RESUMO
Network slicing (NS) is one of the most prominent next-generation wireless cellular technology use cases, promising to unlock the core benefits of 5G network architecture by allowing communication service providers (CSPs) and operators to construct scalable and customized logical networks. This, in turn, enables telcos to reach the full potential of their infrastructure by offering customers tailored networking solutions that meet their specific needs, which is critical in an era where no two businesses have the same requirements. This article presents a commercial overview of NS, as well as the need for a slicing automation and orchestration framework. Furthermore, it will address the current NS project objectives along with the complex functional execution of NS code flow. A summary of activities in important standards development groups and industrial forums relevant to artificial intelligence (AI) and machine learning (ML) is also provided. Finally, we identify various open research problems and potential answers to provide future guidance.
Assuntos
Inteligência Artificial , Aprendizado de Máquina , Automação , ComunicaçãoRESUMO
Underwater wireless sensor networks (UWSNs) contain sensor nodes that sense the data and then transfer them to the sink node or base station. Sensor nodes are operationalized through limited-power batteries. Therefore, improvement in energy consumption becomes critical in UWSNs. Data forwarding through the nearest sensor node to the sink or base station reduces the network's reliability and stability because it creates a hotspot and drains the energy early. In this paper, we propose the cooperative energy-efficient routing (CEER) protocol to increase the network lifetime and acquire a reliable network. We use the sink mobility scheme to reduce energy consumption by eliminating the hotspot issue. We have divided the area into multiple sections for better deployment and deployed the sink nodes in each area. Sensor nodes generate the data and send it to the sink nodes to reduce energy consumption. We have also used the cooperative technique to achieve reliability in the network. Based on simulation results, the proposed scheme performed better than existing routing protocols in terms of packet delivery ratio (PDR), energy consumption, transmission loss, and end-to-end delay.
RESUMO
Artificial intelligence is serving as an impetus in digital health, clinical support, and health informatics for an informed patient's outcome. Previous studies only consider classification accuracies of cardiotocographic (CTG) datasets and disregard computational time, which is a relevant parameter in a clinical environment. This paper proposes a modified deep neural algorithm to classify untapped pathological and suspicious CTG recordings with the desired time complexity. In our newly developed classification algorithm, AlexNet architecture is merged with support vector machines (SVMs) at the fully connected layers to reduce time complexity. We used an open-source UCI (Machine Learning Repository) dataset of cardiotocographic (CTG) recordings. We divided 2126 CTG recordings into 3 classes (Normal, Pathological, and Suspected), including 23 attributes that were dynamically programmed and fed to our algorithm. We employed a deep transfer learning (TL) mechanism to transfer prelearned features to our model. To reduce time complexity, we implemented a strategy wherein layers in the convolutional base were partially trained to leave others in the frozen states. We used an ADAM optimizer for the optimization of hyperparameters. The presented algorithm also outperforms the leading architectures (RCNNs, ResNet, DenseNet, and GoogleNet) with respect to real-time accuracies, sensitivities, and specificities of 99.72%, 96.67%, and 99.6%, respectively, making it a viable candidate for clinical settings after real-time validation.
