Intelligent behavior is an emergent phenomenon observed in biological organisms across all scales. It describes the cooperative behavior of low complexity entities to accomplish complex tasks, which exceed their individual capabilities. This property is particularly important for the Internet of Bio-Nano Things (IoBNT), which consists of Bio-Nano Things (BNTs) used in the human body, where they face many restrictions, such as bio-compatibility and size constraints. In this paper, we present a novel BNT-architecture, called Molecular Nano Neural Networks (M3N), which allows the implementation of intelligence on the micro-/nano-scale. The proposed structure consists of compartments (low complexity entities) that are connected to each other to form a network. Based on reaction and diffusion of molecules in and between connected compartments, this network mimics an artificial neural network, which is an important step towards  artificial intelligence in the IoBNT. We provide design guidelines for the proposed M3N and successfully validate it by applying a regression and classification task.

This work has been submitted to the IEEE OA for publication. Copyrights may be transferred without notice, after which this version may no longer be accessible.

Feature fusion is an effective solution for improving image retrieval performance. Although the more feature types, the better accuracy, complexity also increases. Applications in practice typically afford a limited number of feature types. Due to the strong complementarity, global and local features form an ideal combination for many fusion applications. However, the two kinds of features are intrinsically different in nature, thus cannot be fused in a straightforward way. In this work, we propose an integrated image retrieval and feature fusion framework for global and local features. It is based on inverted index fusion, a technique for efficient image retrieval. The core idea is to rank candidates by weighted voting during candidate selection, which is named pre-ranking. This procedure takes place before re-ranking, and is potentially superior to conventional late fusion. Extensive experiments on three public datasets show that the light-weight pre-ranking stage significantly contributes to accuracy, and brings substantial improvement when used together with re-ranking. Our method is robust and versatile, and can be applied to any scenario where inverted indexing is used. It is a promising technique for multimedia retrieval in the big data era.

This piece of research identifies how DTW and some common environmental parameters influence crop yield or vegetation. A total of 14 DTW and its variants and 10 environmental parameters that promote crop yield or vegetation were adopted. The work points out the potential gaps untapped within DTW application in crop yield prediction and the efficacy of this model and its variants in forecasting yield.

Wearable Internet of Things (WIoT) and Artificial Intelligence (AI) are rapidly emerging technologies for healthcare. These technologies enable seamless data collection and precise analysis toward fast, resource-abundant, and personalized patient care. However, conventional machine learning workflow requires data to be transferred to the remote cloud server, which leads to significant privacy concerns. To tackle this problem, researchers have proposed federated learning, where end-point users collaboratively learn a shared model without sharing local data. However, data heterogeneity, i.e., variations in data distributions within a client (intra-client) or across clients (inter-client), degrades the performance of federated learning. Existing state-of-the-art methods mainly consider inter-client data heterogeneity, whereas intra-client variations have not received much attention. To address intra-client variations in federated learning, we propose a federated clustered multi-domain learning algorithm based on ClusterGAN, multi-domain learning, and graph neural networks. We applied the proposed algorithm to a case study on stress-level prediction, and our proposed algorithm outperforms two state-of-the-art methods by 4.4% in accuracy and 0.06 in the F1 score. In addition, we demonstrate the effectiveness of the proposed algorithm by investigating variants of its different modules.

Traditionally, time series data augmentation has primarily focused on improving the architecture of Generative Adversarial Network (GAN), with the aim of closely matching the original data distribution while also preserving the dynamic behavior of the original data. However, even state-of-the-art GAN models like TimeGAN fall short in preserving the temporal dynamics present in the original time series due to the absence of first-order difference information. To address this limitation, this study proposes a novel process for generating multivariate time series data. The proposed process comprises four essential modules: a) the GAN module for generating multivariate time series data, b) the sampling module for preserving the first-order difference distribution, c) the smoothing module for refining the generated data, and d) an evaluation module using the Kolmogorov-Smirnov Test (KS-test) and Hilbert-Schmidt Independence Criterion (HSIC), along with other metrics to test the synthetic time series data. This comprehensive approach ensures that the synthetic time series data maintains both the distribution and the dynamic behavior of the original data. We extensively discuss the role of the β factor in the modified Metropolis-Hastings algorithm (in the sampling module), which controls the level of information preservation from the original time series. Our experiments reveal that with small β values, periodic information can be retained effectively. The joint distribution of the first-order difference of the synthetic time series data remains consistent when the same β value is applied in the modified Metropolis-Hastings algorithm. However, we observe that β has no impact on the partial autocorrelation functions. Nevertheless, the generated data from the sampling module maintains the memoryless property of the Markov Chain. Therefore, in the smoothing module, we apply the exponential moving average (EMA) method to simulate the long-term relationships within the original time series, and find that an optimal α value is approximately 0.4 or 0.5. Lastly, we employ the synthetic time series data to train a neural network model developed in another work. Our findings indicate that the neural network model trained on synthetic time series data exhibits performance comparable to that of a model trained on the original data.

