Adaptive Network Architecture Research Articles

Retraction Note: Adaptive SDN-based network architecture for vehicle to vehicle communication using flexible optical networks for 5G

Retraction Note: Adaptive SDN-based network architecture for vehicle to vehicle communication using flexible optical networks for 5G

Regulatory and spectrum policy challenges for combined airspace and non-terrestrial networks

The recent advancements in the aviation and space industries facilitate new types of users in the sky, e.g., electrical vertical take-off and landing (eVTOL) aircraft. To unlock the full potential of these innovations, it is crucial to create interconnected three-dimensional networks that integrate airspace and non-terrestrial networks (NTNs) with their terrestrial counterparts, also known as Combined Airspace and Non-Terrestrial Networks (ASN). Combined ASN needs a flexible and adaptive network architecture with multiple, and partly converging technologies, such as air-to-ground, satellite, and high-altitude platforms, with a focus to cover both ground and aerial users. In addition to technical challenges, spectrum policy and regulatory aspects will affect the wireless network design and management schemes in three-dimensional space. Hence, this paper introduces regulatory and spectrum policy challenges posed by the development of combined ASN. This paper investigates a hypothetical urban air mobility use case with an eVTOL aircraft that operates as a flying taxi.

ACGAN: adaptive conditional generative adversarial network architecture predicting skin lesion using collaboration of transfer learning models

Skin cancer has become a serious disease which has the potential to scale up if it is not identified earlier. It is imperative to detect and give treatment to skin cancer promptly. Diagnosing skin cancer manually takes a lot of time and it is costly, and the probability of false diagnosis has increased due to the outstanding resemblances among various skin lesions. Enhancing the classification of multi-class lesions of skin needs the development of investigative systems which should be automated. Data augmentation with GANs and Adaptive Conditional Generative Adversarial Network strategies improves performance. The performance is tested using balanced and unbalanced datasets. Using a proper process of augmentation of data, the suggested system attains a 94% accuracy for the VGG16, 93% for the ResNet50 and 94.25% for ResNet101. The process of collaboration of all such methods improves accuracy further to 95%. In summary, the novelty of the work lies in its holistic approach to automated skin lesion classification, incorporating advanced deep learning models, novel data augmentation techniques and comprehensive performance evaluation on real-world datasets. These contributions collectively advance the field of computer-aided diagnosis for the detection of skin cancer and treatment.

Adaptive Neural Network Architectures for Cross-Domain Generalization

Adaptive Neural Network Architectures for Cross-Domain Generalization

Dynamics of memristor coupled discrete fractional symmetric neural network model

Neural networks, also known as artificial neural networks (ANNs), represent innovative computational models inspired by the functioning of biological neurons in the human body. Currently, neural network models are employed to address intricate real-world challenges. This article focuses on constructing and dynamically analyzing interconnected symmetric neural network models inspired by the Hopfield type. These models incorporate discrete fractional memristor elements featuring quadratic memductance. The primary objective is to comprehend system characteristics by introducing nonlinearity to the inter-neuron weights in a functional manner. Additionally, the study explores the influence of electromagnetic radiation on neurons. Bifurcation diagrams, considering fractional order and Lyapunov exponents, illustrate the chaotic nature of the interconnected neural network model. The investigation delves into coexisting system states, examining coexisting bifurcations and attractors. The article offers potential for developing bio-inspired, energy-efficient, and adaptive neural network architectures, thereby contributing to advancements in artificial intelligence and neuromorphic applications.

TSSG-CNN: A Tuberculosis Semantic Segmentation-Guided Model for Detecting and Diagnosis Using the Adaptive Convolutional Neural Network.

Tuberculosis (TB) is an infectious disease caused by Mycobacterium. It primarily impacts the lungs but can also endanger other organs, such as the renal system, spine, and brain. When an infected individual sneezes, coughs, or speaks, the virus can spread through the air, which contributes to its high contagiousness. The goal is to enhance detection recognition with an X-ray image dataset. This paper proposed a novel approach, named the Tuberculosis Segmentation-Guided Diagnosis Model (TSSG-CNN) for Detecting Tuberculosis, using a combined semantic segmentation and adaptive convolutional neural network (CNN) architecture. The proposed approach is distinguished from most of the previously proposed approaches in that it uses the combination of a deep learning segmentation model with a follow-up classification model based on CNN layers to segment chest X-ray images more precisely as well as to improve the diagnosis of TB. It contrasts with other approaches like ILCM, which is optimized for sequential learning, and explainable AI approaches, which focus on explanations. Moreover, our model is beneficial for the simplified procedure of feature optimization from the perspectives of approach using the Mayfly Algorithm (MA). Other models, including simple CNN, Batch Normalized CNN (BN-CNN), and Dense CNN (DCNN), are also evaluated on this dataset to evaluate the effectiveness of the proposed approach. The performance of the TSSG-CNN model outperformed all the models with an impressive accuracy of 98.75% and an F1 score of 98.70%. The evaluation findings demonstrate how well the deep learning segmentation model works and the potential for further research. The results suggest that this is the most accurate strategy and highlight the potential of the TSSG-CNN Model as a useful technique for precise and early diagnosis of TB.

