This paper introduces GPT-Neo-CRV, a novel adaptation of the GPT-Neo 1.5B model, incorporating a Cross-Referential Validation (CRV) module to significantly enhance the accuracy and reliability of information generated by Large Language Models (LLMs). GPT-Neo-CRV addresses the critical challenge of misinformation in LLM outputs, a growing concern in fields where precision and reliability of information are crucial. Through rigorous testing against the BIG-bench categories, GPT-Neo-CRV demonstrated marked improvements in tasks requiring factual correctness and complex reasoning, surpassing the standard GPT-Neo model. This study delves into the implications of these advancements, potential limitations, and the ethical considerations inherent in integrating factual validation mechanisms into LLMs. It highlights the need for comprehensive, unbiased, and ethically curated validation sources and emphasizes the importance of ongoing research in enhancing LLMs' adaptability, scalability, and ethical integrity. The development of GPT-Neo-CRV represents a significant step forward in the AI field, contributing to a more informed and truthful digital landscape and setting new standards for future LLM developments.

This paper proposes a direct data interpolation method for predicting ferrite core loss in power electronics. The core idea is to accurately construct the B-H loop shape given arbitrary Hfield waveforms. Unlike conventional loss models like the Steinmetz equation and its variations, or recent neural network methods like MagNet that leverage periodic B-H waveforms and frequencies, this method employs a data segmentation and reconstruction process to fully exploit the distinctive features of the B-H loop under varying conditions. The source data is from Princeton University's MagNet open-source datasets.

The nascent tokenized assets industry needs to develop standards around asset definition schemas that permit each industry or vertical to create profiles based on the schemas that are specific for addressing the needs of that industry. Machine-readable asset schemas and profiles are a core element of a proper tokenized assets management lifecycle. As metadata artifacts supporting tokenization, they must be managed as part of the lifecycle. A global network of decentralized registries is needed to provide persistence and accessibility to the published asset schemas and profiles. The notion of schemas, profiles, and registries aligns with the asset-referenced tokens (ART) in the recent EU MiCA Regulation on markets in crypto-assets.

In the evolving domain of autonomous vehicles, the importance of decision-making cannot be overstated. Deep Reinforcement Learning emerges as a pivotal tool in this landscape. However, traditional DRL algorithms grapple with inaccuracies in Q-value estimation, predominantly due to system noise and function approximation errors. Such inaccuracies, coupled with real-world unpredictabilities, often misdirect autonomous vehicles, jeopardizing safety. This work introduces a novel DRL algorithm tailored for uncertainty and noise-aware decisionmaking in autonomous vehicles. This novel approach harnesses Bayesian Neural Networks (BNN) and skew-geometric Jensen-Shannon divergence, rectifying the aforementioned limitations and also improving exploration. Evaluated in the OpenAI gymnasium environment, the algorithm has clear advantages over contemporary methods in terms of cumulative rewards and convergence speed.

Large Language Models (LLMs) have shown their capabilities in solving tasks across various domains. Recently, they have found applications in automating the design of digital circuits. However, there remains a dearth of research investigating the use of LLMs in automating the design of analog circuits. In this work, we propose LADAC: Large Language Model-driven Auto-Designer for Analog Circuits, to assist analog circuit design. LADAC designates an LLM as a decision-making agent, which formulates optimized design strategies based on user specifications and foundational principles of analog circuit design expertise. We applied LADAC to design two kinds of amplifiers with open-loop gain over 80dB, and a ring oscillator with 100MHz oscillation frequency successfully, showing that LADAC is capable of designing analog circuits. Furthermore, it demonstrates the LLMs' potential for designing a broader range of analog circuits.

