Search

Traumatic brain injuries (TBI) are considered a silent epidemic. It affects many people, from automobiles to sports to service members. In this study, we employed a musculoskeletal head-neck model to understand the effect of impact locations, characteristics, and neck strength on head and neck injury severity. Three types of impact forces were studied: low-velocity impact (LVI), intermediate-velocity impact (IVI), and high-velocity impact (HVI). We investigated six parameters: linear and rotational accelerations, the Generalized Acceleration Model For Brain Injury Threshold (GAMBIT), neck force, neck moment, and Neck Injury Criteria (NIC). We consider seven impact locations, three neck strengths, and three impact characteristics. We studied a total of 63 cases. It was found that the linear accelerations do not change much with different neck strengths and impact locations. The impact locations have a significant effect on head and neck injury parameters, and anterolateral impact is the most risky impact location for both head and neck. The maximum average rotational acceleration is for anterolateral eccentric impact which is 4.75 times more than the average anterior central impact. The lateral impacts generate about 10% more linear accelerations than anterior and posterior impacts. Neck forces do not vary more than 20% with impact locations and neck strength. The average head and neck injury parameters do not vary more than 10% based on neck strength. Impact characteristics have a significant role in GAMBIT and NIC. The average GAMBIT for IVI and HVI were 1.44 and 1.54 times higher than LVI. In summary, the anterolateral eccentric impact has a higher probability of head and neck injury than the other six impact locations. These findings provide objective evidence that can inform injury prevention strategies as well as aid tissue and cellular level studies.

Aligning Large Language Models (LLMs) traditionally relies on costly training and human preference annotations. Self-alignment seeks to reduce these expenses by enabling models to align themselves. To further lower costs and achieve alignment without any expensive tuning or annotations, we introduce a new tuning-free approach for self-alignment, Dynamic Rewarding with Prompt Optimization (DRPO). Our approach leverages a search-based optimization framework that allows LLMs to iteratively self-improve and craft the optimal alignment instructions, all without additional training or human intervention. The core of DRPO is a dynamic rewarding mechanism, which identifies and rectifies model-specific alignment weaknesses, allowing LLMs to adapt efficiently to diverse alignment challenges. Empirical evaluations on eight recent LLMs, both open- and closed-sourced, demonstrate that DRPO significantly enhances alignment performance, with base models outperforming their SFT/RLHF-tuned counterparts. Moreover, the prompts automatically optimized by DRPO surpass those curated by human experts, further validating the effectiveness of our approach. Our findings highlight the great potential of current LLMs to achieve adaptive self-alignment through inference-time optimization, complementing tuning-based alignment methods., Comment: EMNLP 2024 Main

As Systems of Systems evolve into increasingly complex networks, harnessing their collective potential becomes paramount. Traditional SoS engineering approaches lack the necessary programmability to develop third party SoS level behaviors. To address this challenge, we propose a software defined approach to enable flexible and adaptive programming of SoS. We introduce the Holon Programming Model, a software-defined framework designed to meet these needs. The Holon Programming Model empowers developers to design and orchestrate complex system behaviors effectively, as illustrated in our disaster management scenario. This research outlines the Holon Programming Model theoretical underpinnings and practical applications, with the aim of driving further exploration and advancement in the field of software defined SoS

Hyperentangled states are highly efficient and resource economical. This is because they enhance the quantum information encoding capabilities due to the correlated engagement of more than one degree of freedom of the same quantum entity while keeping the physical resources at their minimum. Therefore, initially the photonic hyperentangled states have been explored extensively but the generation and respective manipulation of the atomic counterpart states are still limited to only few proposals. In this work, we propose a new and feasible scheme to engineer the atomic hyperentangled cluster and ring graph states invoking cavity QED technique for applicative relevance to quantum biology and quantum communications utilizing the complex quantum networks. These states are engineered using both external quantized momenta states and energy levels of neutral atoms under off-resonant and resonant Atomic Bragg Diffraction (ABD) technique. The study of dynamical capacity and potential efficiency have certainly enhanced the range of usefulness of these states. In order to assess the operational behavior of such states when subjected to a realistic noise environment has also been simulated, demonstrating long enough sustainability of the proposed states. Moreover, experimental feasibility of the proposed scheme has also been elucidated under the prevailing cavity-QED research scenario., Comment: Submitted to Physica Scripta

Recent innovations in language model training have demonstrated that it is possible to create highly performant models that are small enough to run on a smartphone. As these models are deployed in an increasing number of domains, it is critical to ensure that they are aligned with human preferences and safety considerations. In this report, we present our methodology for safety aligning the Phi-3 series of language models. We utilized a "break-fix" cycle, performing multiple rounds of dataset curation, safety post-training, benchmarking, red teaming, and vulnerability identification to cover a variety of harm areas in both single and multi-turn scenarios. Our results indicate that this approach iteratively improved the performance of the Phi-3 models across a wide range of responsible AI benchmarks. Finally, we include additional red teaming strategies and evaluations that were used to test the safety behavior of Phi-3.5-mini and Phi-3.5-MoE, which were optimized for multilingual capabilities.