Robustness test-time augmentation via learnable aggregation and anomaly detection

Test-time augmentation (TTA) has become a widely adopted technique in the computer vision field, which can improve the prediction performance of models by aggregating the predictions of multiple augmented test samples without additional training or hyperparameter tuning. While previous research has demonstrated the effectiveness of TTA in visual tasks, its application in natural language processing (NLP) tasks remains challenging due to complexities such as varying text lengths, discretization of word elements, and missing word elements. These unfavorable factors make it difficult to preserve the label invariance of the standard TTA method for augmented text samples. Therefore, this paper proposes a novel TTA technique called Defy, which combines nearest-neighbor anomaly detection algorithm and an adaptive weighting network architecture with a bidirectional KL divergence entropy regularization term between the original sample and the aggregated sample, to encourage the model to make more consistent and reliable predictions for various augmented samples. Additionally, by comparing with Defy, the paper further explores the problem that common TTA methods may impair the semantic meaning of the text during augmentation, leading to a shift in the model’s prediction results from correct to corrupt. Extensive experimental results demonstrate that Defy consistently outperforms existing TTA methods in various text classification tasks and brings consistent improvements across different mainstream models.

A comprehensive survey on the significance of industrial Internet of Things, energy management and big data analytics

The adaptive worldwide network architecture made up of web-enabled, objects connected through internet generally defines the concept of Internet of Things (IoT). In today’s world, IoT is contributing towards the transformation of the traditional industries to the smart industries by integrating the concept of IoT based energy management system into the analytics-based information system of the industries. Manufacturing businesses have concluded that by providing a digital identity to their tangible resources through IoT-based solutions, they can gain higher clarity into their processes and massively improve them. To estimate and analyze the developments in this field, this paper conducts an in-depth survey on the significance of big data analytics and energy management in shaping the progress of the Industrial Internet of Things (IIoT). It briefs the components related to the building blocks of the IoT, its application in various domains, benefits and the major challenges faced for building IoT technologies. This review present cutting-edge research on how IoT technology adoption might propel the transformation of industrial companies that are energy-efficient and environmentally sustainable.

An Interpretable Adaptive Multiscale Attention Deep Neural Network for Tabular Data.

Deep learning (DL) has been demonstrated to be a valuable tool for analyzing signals such as sounds and images, thanks to its capabilities of automatically extracting relevant patterns as well as its end-to-end training properties. When applied to tabular structured data, DL has exhibited some performance limitations compared to shallow learning techniques. This work presents a novel technique for tabular data called adaptive multiscale attention deep neural network architecture (also named excited attention). By exploiting parallel multilevel feature weighting, the adaptive multiscale attention can successfully learn the feature attention and thus achieve high levels of F1-score on seven different classification tasks (on small, medium, large, and very large datasets) and low mean absolute errors on four regression tasks of different size. In addition, adaptive multiscale attention provides four levels of explainability (i.e., comprehension of its learning process and therefore of its outcomes): 1) calculates attention weights to determine which layers are most important for given classes; 2) shows each feature's attention across all instances; 3) understands learned feature attention for each class to explore feature attention and behavior for specific classes; and 4) finds nonlinear correlations between co-behaving features to reduce dataset dimensionality and improve interpretability. These interpretability levels, in turn, allow for employing adaptive multiscale attention as a useful tool for feature ranking and feature selection.

