This paper presents a blockchain-enabled data sharing framework for latency-sensitive computing services.

In classification problems, mislabeled data can have a dramatic effect on the capability of a trained model. The traditional method of dealing with mislabeled data is through expert review of the data. However, this is not always ideal, due to both the large volume of data in many classification datasets, as with image datasets supporting deep learning models, and the limited availability of human experts for review of the data. Herein we propose an Ordered Sample Consensus (ORSAC) method to support data cleaning by flagging mislabeled data. This method is inspired by the Random Sample Consensus (RANSAC) method for outlier detection. In short, the method involves iteratively training and testing a model on different splits of the dataset, recording misclassifications, and flagging data which is frequently misclassified as probable mislabels. We evaluate the method by purposefully mislabeling subsets of the data and assessing the method’s capabilities to find such data. We demonstrate with three datasets, a mosquito image dataset, CIFAR-10, and CIFAR-100, that this method is reliable in finding mislabeled data with a high degree of accuracy. Our experimental results indicate a high proficiency of our methodology in identifying mislabeled data across these diverse datasets, with performance assessed using different mislabeling frequencies.

Spectrum sensing is an essential function of cognitive radio technology that can enable the reuse of available radio resources by so-called secondary users without creating harmful interference with licensed users. The application of machine learning techniques to spectrum sensing has attracted consid?erable interest in the literature. In this contribution, we study cooperative spectrum sensing in a cognitive radio network where multiple secondary users cooperate to detect a primary user. We introduced multiple cooperative spectrum sensing schemes based on a tree deep neural network architecture, which incorporate a one-dimensional convolutional neural network and a long short-term memory network. The primary objective of these schemes is to effectively learn the activity pattern of the primary user. The scenario of an imperfect transmission channel is considered to demonstrate the robustness of the proposed model. The performance of the proposed methods are evaluated with the receiver operating characteristic curves, the probability of detection for various SNR levels and the computational time. The simulation results confirm the effectiveness of the bidirectional long short-term memory based method, surpassing the performance of the other proposed schemes and the current state of the art in terms of detection probability while ensuring a reasonable online detection time.

The recent progress of artificial intelligence (AI) opens up new frontiers in the possibility of automating many tasks involved in Telecom networks design, implementation, and deployment. This has been further pushed forward with the evolution of generative artificial intelligence (AI), including the emergence of large language models (LLMs), which is believed to be the cornerstone toward realizing self-governed, interactive AI agents. Motivated by this, in this paper, we aim to adapt the paradigm of LLMs to the Telecom domain. In particular, we fine-tune several LLMs including BERT, distilled BERT, RoBERTa and GPT-2, to the Telecom domain languages, and demonstrate a use case for identifying the \ac{3gpp} standard working groups. We consider training the selected models on 3GPP techincal documents (Tdoc) pertinent to years 2009-2019 and predict the Tdoc categories in years 2020-2023. The results demonstrate that fine-tuning BERT and RoBERTa model achieves 84.6% accuracy, while GPT-2 model achieves 83% in identifying 3GPP working groups. The distilled BERT model with around 50% less parameters achieves similar performance as others. This corroborates that fine-tuning pretrained LLM can effectively identify the categories of Telecom language. The developed framework shows a stepping stone towards realizing intent-driven and self-evolving wireless networks from Telecom languages, and paves the way for the implementation of generative AI in the Telecom domain.

Smart cities play a vital role in limiting the ill-effects of rapid urbanization on the environment without compromising on benefits such as improving infrastructure, standard of living, and productivity. However, the collection, storage, and sharing of data from the plethora of sensor networks in a typical smart city deployment warrants a well-defined data platform architecture. In this paper, we propose a multi layer architecture compliant with the oneM2M standards and the Indian Urban Data Exchange (IUDX) framework. The proposed architecture consists of Data Monitoring (DML), Data Storage (DSL), and Data Exchange (DEL) layers. The DML employs oneM2M as the middleware platform to achieve interoperability. The DSL uses a multi-tenant architecture with multiple logical databases, enabling efficient and reliable data management. The DEL utilizes standard data schemas and open APIs of IUDX to avoid data silos, and enables secure data sharing. Further, we present a proof-of-concept implementation of our architecture deployed in a university campus using OM2M, PostgreSQL, and Django. Finally, simulations mimicking real-time data insertion and retrieval showed that the DML can handle 600 concurrent users with an average latency under 100 milli seconds. The DSL improved the latency compared to a single database architecture and the DEL could handle 100 concurrent users with zero failed requests.

In the modern era of digital transformation, the evolution of the fifth-generation (5G) wireless network has played a pivotal role in revolutionizing communication technology and accelerating the growth of smart technology applications. As an integral element of smart technology, the Internet of Things (IoT) grapples with the problem of limited hardware performance. An IoT system based on cloud and fog computing is a highly efficacious solution but often faces concept drift challenges in real-time data processing, due to the dynamic and imbalanced nature of IoT environments, leading to performance degradation. In this study, we introduce a novel framework for drift-adaptive ensemble called the Adaptive Exponentially Weighted Average Ensemble (AEWAE), consisting of three stages: IoT data preprocessing, base model learning, and online ensembling. It integrates four advanced online learning methods with an ensemble approach. The crucial parameter of the AEWAE method is fine-tuned using the Hyperparameter Optimization (HPO) method. Experimental results on two public IoT datasets exhibit that AEWAE-based anomaly detection significantly detects concept drift and effectively identifies anomalies in imbalanced IoT data streams, compared with other baseline methods in terms of accuracy, F1 score, latency, and throughput.

