6G networks aim to facilitate the global sustainability drive. However, sustainability of 6G networks itself will pose major research questions due to the increasing number of devices, systems, and services that can exacerbate the consumption of key resources. In this work, we focus our investigation to 6G security, since sustainability is mostly overlooked when it comes to security. Emerging security technologies which are highly dependent on developing concepts in the realm of security such as AI and blockchain require huge amounts of resources. This article aims to stir further research on sustainability of 6G security through highlighting the main research challenges and future research directions in this domain.

Using advanced data mining techniques, specifically association rule mining (ARM) and clustering, this study presents a novel approach to maritime CO2 emissions analysis, revealing hidden patterns and relationships that traditional statistical models cannot capture. Various ship types can be analyzed for operational and technical efficiency to provide actionable insights into reducing emissions. In addition, robust cybersecurity measures are integrated to ensure the integrity and reliability of the data, allowing compliant and secure decision-making. The findings indicate that oil tankers and LNG carriers, which emit significant amounts of pollution, are prime candidates for retrofitting and implementing cleaner technologies in the near future.

A critical component for advancing driving automation is trajectory prediction, which enables vehicles to navigate complex driving scenarios and make informed decisions in unfamiliar environments. However, training models exclusively on trajectory supervision presents significant challenges for trajectory prediction in autonomous systems. We propose a Velocity-Angle Trajectory Network (VATNet), an integrated approach that enhances trajectory prediction tasks with an additional velocity prediction and angle prediction task in a multi-task learning framework. This assists the model in cross-validating and correcting errors in trajectory prediction, leveraging temporal relationships and directional context to achieve more reliable outcomes. To address the challenges posed by the periodic nature of angles, we use a classification approach. This method discretizes angles into bins and focuses on probability distributions rather than precise values, thereby reducing numerical instability associated with regression. To mitigate the issue of overfitting to any single task, we introduce an uncertainty-aware weighted loss that dynamically assigns higher priority to tasks identified as challenging or uncertain. The VATNet model has been evaluated on Argoverse 2 dataset and outperforms state-of-the-art models by a margin of 3.76%-33.83%, 5.68%-42.97%, 11.84%-90.78% and 0.37%-29.73% on the minADE6, minFDE6, MR6 and b-FDE6 respectively.

Understanding brain dynamics during motor tasks is a significant challenge in neuroscience, often limited to studying pairwise interactions. This study provides a comprehensive hierarchical characterization of node-specific, pairwise and higher-order interactions within the human brain's motor network during handgrip task execution. Methods: The cortical activity was reconstructed from the scalp EEG signals of ten healthy subjects performing a motor task, identifying five brain regions within the contralateral and ipsilateral motor networks. Using the spectral entropy rate as the basis for the decomposition of dynamic information in the alpha and beta frequency bands, we assessed the predictability of the individual rhythms within each brain region, the information shared between the activity of pairs of regions, and the higher-order interactions among groups of signals from more than two regions. Results: An overall decrease in hierarchical interactions at various orders within the motor network is observed during motor task execution, primarily in the alpha frequency band, due to the well-known sensorimotor mu rhythm. Conclusions and Significance: This work emphasizes the importance of examining brain interactions at multiple levels within the frequency domain using a unified framework which fully captures the complex dynamics of the motor network highlighting the critical role of its hierarchical organization.

The "No Free Lunch" (NFL) theorem in machine learning asserts that there is no universal algorithm or model that excels across all possible problem instances. In the context of machine learning applications for stock market prediction, this theorem implies that no single predictive model can consistently outperform others under all market conditions. The NFL theorem, introduced by David Wolpert in 1996, emphasizes the importance of considering the specific characteristics of the problem domain. In this paper, we extend the NFL Theorem as "No Free Money(NFM) Theorem for Machine learning applications in stock market predictions. The data gathered from Machine Learning competition for stock market prediction are utilized for providing experimental evidence for NFM theorem. For stock market prediction, the NFM theorem underscores the need for tailored approaches, acknowledging that the effectiveness of machine learning models is contingent on factors such as market dynamics, economic conditions, and the quality of historical data. It cautions against assuming a one-size-fits-all solution and highlights the challenge of developing models that generalize well to diverse and evolving market scenarios. The theorem prompts practitioners to approach stock market prediction with a realistic understanding of the limitations inherent in algorithmic approaches, encouraging careful consideration of the data, features, and context relevant to each specific application.