RETRACTED ARTICLE: Adaptive SDN-based network architecture for vehicle to vehicle communication using flexible optical networks for 5G

RETRACTED ARTICLE: Adaptive SDN-based network architecture for vehicle to vehicle communication using flexible optical networks for 5G

Data-driven Energy-efficient Adaptive Sampling Using Deep Reinforcement Learning

This article presents a resource-efficient adaptive sampling methodology for classifying electrocardiogram (ECG) signals into different heart rhythms. We present our methodology in two folds: ( i ) the design of a novel real-time adaptive neural network architecture capable of classifying ECG signals with different sampling rates and ( ii ) a runtime implementation of sampling rate control using deep reinforcement learning (DRL). By using essential morphological details contained in the heartbeat waveform, the DRL agent can control the sampling rate and effectively reduce energy consumption at runtime. To evaluate our adaptive classifier, we use the MIT-BIH database and the recommendation of the AAMI to train the classifiers. The classifier is designed to recognize three major types of arrhythmias, which are supraventricular ectopic beats (SVEB), ventricular ectopic beats (VEB), and normal beats (N). The performance of the arrhythmia classification reaches an accuracy of 97.2% for SVEB and 97.6% for VEB beats. Moreover, the designed system is 7.3× more energy-efficient compared to the baseline architecture, where the adaptive sampling rate is not utilized. The proposed methodology can provide reliable and accurate real-time ECG signal analysis with performances comparable to state-of-the-art methods. Given its time-efficient, low-complexity, and low-memory-usage characteristics, the proposed methodology is also suitable for practical ECG applications, in our case for arrhythmia classification, using resource-constrained devices, especially wearable healthcare devices and implanted medical devices.

ASMEvoNAS: Adaptive segmented multi-objective evolutionary network architecture search

Network architecture search (NAS) has attracted much attention as an automatic design technique of network architecture. In particular, multi-objective evolutionary algorithms (MOEAs) have been a popular kind of optimizer in NAS due to their global optimization capability. However, as a population-based iterative search method, MOEAs are subject to the unbearable computational cost of individual evaluation on multiple objectives at each generation, which affects their generalization ability and transferability of MOEA-based NAS. Therefore, an adaptive segmented multi-objective evolutionary network architecture search (ASMEvoNAS) method is proposed in this paper. Firstly, an adaptive segmented evaluation strategy is designed to adaptively select different but more suitable objectives to efficiently assess the candidate architectures at different evolutionary stages, instead of evaluating them by all the considered objectives simultaneously. Thus, the computational cost and complexity of the search process can be controlled and reduced to some extent. Secondly, a preference-based pre-selection strategy is designed to filter out the initialized architectures with high parameter quantities to reduce the total parameter scale of the whole population and memory consumption. Last, a novel desirable gene reservation-based crossover and a directed connection-based mutation are proposed to produce offspring. Experimental results show that ASMEvoNAS shows promising performance on CIFAR-10, CIFAR-100, and ImageNet with error rates of 2.21%, 15.57%, and 24.43% top-1, respectively. The proposed method reduces the search cost to 0.36 GPU-Days on CIFAR-10 while maintaining competitive classification performance compared to state-of-the-art networks. In addition, ASMEvoNAS presents superior performance when dealing with the considered transfer tasks, as well as the benchmark dataset of NAS.

Optimizing Telematics Network Performance through Resource Virtualization in a Disruptive Environment: The Case of the IP/MPLS Core Network

We offer a security solution to considerably reduce latency in an IP network by virtualizing the IP/MPLS core network. It consists of adapting a virtualization method to a complex IP network, presenting the simulation of the implementation of this virtualization and the modifications to be made to certain aspects of the code of the solution. These modifications would take into account the key performance indicators of the network in order to guarantee its security and the transmission through very wide bands of data. To do this, we use Software Defined Network (SDN) technology. It allows us to have an emergent, scalable, dynamic, secure, laudable and adaptable network architecture, making it suitable for today's high bandwidth applications and IT services. This architecture decouples network control and digital data transfer functions, making network control directly programmable and the underlying infrastructure abstracted to network applications and services. After describing the soft failover to a virtualized network, we present the new architecture that describes the separation of the control and data planes of the core of the IP/MPLS network of the Autonomous Port of Kribi (PAK) in Cameroon, as part of our research work. We will then present the aspects in which modifying the code would contribute to improving one of the key qualities of service, namely latency in the heart of the network. We go from latencies above 100 ms to latencies below 1 ms; finally we recommend the approach for a continuous modification of the code with a view to optimizing the performance of the network in a continuous process for the reduction of its latency.

