Finger vein recognition and user identification is a relatively recent biometric recognition technology with a broad variety of applications, and biometric authentication is extensively employed in the information age. As one of the most essential authentication technologies available today, finger vein recognition captures our attention owing to its high level of security, dependability, and track record of performance. Embedded convolutional neural networks are based on the early or intermediate fusing of input. In early fusion, pictures are categorized according to their location in the input space. In this study, we employ a highly optimized network and late fusion rather than early fusion to create a Fusion convolutional neural network that uses two convolutional neural networks (CNNs) in short ways. The technique is based on using two similar CNNs with varying input picture quality, integrating their outputs in a single layer, and employing an optimized CNN design on a proposed Sains University Malaysia (FV-USM) finger vein dataset 5904 images. The final pooling CNN, which is composed of the original picture, an image improved using the contrast limited adaptive histogram (CLAHE) approach and the Median filter, And, using Principal Component Analysis (PCA), we retrieved the features and got an acceptable performance from the FV-USM database, with a recognition rate of 98.53 percent. Our proposed strategy outperformed other strategies described in the literature.
Researchers are increasingly using multimodal biometrics to strengthen the security of biometric applications. In this study, a strong multimodal human identification model was developed to address the growing problem of spoofing attacks in biometric security systems. Through the use of metaheuristic optimization methods, such as the Genetic Algorithm(GA), Ant Colony Optimization(ACO), and Particle Swarm Optimization (PSO) for feature selection, this unique model incorporates three biometric modalities: face, iris, and fingerprint. Image pre-processing, feature extraction, critical image feature selection, and multibiometric recognition are the four main steps in the workflow of the system. To determine its performance, the model wa
... Show More
Building a system to identify individuals through their speech recording can find its application in diverse areas, such as telephone shopping, voice mail and security control. However, building such systems is a tricky task because of the vast range of differences in the human voice. Thus, selecting strong features becomes very crucial for the recognition system. Therefore, a speaker recognition system based on new spin-image descriptors (SISR) is proposed in this paper. In the proposed system, circular windows (spins) are extracted from the frequency domain of the spectrogram image of the sound, and then a run length matrix is built for each spin, to work as a base for feature extraction tasks. Five different descriptors are generated fro
... Show More
(7)
(2)
(6)
(2)
Abstract— The growing use of digital technologies across various sectors and daily activities has made handwriting recognition a popular research topic. Despite the continued relevance of handwriting, people still require the conversion of handwritten copies into digital versions that can be stored and shared digitally. Handwriting recognition involves the computer's strength to identify and understand legible handwriting input data from various sources, including document, photo-graphs and others. Handwriting recognition pose a complexity challenge due to the diversity in handwriting styles among different individuals especially in real time applications. In this paper, an automatic system was designed to handwriting recognition
... Show More
(1)
Background:Â Various fluids in the oral environment can affect the surface roughness of resin composites. This in vitro study was conducted to determine the influence of the mouth rinses on surface roughness of two methacrylate-based resin (nanofilled and packable composite) and siloraine-based resin composites.
Materials and methods: Disc-shaped specimens (12 mm in diameter and 2mm in height) were prepared from three types of composi
... Show More
Prostate cancer is the commonest male cancer and the second leading cause of cancer-related death in men. Over many decades, prostate cancer detection represented a continuous challenge to urologists. Although all urologists and pathologists agree that tissue diagnosis is essential especially before commencing active surgical or radiation treatment, the best way to obtain the biopsy was always the big hurdle. The heterogenicity of the tumor pathology is very well seen in its radiological appearance. Ultrasound has been proven to be of limited sensitivity and specificity in detecting prostate cancer. However, it was the only available targeting technique for years and was used to guide biopsy needle passed transrectally or transperineally
... Show More
The security of message information has drawn more attention nowadays, so; cryptography has been used extensively. This research aims to generate secured cipher keys from retina information to increase the level of security. The proposed technique utilizes cryptography based on retina information. The main contribution is the original procedure used to generate three types of keys in one system from the retina vessel's end position and improve the technique of three systems, each with one key. The distances between the center of the diagonals of the retina image and the retina vessel's end (diagonal center-end (DCE)) represent the first key. The distances between the center of the radius of the retina and the retina vessel's end (ra
... Show More
(6)
(2)
An adaptive nonlinear neural controller to reduce the nonlinear flutter in 2-D wing is proposed in the paper. The nonlinearities in the system come from the quasi steady aerodynamic model and torsional spring in pitch direction. Time domain simulations are used to examine the dynamic aero elastic instabilities of the system (e.g. the onset of flutter and limit cycle oscillation, LCO). The structure of the controller consists of two models :the modified Elman neural network (MENN) and the feed forward multi-layer Perceptron (MLP). The MENN model is trained with off-line and on-line stages to guarantee that the outputs of the model accurately represent the plunge and pitch motion of the wing and this neural model acts as the identifier. Th
... Show MoreMalaysia has been supported by one of the high-speed fiber internet connections called TM UniFi. TM UniFi is very familiar to be used as a medium to apply Small Office Home Office (SOHO) concept due to the COVID-19 pandemic. Most of the communication vendors offer varieties of network services to fulfill customers' needs and satisfaction during the pandemic. Quality of Services is queried by most users by the fact of increased on users from time to time. Therefore, it is crucial to know the network performance contrary to the number of devices connected to the TM UniFi network. The main objective of this research is to analyze TM UniFi performance with the impact of multiple device connections or users' services. The study was conducted
... Show More
Medulloblastomas and ependymomas are the most common malignant brain tumors in children. However genetic abnormalities associated with their development and prognosis remain unclear. Recently two gene fusions, KIAA1549–BRAF and SRGAP3–RAF1 have been detected in a number of brain tumours. We report here our development and validation of RT-RQPCR assays to detect various isoforms of these two fusion genes in formalin fixed paraffin embedded (FFPE) tissues of medulloblastoma and ependymoma. We examined these fusion genes in 44 paediatric brain tumours, 33 medulloblastomas and 11 ependymomas. We detected both fusion transcripts in 8/33, 5/33 SRGAP3 ex10/RAF1 ex10, and 3/33 KIAA1549 ex16/BRAF ex9, meduloblastomas but none in the 11 ep
... Show More