Speech Recognition Using Artificial Neural Network

C.; M.; N.

doi:https://doi.org/10.54216/JCHCI.050201

Journal of Cybersecurity and Information Management | 2021

An Improved Image Encryption Consuming Fusion Transmutation and Edge Operator

The field of cryptography oversees the development of methods for transforming information between coherent and incoherent formats. Encryption and decryption techniques controlled by keys maintain the privacy of the substance and who can access it. Private key cryptography refers to methods of encryption and decryption that employ the same secret key. The alternative is public key cryptography, wherever the encryption and decryption keys are different. It is essential for the sanctuary of any crypto scheme that the confusion and diffusion properties be met. While the diffusion property rearranges the pixels in an image, the confusion property simply replaces the pixel values. In-depth discussion of a genetic-algorithm-based hybrid approach to secure and complex three-dimensional chaos-based image encryption (SCIE) has been presented. Here, we use mathematics edge, multipoint edges operator, and coupled transmutation operatives to accomplish permutation. In this method, a key stream is created using a 3D CSI (Compound Sine and ICMIC) map. Using a private key, hybrid operators are used to encrypt data. Several metrics were considered while evaluating the suggested algorithm's efficacy, including the UACI (Unified Average Change Intensity), correlation constant, NPCR (Net Pixel Change Rate). Experiments with the same have shown promising results in protecting real-time photos.

groups

Vandana Roy mail

link https://doi.org/10.54216/JCIM.080105

Volume & Issue

Vol. Volume 8 / Iss. Issue 1

Details open_in_new

Journal of Cybersecurity and Information Management | 2023

Lightweight Symmetric Encryption and Attribute Based Encryption Method to Increase Information Safety in Wireless Sensor Network

Direct data transmission in a wireless sensor network raises the data transfer cost. In addition, the lifetime of sensor networks is shortened because of the rise in energy required for data exchange. As a result, data aggregation is utilized in WSN to lessen the burden of transmission costs and lengthen the useful life of the sensor networks. The sensor nodes and their collected data are vulnerable to destruction because they are broadcasting in a hostile environment. Therefore, data security is a major topic of study for WSN. Due to the limited resources of the sensor network, conventional wireless network security measures are ineffective.  With Speck encryption and CP-ABE, the proposed Lightweight Secured remote Health monitoring System (LSHS) can protect health data and restrict who can access it while using less power. Lightweight block ciphers are optimal for protecting medical records, according to the research. Using the LSHS, we evaluate how well-known lightweight block ciphers like AES, Simon, and Speck perform. Both encrypting and decrypting with the Speck technique require less processing time. Therefore, medical records are encrypted using the Speck algorithm.

groups

Rajeev Pandey mail

link https://doi.org/10.54216/JCIM.100205

Volume & Issue

Vol. Volume 10 / Iss. Issue 2

Details open_in_new

Journal of Cybersecurity and Information Management | 2023

An Encrypted Rules and Extreme Learning Machine Approach for Enhancement of Data Security

Among the many uses for WSN, which is an ad hoc wireless system, are conveyance, calamity administration, industrialized observing, health observing, and so on. Intrusion Detection System (IDS) is a top-tier network security measure. In order to prevent cross-layer attacks, IDS detection rates must be high. Using a technique known as the "Rule of Thumb" or ELM (Extreme Learning Machine) algorithm, WSN is able to predict the future with a great grade of accurateness. The projected RELM provides a comprehensive overview of both the attacks and the rules for detecting them. The rules can identify threats at the different layers. If the rule-founded IDS were deployed at the sensor nodes, less data would need to be transmitted over the network, saving power. Relative to the SVM (Support Vector Machine) and BPN (Back Propagation Neural Network) on the NSL-KDD dataset, RELM evaluates ELM's detection rate. Because of its superior detection rate, ELM has been used as the foundation of the IDS deployed at the BS to protect it against intrusion. If the criteria were combined with the ELM algorithm, the resulting system would have a higher detection rate than any currently available alternative.

groups

Amit Kumar Chandanan mail

link https://doi.org/10.54216/JCIM.110205

Volume & Issue

Vol. Volume 11 / Iss. Issue 2

Details open_in_new

Journal of Neutrosophic and Fuzzy Systems | 2023

Using the Inverse Transformation Method to Generate Random Variables that follow the Neutrosophic Uniform Probability Distribution