Accurately estimating the position of a patient's side robotic arm in real time in a remote surgery task is a significant challenge, particularly in Tactile Internet (TI) environments. This paper presents a Kalman Filter (KF) based computationally efficient position estimation method. The study also assume no prior knowledge of the dynamic system model of the robotic arm system. Instead, The JIGSAW dataset, which is a comprehensive collection of robotic surgical data, and the Master Tool Manipulator's (MTM) input are utilized to learn the system model using System Identification (SI) toolkit available in Matlab. We further investigate the effectiveness of KF to determine the position of the Patient Side Manipulator (PSM) under simulated network conditions that include delays, jitter, and packet loss. These conditions reflect the typical challenges encountered in real-world Tactile Internet applications. The results of the study highlight KF's resilience and effectiveness in achieving accurate state estimation despite network-induced uncertainties with over 90\% estimation accuracy., Comment: 8 pages, 5 figures, [IWCMC 2024 AI-NECOS]

In this work, an advanced deep reinforcement learning architecture is used to train neural network agents playing atari games. Given only the raw game pixels, action space, and reward information, the system can train agents to play any Atari game. At first, this system uses advanced techniques like deep Q-networks and dueling Q-networks to train efficient agents, the same techniques used by DeepMind to train agents that beat human players in Atari games. As an extension, plastic neural networks are used as agents, and their feasibility is analyzed in this scenario. The plasticity implementation was based on backpropagation and the Hebbian update rule. Plastic neural networks have excellent features like lifelong learning after the initial training, which makes them highly suitable in adaptive learning environments. As a new analysis of plasticity in this context, this work might provide valuable insights and direction for future works.

Phishing emails continue to pose a significant threat, causing financial losses and security breaches. This study addresses limitations in existing research, such as reliance on proprietary datasets and lack of real-world application, by proposing a high-performance machine learning model for email classification. Utilizing a comprehensive and largest available public dataset, the model achieves a f1 score of 0.99 and is designed for deployment within relevant applications. Additionally, Explainable AI (XAI) is integrated to enhance user trust. This research offers a practical and highly accurate solution, contributing to the fight against phishing by empowering users with a real-time web-based application for phishing email detection., Comment: 19 pages, 7 figures, dataset link: https://www.kaggle.com/datasets/naserabdullahalam/phishing-email-dataset/

In the 6G era, integrating Mobile Edge Computing (MEC) and Digital Twin (DT) technologies presents a transformative approach to enhance network performance through predictive, adaptive control for energy-efficient, low-latency communication. This paper presents the EcoEdgeTwin model, an innovative framework that harnesses the synergy between MEC and DT technologies to ensure efficient network operation. We optimize the utility function within the EcoEdgeTwin model to balance enhancing users' Quality of Experience (QoE) and minimizing latency and energy consumption at edge servers. This approach ensures efficient and adaptable network operations, utilizing DT to synchronize and integrate real-time data seamlessly. Our framework achieves this by implementing robust mechanisms for task offloading, service caching, and cost-effective service migration. Additionally, it manages energy consumption related to task processing, communication, and the influence of DT predictions, all essential for optimizing latency and minimizing energy usage. Through the utility model, we also prioritize QoE, fostering a user-centric approach to network management that balances network efficiency with user satisfaction. A cornerstone of our approach is integrating the advantage actor-critic algorithm, marking a pioneering use of deep reinforcement learning for dynamic network management. This strategy addresses challenges in service mobility and network variability, ensuring optimal network performance matrices. Our extensive simulations demonstrate that compared to benchmark models lacking DT integration, EcoEdgeTwin framework significantly reduces energy usage and latency while enhancing QoE.