This material is fully dedicated to the “Incoherent approach for Power NOMA-RIS-MIMO transmission in wireless channels”. Such kind of approach might be successfully applied in dense networks formed by high-speed-vehicles (HSV networks, etc.), as those scenarios take place in Doubly-Selective communication channels typical for such kind of radio networks. The proposal for the, hereafter presented, incoherent view (“paradigm”) is based on several basic principles: - Rejection of the Channel State Information (CSI, CSIT) approach, i.e. rejection of the “coherent” paradigm (ideology); - Application of the so-called “invariant” (in relation to the communication channel’s distortions) modulation technique; - Orthogonal channel decomposition by means of “universal” eigen-basis (in the form of Prolate Spheroidal Wave Functions, PSWF) as “artificial trajectories” of wave propagation. - Chaotic filtering (with chaos parameters settings as UE signatures) together with sequential multiuser parallel detection algorithms for users’ identification. It is shown that the proposed paradigm might provide an effective use of the radio-resource and it is relatively simple for implementation.

The risk of information leaking has grown significantly as a result of social networking sites' broad use in today's digital culture. Using the CIA triad's principles of confidentiality, integrity, and availability, this conference paper analyses the issues related to information leaking through social networking sites and suggests remedies. The study identifies a number of elements, such as social engineering assaults, flaws in third-party applications, difficulties in data sharing, insider threats, and a lack of user privacy awareness, that contribute to information leakage on social networking sites. It examines how these elements may jeopardize the privacy, accuracy, and accessibility of users' personal information and offers solutions..

With a variety of software and hardware services available to users, cloud computing has developed in recent years as a very influential and transformational technology. It functions as a fundamental method for sharing resources via the internet, with virtualization being essential to making this sharing of cloud resources possible. The National Institute of Standards and Technology (NIST) has described cloud computing as a concept that permits easy, on-demand network access to a shared pool of reconfigurable computing resources. With little management work or communication with the cloud provider, these resources can be quickly supplied and released. A significant amount of businesses have adopted cloud computing due to the many advantages and opportunities it provides. But the quick shift to the cloud has also given rise to security worries. Cloud computing is one of the modern technology that must to be used with caution. Cloud computing does not come with strong data privacy protections. Therefore, it is very important to ensure the confidentiality of data storage in order to protect data security. The objective of this paper is to discuss about the cloud computing models, the cloud service providers, the security and privacy issues surrounding cloud computing. Furthermore, prevention strategies and best practices for security and privacy issues in cloud computing will also be discussed in this paper.

A unified affine-projection-like adaptive (UAPLA) algorithm is deivised and verified for system identification. The UAPLA algorithm uses a generalized cost function encompassing some data-reusing methods to cope with colored input signals. Furthermore, the UAPLA algorithm is derived based on the new cost function to generalize multiple affine-projection algorithms. As a result, the proposed UAPLA algorithm includes some classical adaptive filters as exceptional cases while allowing flexibility to achieve low estimation errors under impulsive noises. The obtained results conducted by simulations help to corroborate the superiority of the proposed UAPLA algorithm over other popular AP algorithms.

Brain tumor is one of the diseases with less survival chances. There are different types of tumor found in human brain mainly classified as cancerous tumor or non cancerous tumor. Further these tumors can be distinguished on the basis of their type and location such as pituitary tumor, glioma tumor or meningioma tumor. Magnetic resonance images (MRI) is an imaging technique which is widely used to study brain tumors because of its various advantages over other imaging methods. As there are hundreds of brain slices in MRI images and to study those manually is a tedious task and can be a very time consuming process. To facilitate the medical experts, this research work proposed an automated brain tumor classification and segmentation process. The study focuses on two major tasks of brain classification and brain segmentation. An EfficientNetB7 neural network is used to classify brain tumors from the MRI images. The overall classification accuracy of the model achieved was 98.485 percent. Which is better than the other existing models such as VGG-16, CNN, MobileNet, ResNet152v1 and some recent works. For segmentation of brain images consisting tumor an effective non linear curve fitting based method is proposed using levenberg-Marquardt algorithm. The proposed method showed better results than the existing state of art methods.

In this paper, starting with an introductory review of the applications of liquid crystals and polymer-dispersed liquid crystal systems in (bio)sensors and microfluidics, the possibilities of visualizing self-organization products of liquid crystalline media or field-induced instabilities of liquid crystalline systems are considered. In particular illustrated cases, it is proposed to use FemtoScan software-containing metrological complexes to visualize instabilities in liquid crystalline systems and products of self-organization in liquid crystalline media.

