scispace - formally typeset
Search or ask a question
Author

Prasanalakshmi Balaji

Bio: Prasanalakshmi Balaji is an academic researcher from King Saud University. The author has contributed to research in topics: Computer science & Artificial intelligence. The author has an hindex of 2, co-authored 4 publications receiving 7 citations.

Papers
More filters
Journal ArticleDOI
TL;DR: This work proposes a system to filter the attacks using rule-based IDS at the sensor nodes to reduce the amount of packet transmission to the base station and reduce the energy consumption of the sensor network.
Abstract: Wireless sensor networks consist of a collection of sensors to monitor physical or environmental events. Nowadays, the sensor networks are used in important applications like military, health and civilian monitoring. Since it is a wireless medium, deployed in remote locations and resource-constrained nature, the sensor networks are easily vulnerable to attacks. The attack creates significant damages to the sensor networks. To avoid these problems, intrusion detection system (IDS) is implemented at the base station to filter any abnormal packets. In the proposed system, a survey is made on the attacks and rules to detect the attacks. Filtering the attacks using rule-based IDS at the sensor nodes would reduce the amount of packet transmission to the base station which, in turn, would reduce the energy consumption of the sensor network. Extreme learning machine (ELM) algorithm is implemented at the base station to detect the abnormal packets. The experimental result shows the performance of different classification techniques and cross-layer rules over the NSL-KDD and real-time datasets. The detection rate of the ELM algorithm is higher compared to other systems.

16 citations

Journal ArticleDOI
TL;DR: In this paper , a hybrid deep learning approach for early detection of Alzheimer's disease is proposed, which combines multimodal imaging and Convolutional Neural Network with the Long Short-term Memory algorithm.
Abstract: Alzheimer’s disease (AD) is mainly a neurodegenerative sickness. The primary characteristics are neuronal atrophy, amyloid deposition, and cognitive, behavioral, and psychiatric disorders. Numerous machine learning (ML) algorithms have been investigated and applied to AD identification over the past decades, emphasizing the subtle prodromal stage of mild cognitive impairment (MCI) to assess critical features that distinguish the disease’s early manifestation and instruction for early detection and treatment. Identifying early MCI (EMCI) remains challenging due to the difficulty in distinguishing patients with cognitive normality from those with MCI. As a result, most classification algorithms for these two groups perform poorly. This paper proposes a hybrid Deep Learning Approach for the early detection of Alzheimer’s disease. A method for early AD detection using multimodal imaging and Convolutional Neural Network with the Long Short-term memory algorithm combines magnetic resonance imaging (MRI), positron emission tomography (PET), and standard neuropsychological test scores. The proposed methodology updates the learning weights, and Adam’s optimization is used to increase accuracy. The system has an unparalleled accuracy of 98.5% in classifying cognitively normal controls from EMCI. These results imply that deep neural networks may be trained to automatically discover imaging biomarkers indicative of AD and use them to identify the illness accurately.

4 citations

Journal ArticleDOI
TL;DR: A brief overview of biometric methods both Unimodal and Multibiometric as well as their advantages and disadvantages are to be presented.
Abstract: Biometrics involves recognizing individuals based on the features derived from their Physiological and or behavioral characteristics. Biometric systems provide reliable recognition schemes to determine or confirm the individual identity.Applications of these systems include computer systems security,e-banking, credit card, access to buildings in a secure way. Here the person or object itself is a password. User verification systems that use a single Biometric indicator is disturbed by noisy data,restricted degrees of freedom and error rates. Improving the performance of Unimodal biometric systems now becomes problematic. Multibiometric systems tries to overcome these drawbacks by providing multiple evidences to the same identity hence the performance may be increased. Furthermore intruders trying to hack the biometric identity finds it difficult to work on Multibiometric systems. However an effective fusion scheme is necessary to combine multiple information of an identity. This paper addresses a brief overview of biometric methods both Unimodal and Multimodal as well as their advantages and disadvantages are to be presented.

3 citations

Journal ArticleDOI
TL;DR: In this article , the authors investigated the global asymptotic stability problem for a class of quaternion-valued Takagi-Sugeno fuzzy BAM neural networks with time-varying delays.
Abstract: This paper investigates the global asymptotic stability problem for a class of quaternion-valued Takagi-Sugeno fuzzy BAM neural networks with time-varying delays. By applying Takagi-Sugeno fuzzy models, we first consider a general form of quaternion-valued Takagi-Sugeno fuzzy BAM neural networks with time-varying delays. Then, we apply the Cauchy-Schwarz algorithm and homeomorphism principle to obtain sufficient conditions for the existence and uniqueness of the equilibrium point. By utilizing suitable Lyapunov-Krasovskii functionals and newly developed quaternion-valued Wirtinger-based integral inequality, some sufficient criteria are obtained to guarantee the global asymptotic stability of the considered networks. Further, the results of this paper are presented in the form of quaternion-valued linear matrix inequalities, which can be solved using the MATLAB YALMIP toolbox. Two numerical examples are presented with their simulations to demonstrate the validity of the theoretical analysis.