In the pursuit of understanding the enigmatic world of prime numbers, a unique formula has been identified, which can be used to generate prime numbers, with the exception of 2 and 3. This formula is expressed as (n = positive integer, p = prime number), where, intriguingly, the output for other positive integers results in irrational numbers. This enigmatic formula not only reveals prime numbers but also unveils a peculiar pattern related to composite numbers derived from prime factors. These composite numbers, which arise as exceptions in the context of prime generation, exhibit regularity and may offer new insights into the interconnected of prime and composite numbers. This discovery promises to broaden our understanding of the intricate world of number theory and provides a fresh perspective on the nature of prime numbers. Further exploration of this formula may uncover deeper mathematical principles and unlock novel avenues in number theory research. p =√1 + 24n

In the contemporary digital landscape, the integration of blockchain technology with SAP systems has emerged as a pivotal advancement for businesses across various sectors. This research delves into the transformative potential of blockchain when synergized with SAP, a leading enterprise resource planning (ERP) system. The inherent strengths of blockchain, such as unparalleled transparency, robust security, and decentralized control, offer a myriad of opportunities to enhance SAP modules, revolutionizing traditional business processes and driving both efficiency and innovation. Â Central to this study is the exploration of real-world applications, particularly through case studies of three companies, referred to as “Company A,” “Company B,” and “Company C.” These placeholders have been intentionally used to maintain the confidentiality and anonymity of the companies involved, ensuring that proprietary strategies, sensitive data, and competitive advantages are not inadvertently disclosed. Such a measure is crucial in academic and industry research to uphold the integrity of the study while safeguarding the interests of the participating entities. Â “Company A” represents a firm in the electricity sector that has harnessed blockchainâ\euro™s capabilities to enhance supply chain transparency and traceability. “Company B,” from the insurance industry, has streamlined its financial operations, leveraging blockchain to reduce inefficiencies and bolster trust among stakeholders. Lastly, “Company C” from the automotive sector has transformed its asset management and tracking processes, utilizing blockchain to provide real-time, immutable records, significantly reducing discrepancies. Â However, the journey of integrating blockchain with SAP presents challenges, including technical complexities, organizational resistance, and scalability concerns. Yet, the case studies underscore the tangible benefits that can be reaped, offering valuable lessons for businesses contemplating a similar technological convergence. Â In an era where digital transformation is paramount, the fusion of blockchain and SAP emerges as a promising avenue for achieving operational excellence. This research provides an in-depth guide, highlighting the intricacies, potential pitfalls, and immense rewards of this integration, with a special emphasis on real-world implementations and their impact. Â

Product pricing is a critical task that has a profound impact on demand and the target audience. Setting the price of an existing product is even more challenging, as it can significantly affect business growth, customer purchasing patterns, and brand perception. In this paper, we propose an approach that leverages a deep learning Multi-layer Perceptron (MLP) Neural Network to predict changes in drug prices. Our model differs from existing approaches as it focuses on utilizing the stated reasons for price changes rather than product or market attributes for price change prediction. The MLP-based model is designed to learn complex patterns and dependencies within the drug price data, providing a data-driven solution for accurate forecasting. The text field containing the reason for the price change is pre-processed and then fed into the MLP neural network. We employ a Continuous Bag of Words approach to convert the text into a numerical format for model development. The model is trained on a diverse dataset, and its performance is evaluated using various metrics, including Mean Absolute Error (MAE) and Root Mean Square Error (RMSE), which indicate the model’s predictive accuracy. The results demonstrate that the MLP-based model excels in predicting fluctuations in drug prices, showcasing its ability to adapt to the dynamic nature of the pharmaceutical market.