A new 2 parameter unit Weibull distribution is defined on the unit interval (0,1). The methodology of deducing its PDF, some of its properties and related functions are discussed. The paper is supplied by many figures illustrating the new distribution and how this can make it illegible to fit a wide range of skewed data. The new distribution holds a name (Attia) as a nickname.

This study aims to categorize the following dogs' primary emotional states: anger, fear, and happiness. The research team utilized Transfer Learning (TL) and advanced 2D/3D Convolutional Neural Networks (CNNs) to identify these emotions from two small datasets-static images and video clips. The image dataset covers various canine emotional expressions across various contexts, forming the basis for the training of Dog Emotion Recognition-Transfer Learning Neural Network (DER-TLNN) algorithm. DER-TLNN has an accuracy rate of 70% for emotion classification based on static images (400 images). In addition, DER-TLNN is the basis for the Video Dog Emotion Recognition Network (VDERNet) algorithm, which is designed to categorize video clips depicting dogs' emotional states. Trained on video data sourced online (39 videos), VDERNet achieves an accuracy of 96%, highlighting AI's potential in understanding canine emotions in dynamic contexts with non-invasive techniques. These findings demonstrate the efficacy of TL and 3D CNNs in animal behavior analysis and contribute to a better understanding of canine emotions. The research provides promising applications in improving human-dog interactions and enhancing canine welfare, showcasing the immense potential of AI in animal behavior studies. The achievement of notable results with small datasets, along with data augmentation and regularization techniques, underscores our innovative approach and the potential impact of AI in animal behavior studies.

This study introduces a novel transformer architecture that integrates Gaussian Attention, adapter modules, and Rotary Position Embeddings (RoPE) to enhance efficiency in natural language processing tasks. Preliminary experiments with a low-quality dataset demonstrated the model's ability to generate responses, though the output lacked coherence and relevance. These findings highlight the necessity for further training on high-quality datasets, which is currently hindered by limited computational resources. Consequently, this research seeks collaborative opportunities and funding to facilitate comprehensive pretraining and fine-tuning of the model, aiming to develop efficient and effective language models accessible to researchers with constrained capabilities.

Integrated Sensing and Communication (ISAC) technology is pivotal in advancing multifunctional radio applications for nextgeneration wireless communications. One of the primary challenges in ISAC systems lies in understanding and interpreting wireless channels for both sensing and communication purposes. A clear relationship between these channels would allow ISAC systems to reduce channel estimation complexity. This paper introduces a comprehensive framework for reconstructing communication channels using monostatic sensing channels within an ISAC system. We first consider the frequency spacing of an ISAC system to geometrically illustrate the synergies and differences between the sensing and communication regions. Subsequently, we construct a communication propagation channel based on overlap determined by this geometric relationship and a simplified monostaticto-bistatic equivalence theorem. Lastly, we combine multipaths located in the same delay bin to construct channel state information (CSI), taking bandwidth limitation into account. Simulations demonstrate that the proposed framework efficiently generates communication channels across various configurations, with numerical results highlighting the impacts of environmental and system constraints on key channel characteristics.

This manuscript summarizes work on the Capsule Vision Challenge 2024 by MISAHUB. To address the multi-class disease classification task, which is challenging due to the complexity and imbalance in the Capsule Vision challenge dataset, this paper proposes CASCRNet (Capsule endoscopy-Aspp-SCR-Network), a parameter-efficient and novel model that uses Shared Channel Residual (SCR) blocks and Atrous Spatial Pyramid Pooling (ASPP) blocks. Further, the performance of the proposed model is compared with other well-known approaches. The experimental results yield that proposed model provides better disease classification results. The proposed model was successful in classifying diseases with an F1 Score of 78.5% and a Mean AUC of 98.3%, which is promising given its compact architecture.