In the field of dentistry, there is a growing demand for increased precision in diagnostic tools, with a specific focus on advanced imaging techniques such as computed tomography, cone beam computed tomography, magnetic resonance imaging, ultrasound, and traditional intra-oral periapical X-rays. Deep learning has emerged as a pivotal tool in this context, enabling the implementation of automated segmentation techniques crucial for extracting essential diagnostic data. This integration of cutting-edge technology addresses the urgent need for effective management of dental conditions, which, if left undetected, can have a significant impact on human health. The impressive track record of deep learning across various domains, including dentistry, underscores its potential to revolutionize early detection and treatment of oral health issues. Objective: Having demonstrated significant results in diagnosis and prediction, deep convolutional neural networks (CNNs) represent an emerging field of multidisciplinary research. The goals of this study were to provide a concise overview of the state of the art, standardize the current debate, and establish baselines for future research. Method: In this study, a systematic literature review is employed as a methodology to identify and select relevant studies that specifically investigate the deep learning technique for dental imaging analysis. This study elucidates the methodological approach, including the systematic collection of data, statistical analysis, and subsequent dissemination of outcomes. Results: In incorporating 45 studies, we identified selection criteria and research objectives, addressing significant gaps in the existing literature. These studies assist clinicians in examining dental conditions and classifying dental structures, including caries detection and the identification of various tooth types. We evaluated model performance, addressing the identified gaps, using diverse metrics that we strive to list and explain. Conclusion: This work demonstrates how Convolutional Neural Networks (CNNs) can be employed to analyze images, serving as effective tools for detecting dental pathologies. Although this research acknowledged some limitations, CNNs utilized for segmenting and categorizing teeth exhibited their highest level of performance overall.

Environmental movements of the late 20th century resulted in sweeping legislation and regulatory actions to reduce the prevalence of diverse pollutants. Although the consequences of noise pollution to public health, the environment, and the economy have been recognized over the same time period, noise has received far less policy attention. Correspondingly, even while recent decades have seen robust advancements in assessing the impacts of noise pollution, solutions and actual reductions in environmental noise have remained seemingly out of reach. To address this shortcoming, we developed a prospectus for environmental noise reduction through technology-forcing policies. Technology-forcing describes intent to encourage technological solutions for pollution control through policy and regulations, and has been a critical component of national and global progress in reducing environmental pollutants. We take advantage of the unique policy history for noise in the United States - which initially enacted, but then abandoned federal noise regulation. We compare this history against outcomes from contemporaneous environmental legislation for air, water, and occupational pollution control, to demonstrate the potential for technology-forcing to reduce noise pollution. Our review then identifies promising solutions, in the form of existing technologies suitable for innovation and diffusion through technology-forcing regulations and incentives. Based on this review, we outline a program for noise policy development that is intended to support efforts to reduce environmental noise pollution worldwide. The proposed program consists of three steps, 2 which are to (i) identify dominant sources of noise pollution, (ii) combine legislative or regulatory provisions with suitable systems of enforcement and incentives, and (iii) anticipate and prepare for stages of technological change. This work is intended to support and advocate for noise policies designed around technology-forcing, to advance technologies that not only improve public health and sustainable development, but ensure that these benefits are distributed equitably.

The current large language models (LLMs) mainly lacks this capability: answering  high-precision questions/prompts. LLMs is actually a powerful fuzzy memory system that makes it difficult to answer high-precision questions. The results of code execution is a kind of high-precision answer. And expert system applications need to answer these kinds of questions. In this paper, to solve the above problem, We propose a design of LLMs combined with the text2code approach.

Designing Brain Computer Interfaces (BCIs), for helping patients, needs appropriate datasets which are relevant for the language of the patients. There exists a significant shortage of datasets for Indian languages that can be used for BCI research. Malayalam is a prominent south Indian language spoken by more than 34 million people, yet, there exist no BCI datasets for research. We address this issue by creating a dataset for selected Malayalam words by collecting Electro Encephalograph (EEG) signal samples. Our dataset was created by generating EEG samples using the OpenBCI Cyton device when the commonly used Malayalam words were spoken by a volunteer. The created dataset consists of three major types of data: (i) EEG data for spoken Malayalam words, (ii) EEG data for the spoken English words which were closest to the English translation of the corresponding Malayalam words, and (iii) EEG data for sub-vocal (silent) pronunciation of the Malayalam words. We created the dataset for 26 words where each of these words had been recorded for the above mentioned three types. For each word, 10 EEG samples over 8 channels were recorded. This dataset is useful for developing BCI solutions for patients suffering from neuro-degenerative diseases by developing Machine Learning (ML) classifiers for translating EEG-signals to Malayalam words, vocal or sub-vocal, especially considering the scarcity of datasets available in Indian languages.