Shift to 6G: Exploration on trends, vision, requirements, technologies, research, and standardization efforts

Recent technological breakthroughs and significant expansion in the number of Internet-of-Things (IoT) devices, a new paradigm of unparalleled user experiences, dramatically improved a host of innovative applications, and the emergence of various use cases has begun. To achieve this, a much better adaptable communication network architecture is required, one that is exceptionally intelligent and capable of providing hyper-fast, ultra-reliable, and low-latency communications. These needs of the next-generation wireless communication systems are expected to be met by sixth-generation (6G) communication technologies. The standardization process for fifth-generation is now complete, and the worldwide installation has begun. To keep cellular networks competitive, a collaboration between industry and academics has already commenced in designing the next phase called “6G” in communication networks. It provides the groundwork for layering the communication demands arising in the 2030s. 6G perception, services, technology, and standardization are all hot topics in academics and industries. In pursuit of this ambition, this paper outlines the most prospective avenues of 6G research from current literature. In this investigation, the paper highly focuses on state-of-art driving factors and technological developments propelling the 6G revolution. In this study, emerging applications and requirements are also discussed in depth. Then, to provide a perspective on the global aspect of 6G development, the frameworks for existing and ongoing research projects and activities, including standardization efforts, are reviewed. Finally, specific issues have been incorporated to give new insight into future development approaches towards 6G based on developing demands in the coming years.

Fusion Evaluation of College Cultivation by Adaptive Multivariate Neural Network Model.

The quality of graduates is the key factor in evaluating the cultivation effect of colleges and universities. Quantification of whether the graduates qualify for their working post in companies and industries provides conduction for further college cultivation reform enhancement. In this work, we proposed an adaptive multivariate neural network architecture for fusion evaluation of college student cultivation. Specifically, we designed a questionnaire to collect data on the current working status of 1231 graduates and recorded 32 in-school training items categorized into four different modules. For quantitative evaluation, 10 indices of career-require competence were set to describe the graduates' job abilities. The fused contribution of the in-school training items to the career-required competence was predicted by the multivariate network model with the linking weights adaptively trained. A comprehensive contribution matrix was generated by discrete PCA multivariate transforming to provide a digital reference for the network training. A 7-level scoring system was designed for quantifying the contribution matrix. For model optimization, the network structure was tuned by testing a different number of hidden nodes. The model was trained and optimized to reveal the direct correlation between college cultivation and job-required abilities. Experimental results indicated that the methodology we proposed is feasible to evaluate the cultivation mode in colleges and universities, theoretically and technically providing positive directions for colleges and universities to make their cultivation reforming, as to enhance the quality of their graduates.

Optimization techniques for task scheduling criteria in IaaS cloud computing atmosphere using nature inspired hybrid spotted hyena optimization algorithm

SummaryCloud computing has garnered unprecedented growth in recent years in the field of Information Technology. It has emerged as a high‐performance computing option owing to its infrastructure that comprises of heterogeneous collection of autonomous computers and adaptable network architecture. The tasks that are scheduled in an optimized manner for their execution could be classified under NP‐hard problems. Though meta‐heuristic scheduling algorithms emerge as scheduling options, they need to be much more consistent while dealing with the dynamic set up of the cloud environment. In this paper, we had proposed a multi‐objective meta‐heuristic scheduling algorithm namely Quasi Oppositional Genetic Spotted Hyena Optimization (QOGSHO) algorithm that globally optimizes the makespan, resource consumption and SLA violation QoS parameters, thereby improving the performance. The algorithm proposed is an amalgamated product of meta‐heuristic algorithms like Quasi Oppositional Based Learning (QOBL), Spotted Hyena Optimization (SHO), and Genetic Algorithm (GA). The performance efficiency of the proposed QOGSHO algorithm had been compared with various scheduling algorithms using uniform datasets by varying the data instance sizes in a simulated cloud environment. The obtained results clearly justify the task scheduling efficiency of the proposed algorithm with respect to the QoS parameters namely makespan, resource utilization and SLA violation.

ASPCNet: Deep adaptive spatial pattern capsule network for hyperspectral image classification

Previous studies have shown the great potential of capsule networks for the spatial contextual feature extraction from hyperspectral images (HSIs). However, the sampling locations of the convolutional kernels of capsules are fixed and cannot be adaptively changed according to the inconsistent semantic information of HSIs. Based on this observation, this paper proposes an adaptive spatial pattern capsule network (ASPCNet) architecture by developing an adaptive spatial pattern (ASP) unit, that can rotate the sampling location of convolutional kernels on the basis of an enlarged receptive field. Note that this unit can learn more discriminative representations of HSIs with fewer parameters. Specifically, two cascaded ASP-based convolution operations (ASPConvs) are applied to input images to learn relatively high-level semantic features, transmitting hierarchical structures among capsules more accurately than the use of the most fundamental features. Furthermore, the semantic features are fed into ASP-based conv-capsule operations (ASPCaps) to explore the shapes of objects among the capsules in an adaptive manner, further exploring the potential of capsule networks. Finally, the class labels of image patches centered on test samples can be determined according to the fully connected capsule layer. Experiments on three public datasets demonstrate that ASPCNet can yield competitive performance with higher accuracies than state-of-the-art methods. For the convenience of follow-up research and engineering applications, we packaged the algorithm into an arbitrary plug-in module and released it at https://github.com/Cimy-wang.

