrics are observed to provide a high area under the curve (AUC) and F1-score.</span>
Sandhya Aneja, Nagender Aneja, Pg Emeroylariffion Abas, and Abdul Ghani Naim
Institute of Advanced Engineering and Science
Transfer learning allows us to exploit knowledge gained from one task to assist in solving another but relevant task. In modern computer vision research, the question is which architecture performs better for a given dataset. In this paper, we compare the performance of 14 pre-trained ImageNet models on the histopathologic cancer detection dataset, where each model has been configured as naive model, feature extractor model, or fine-tuned model. Densenet161 has been shown to have high precision whilst Resnet101 has a high recall. A high precision model is suitable to be used when follow-up examination cost is high, whilst low precision but a high recall/sensitivity model can be used when the cost of follow-up examination is low. Results also show that transfer learning helps to converge a model faster.
Anand Kumar, Dharmesh Dhabliya, Pankaj Agarwal, Nagender Aneja, Pankaj Dadheech, Sajjad Shaukat Jamal, and Owusu Agyeman Antwi
Hindawi Limited
The Internet of Things (IoT) ushers in a new era of communication that depends on a broad range of things and many types of communication technologies to share information. This new age of communication will be characterised by the following characteristics: Because all of the IoT’s objects are connected to one another and because they function in environments that are not protected, it poses a significantly greater number of issues, constraints, and challenges than do traditional computing systems. This is due to the fact that traditional computing systems do not have as many interconnected components. Because of this, it is imperative that security be prioritised in a new approach, which is not something that is currently present in conventional computer systems. The Wireless Sensor Network, often known as WSN, and the Mobile Ad hoc Network are two technologies that play significant roles in the process of building an Internet of Things system. These technologies are used in a wide variety of activities, including sensing, environmental monitoring, data collecting, heterogeneous communication techniques, and data processing, amongst others. Because it incorporates characteristics of both MANET and WSN, IoT is susceptible to the same kinds of security issues that affect those other networks. An assault known as a Delegate Entity Attack (DEA) is a subclass of an attack known as a Denial of Service (DoS). The attacker sends an unacceptable number of control packets that have the appearance of being authentic. DoS assaults may take many different forms, and one of those kinds is an SD attack. Because of this, it is far more difficult to recognise this form of attack than a simple one that depletes the battery’s capacity. One of the other key challenges that arise in a network during an SD attack is that there is the need to enhance energy management and prolong the lifespan of IoT nodes. This is one of the other significant issues that arise in a network when an SD attack is occurs. It is recommended that you make use of a Random Number Generator with Hierarchical Intrusion Detection System, abbreviated as RNGHID for short. The ecosystem of the Internet of Things is likely to be segmented into a great number of separate sectors and clusters. The HIPS system has been partitioned into two entities, which are referred to as the Delegate Entity (DE) and the Pivotal Entity, in order to identify any nodes in the network that are behaving in an abnormal manner. These entities are known, respectively, as the Delegate Entity and the Pivotal Entity (PE). Once the anomalies have been identified, it will be possible to pinpoint the area of the SD attack torture and the damaging activities that have been taken place. A warning message, generated by the Malicious Node Alert System (MNAS), is broadcast across the network in order to inform the other nodes that the network is under attack. This message classifies the various sorts of attacks based on the results of an algorithm that employs machine learning. The proposed protocol displays various desired properties, such as the capacity to conduct indivisible authentication, rapid authentication, and minimum overhead in both transmission and storage. These are only a few of the desirable attributes.
Gagan Thakral, Sapna Gambhir, and Nagender Aneja
IEEE
Sudhir Sharma, Kaushal Kishor Bhatt, Rimmy Chabra, and Nagender Aneja
Springer Nature Singapore
Sandeep Singh, Shalini Bhaskar Bajaj, Khushboo Tripathi, and Nagendra Aneja
IEEE
In this paper the Mobile Ad Hoc Network (MANET) was considered for analyzing the performance of Destination Sequenced Distance Vector (DSDV) of Proactive class and Ad Hoc On-Demand Distance Vector (AODV) and Dynamic Source Routing Protocol (DSR) of Reactive class. The protocols were simulated using the NS-2 (Network Simulator 2.35) package on Linux 12.04. The paper focuses on performance parameters e.g. Packet size, Speed, Packet rate, Transmission Control Protocol (TCP) types and Number of Packets and energy in the network. Simulation results shows that DSR gives better performance as compared to AODV and DSDV. The results were compared for inspection of packet delivery rate, % Lost packets, throughput and Jitter on varying Packet size, TCP types, and the number of packets in queue by changing packet size. The implementation study can further extend by applying artificial algorithms in MANET for enhancing the better results in presence of any type of attacks too.