The profound association between music and human emotion has transcended epochs, underscoring the capacity of musical compositions to elicit a spectrum of feelings, from exuberance to introspection. In the contemporary landscape, the intersection of music and technological advancements has engendered a paradigmatic shift in the creation and interpretation of musical compositions. Central to this transformation is the integration of artificial intelligence (AI) into the realm of music composition, a domain historically governed by human creativity. This research endeavors to navigate this juncture, unraveling the prospect of imbuing AI-generated music with heightened emotional resonance, thereby amplifying the scope of artistic expression. At the crux of this exploration lies the innovative utilization of Generative Adversarial Networks (GANs) to infuse the synthesized musical compositions with an intricate tapestry of human-like emotions. This paper sets out to elucidate the multifaceted dimensions of this venture by charting a trajectory that traverses the historical lineage of emotional undertones in music, culminating in a contemporary synergy between AI capabilities and human sentiment. Our approach is encapsulated within the nexus of technology and creativity, where GANs are envisaged as a conduit to facilitate the infusion of emotions into AI-generated musical compositions. In subsequent sections, we delve into an immersive analysis of the seminal role that music has played in articulating emotions throughout history. Moreover, we embark on a comprehensive exploration of the confluence of AI advancements and the nuanced realm of emotional resonance, delineating the profound possibilities that emerge from this amalgamation. Crucially, the research postulates a novel framework that leverages GANs to imbue AI-generated harmonies with a poignant emotional depth, elucidating the pivotal role of technology in elevating the emotive tenor of musical compositions. The subsequent chapters unravel the intricate methodology underpinning this research, encapsulating data collection processes, GAN architecture elucidation, techniques for embedding emotional facets, and the meticulous training process. Furthermore, a meticulous analysis of the emotional impact of AI-generated music on human perception is presented, both quantitatively and qualitatively, shedding light on the efficacy of the GAN-powered approach. Conclusively, the research extends its purview to expound upon the ethical considerations embedded within this paradigmatic juncture, while also envisioning potential trajectories for the practical application and validation of the proposed GAN-powered methodology. As the curtains are drawn on this introductory exposition, the subsequent sections promise a symphony of insights, culminating in a harmonious synthesis of AI ingenuity and human emotional resonance within the tapestry of musical composition.

The medical care industry is on the cusp of an extraordinary period, with large language models (LLMs) arising as incredible assets for reclassifying medical care elements. This paper investigates the potential and effect of LLMs in different parts of medication, including diagnostics, patient consideration, drug revelation, and medical services organization. It dives into the open doors and difficulties introduced by LLMs, accentuating the moral contemplations and the requirement for capable reception. By looking at late turns of events and contextual investigations, this paper offers a brief look into the developing scene of medical services, where LLMs are ready to assume a focal part in reshaping the eventual fate of medication.

BREN-Tech deals with the advancement of human brain and human body.It is a more effective and faster way where a chip like micro/macro machine is inserted into the body and many procees takes place in a short time.It involves minute comonents and can be connected to external systems as well.It can help towards the growth of human evolution which can be equal or more than the advancement of AI in the modern world

Abstractâ\euro”An effective fraud detection system must protect millions of clients for a secure banking system, which can be achieved using machine learning and AI. In this article, we have applied four supervised machine learning models: k-nearest neighbors (KNN), random forest (RF), decision tree, and logistic regression (LR) algorithm to detect bank fraud for a synthetic dataset having 1,00,000 rows and 32 columns. Adequate preprocessing, decoding, rigorous feature engineering, validation, performance evaluation, and explanation have allowed the readers to understand the whole study. Though the algorithms’ accuracy is similar, logistic regression shows a higher accuracy of 0.98921 for label encoding, which is not prescribed. Still, a significant AUC of 95% has been achieved in XGBoost and LGBM. Further application of this study can be done in real-life cases of banks, insurance, and finance institutions.