Assuntos
Inteligência Artificial , Aprendizado Profundo , Algoritmos , Feto , Nível de Saúde , Humanos , Redes Neurais de Computação , Máquina de Vetores de SuporteRESUMO
Biometrics is the term for measuring human characteristics. If the term is divided into two parts, bio means life, and metric means measurement. The measurement of humans through different computational methods is performed to authorize a person. This measurement can be performed via a single biometric or by using a combination of different biometric traits. The combination of multiple biometrics is termed biometric fusion. It provides a reliable and secure authentication of a person at a higher accuracy. It has been introduced in the UIDIA framework in India (AADHAR: Association for Development and Health Action in Rural) and in different nations to figure out which biometric characteristics are suitable enough to authenticate the human identity. Fusion in biometric frameworks, especially FKP (finger-knuckle print) and iris, demonstrated to be a solid multimodal as a secure framework. The proposed approach demonstrates a proficient and strong multimodal biometric framework that utilizes FKP and iris as biometric modalities for authentication, utilizing scale-invariant feature transform (SIFT) and speeded up robust features (SURF). Log Gabor wavelet is utilized to extricate the iris feature set. From the extracted region, features are computed using principal component analysis (PCA). Both biometric modalities, FKP and iris, are combined at the match score level. The matching is performed using a neuro-fuzzy neural network classifier. The execution and accuracy of the proposed framework are tested on the open database Poly-U, CASIA, and an accuracy of 99.68% is achieved. The accuracy is higher compared to a single biometric. The neuro-fuzzy approach is also tested in comparison to other classifiers, and the accuracy is 98%. Therefore, the fusion mechanism implemented using a neuro-fuzzy classifier provides the best accuracy compared to other classifiers. The framework is implemented in MATLAB 7.10.
Assuntos
Dedos , Iris , Biometria , Bases de Dados Factuais , Humanos , Redes Neurais de ComputaçãoRESUMO
In the last decade, the communication of images through the internet has increased. Due to the growing demands for data transfer through images, protection of data and safe communication is very important. For this purpose, many encryption techniques have been designed and developed. New and secured encryption schemes based on chaos theory have introduced methods for secure as well as fast communication. A modified image encryption process is proposed in this work with chaotic maps and orthogonal matrix in Hill cipher. Image encryption involves three phases. In the first phase, a chaotic Henon map is used for permuting the digital image. In the second phase, a Hill cipher is used whose encryption key is generated by an orthogonal matrix which further is produced from the equation of the plane. In the third phase, a sequence is generated by a chaotic tent map which is later XORed. Chaotic maps play an important role in the encryption process. To deal with the issues of fast and highly secured image processing, the prominent properties of non-periodical movement and non-convergence of chaotic theory play an important role. The proposed scheme is resistant to different attacks on the cipher image. Different tests have been applied to evaluate the proposed technique. The results of the tests such as key space analysis, key sensitivity analysis, and information entropy, histogram correlation of the adjacent pixels, number of pixel change rate (NPCR), peak signal to noise ratio (PSNR), and unified average changing intensity (UCAI) showed that our proposed scheme is an efficient encryption technique. The proposed approach is also compared with some state-of-the-art image encryption techniques. In the view of statistical analysis, we claim that our proposed encryption algorithm is secured.
RESUMO
Alzheimer's Disease (AD) is a health apprehension of significant proportions that is negatively impacting the ageing population globally. It is characterized by neuronal loss and the formation of structures such as neurofibrillary tangles and amyloid plaques in the early as well as later stages of the disease. Neuroimaging modalities are routinely used in clinical practice to capture brain alterations associated with AD. On the other hand, deep learning methods are routinely used to recognize patterns in underlying data distributions effectively. This work uses Convolutional Neural Network (CNN) architectures in both 2D and 3D domains to classify the initial stages of AD into AD, Mild Cognitive Impairment (MCI) and Normal Control (NC) classes using the positron emission tomography neuroimaging modality deploying data augmentation in a random zoomed in/out scheme. We used novel concepts such as the blurring before subsampling principle and distant domain transfer learning to build 2D CNN architectures. We performed three binaries, that is, AD/NC, AD/MCI, MCI/NC and one multiclass classification task AD/NC/MCI. The statistical comparison revealed that 3D-CNN architecture performed the best achieving an accuracy of 89.21% on AD/NC, 71.70% on AD/MCI, 62.25% on NC/MCI and 59.73% on AD/NC/MCI classification tasks using a five-fold cross-validation hyperparameter selection approach. Data augmentation helps in achieving superior performance on the multiclass classification task. The obtained results support the application of deep learning models towards early recognition of AD.