This paper presents a comprehensive review of the robustness of hand gesture recognition systems in low light intensity environments spanning the years 2018 to 2023. The primary objective is to assess the progress made during this period and identify areas requiring further attention. An extraction of 20 relevant journals from reputable online databases was conducted using selected keywords. Most of the reviewed articles delve into three crucial aspects of hand gesture recognition systems: data acquisition, data environment, and hand gesture representation. The system performance evaluation reveals that machine learning models achieve recognition accuracy between 94% and 98%, while computer vision models report accuracy within the range of 90% to 95%. The deep learning approach shows a broader accuracy range, spanning from 90% to 98%. Notably, the studies reviewed utilized datasets comprising 37 hand gestures, including 26 letters of American Sign Language (ASL) and numeric gestures ranging from 0 to 9. This paper sheds light on the current state of hand gesture recognition in low light environments and provides insights into potential opportunities for further research and development.

In this paper, we consider an unmanned aerial vehicle (UAV) assisted communications system, including two cooperative UAVs, a wireless-powered ground destination node leveraging simultaneous wireless information and power transfer (SWIPT) technique, and a terrestrial passive eavesdropper. One UAV delivers confidential information to destination and the other sends jamming signals to against eavesdropping and assist destination with energy harvesting. Assuming UAVs have partial information about eavesdropper’s location, we propose two transmission schemes: friendly UAV jamming (FUJ) and Gaussian jamming transmission (GJT) for the cases when jamming signals are known and unknown a priori at destination, respectively. Then, we formulate an average secrecy rate maximization problem to jointly optimize the transmission power and trajectory of UAVs, and the power splitting ratio of destination. Being non-convex and hence difficult to solve the formulated problem, we propose a computationally efficient iterative algorithm based on block coordinate descent and successive convex approximation to obtain a suboptimal solution. Finally, numerical results are provided to substantiate the effectiveness of our proposed multiple-UAV schemes, compared to other existing benchmarks. Specifically, we find that the FUJ demonstrates significant secrecy performance improvement in terms of the optimal instantaneous and average secrecy rate compared to the GJT and the conventional single-UAV counterpart.

This paper investigates an average secrecy rate (ASR) maximization problem for an unmanned aerial vehicle (UAV) enabled wireless communication system, wherein a UAV is employed to deliver confidential information to a ground destination in the presence of a terrestrial passive eavesdropper. By employing an artificial noise (AN) injection based secure two-phase transmission protocol, we aim at jointly optimizing the UAV’s trajectory, network transmission power, and AN power allocation over a given time horizon to enhance the ASR performance. Specifically, we divide the original non-convex problem into four subproblems, and propose a successive convex approximation based efficient iterative algorithm to solve it suboptimally with guaranteed convergence. Simulation results demonstrate significant security advantages of our designed scheme over other known benchmarks, particularly for stringent flight durations.

Short-packet communication (SPC) and unmanned aerial vehicles (UAVs) are anticipated to play crucial roles in the development of 5G-and-beyond wireless networks and the Internet of Things (IoT). In this paper, we propose a secure SPC system, where a UAV serves as a mobile decode-and-forward (DF) relay, periodically receiving and relaying small data packets from a remote IoT device to its receiver in two hops with strict latency requirements, in the presence of an eavesdropper. This system requires careful optimization of important design parameters, such as the coding blocklengths of both hops, transmit powers, and the UAV’s trajectory. While the overall optimization problem is nonconvex, we tackle it by applying a block successive convex approximation (BSCA) approach to divide the original problem into three subproblems and solve them separately. Then, an overall iterative algorithm is proposed to obtain the final design with guaranteed convergence. Our proposed low-complexity algorithm incorporates robust trajectory design and resource management to optimize the effective average secrecy throughput of the communication system over the course of the UAV-relay’s mission. Simulation results demonstrate significant performance improvements compared to various benchmark schemes and provide useful design insights on the coding blocklengths and transmit powers along the trajectory of the UAV.