The limitations of fifth generation (5G) networks in simultaneously addressing the growing demands of diverse applications, including ultra-reliable low-latency communication (URLLC), massive machine-type communication (mMTC), and high-throughput services, drive the exploration of 6G technologies. Given the multifaceted nature of 6G use cases and the proliferation of edge functions, such as computing nodes, charging nodes, and sensing targets, selecting an optimal multiple access (MA) technique becomes paramount. This article reviews the literature to identify key milestones and insights from the recent progression of MA technology, exploring robust research directions and optimization aspects of developing an intelligent, unified MA framework for 6G. The article examines promising access schemes such as rate-splitting multiple access (RSMA) and non-orthogonal multiple access (NOMA) and discusses the pivotal role of the latest paradigms, such as artificial intelligence (AI) and Open radio access network (RAN), in optimizing the MA framework.

Wireless sensor networks (WSNs) were originally envisioned to consist of a massive number of diminutive, lowcost, and long-life wireless sensors. However, this vision has faced significant obstacles, particularly in transferring sensing information to data centers. This article proposes a novel protocol, termed relaying-as-a-service (RaaS), to leverage public smart devices to relay sensing information to data centers. By offloading major communications and networking operations to these more powerful smart devices and well-developed fifth generation (5G) or sixth generation (6G) networks, the size and cost of sensors can be significantly reduced, and the need for extensive network infrastructure can be eliminated. This reduction in complexity can greatly streamline the development and implementation of WSNs and Internet of Things (IoT) solutions. Furthermore, using low-power sensors enables large-scale frequency-reuse, which can help alleviate the load on the already congested spectrum.

Quantum computing is poised to revolutionize computational performance and capabilities, offering unprecedented efficiency in solving complex problems that surpasses classical approaches. This potential is particularly evident in fields such as optimization and AI. This chapter delves into critical priority areas in quantum computing, including the development and application of quantum software tools. We place a strong emphasis on reimagining the use of quantum computing for modeling and simulation, sensing, and secure communication. Furthermore, we explore current trends like quantum communications for 6G networks, quantum cloud and serverless computing, scalable qubit arrays, and the pursuit of robust and reliable quantum systems. Lastly, we address emerging research areas and the open challenges ahead, encompassing advancements in foundational theory, education, ethical and societal considerations, and pathways to commercialization.

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder that adversely affects the healthy development of children. The current clinical diagnosis of ASD relies on demographics and descriptions of clinical symptoms and assessments based on rating scales, which are both time-consuming and subjective. Previous research reported atypical visual patterns exhibited by ASD children, implying that eye-tracking could be a potential tool to assist in distinguishing ASD from others. However, most studies only examined a singular dimension of visual trajectory, neglecting the possible use of comprehensive information on eye scan paths. Given this, the present study introduced the FF-ASDNET - a framework designed for the automated screening of ASD individuals leveraging eye-tracking technologies in conjunction with deep representation learning and multi-scale feature fusion. Eye movement trajectory was first objectively quantified from multi-scale perspectives, including Gaze Movements (GM), Spatial Attention Distribution (SAD), and Temporal Visual Information (TVI). The residual network (ResNet) and the rectangular residual convolutional temporal network (RecResTCNN) were then proposed to learn the features of the three representations. Finally, the features of the three scales were fused using a convolutional neural network. The proposed design achieved an AUC of 85.96% and an F1 score of 0.85 on an independent dataset, showing that fusing multi-scale representations of eye scan trajectories could significantly improve the model’s performance, rendering the development of an automated ASD screening plausible. In summary, FF-ASDNET is a promising tool for screening ASD individuals, with potential applications in clinical diagnosis and intervention.