Sandhya Aneja, Nagender Aneja, Bharat Bhargava, and Rajarshi Roy Chowdhury
Inderscience Publishers
Device fingerprinting is a problem of identifying a network device using network traffic data to secure against cyber-attacks. Automated device classification from a large set of network traffic features space is challenging for the devices connected in the cyberspace. In this work, the idea is to define a device-specific unique fingerprint by analysing solely inter-arrival time of packets as a feature to identify a device. Neural networks are the universal function approximation which learn abstract, highlevel, nonlinear representation of training data. Deep convolution neural network is used on images of inter-arrival time signature for device fingerprinting of 58 non-IoT devices of 5-11 types. To evaluate the performance, we compared ResNet-50 layer and basic CNN-5 layer architectures. We observed that device type identification models perform better than device identification. We also found that when deep learning models are attacked over device signature, the models identify the change in signature, and classify the device in the wrong class thereby the classification performance of the models degrades. The performance of the models to detect the attacks are significantly different from each other though both models indicate the system under attack.
Sandhya Aneja, Melanie Ang Xuan En, and Nagender Aneja
IEEE
Artificial Intelligence (AI) development has encouraged many new research areas, including AI-enabled Internet of Things (IoT) network. AI analytics and intelligent paradigms greatly improve learning efficiency and accuracy. Applying these learning paradigms to network scenarios provide technical advantages of new networking solutions. In this paper, we propose an improved approach for IoT security from data perspective. The network traffic of IoT devices can be analyzed using AI techniques. The Adversary Learning (AdLIoTLog) model is proposed using Recurrent Neural Network (RNN) with attention mechanism on sequences of network events in the network traffic. We define network events as a sequence of the time series packets of protocols captured in the log. We have considered different packets TCP packets, UDP packets, and HTTP packets in the network log to make the algorithm robust. The distributed IoT devices can collaborate to cripple our world which is extending to Internet of Intelligence. The time series packets are converted into structured data by removing noise and adding timestamps. The resulting data set is trained by RNN and can detect the node pairs collaborating with each other. We used the BLEU score to evaluate the model performance. Our results show that the predicting performance of the AdLIoTLog model trained by our method degrades by 3-4% in the presence of attack in comparison to the scenario when the network is not under attack. AdLIoTLog can detect adversaries because when adversaries are present the model gets duped by the collaborative events and therefore predicts the next event with a biased event rather than a benign event. We conclude that AI can provision ubiquitous learning for the new generation of Internet of Things.
Rajarshi Roy Chowdhury, Sandhya Aneja, Nagender Aneja, and Pg Emeroylariffion Abas
Data in Brief Elsevier BV
With the growth of wireless network technology-based devices, identifying the communication behaviour of wireless connectivity enabled devices, e.g. Internet of Things (IoT) devices, is one of the vital aspects, in managing and securing IoT networks. Initially, devices use frames to connect to the access point on the local area network and then, use packets of typical communication protocols through the access point to communicate over the Internet. Toward this goal, network packet and IEEE 802.11 media access control (MAC) frame analysis may assist in managing IoT networks efficiently, and allow investigation of inclusive behaviour of IoT devices. This paper presents network traffic traces data of D-Link IoT devices from packet and frame levels. Data collection experiment has been conducted in the Network Systems and Signal Processing (NSSP) laboratory at Universiti Brunei Darussalam (UBD). All the required devices, such as IoT devices, workstation, smartphone, laptop, USB Ethernet adapter, and USB WiFi adapter, have been configured accordingly, to capture and store network traffic traces of the 14 IoT devices in the laboratory. These IoT devices were from the same manufacture (D-Link) with different types, such as camera, home-hub, door-window sensor, and smart-plug.
Nagender Aneja and Sapna Gambhir
Springer Science and Business Media LLC
Ad-hoc Social Networks are formed by groups of nodes, designating a similarity of interests. The network establishes a two-layer hierarchical structure that comprises communication within-group and joining with other groups. This paper presents survey and future directions in four areas of establishing ad-hoc social network using mobile ad-hoc social network (MANET) that includes architecture or implementation features, Profile Management of users, Similarity Metric, and Routing Protocols. The survey presents the need to provide social applications over MANET, optimizing profile matching algorithms of users, and context aware routing protocols. Future directions include multi-hop social network applications that can be useful for users even in airplane mode and notifying over MANET when a user of profile with similar interest is nearby.
Nur Umairah Ali Hazis, Nagender Aneja, Rajan Rajabalaya, and Sheba Rani David
Bentham Science Publishers Ltd.
Background: The application of nanotechnology has been considered a powerful platform in improving the current situation in drug delivery and cancer therapy, especially in targeting the desired site of action. Objective: The main objective of the patent review is to survey and review patents from the past ten years that are related to the two particular areas of nanomedicines. Methods: The patents related to the nanoparticle-based inventions utilized in drug delivery and cancer treatment from 2010 onwards were browsed in databases like USPTO, WIPO, Google Patents, and Free Patents Online. After conducting numerous screening processes, a total of 40 patents were included in the patent analysis. See the PRISMA checklist 2020 checklist. Results: Amongst the selected patents, an overview of various types of nanoparticles is presented in this paper, including polymeric, metallic, silica, lipid-based nanoparticles, quantum dots, carbon nanotubes, and albumin-based nanomedicines. Conclusion: Nanomedicines advantages include improvements in terms of drug delivery, bioavailability, solubility, penetration, and stability of drugs. It is concluded that the utilization of nanoparticles in medicines is essential in the pursuit of better clinical practice.
RECENT SCHOLAR PUBLICATIONS
MOST CITED SCHOLAR PUBLICATIONS
STARTUP
Founder and Developer,