When conducting the simulation process for any of the systems according to classical logic, we start by generating random numbers belonging to the regular probability distribution on the field [0, 1] using one of the known methods, and then we convert these random numbers into random variables that follow the probability distribution that the system to be simulated works with, the simulation process that we perform it gives specific results that do not take into account the changes that may occur in the work environment of the system, to obtain more accurate results In a previous research, we prepared a study through which we reached random neutrosophic numbers follow the uniform distribution of the neutrosophic on the field with [1 , 0] no determination that can be enjoyed by the two parties of the field, one or both together, it may be in the form of a group or a field in another research , we converted these neutrosophic random numbers into neutrosophic random variables that follow the neutrosophic exponential distribution using the opposite conversion method that depends on the cumulative distribution function of the probability distribution by which the system to be simulated works, in this research we have useda method The opposite transformation to generate random variables that follow the neutrosophic uniform distribution and we have reached relationships through which we can convert the neutrosophic random numbers that follow the neutrosophic uniform distribution defined on the domain [1 , 0]  with the indeterminacy enjoyed by each end of the field, one or the other, into random variables that follow the neutrosophic uniform distribution, a b , which is a classical uniform distribution whose medians are notprecisely defined values , one or both may be cognitiven in the form of a set or a domain, so that n take into account all possible cases of mediators while maintaining the condition , and the b,a ;a<b method was illustrated through an applied example and we came up with neutrosophic random variables that follow the uniform distribution that give us more accurate simulation results when used due to the indeterminacy of neutrosophic values.

groups

Maissam Jdid mail -

A. Salama mail

link https://doi.org/10.54216/JNFS.060202

Volume & Issue

Vol. Volume 6 / Iss. Issue 2

Details open_in_new

Journal of Artificial Intelligence and Metaheuristics | 2022

Solving the Inverse Initial Value Problem for the Heat Conductivity Equation by Using the Picard Method

In this work, the inverse initial value problem IVP for the heat equation is formulated and solved. Initial temperature (initial condition) distribution is unknown in this problem, and instead, the temperature spreading at period t= T> 0 is assumed. Among mathematical problems, a class of problems is singled out, the solutions of which are unstable to minor variations in the initial information. It is well identified that this problem is ill-posed. In order to solve the direct problem, we has used the separation of variables way. Note that the method of separation of variables is completely inapplicable for solving IVP, since it principals to rather errors, also divergent series. Ivanov V.K. noticed that if the inverse problem IP  is solved by the method separation of variables, and then the resulting series is changed by a incomplete sum of the series, in which the term number is depending on δ, N=N(δ), then as a result we obtain a stable approximate solution. The Picard method customs a regularizing family of operators  that map space  to same space.

groups

H. K. Al-Mahdawi mail -

Mostafa Abotaleb mail -

Hussein Alkattan mail -

El-Sayed M. El-Kenawy mail -

E. M. Mohamed mail

link https://doi.org/10.54216/JAIM.020205

Volume & Issue

Vol. Volume 2 / Iss. Issue 2

Details open_in_new

Journal of Cybersecurity and Information Management | 2023

A Concentrated Energy Consumption Wireless Sensor Network by Symmetric Encryption and Attribute Based Encryption Technique

Wireless sensor networks (WSNs) are increasingly used in a wide variety of settings, including defence, industry, healthcare, and education. Hundreds or even thousands of sensor nodes are spread out across a given area and linked to a central Base Station (BS) in order to keep tabs on the environment. The BS then sends the data out to the users over the internet. The sensor network's adaptability, portability, dependability, and quickness are driving its widespread use across industries. The suggested SHS evaluates the efficiency of well-established symmetric algorithms to see where it stands in the spectrum of security. The Blowfish encryption algorithm was proven to require the least amount of processing power after extensive benchmarking. Therefore, the Blowfish algorithm is selected to protect sensitive medical information. The medical database receives the encrypted health records. Only those with proper permissions should be able to access them. Therefore, the CP-ABE is implemented to regulate access to patient records. The SHS's results on the dataset are compared to those of other existing systems. With SHS, health data may be transmitted to doctors rapidly and securely because it requires less computing time and energy. In addition to these benefits, SHS also offers privacy, authentication, and authorization.

groups

Anita Soni mail

link https://doi.org/10.54216/JCIM.120101

Volume & Issue

Vol. Volume 12 / Iss. Issue 1

Details open_in_new

Journal of Cybersecurity and Information Management | 2023

An Upgraded Data Security Based on Homomorphic Encryption and Aggregate Signature Method in Wireless Sensor Network

Wireless sensor networks (WSN) have been implemented in nearly every field of use because they offer a solution to practical problems that can also be affordably implemented. The sensor nodes have limited computing resources, weak batteries, and limited storage space. The environmental or physical data collected by these nodes is transmitted straight to the BS. The data transfer cost is raised due to the direct data transmission. In addition, the lifetime of sensor networks is shortened because of the rise in energy required for data exchange. As a result, data aggregation is utilized in WSN to lessen the burden of transmission costs and lengthen the useful life of the sensor networks. Each sensor node's transmission is encrypted with cipher text generated by the Paillier homomorphic cryptosystem. In addition, the Bilinear aggregate signature method is used to create a digital signature at each sensor node. The cluster head / BS is where the aggregation takes place once the cipher text and signature have been combined. Before deciding whether to accept or reject the message, the BS checks the aggregate signature. The homomorphic cryptosystem saves power because it does not perform intermediate-level or cluster-head decryption. Data integrity, authenticity, and confidentiality are all maintained while using less power with this technology. The Intel laboratory dataset is used in the implementation. When compared to current systems, the proposed SDA method requires less time and energy to calculate.

