This paper presents an innovative approach to enhancing underwater forensic exploration with advancements in soft robotics, adaptive evolution, and artificial intelligence. Focusing on the development of self-adaptive materials integrated with sensing and actuation capabilities, this research introduces the 'Evolutionary Algorithm Reinforcement Learning (EARL)' system. Inspired by the adaptability, reliability, and robustness of biological systems in unstructured environments, EARL employs a forward-looking adaptive mechanism that utilizes partial reinitialization in response to environmental changes, leveraging environmental similarities for real-time adaptations. Our computational model not only navigates the design space for underwater robotics but also provides insights into biological adaptation strategies. By analysing the effectiveness of design choices and exploring state-action probabilities, the study underscores the importance of tuning material properties, such as stiffness and buoyancy, to suit varying environmental conditions. The experimental outcomes demonstrate the system's capability to adapt and reinitialize partially, marking a significant advancement over existing AI-based methods in soft robotics. This work lays a foundation for future innovations in the field, suggesting directions for improving design and policy strategies to create adaptable, robust robots for complex underwater exploration tasks.

Multi-objective optimization is critical in SCM to balance conflicting objectives such as cost minimization and service level maximization. This paper presents a comprehensive study on the application of Simulated Annealing (SA) as a metaheuristic approach to address these challenges. The study includes detailed mathematical formulations, Python code implementation, and empirical evaluations using real-world SCM datasets to demonstrate SA's effectiveness and practical application.

In this study, we present a novel approach to enable high-throughput characterization of transition-metal dichalcogenides (TMDs) across various layers, including mono-, bi-, tri-, four, and multilayers, utilizing a generative deep learning-based image-to-image translation method. Graphical features, including contrast, color, shapes, flake sizes, and their distributions, were extracted using color-based segmentation of optical images, and Raman and photoluminescence spectra of chemical vapor deposition-grown and mechanically exfoliated TMDs. The labeled images to identify and characterize TMDs were generated using the pix2pix conditional generative adversarial network (cGAN), trained only on a limited data set. Furthermore, our model demonstrated versatility by successfully characterizing TMD heterostructures, showing adaptability across diverse material compositions. Impact statement Deep learning has been used to identify and characterize transition-metal dichalcogenides (TMDs). Although studies leveraging convolutional neural networks have shown promise in analyzing the optical, physical, and electronic properties of TMDs, they need extensive data sets and show limited generalization capabilities with smaller data sets. This work introduces a transformative approach-a generative deep learning (DL)-based image-toimage translation method-for high-throughput TMD characterization. Our method, employing a DL-based pix2pix cGAN network, transcends traditional limitations by offering insights into the graphical features, layer numbers, and distributions of TMDs, even with limited data sets. Notably, we demonstrate the scalability of our model through successful characterization of different heterostructures, showcasing its adaptability across diverse material compositions.

Performance of MIMO precoder for heterogeneous networks can be hindered by a lack of accurate channel state information. The single-parameter Norm Ball Mismatch Model (NBMM) has traditionally been used to tackle this problem, but its lack of performance has prompted several alternatives including the Sparsity Enhanced Mismatch Model (SEMM) and Orthogonalized SEMM (OSEMM), where its dual parameters allow for greater flexibility in dealing with channel mismatch error. The OSEMM was designed to deal in particular with the problem of high correlated channels but needs to be redesigned for multiuser (MU) transmission where every user is a service user and a victim simultaneously, especially when the users' channels are highly correlated. The impact of correlated channels is more detrimental to OSEMM-based methods than to the NBMM based ones due to the small channel gains resulted from the "decorrelation". Three multiuser OSEMM (MUOSEMM) based schemes are proposed herein that progressively attain better transmission performance than NBMM based schemes. Algorithmic details of the MUOSEMM schemes are given and simulation results are presented to demonstrate their superior performance to that of NBMM, especially in the case where users' channels are highly correlated.

A document by Takuma Yoshimura . Click on the document to view its contents.

This work presents the design of a broadband frequencyselective surface absorber (FSSA) using laser-induced graphene (LIG). This type of resistive material composed of porous graphene has been analyzed, and its performance has been modeled through different cases of FSS based on LIG patches. The results of this analysis, both simulated and experimental, show the existence of periodic frequency bands of absorption ranging from a few GHz to 50 GHz. Taking advantage of this absorbing behavior, a single-layer FSSA, including a circular LIG patch at the center of the unit cell, is proposed. A circuit model for this FSSA unit cell is introduced, which allows us to efficiently improve the absorption over a large bandwidth by including an ad-hoc dielectric layer. The FSSA is fabricated and measured: the experimental results show a good agreement with the simulated ones, providing absorption of more than 0.9 from 14 GHz to 48 GHz (109.7% relative bandwidth). In addition, the proposed design exhibits robust behavior to both TE and TM oblique incidence up to 45º.