X-ray computed tomography (CT) is a crucial tool for non-invasive medical diagnosis that uses differences in materials’ attenuation coefficients to generate contrast and provide 3D information. Grating-based phase- and dark-field-contrast X-ray imaging is an innovative technique that utilizes refraction and small-angle scattering to generate additional co-registered images with improved contrast and microstructural information. While it is already possible to perform human chest dark-field radiography, it is assumed that its diagnostic value increases when performed in a tomographic setup. However, the susceptibility of Talbot-Lau interferometers to mechanical vibrations coupled with a need to minimize data acquisition times has hindered its application in clinical routines and the combination of the two techniques in the past. In this work, we propose a processing pipeline to address this issue in a human-sized clinical dark-field CT system. We present the corrective measures that have to be applied in the employed processing and reconstruction algorithms to mitigate the effects of vibrations and deformations of the interferometer gratings. This is achieved by identifying and mitigating spatially and temporally variable vibrations in the interferometer. By exploiting correlations in the modular grating setup, we can identify relevant fluctuation modes and separate the fluctuation and sample information, enabling vibration-artifact free sample reconstruction.

Blockchain technology has gained significant attention due to its decentralized, tamper-resistant, and transparent nature. However, the inherent immutability of blockchain poses challenges for certain applications. This article presents a novel three-chain model based on the chameleon hash function to address the need for editability in blockchain systems. The model includes a dedicated pool chain that provides optimal conditions for editing operations, along with composite supervision and audit strategies to ensure compliance, security, and traceability. To maintain ledger consistency, a correction chain stores audited edited blocks, while the main chain is updated accordingly. The modelâ\euro™s feasibility is validated through experimentation, showing a minimal impact on the performance of the editable main chain. Contributions of this research include clear definitions of data ownership, editing permissions, and the completion flag for editing operations on the blockchain. Furthermore, it effectively resolves conflicts between decentralized editing and editing waiting, while ensuring the ledger consistency. The proposed three-chain model offers a secure and efficient solution to enhance blockchain editability, opening up new possibilities for its application in diverse domains.

Low-density parity check codes (LDPC) are efficient in terms of coding performance and parallelism but need a higher code length to reduce the decoding complexity. In modern5G networks, hardware utilization issues have been addressed with a min-sum algorithm adopting quasi-cyclic LDPC. The present paper proposes a modified layered min-sum algorithm by presenting an intelligent strategy to introduce concurrency in processing by grouping the rows in the base matrix. The algorithm also considers the case where the column weight of a layer is greater than one and makes a suitable connection hierarchy to maximize hardware re-usability. The architecture employs the tree-structure (TS) approach to design an effective hardware block for the check-node unit (CNU). The proposed CNU architecture processes input belief parallelly and enhances hardware reusability by adapting data path reconfiguration. This scheme ensures that even though the processing of the grouped rows in the layer happens simultaneously, the rows are isolated from each other during this process. The routing and processing hardware architecture of the proposed system has been synthesized on Zinc-ultra scale+ zcu106 after functional verification on Xilinx-Vivado to claim an increase in throughput.

Agile development uses rapid releases to deliver features early and often to users, enabling them to provide quick feedback about the software. We observed that relevant projects, such as Firefox and Chrome, adopt rapid release, but in some cases, the development duration takes longer than the release cycle. This work analyzed whether other projects adopting rapid release also present similar behavior. We analyzed an open-source corpus comprising 1,039 relevant open-source projects, with 13,102 rapid releases and 7,071 traditional releases (without counting the patches), totaling 20,173 releases with 3,167,563 commits. We compared rapid and traditional releases to understand changes regarding the development duration, the development start delay, and the percentage of percentage of commits in the release cycle. We discovered that, in most cases, the development duration of rapid releases is higher than its release cycle, meaning that most projects delivering rapid releases employ parallel release development. However, on average, the amount of work done in parallel has a small impact on the release development. Moreover, the development of rapid releases starts early and without delays. Traditional releases’ development is generally preceded by a pause, probably due to patch development and release stabilization. Therefore, our results suggest that projects that intend to adopt rapid release do not necessarily need to reduce the development duration. The projects may start the release development early and manage parallel release development to achieve a rapid release cycle. This paper was submitted to IEEE Transactions on Software Engineering in October 2023 and is under review.

