scispace - formally typeset
Search or ask a question
Author

P. Ebby Darney

Bio: P. Ebby Darney is an academic researcher from Techno India. The author has contributed to research in topics: Computer science & Wireless network. The author has an hindex of 4, co-authored 12 publications receiving 59 citations.

Papers
More filters
Journal ArticleDOI
27 Aug 2021
TL;DR: The research discoveries on the application of deep learning in the Internet of Things (IoT) system are summarized in an image-based identification method that introduces a variety of appropriate criteria.
Abstract: The Internet of Things (IoT) is an ecosystem comprised of multiple devices and connections, a large number of users, and a massive amount of data. Deep learning is especially suited for these scenarios due to its appropriateness for "big data" difficulties and future concerns. Nonetheless, guaranteeing security and privacy has emerged as a critical challenge for IoT administration. In many recent cases, deep learning algorithms have proven to be increasingly efficient in performing security assessments for IoT devices without resorting to handcrafted rules. This research work integrates principal component analysis (PCA) for feature extraction with superior performance. Besides, the primary objective of this research work is to gather a comprehensive survey data on the types of IoT deployments, along with security and privacy challenges with good recognition rate. The deep learning method is performed through PCA feature extraction for improving the accuracy of the process. Our other primary goal in this study paper is to achieve a high recognition rate for IoT based image recognition. The CNN approach was trained and evaluated on the IoT image dataset for performance evaluation using multiple methodologies. The initial step would be to investigate the application of deep learning for IoT image acquisition. Additionally, when it comes to IoT image registering, the usefulness of the deep learning method has been evaluated for increasing the appropriateness of image recognition with good testing accuracy. The research discoveries on the application of deep learning in the Internet of Things (IoT) system are summarized in an image-based identification method that introduces a variety of appropriate criteria.

122 citations

Journal ArticleDOI
29 Mar 2021
TL;DR: The throughput of wireless multi-channel networks are enhanced using artificial intelligence algorithm and the nature inspired routing algorithm offers improved performance when compared to the existing state-of-the-art models.
Abstract: The throughput of wireless multi-channel networks are enhanced using artificial intelligence algorithm. The performance of the network may be improved while reducing the interference. This technique involves three steps namely creation of wireless environment specific model, performance optimization using the right tools and improvement of routing by selecting the performance indicators cautiously. Artificial bee colony optimization algorithm and its evaluative features positively affects communication in wireless networks. The simple behavior of bee agents in this algorithm assist in making synchronous and decentralized routing decisions. The advantages of this algorithm is evident from the MATLAB simulations. The nature inspired routing algorithm offers improved performance when compared to the existing state-of-the-art models. The simple agent model can improve the performance values of the network. The breadth first search variant is utilized for discovery and deterministic evaluation of multiple-paths in the network increasing the overall routing protocol output.

62 citations

Journal ArticleDOI
03 Dec 2019
TL;DR: The improved fuzzy logic that relies on the decision (IFDSS-GA) support system to handle both the switching of the channels and genetic algorithm to select the proper spectrum for conveyance is put forth.
Abstract: The rapid increase in the mobile device and the different types of wireless communication has led to the necessity of the extra spectrum allocation for the proper transmission of the information. Since the additional spectrum allocation for every network involved in the data transmission is a strenuous process, the efficient management of the spectrum allocation is preferred. The cognitive radio technology does a befitting service in the managing the allocation of the spectrum efficiently by providing the vacant spaces of the licensed users to the secondary users and vacating the secondary users when the licensed user request for the spectrum. This results in the deterioration in the performance of the secondary users due to the immediate evacuating. The conventional methods in the deciding the channel switching remains unsuitable for the cognitive radio network, so to have an effective decision on switching and selecting the channel the paper put forth the improved fuzzy logic that relies on the decision (IFDSS-GA) support system to handle both the switching of the channels and genetic algorithm to select the proper spectrum for conveyance. The evaluation of the proposed approach using the network simulator -2 determines the competency the IFDSS in terms of the throughput and switching rate.

24 citations

Journal ArticleDOI
04 Sep 2021
TL;DR: This research work includes sparse coding process for removing rain streak by incorporating morphological component analyses (MCA) based algorithm and is combined with sparsity coding process to provide better PSNR and less MSE results from the reconstructed images.
Abstract: During the rainy season, many public outdoor crimes have been caught through video surveillance, and they do not have complete feature information to identify the image features. Rain streak removal techniques are ideal for indexing and obtaining additional information from such images. Furthermore, the rain substantially changes the intensity of images and videos, lowering the overall image quality of vision systems in outdoor recording situations. To be successful, the elimination of rain streaks in the film will require an advanced trial and error method. Different methods have been utilized to identify and eliminate the rainy effects by using the data on photon numbers, chromaticity, and probability of rain streaks present in digital images. This research work includes sparse coding process for removing rain streak by incorporating morphological component analyses (MCA) based algorithm. Based on the MCA algorithm, the coarse estimation becomes very simple to handle the rain streak or impulsive noisy images. The sparse decomposition of coarse is possible by estimating and eliminating all redundancies from the sources. This novel MCA approach is combined with sparsity coding process to provide better PSNR and less MSE results from the reconstructed images. This method is compared with of the existing research works on rain streak removal process. Besides, the obtained the results are illustrated and tabulated.