In the domain of highly directive wireless networks, hybrid beamforming is a solution to overcome the complexities of baseband processors and make a good trade-off between transmission performance and cost. Nonetheless, the conventional hybrid beamformer, which employs phase shifters (PSs), has several significant concerns. These include limited amplitude constraints, expensive power consumption, and inefficient hardware architecture that results in exponential complexity in the number of antennas. As a result, this paper proposes a branchwise double phase shifter (B-DPS) architecture as a solution to achieve computationally efficient hybrid beamforming, where each RF chain is connected to two distinct PSs and antenna branches using a power splitting strategy. The proposed B-DPS hybrid beamformer implementation can comfortably rescale the beamforming coverage, thereby maximizing the spectral efficiency in scenarios involving mmWave massive multiple-input and multiple-output systems. Furthermore, we consider zero-forcing with an iterative algorithm as the digital beamformer to solve the joint optimization problem of hybrid beamforming. The outcomes of the simulation results validate the beam coverage of the proposed B-DPS architecture, which outperforms the conventional non-blockwise PSs implementation.

This research paper aims to provide an overview of the role of media in promoting values and meditation for sustainable development. Sustainable development requires a shift in individual and collective values and a deeper understanding of interconnectedness and mindfulness. As a powerful communication tool, the media can play a crucial role in disseminating information, shaping public opinion, and fostering positive behavioral changes. Meditation practices can enhance mindfulness and values-based decision-making, contributing to sustainable development efforts. This paper explores the potential of media and meditation as complementary approaches to promoting sustainable development values and practices.

The paper explores how deep LSTM and deep spiking neural networks (SNN) can be used to extract meaningful features from spatio-temporal EEG brain data for early, on-line diagnosis. It introduces a new online spike encoding algorithm for Izhikevich neural networks and new methods for learning and diagnostic biomarker discovery for each of the three most popular deep learning neural network models, namely: deep BiLSTM; reservoir SNN; and NeuCube. The methods reveal that hidden neurons in a BiLSTM can capture biological meaning, while a reservoir SNN neuron activities and the spiking activities in a NeuCube model can be used to discover EEG channels that can be utilized as brain biomarkers. The study used EEG data from three datasets related to epileptic-, migraine- and healthy subjects. The problem of discriminating epilepsy from migraine using EEG data is a well known hard problem.  LSTM and a reservoir SNN achieved 90% and 85% classification accuracy correspondingly and indicated that channels F8, T3,T’6 and F7,T6 correspondingly can be explored as potential biomarkers, while a NeuCube model achieved 97% with T6, F7 and also C4 and F8 as potential biomarkers for a better classification. In addition, a 2 class NeuCube model discriminated perfectly well epilepsy from migraine and pointing to two channels C4 and F8 as potential biomarkers for the task. While all models resulted in a good classification and feature selected, the main reason for the superior performance of NeuCube is its brain-inspired architecture, where a brain map is used to structure a 3D SNN model to capture deep spatio-temporal dynamics from EEG data. This research has important implications for the development of more effective algorithms for on-line EEG classification, analysis and early brain state diagnosis, adding new features of explainability and discovery to otherwise effective AI models. The proposed methods and findings can be used for the development of more efficient brain-computer interfaces and for clinical practice.

A document by Usman Zafar . Click on the document to view its contents.

Image segmentation is a fundamental problem in medical image analysis. Deep learning (DL) methods have achieved state-of-the-art (SOTA) results in various medical image segmentation tasks. This success is largely attributable to the use of large annotated datasets for training. However, due to anatomical variations and complexity of medical image data, annotations of large medical image datasets are not only labor-intensive and time-consuming but also demand specialty-oriented skills. In this paper, we report a novel segmentation quality assessment (SQA) framework that combines active learning and assisted annotation to dramatically reduce annotation effort both in image selection and annotation querying from human experts. We propose a two-branch network that integrates a spatial and channel-wise probability attention module into the segmentation network to perform segmentation and predict potential segmentation errors simultaneously. By directly assessing the segmentation quality of unannotated images, human experts can focus on the most relevant image samples, judiciously determine the most ‘valuable’ images for annotation and effectively employ adjudicated segmentations as the next-batch training annotations with the assistance of the automatically predicted salient erroneous areas. The model performance is thus incrementally boosted via fine-tuning on the newly annotated datasets. Extensive experiments on intravascular ultrasound (IVUS) image data demonstrate that our approach achieves SOTA segmentation performance using no more than 10% of training data and significantly reduces the annotation effort.

This work presents a procedural method for analytically computing losses in solid conductor air-core coils. The approach was developed for the coaxial subset of air-core coil systems in which hoop-turn, axisymmetric assumptions can be made. It encapsulates loss generally associated with magnetic diffusion, including that induced by rotating magnetic fields from multi-phase current sources, without computing the complex eddy current distribution in a conductor cross-section. Each turn in the system is replaced with an infinitesimally thin circular current loop and is independently excited according to a peak current and phase. Field contributions are summed up at each loop center, with the inclusion of phase to calculate the major and minor components of the resultant magnetic field at each turn. Well established analytic formulae are then used to compute loss accordingly. The approach is significantly faster than 2D axisymmetric finite element analysis (FEA) and greatly improves approximations for losses in isolated coils.