Ransomware continues to pose a significant threat to global cybersecurity, with increasingly sophisticated variants that can evade traditional detection methods. Dynamic Code Sequence Mapping (DCSM) offers a novel solution that addresses this challenge through the real-time monitoring of execution behavior, allowing for the detection of ransomware based on its dynamic characteristics rather than relying on static signatures. DCSM operates through a modular framework that analyzes code sequences, identifies patterns associated with ransomware activity, and triggers protective measures before the malware can execute its payload. Extensive testing has demonstrated the system's ability to maintain high detection accuracy, even in the presence of advanced evasion techniques such as code obfuscation and polymorphism, while minimizing false positives. Moreover, DCSM's adaptability and integration potential within existing cybersecurity infrastructures make it a versatile tool capable of responding to the continuously evolving ransomware landscape. The overall impact of DCSM lies in its ability to enhance ransomware detection capabilities, providing a more resilient and adaptive approach to mitigating one of the most persistent threats in modern cybersecurity.

Due to the inherent complexity arising from powertrain, aerodynamic, and unseen driving scenarios, efficient coordination of connected hybrid electric vehicles (C-HEVs) platooning encounters complex challenges. Existing studies primarily do not consider thermal load impacts. However, this overlooks the interconnection between the C-HEVs related to powertrain power and thermal loads, which can hinder effective optimization and collaboration across C-HEV platoon members. To fully address this gap, a multi-agent deep reinforcement learning (DRL)-based joint cooperative adaptive cruise control (CACC) with an integrated thermal and energy management (ITEM) framework is proposed. Additionally, to decrease the sample complexity and accelerate policy learning, the vehicle-level (string stability and time headway) and powertrain-level (energy consumption and health indicator) information are integrated into the reward function to design a safety-and physics-informed DRL framework. To meticulously assess the mutual impact of thermal load and management on the platooning optimization problem, air drag and airflow reductions related to inter-vehicle distance (IVD) are accounted for with a high-fidelity model provided by Autonomie. Numerical and hardware-in-the-loop (HIL) experiments demonstrate that the proposed CACC+ITEM algorithm outperforms the classic DRL version in stability, energy-saving, driving comfort, and battery longevity.

In an era of growing security concerns, with the context of Ad hoc wireless communication which is common in the domain of Internet of Things (IoT) or remote areas where Internet is not a viable option, establishing trust between two entities is challenging. Not only the protocol should be formidable to deny connection for untrusted entities but also cost-effective and practically viable. This paper demonstrates how zero-trust framework can be employed in ad hoc wireless communications through a surveillance robot with remote control and live video stream. We achieve zero-trust connection using mutual-Transport Layer Security (mTLS) protocol between the endpoints. This secure connection is then used to exchange control messages for robot movement and for the live video stream. The endpoints communicate over Ad hoc Wi-Fi and hence there is no need for router or Wi-Fi access points or internet. Since Wi-Fi has limited range, this work can be further extended over long-distance communication where a network of Ad Hoc peers employs a routing protocol for transfer of packets between two endpoints within their network.

The increasing complexity of linguistic tasks has driven a need for more adaptable and contextually aware language models, capable of producing accurate and coherent outputs even when faced with ambiguous or evolving input. Traditional token embedding methods, which rely on static representations, often fall short in capturing the complex relationships between tokens and their contextual dependencies. Introducing a novel approach, Dynamic Token Embedding Sampling (DTES), allows embeddings to be dynamically adjusted during inference based on the evolving input sequence, offering a significant improvement in predictive accuracy and reduction in hallucinations. Through seamless integration into transformer architectures, DTES enhances both the flexibility and efficiency of token processing, ensuring more precise and contextually relevant outputs across various natural language processing tasks. Experimental results demonstrate considerable improvements in key metrics, including accuracy, inference speed, and factual consistency, further highlighting the potential of DTES to optimize language models for real-world applications. The method's scalability and adaptability across diverse linguistic domains make it a compelling advancement in the ongoing effort to improve the performance and reliability of language models in increasingly complex environments.