Adaptive Multiscale Superpixel Embedding Convolutional Neural Network for Land Use Classification

Currently, large quantities of remote sensing images with different resolutions are available for earth observation and land monitoring, which are inevitably demanding intelligent analysis techniques for accurately identifying and classifying land use (LU). This article proposes an adaptive multi-scale superpixel embedding convolutional neural network architecture (AMUSE-CNN) for tackling land use classification. Initially, the images are parsed via the superpixel representation so that the object based analysis (via a superpixel embedding CNN scheme) can be carried out with the pixel context and neighborhood information. Then, a multi-scale convolutional neural network (MS-CNN) is proposed to classify the superpixel based images by identifying object features across a variety of scales simultaneously in which multiple window sizes are used to fit to the various geometries of different LU classes. Furthermore, a proposed adaptive strategy is applied to best exert the classification capability of MS-CNN. Subsequently two modules are developed to fully implement the AMUSE-CNN architecture. More specifically, Module I is to determine the most suitable classes for each window size (scale) by applying majority voting to a series of MS-CNNs. Module II carries out the classification of the classes identified in Module I for the given scale used in MS-CNN and therefore complete the LU classification of the entire classes. The proposed AMUSE-CNN architecture is both quantitatively and qualitatively validated using remote sensing data collected from two cities, Kano and Lagos in Nigeria due to the spatially complex land use distribution. Experimental results show the superior performance of our approach against several state-of-the-art techniques.

ReLeDP: Reinforcement-Learning-Assisted Dynamic Pricing for Wireless Smart Grid

The smart grid must ensure that power providers can obtain substantial benefits by selling energy, while at the same time, they need to consider the cost of consumers. To realize this win-win situation, the smart grid relies on dynamic pricing mechanisms. However, most of the existing dynamic pricing schemes are based on artificial objective rules or conventional models, which cannot ensure the desired effectiveness. Thus, we apply reinforcement learning to model the supply-demand relationship between power providers and consumers in a smart grid. The dynamic pricing problem of the smart grid is modeled as a discrete Markov decision process, and the decision process is solved by Q-learning. Now, the success of any intelligent dynamic pricing scheme relies on timely data transmission. However, the scale and speed of data generation can create several network bottlenecks that can further reduce the performance of any dynamic pricing scheme. Hence, to overcome this challenge, we have proposed an artificial-intelligence-based adaptive network architecture that adopts software-defined networking. In this architecture, we have used a self-organized map-based traffic classification approach followed by a dynamic virtual network embedding mechanism. We demonstrate the effectiveness of the dynamic pricing strategy supported through adaptive network architecture based on various performance indicators. The outcomes suggest that the proposed strategy is of great significance to realize the sustainability of power energy in the future. Lastly, we discuss various implementation challenges and future directions before concluding the article.

Electricity Theft Detection in Power Consumption Data Based on Adaptive Tuning Recurrent Neural Network

Electricity theft behavior has serious influence on the normal operation of power grid and the economic benefits of power enterprises. Intelligent anti-power-theft algorithm is required for monitoring the power consumption data to recognize electricity power theft. In this paper, an adaptive time-series recurrent neural network (TSRNN) architecture was built up to detect the abnormal users (i.e., the electricity theft users) in time-series data of the power consumption. In fusion with the synthetic minority oversampling technique (SMOTE) algorithm, a batch of virtual abnormal observations were generated as the implementation for training the TSRNN model. The power consumption record was characterized with the sharp data (ARP), the peak data (PEA), and the shoulder data (SHO). In the TSRNN architectural framework, a basic network unit was formed with three input nodes linked to one hidden neuron for extracting data features from the three characteristic variables. For time-series analysis, the TSRNN structure was re-formed by circulating the basic unit. Each hidden node was designed receiving data from both the current input neurons and the time-former neuron, thus to form a combination of network linking weights for adaptive tuning. The optimization of the TSRNN model is to automatically search for the most suitable values of these linking weights driven by the collected and simulated data. The TSRNN model was trained and optimized with a high discriminant accuracy of 95.1%, and evaluated to have 89.3% accuracy. Finally, the optimized TSRNN model was used to predict the 47 real abnormal samples, resulting in having only three samples false predicted. These experimental results indicated that the proposed adaptive TSRNN architecture combined with SMOTE is feasible to identify the abnormal electricity theft behavior. It is prospective to be applied to online monitoring of distributed analysis of large-scale electricity power consumption data.