Standardization, which defines functionalities and  interfaces, is a critical aspect for driving the industry alignment  required for B5G networks. It is often the case that a  topic, discussed in different standard developing organizations  (SDOs), is specified and implemented differently. This can lead  to confusion and uncertainty about which SDO or standards to  follow or which aspects of a particular SDO to embrace. Intent-driven  management, which is a key aspect in management and  automation of next generation mobile networks, is such a topic  that is currently being discussed in multiple SDOs, including  3rd Generation Partnership Project (3GPP), Open Radio Access  Network (O-RAN) Alliance and TM Forum (TMF). This article  provides an analysis of the 3GPP, TMF and O-RAN perspectives  on the standardization of intent-driven management, including its  fundamentals and evolution towards the future. We also identify  several key areas and issues for further exploration to accelerate  the adoption of intent-driven management in the industry.

Semantic change detection (SCD) represents a challenging task in the interpretation of remote sensing images (RSIs), with the goal of identifying change regions and extracting semantic information from bi-temporal RSIs simultaneously. The recent integration of deep neural networks leveraging multi-task learning has shown promise in enhancing SCD performance. However, there is still a challenge in improving SCD performance, specifically in designing a fine-grained network structure that can handle the two subtasks of change region localization and semantic information recognition in parallel. In this context, a novel multi-task Siamese network, termed EGMS-Net, is proposed to boost the performance of SCD, which consists of three core components. Firstly, a coarse-to-fine multi-task Siamese network is constructed to obtain semantic information and change information at multiple levels. Secondly, an adaptive change information enhancement method based on spatialspectral collaborative attention mechanism is proposed, which can assist the accurate localization of change regions without significantly increasing the model parameters. Thirdly, a change information guidance module is developed to strengthen the interaction between multi-task branches and reduce the difficulty of network training. Experiments on two benchmark datasets demonstrate that the proposed EGMS-Net outperforms existing state-of-the-art methods in the SCD community. The code of this work will be available at https://github.com/IceStreams/EGMS-Net.

Given the crucial role of the earth observation satellites in numerous key applications, accessing the Low Earth Orbit (LEO) satellite Internet as intermediaries via Laser Inter-Satellite Links (LISLs) has emerged as a promising solution to help transmit substantial amounts of observation data to ground stations. For Very Low Earth Orbit (VLEO) observation satellites, optimizing the cross-layer topology between themselves and LEO communication satellites has become paramount. To mitigate existing centralized algorithms' reliance on global data transfer requirement information, a Novel Distributed Interactive Mechanism (NDIM) for cross-layer LISLs establishment is proposed. Here, the VLEO observation satellite decides its own access strategy based on local network information gleaned from three information exchanges with the LEO communication satellite. Within this mechanism, the crosslayer link optimization is performed via the formulation of a many-objective topology optimization model, which considers the transmission requirements of observation satellites, load balancing amongst the communication satellite layer, and the transmission delay of emergency tasks. Based on which, we propose a Distributed Many-objective cross-layer Topology Optimization (DMTO) algorithm. Our algorithm is novel in considering the remaining loads of the intermediary communication satellites, and it allows observation satellites to decide on access plans on demand, given incoming data. Additionally, we used real data (from Typhoon LEKIMA) to establish a multi-task scenario and conducted packet-level simulations based on the Starlink and Dove constellations. The results indicate that, compared to the existing baseline, the DMTO algorithm increased the observation data throughput by 326.95 GB and reduced the average transmission delay of emergency task data by 20.5 seconds.

A multi-beam antenna without a phase shifter has been designed for railway communications at the upper 5G band (28 GHz). Considering the curvature of railway tracks in practice, the required beam deflection range is within-30 to 30 degrees. The limited beam deflection range allows the Rotman lens to replace the phase shifters for beam steering, which saves the system cost considerably. Depending on the choice of the antenna element, it can create either a linear or a circular polarization. The measurement results demonstrate that the linearly and circularly polarized antenna achieves maximum directivity of 10.8 dBi and 11.2 dBi, respectively. The antenna's bandwidth for the linear (circular) polarization reaches 2 GHz (1.8 GHz), sufficient to support the high data rate of the 5G band. The antenna size is minimized to fit in a shark-fin cover mounted on the vehicle.

A new proof of Goldbach's Conjecture will be presented in this paper using equations like (a + b) = 2 √ A1 in the first quadrant of the space coordinate system with n dimensions. We shall show that (a + b) is equal to the sum of the two numbers n raised to the power of N by summing (a + b) for any real numbers. It follows that for every pair of real numbers (a+b) must be equal to n n N in quarter of square whose side length is equal to √ 2 times n raised to the power of N. Our method hereby formulates the magnitude of N as n ∈ N , in which n is an infinite positive integral set. Concerning the Goldbach Conjecture, our approach provides original viewpoint and prospects for forking paths in pure mathematics.