Unmanned aerial vehicles (UAVs) and Terahertz (THz) technology are envisioned to play paramount roles in next-generation wireless communications. In this paper, we present a novel secure UAV-assisted mobile relaying system operating at THz bands for data acquisition from multiple ground user equipments (UEs) towards a destination. We assume that the UAV-mounted relay may act, besides providing relaying services, as a potential eavesdropper called the untrusted UAV-relay (UUR). To safeguard end-to-end communications, we present a secure two-phase transmission strategy with cooperative jamming. Then, we devise an optimization framework in terms of a new measure − secrecy energy efficiency (SEE), defined as the ratio of achievable average secrecy rate to average system power consumption, which enables us to obtain the best possible security level while taking UUR’s inherent flight power limitation into account. For the sake of quality of service fairness amongst all the UEs, we aim to maximize the minimum SEE (MSEE) performance via the joint design of key system parameters, including UUR’s trajectory and velocity, communication scheduling, and network power allocation. Since the formulated problem is a mixed-integer nonconvex optimization and computationally intractable, we decouple it into four subproblems and propose alternative algorithms to solve it efficiently via greedy/sequential block successive convex approximation and non-linear fractional programming techniques. Numerical results demonstrate significant MSEE performance improvement of our designs compared to other known benchmarks.

A document by Songze Li. Click on the document to view its contents.

This paper introduces the QLSTM-DLEM model, a quantum model combining Quantum Long Short Term Memory (QLSTM) and Dynamic Land Ecosystem Model (DLEM), for predicting nitrous oxide (N2O) emissions in agricultural fields. Given the time series data collected from different bifurcation branches, integrating all the data into a single model becomes challenging. To address this, time series data, accompanied by signatures, is utilized to distinguish data from different branches. The auto-correlation function (ACF), partial auto-correlation function (PACF), data distribution, and joint distribution of the first-order difference illustrate that time series data collected under different initial conditions and parameters exhibit slight differences but share several similar characteristics. Performance evaluation metrics, including mean absolute error (MAE), mean absolute percentage error (MAPE), root mean square error (RMSE), and coefficient of determination (R 2), are employed to assess the model. The results indicate that the QLSTM-DLEM model outperforms the classical LSTM-DLEM model in terms of generalization and stability, possibly attributed to the parallelism and superposition of quantum computing. Overall, our simulation results demonstrate that the proposed QLSTM-DLEM hybrid model can effectively predict N2O emissions in agricultural fields, with potential applications in environmental monitoring and management.

The reachable and feasible sets of spacecraft are important tools for many areas of astrodynamics such as mission design, space situational awareness, and assessment of potential threats. Whilst these may be obtained by solving many optimal control problems in the indirect formulation, this process is slow and can suffer from convergence issues with a lack of a good initial guess. This work presents an analytical method of rapidly estimating the reachable and feasible sets utilizing the D matrix, an error state transition matrix under linearity assumptions for Keplerian motion which employs time as a state variable and true anomaly as the reference variable. Analytical expressions for the control laws are derived to produce the maximum/minimum change in orbital radius, time-offlight, and out-of-plane height. Moreover, an analytical expression for the control efficiency is derived to allow thrust activation only when it is efficient to do so, allowing a target fuel consumption to be attained. By mixing the contributions of these controls, the complete reachable or feasible sets can then be rapidly swept over with minimal effort, which is demonstrated in a series of numerical simulations. The results show that the optimal control problem solution presents only minor improvements, highlighting the capacity of the D matrix to provide marginally sub-optimal results within a fraction of the computational time.

Software Defined Networks (SDN) can logically route traffic and utilize underutilized network resources, which has enabled the deployment of SDN-enabled Internet of Things (IoT) architecture in many industrial systems. SDN also removes bottlenecks and helps process IoT data efficiently without overloading the network. An SDN-based IoT in an evolving environment is vulnerable to various types of distributed denial of service (DDoS) attacks. Many research papers focus on highrate DDoS attacks, while few address low-rate DDoS attacks in SDN-based IoT networks. There's a need to enhance the accuracy of LDDoS attack detection in SDN-based IoT networks and OpenFlow communication channel. In this paper, we propose LDDoS attack detection approach based on deep learning (DL) model that consists of an activation function of the Long-Short Term Memory (LSTM) to detect different types of LDDoS attacks in IoT networks by analyzing the characteristic values of different types of LDDoS attacks and natural traffic, improve the accuracy of LDDoS attack detection, and reduce the malicious traffic flow. The experiment result shows that the model achieved an accuracy of 98.88%. In addition, the model has been tested and validated using benchmark Edge IIoTset dataset which consist of cyber security attacks.