The current ML-driven approaches for omics-driven biomarker discovery often result in panels that are not reproducible in external validation datasets, and their optimization in terms of feature set size remains unsolved, which jeopardizes their translation into cost-effective clinical tools. The present study investigates how to optimize the feature set size by testing six algorithms on eight large-scale transcriptomics datasets for breast, lung, renal, and ovarian cancer. Most importantly, we propose a new evaluation metric called Cross Hypervolume (CHV) to assess the performance of multi-objective feature selection algorithms on both training and test datasets. CHV is an improvement over other metrics as it considers the trade-off between classification accuracy and the size of the selected features. The CHV metric allows for better assessment of biomarker models and helps to select the most accurate and biologically relevant ones.Â

Computational science is a rapidly growing multi-and inter-disciplinary area where science, mathematics, computation, management, and its collaboration use advanced computing capabilities to understand and solve the most complex real-life problems. In this article, the computation of geometric series on radicals is introduced for the application of computational science.

This paper deals with the implementation of a light fifth generation (5G) base station (gNB) intended  for specific use cases requiring an airborne deployment of the network. We focus on the radio unit (RU) and give details on the components, the implementations, and the technical choices that have been made, driven by the strong constraints inherent to the considered use cases.

This article studies the security gains and challenges in IBN from the aspect of enabling concepts and technologies. Furthermore, the article highlights potential solutions to existing challenges, outlines the standardization efforts, and summarizes the most important research gaps to advance future research in this direction.

Digitization has changed the way and ease of doing business which affects almost everything in today’s enterprise organization. Digital Experience platforms (DXPs) are unified approach to integrate all technology stacks available in the market across every touchpoints such as Wearable devices, WEB, IVR, and Mobile etc. US Banking & Finance Industry have lot of potential to transform, digitize their banking and finance (Fintech) applications using unified approach such as DXPs. In this article, we have evaluated many digital strategy from various stakeholders in the industry. Enterprises uses various technology, tool, techniques and concepts to develop digital capabilities whereas DXPs has integrated approach to develop, implement and digitize the strategy to transform banking and finance industry. DXPs is gaining momentum & it is now used by banking & finance sector, such as Standard Bank, Citizen Bank, TP Bank etc.

Cell localization in medical pathology image analysis is a challenging task due to the significant variation in cell shape, size and color shades. Existing localization methods continue to tackle these challenges separately, frequently facing complications where these difficulties intersect and adversely impact model performance. In this paper, these challenges are first reframed as issues of feature misalignment between cell images and location maps, which are then collectively addressed. Specifically, we propose a feature alignment model based on a multi-scale hypergraph attention network. The model considers local regions in the feature map as nodes and utilizes a learnable similarity metric to construct hypergraphs at various scales. We then utilize a hypergraph convolutional network to aggregate the features associated with the nodes and achieve feature alignment between the cell images and location maps. Furthermore, we introduce a stepwise adaptive fusion module to fuse features at different levels effectively and adaptively. The comprehensive experimental results demonstrate the effectiveness of our proposed multi-scale hypergraph attention module in addressing the issue of feature misalignment, and our model achieves state-of-the-art performance across various cell localization datasets.

Network slicing plays a crucial role in the progression of 5G and beyond, facilitating dedicated logical networks to meet diverse and specific service requirements. The principle of End-to-End (E2E) slice includes not only a service chain of physical or virtual functions for the radio and core of 5G/6G networks but also the full path to the application servers that might be running at some edge computing or at central cloud. Nonetheless, the development and optimization of E2E network slice management systems necessitate a reliable simulation tool for evaluating different aspects at large-scale network topologies such as resource allocation and function placement models.  This paper introduces Slicenet, a mininet-like simulator crafted for E2E network slicing experimentation at the flow level. Slicenet aims at facilitating the investigation of a wide range of slice optimization techniques, delivering measurable, reproducible results without the need for physical resources or complex integration tools. It provides a well-defined process for conducting experiments, which includes the creation and implementation of policies for various components such as edge and central cloud resources, network functions of multiple slices of different characteristics. Furthermore, Slicenet effortlessly produces meaningful visualizations from simulation results, aiding in comprehensive understanding.  Utilizing Slicenet, service providers can derive invaluable insights into resource optimization, capacity planning, Quality of Service (QoS) assessment, cost optimization, performance comparison, risk mitigation, and Service Level Agreement (SLA) compliance, thereby fortifying network resource management and slice orchestration.