Face recognition is a crucial biometric technology used in various security and identification applications. Ensuring accuracy and reliability in facial recognition systems requires robust feature extraction and secure processing methods. This study presents an accurate facial recognition model using a feature extraction approach within a cloud environment. First, the facial images undergo preprocessing, including grayscale conversion, histogram equalization, Viola-Jones face detection, and resizing. Then, features are extracted using a hybrid approach that combines Linear Discriminant Analysis (LDA) and Gray-Level Co-occurrence Matrix (GLCM). The extracted features are encrypted using the Data Encryption Standard (DES) for security and then sent to the cloud server hosting the deep model. Upon reaching the server, the features are decrypted and fed into the proposed Fuzzy Face Deep Model (FFDM), which incorporates a fuzzy layer to enhance recognition accuracy. The model was evaluated using the MUCT and LFW datasets, demonstrating high accuracy and notable results, with precision of 99.65% and 100% on MUCT and LFW, respectively.
A new method for determination of allopurinol in microgram level depending on its ability to reduce the yellow absorption spectrum of (I-3) at maximum wavelength ( ?max 350nm) . The optimum conditions such as "concentration of reactant materials , time of sitting and order of addition were studied to get a high sensitivity ( ? = 27229 l.mole-1.cm-1) sandal sensitivity : 0.0053 µg cm-2 ,with wide range of calibration curve ( 1 – 9 µg.ml-1 ) good stability (more then24 hr.) and repeatability ( RSD % : 2.1 -2.6 % ) , the Recovery % : ( 98.17 – 100.5 % ) , the Erel % ( 0.50 -1.83 % ) and the interference's of Xanthine , Cystein , Creatinine , Urea and the Glucose in 20 , 40 , 60 fold of analyate were also studied .
The rapid development of Internet of Things (IoT) devices and their increasing numbers have caused a tremendous increase in network traffic and a wider range of cyber-attacks. This growing trend has complicated the detection process for traditional intrusion detection systems and heightened the challenges faced by these devices, such as imbalanced and large training data. This study presents a cohesive methodology of a series of intelligent techniques to prepare clean and balanced data for training the first (core) layer of a robust hierarchical intrusion detection system. The methodology was built by cleaning and compressing the data using an Autoencoder and preparing a strong latent space for balancing using a hybrid method that combines
... Show MoreThe exponential growth of audio data shared over the internet and communication channels has raised significant concerns about the security and privacy of transmitted information. Due to high processing requirements, traditional encryption algorithms demand considerable computational effort for real-time audio encryption. To address these challenges, this paper presents a permutation for secure audio encryption using a combination of Tent and 1D logistic maps. The audio data is first shuffled using Tent map for the random permutation. The high random secret key with a length equal to the size of the audio data is then generated using a 1D logistic map. Finally, the Exclusive OR (XOR) operation is applied between the generated key and the sh
... Show MoreToday in the digital realm, where images constitute the massive resource of the social media base but unfortunately suffer from two issues of size and transmission, compression is the ideal solution. Pixel base techniques are one of the modern spatially optimized modeling techniques of deterministic and probabilistic bases that imply mean, index, and residual. This paper introduces adaptive pixel-based coding techniques for the probabilistic part of a lossy scheme by incorporating the MMSA of the C321 base along with the utilization of the deterministic part losslessly. The tested results achieved higher size reduction performance compared to the traditional pixel-based techniques and the standard JPEG by about 40% and 50%,
... Show MoreAbstract
In this paper, fatigue damage accumulation were studied using many methods i.e.Corton-Dalon (CD),Corton-Dalon-Marsh(CDM), new non-linear model and experimental method. The prediction of fatigue lifetimes based on the two classical methods, Corton-Dalon (CD)andCorton-Dalon-Marsh (CDM), are uneconomic and non-conservative respectively. However satisfactory predictions were obtained by applying the proposed non-linear model (present model) for medium carbon steel compared with experimental work. Many shortcomings of the two classical methods are related to their inability to take into account the surface treatment effect as shot peening. It is clear that the new model shows that a much better and cons
... Show MoreA QR code is a type of barcode that can hold more information than the familiar kind scanned at checkouts around the world. The “QR” stands for “Quick Response”, a reference to the speed at which the large amounts of information they contain can be decoded by scanners. They are being widely used for advertising campaigns, linking to company websites, contest sign-up pages and online menus. In this paper, we propose an efficient module to extract QR code from background and solve problem of rotation in case of inaccurate image taken from mobile camera.
Numeral recognition is considered an essential preliminary step for optical character recognition, document understanding, and others. Although several handwritten numeral recognition algorithms have been proposed so far, achieving adequate recognition accuracy and execution time remain challenging to date. In particular, recognition accuracy depends on the features extraction mechanism. As such, a fast and robust numeral recognition method is essential, which meets the desired accuracy by extracting the features efficiently while maintaining fast implementation time. Furthermore, to date most of the existing studies are focused on evaluating their methods based on clean environments, thus limiting understanding of their potential a
... Show MoreThe aim of this essay is to use a single-index model in developing and adjusting Fama-MacBeth. Penalized smoothing spline regression technique (SIMPLS) foresaw this adjustment. Two generalized cross-validation techniques, Generalized Cross Validation Grid (GGCV) and Generalized Cross Validation Fast (FGCV), anticipated the regular value of smoothing covered under this technique. Due to the two-steps nature of the Fama-MacBeth model, this estimation generated four estimates: SIMPLS(FGCV) - SIMPLS(FGCV), SIMPLS(FGCV) - SIM PLS(GGCV), SIMPLS(GGCV) - SIMPLS(FGCV), SIM PLS(GGCV) - SIM PLS(GGCV). Three-factor Fama-French model—market risk premium, size factor, value factor, and their implication for excess stock returns and portfolio return
... Show MoreStereolithography (SLA) has become an essential photocuring 3D printing process for producing parts of complex shapes from photosensitive resin exposed to UV light. The selection of the best printing parameters for good accuracy and surface quality can be further complicated by the geometric complexity of the models. This work introduces multiobjective optimization of SLA printing of 3D dental bridges based on simple CAD objects. The effect of the best combination of a low-cost resin 3D printer’s machine parameter settings, namely normal exposure time, bottom exposure time and bottom layers for less dimensional deviation and surface roughness, was studied. A multiobjective optimization method was utilized, combining the Taguchi me
... Show More