10 citations

Journal ArticleDOI
TL;DR: An attempt of feature transformation is experimented in this paper by DNA based encoding methodology and the complexity and the performance of the proposed method proved challenging to the state of art techniques.
Abstract: Feature transformation is the most primary step in biometric template protection whose effectiveness is directly dependent upon the test and trained samples. The minutiae points are segregated to retrieve the attributes with the singular point data to enlarge the secure user template. The user fingerprint information could be revealed to produce the secured template with the help of the fingerprint image. An attempt of feature transformation is experimented in this paper by DNA based encoding methodology. The general formation of the proposed technique is constructed from the Biometric data to generate the feature extraction; the Z pattern generation is used for implementing the transformation and produced the DNA codec. The evaluation of each step in the proposed scheme is theoretically evaluated and experimented with. The revocability, diversity and the security parameters are analyzed and compared with the relevant methods using the images from FVC2004 dataset that the accuracy for biometric template is achieved through the enhanced recognition rate. The complexity and the performance of the proposed method proved challenging to the state of art techniques.

7 citations


Cited by
More filters
01 Jan 2012
TL;DR: 2年前,谷歌Android平台还是个默 默无闻的无名小卒 ,然而最近:、在通信、家电、lT等各个 领域遍地开花)
Abstract: 2年前,谷歌Android平台还是个默默无闻的无名小卒,然而最近,谷歌Android平台以风卷残云之势,在通信、家电、lT等各个领域遍地开花,呈现出一派“忽如一夜春风来,千树万树梨花开”的欣欣向荣景象。

57 citations

Journal ArticleDOI
19 Jul 2021
TL;DR: The neural network model outperforms the existing linear models in a significant manner and can also perform stock predictions for other stock markets despite being trained with single market data as a common inner dynamics that has been shared between certain stock markets.
Abstract: Several intelligent data mining approaches, including neural networks, have been widely employed by academics during the last decade. In today's rapidly evolving economy, stock market data prediction and analysis play a significant role. Several non-linear models like neural network, generalized autoregressive conditional heteroskedasticity (GARCH) and autoregressive conditional heteroscedasticity (ARCH) as well as linear models like Auto-Regressive Integrated Moving Average (ARIMA), Moving Average (MA) and Auto Regressive (AR) may be used for stock forecasting. The deep learning architectures inclusive of Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Recurrent Neural Networks (RNN), Multilayer Perceptron (MLP) and Support Vector Machine (SVM) are used in this paper for stock price prediction of an organization by using the previously available stock prices. The National Stock Exchange (NSE) of India dataset is used for training the model with day-wise closing price. Data prediction is performed for a few sample companies selected on a random basis. Based on the comparison results, it is evident that the existing models are outperformed by CNN. The network can also perform stock predictions for other stock markets despite being trained with single market data as a common inner dynamics that has been shared between certain stock markets. When compared to the existing linear models, the neural network model outperforms them in a significant manner, which can be observed from the comparison results.

56 citations

Journal ArticleDOI
13 Jun 2020
TL;DR: The artificial intelligence antenna is proposed to identify the choicest antenna to be integrated in the diverse environments for improving the throughput, signal performance and the data conveyance speed.
Abstract: Artificial intelligence based long term evolution multi in multi output antenna supporting the fifth generation mobile networks is put forth in the paper. The mechanism laid out in paper is devised using the monopole-antenna integrated with the switchable pattern. The long term evolution based multiple input and multiple output antenna is equipped with four antennas and capable of providing a four concurrent data streams quadrupling the theoretical maximum speed of data transfer allowing the base station to convey four diverse signals through four diverse transmit antennas for a single user equipment. The utilization of the long term evolution multiple input multiple output is capable of utilizing the multi-trial broadcasting to offer betterments in the signal performance as well as throughput and spectral efficiency when used along the fifth generation mobile networks. So the paper proposes the artificial intelligence based long term evolution multiple input multiple output four transmit antenna with four diverse signal transmission capacity that is operating in the frequency of 3.501 Gigahertz frequency. The laid out design is evaluated using the Multi-input Multi output signal analyzer to acquire the capacity of the passive conveyance of the various antennas with the diverse combination of patterns. The outcomes observed enables the artificial intelligence antenna to identify the choicest antenna to be integrated in the diverse environments for improving the throughput, signal performance and the data conveyance speed.

43 citations

Proceedings ArticleDOI
23 Feb 2022
TL;DR: In this paper , an eye blink sensor and a photoplethysmography sensor are employed to assess whether a driver is awake or asleep, as well as whether the driver has any health issues.
Abstract: Road accidents lead to fear in anyone who travels in their daily life. Violations of traffic restrictions, negligence, and other reasons can cause road accidents, but most studies show that the majority of accidents are caused by drivers’ sudden health concerns or tiredness. Despite their unpredictability, these events have a huge impact on human lives. These problems are solved by the proposed method. To assess whether a driver is awake or asleep, as well as whether the driver has any health issues, the system employs an eye blink sensor and a photoplethysmography sensor accordingly. The sensors’ output is connected to the driver’s phone via GSM module and any other human monitor via NodeMCU (cloud server) in that order. As a result, if the driver falls asleep, he or she will be awoken. And if a medical emergency arises, he or she will be able to receive immediate assistance because they are being monitored by another person via NodeMCU, which connects to the cloud server.

32 citations

Journal ArticleDOI
18 May 2020
TL;DR: A game theory based Cognitive Radio Network with Dynamic Spectrum Allocation model is proposed in this paper and M|M|1 queuing model is implemented along with Preemptive Resume Priority for accommodation of all the cases.
Abstract: Significant enhancement of spectrum utilization can be performed by means of Cognitive Radio technology. A game theory based Cognitive Radio Network with Dynamic Spectrum Allocation model is proposed in this paper. M|M|1 queuing model is implemented along with Preemptive Resume Priority for accommodation of all the cases. An Incremental Weights-Decremental Ratios (IW-DR) algorithm based on priority-based scheduling is used for supplementing this theory. Regression models are used for restructuring and improving the efficiency of the system.

25 citations