2 citations

Book ChapterDOI
08 May 2019
TL;DR: This chapter unveils an enhancement strategy for nap-of-the-earth (NOE) mode, the issue to expand the performance of the airplane by extending the terrain by a few modes of the TAWS, which given by various aviation authorities are analyzed.
Abstract: This chapter unveils an enhancement strategy for nap-of-the-earth. The nap-of-the-earth (NOE) mode is the most energizing, most unsafe, and is generally the slowest. Military aircraft to maintain a strategic distance from opponent detection and assault in a highthread circumstance use it. NOE used to limit discovery by the ground-based radar, targets and the control system. The radar altimeter (RA) or terrain following radar (TFR), terrain awareness and warning system (TAWS) used to identify the curbs during flying in NOE flights. Here, while the plane is at the nap of the earth activity, the speed and the height must be moderate as effectively decided. The terrain following radar (TFR) keeps up the altitude from the beginning. Therefore, we analyze the issue to expand the performance of the airplane by extending the terrain by a few modes of the TAWS, which given by various aviation authorities1. Further to this, different TAWS modes of action, explanation of mode selection and progression in TAWS clarified in detail. This chapter displays the MATLAB programme for a few patterns of TAWS mission, and simulation of the flight path for the excessive terrain closure rate from mode two operation of the flight.

2 citations


Cited by
More filters
Journal ArticleDOI
Taeyoung Kim1, Luiz Felipe Vecchietti1, Kyujin Choi1, Sangkeum Lee1, Dongsoo Har1 
TL;DR: In this review, recent developments of ML techniques for WSNs are presented with much emphasis on DL techniques, and it is found that large training time and large dataset to get acceptable performance are accompanied with large energy consumption which is not favorable for resource-restrained W SNs.
Abstract: Wireless sensor networks (WSNs) are typically used with dynamic conditions of task-related environments for sensing(monitoring) and gathering of raw sensor data for subsequent forwarding to a base station. In order to deploy WSNs in real environments, a variety of technical challenges must be addressed. With traditional techniques developed for a specific task, it is hard to react in dynamic situations beyond the scope of the intended task. As a solution to this problem, machine learning (ML) techniques that are able to handle dynamic situations with successful learning process have been applied lately in WSNs. Particularly, deep learning (DL) techniques, a class of ML techniques characterized by the use of deep neural network, are used for WSNs to extract higher level features from raw sensor data. A range of benefits obtained from ML techniques applied to WSNs can be described as reduced computational complexity, increased feasibility in finding optimal solutions, increased energy efficiency, etc. On the other hand, it is found from our survey that large training time and large dataset to get acceptable performance are accompanied with large energy consumption which is not favorable for resource-restrained WSNs. Reviews on the applications of ML techniques in WSNs appeared in the literature. However, few reviews have dealt with the applications of DL techniques in WSNs. In this review, recent developments of ML techniques for WSNs are presented with much emphasis on DL techniques. The DL techniques developed for various applications in WSNs are addressed together with their respective deep neural network architectures.

39 citations

Journal ArticleDOI
TL;DR: The coverage optimization and hole healing protocol is proposed to optimized the overlapping and coverage hole problem in the network using the various phases as Initialization of the network, cluster formation, cluster head selection and sleep and wake-up phase.

19 citations

Proceedings ArticleDOI
01 Dec 2019
TL;DR: An overview presented on the benefits of incorporating a human DNA based security systems and the overall effect on how such systems enhance the security of a system.
Abstract: the fast advancement in the last two decades proposed a new challenge in security. In addition, the methods used to secure information are drawing more attention and under intense investigation by researchers around the globe. However, securing data is a very hard task, due to the escalation of threat levels. Several technologies and techniques developed and used to secure data throughout communication or by direct access to the information as an example encryption techniques and authentication techniques. A most recent development methods used to enhance security is by using human biometric characteristics such as thumb, hand, eye, cornea, and DNA; to enforce the security of a system toward higher level, human DNA is a promising field and human biometric characteristics can enhance the security of any system using biometric features for authentication. Furthermore, the proposed methods does not fulfil or present the ultimate solution toward tightening the system security. However, one of the proposed solutions enroll a technique to encrypt the biometric characteristic using a well-known cryptosystem technique. In this paper, an overview presented on the benefits of incorporating a human DNA based security systems and the overall effect on how such systems enhance the security of a system. In addition, an algorithm is proposed for practical application and the implementation discussed briefly.

6 citations