groups

Raju Ranjan mail -

Vinay Kumar Ahlawat mail

link https://doi.org/10.54216/JCIM.120102

Volume & Issue

Vol. Volume 12 / Iss. Issue 1

Details open_in_new

Journal of Cybersecurity and Information Management | 2023

An Improved Analysis of Secured Permutation and Substitution based Image Encryption

The transmission and storage of digital data raises serious security concerns as information technology evolves at a breakneck pace. To ensure the safety of the transferred data, security methods must be put in place. Encrypting an image is a method of protecting sensitive data by converting it into an unrecognizable format. The procedure includes access control, privacy, validation, and copyright protection. Cryptography, steganography, and watermarking are three distinct methods to prevent unauthorized access to digital data. Of these three methods, cryptography has emerged as one of the most important ways to ensure complete safety. Therefore, a secure and efficient cipher algorithm is required for trustworthy communication.  In this work, we offer a practical Secured Asymmetric Image Cipher (SAIC) Algorithm for encrypting images with a secret key of arbitrary length. At first, the KG algorithm creates two unique keys. Both the encryption and decryption processes require a key.  The experimental results reveal that the encrypted image lacks the original image's independence (NPCR > 99.89%, UACI > 36.89%). The suggested approach has a high encryption rate, can be implemented easily, and is computationally secure. The reproduced data validates the safety and practicability of the proposed architecture.

groups

Vikas Goel mail -

Amit Kumar Goyal mail

link https://doi.org/10.54216/JCIM.120103

Volume & Issue

Vol. Volume 13 / Iss. Issue 1

Details open_in_new

Fusion: Practice and Applications | 2025

Building Prediction Models for the E-Government Development Index (EGDI) in Iraq and KSA: A Comparative ARIMA - Based Approach

The E-Government Development Index (EGDI) represents the performance and reality of e-government. The importance of maintaining and planning for the enhancement of such an index enables the policymakers to understand, process, and develop the right plans and strategies for it. In this paper, the Auto Regressive Integrated Moving Average (ARIMA) has been utilized to build predictive models. The time-series data collected from the UN survey versions for the years 2003, 2005, 2008, 2010, 2012, 2014, 2016, 2018, 2020, 2022, and 2024 for the countries of Iraq and KSA. The necessary data maintenance was implemented, then analyzed, covering the inspection of their temporal behavior. Afterwards, two individual data sets were created for both countries under study, containing 253 months. The optimal values for the ARIMA models were determined by implementing the data transformation, including the autocorrelation function (ACF) and partial autocorrelation function (PACF). 80% of the dataset is used for training, and 20% is used for testing. The data residuals analyzed by ACF, PACF, and the Ljung-Box test were performed for the residuals independence check. Nine metrics were utilized for model evaluation and ruthlessness. By using ARIMA models, the e-government performance (EGDI) has been predicted for the next five years for Iraq and KSA. The ARIMA models for both Iraq and KSA showed high performance, where the RMSE value for the Iraq model was (0.0054) and the MAE value was (0.0031) compared to the RMSE value (0.0481) and the MAE value (0.0093) for the KSA model. The Iraq arima model has better quality of the prediction in absolute terms. On the other hand, the ARIMA model for KSA was better in terms of predicted trends with an accuracy of 98.44% compared to 97.39% for the Iraq model.

groups

Ali Ahmed Ali mail -

Atef Masmoudi mail

link https://doi.org/10.54216/FPA.190211

Volume & Issue

Vol. Volume 19 / Iss. Issue 2

Details open_in_new

Journal of Cognitive Human-Computer Interaction | 2023

Speech Recognition Using Artificial Neural Network

Speech is a verbal communication used by humans through language. Likewise speech recognition is a process of converting speech to text. This paper provides a study of use of artificial neural networks(ANN) in speech recognition. Hidden Markov models (HMM) is a traditional statistical techniques for performing speech recognition. In speech detection software, Mel frequency cepstral coefficients (MFCCs) are frequently used. With different approaches evolving, we deal with the features used to recognize the speech pattern and implementation of speech recognition in the efficient types of artificial neural network (ANN).

groups

C. Vivek mail -

M. Indu mail -

N. Nandhini mail

link https://doi.org/10.54216/JCHCI.050201

Volume & Issue

Vol. Volume 5 / Iss. Issue 2

Details open_in_new