The complexity and dynamic nature of System of Systems (SoS) necessitate efficient communication mechanisms to ensure interoperability and collaborative functioning among constituent systems, termed holons. This paper proposes an innovative approach to enhance holon communication within SoS through the integration of Conversational Generative Intelligence (CGI) techniques. Our approach leverages advancements in CGI, specifically Large Language Models (LLMs), to enable holons to understand and act on natural language instructions. This fosters more intuitive human-holon interactions, improving social intelligence and ultimately leading to better coordination among diverse systems. This position paper outlines a conceptual framework for CGI-enhanced holon interaction, discusses the potential impact on SoS adaptability, usability and efficiency, and sets the stage for future exploration and prototype implementation., Comment: Preprint accepted in ICSOFT'24

Massive multiple input multiple output (M-MIMO) technology plays a pivotal role in fifth-generation (5G) and beyond communication systems, offering a wide range of benefits, from increased spectral efficiency (SE) to enhanced energy efficiency and higher reliability. However, these advantages are contingent upon precise channel state information (CSI) availability at the base station (BS). Ensuring precise CSI is challenging due to the constrained size of the coherence interval and the resulting limitations on pilot sequence length. Therefore, reusing pilot sequences in adjacent cells introduces pilot contamination, hindering SE enhancement. This paper reviews recent advancements and addresses research challenges in mitigating pilot contamination and improving channel estimation, categorizing the existing research into three broader categories: pilot assignment schemes, advanced signal processing methods, and advanced channel estimation techniques. Salient representative pilot mitigation/assignment techniques are analyzed and compared in each category. Lastly, possible future research directions are discussed., Comment: Accepted At IWCMC 2024 Comm & SP Symposium

Earth system predictability is challenged by the complexity of environmental dynamics and the multitude of variables involved. Current AI foundation models, although advanced by leveraging large and heterogeneous data, are often constrained by their size and data integration, limiting their effectiveness in addressing the full range of Earth system prediction challenges. To overcome these limitations, we introduce the Oak Ridge Base Foundation Model for Earth System Predictability (ORBIT), an advanced vision transformer model that scales up to 113 billion parameters using a novel hybrid tensor-data orthogonal parallelism technique. As the largest model of its kind, ORBIT surpasses the current climate AI foundation model size by a thousandfold. Performance scaling tests conducted on the Frontier supercomputer have demonstrated that ORBIT achieves 684 petaFLOPS to 1.6 exaFLOPS sustained throughput, with scaling efficiency maintained at 41% to 85% across 49,152 AMD GPUs. These breakthroughs establish new advances in AI-driven climate modeling and demonstrate promise to significantly improve the Earth system predictability.

Vision Transformers (ViTs) are pivotal for foundational models in scientific imagery, including Earth science applications, due to their capability to process large sequence lengths. While transformers for text has inspired scaling sequence lengths in ViTs, yet adapting these for ViTs introduces unique challenges. We develop distributed sequence parallelism for ViTs, enabling them to handle up to 1M tokens. Our approach, leveraging DeepSpeed-Ulysses and Long-Sequence-Segmentation with model sharding, is the first to apply sequence parallelism in ViT training, achieving a 94% batch scaling efficiency on 2,048 AMD-MI250X GPUs. Evaluating sequence parallelism in ViTs, particularly in models up to 10B parameters, highlighted substantial bottlenecks. We countered these with hybrid sequence, pipeline, tensor parallelism, and flash attention strategies, to scale beyond single GPU memory limits. Our method significantly enhances climate modeling accuracy by 20% in temperature predictions, marking the first training of a transformer model on a full-attention matrix over 188K sequence length.

5G sets the foundation for an era of creativity with its faster speeds, increased data throughput, reduced latency, and enhanced IoT connectivity, all enabled by Massive MIMO (M-MIMO) technology. M-MIMO boosts network efficiency and enhances user experience by employing intelligent user scheduling. This paper presents a user scheduling scheme and pilot assignment strategy designed for IoT devices, emphasizing mitigating pilot contamination, a key obstacle to improving spectral efficiency (SE) and system scalability in M-MIMO networks. We utilize a user clustering-based pilot allocation scheme to boost IoT device scalability in M-MIMO systems. Additionally, our smart pilot allocation minimizes interference and enhances SE by treating pilot assignment as a graph coloring problem, optimizing it through integer linear programming (ILP). Recognizing the computational complexity of ILP, we introduced a binary search-based heuristic predicated on interference threshold to expedite the computation, while maintaining a near-optimal solution. The simulation results show a significant decrease in the required pilot overhead (about 17%), and substantial enhancement in SE (about 8-14%)., Comment: Accepted At ICC-2024