The detection of faults in photovoltaic (PV) systems plays a major role in extending the lifetime of the employed modules and maintaining the system's efficiency. Machine learning (ML) algorithms are one of the most popular approaches for fault detection in PV systems. In this paper, it is proposed a novel approach called Logistic Model Tree (LMT) algorithm for the analysis of I-V curves of line-to-line fault, shading fault, degradation fault, and open circuit fault on the DC side of the PV systems. At first, a 2x2 PV system is built in MATLAB Simulink environment to generate I-V curves under healthy and different fault conditions and as a result, an imbalanced fault dataset is created. The imbalanced fault dataset is divided into training and testing datasets and then k-means under sampling method is used to resolve the class imbalance problem. LMT and other popular machine learning algorithms that are used in PV fault detection are trained on the training dataset with the 5-fold cross-validation method with grid-search and their performances are evaluated on the testing dataset. In the end, Matthew's Correlation Coefficient (MCC), Cohen's Kappa, and Macro F-1 of the algorithms is computed from the confusion matrices, and the performances of the algorithms are compared with each other. According to the findings, the LMT algorithm emerges as the top performer with the highest MCC (0.8657443), Kappa (0.8609745), and F-1 scores (0.8539005), solidifying its place as the most effective machine learning algorithm for detecting faults in PV systems.

This paper explores agents in artificial intelligence, focusing on their definitions, characteristics, and applications. Agents are autonomous entities that perceive, decide, and act to achieve goals, with key attributes like autonomy, reactivity, and social ability. The use of agent-based models in economic and environmental research is highlighted. Future directions and challenges, including ethical considerations and technical improvements, are discussed, emphasizing agents' potential to address complex real-world problems.

(This paper is under review by IEEE Transactions on Wireless Communications.) To reduce the cost of radio equipment hardware and the power consumption of circuits, wireless communication systems with low-resolution analog-to-digital converters (ADCs) have been studied. Extreme examples include radios with one-bit ADCs, where a phenomenon referred to as stochastic resonance, which can suppress quantization errors by adding noise to the input signal, has been reported. Regarding this phenomenon, theoretical and experimental studies have been reported for single-carrier signals. In this paper, we extend the study target to general Wiener-Hammerstein systems and complex Gaussian signaling using a new theoretical framework, i.e., the "twodimensional Fourier-Laguerre theory." We demonstrate that any nonlinear distortions higher than the first order can be relaxed by adding wide-band Gaussian noise to the input signal. In addition, taking an orthogonal frequency division multiplexing receiver using one-bit quantizers as a practical example, we compare the theoretical analysis with simulation results in terms of power spectral density and bit error rate, and we demonstrate that the derived theoretical analysis results are valid.

Bunyakovsky conjecture is proved to be true.

Legendre's conjecture is proved to be true.

Early diagnosis and accurate judgment are paramount in cancer diagnosis and treatment. Establishing an effective cancer early warning system is crucial to improve patient outcomes. Data mining technology, particularly association rule mining, plays a vital role in cancer surveillance and early warning by processing large datasets. Our study focuses on lung cancer, one of the leading causes of death worldwide. Despite numerous approaches, challenges such as high computational costs and memory limitations persist when attempting to extract meaningful rules from databases. In this paper, we propose leveraging the Apriori algorithm within the Apollo framework, based on the Apollo multicloud orchestration framework developed by the University of Innsbruck, for distributed association rule mining. By harnessing serverless functions, we achieve distributed processing, enhancing scalability and performance. Our experiments demonstrate that Apollo outperforms Apache Spark in terms of speed (about 15 percent), and extracts more rules. The results highlight the efficacy of distributed association rule mining using serverless functions for cancer early warning systems. We conclude that this approach shows promise and warrants further exploration and extension in future research endeavors.

In this paper, a novel miniaturized symmetrical hexagonal shaped substrate integrated waveguide (SIW) cavitybacked antenna with 3D dielectric lens loading is presented. The compact antenna achieves high gain, high isolation and wideband with a miniaturized layout. The proposed antenna has a 10-dB bandwidth of 27.9 to 29 GHz and was achieved using a pair of parallel slots on top of the SIW cavity. The proposed miniaturized design offers a simulated gain of 6.5 dBi which was then enhanced to 18.5 dBi at 28.4 GHz with the integration of a 3D-printed dielectric homogeneous lens. The cavity backed lens antenna is used to realize a 4×4 multiple input multiple output (MIMO) antenna structure. The 4×4 MIMO SIW lens antenna has isolation below-30 dB (between the four antenna elements) throughout the frequency band of operation. The measured results are in good agreement with Ansys HFSS simulations. The stable antenna performance makes it suitable for applications in satellite, radar imaging, and point to multi-point wireless communications.