Hasil untuk "Cybernetics"

Dechuan Teng, Chunlin Lu, Libo Qin et al.

Existing end-to-end modeling methods for modular task-oriented dialog systems are typically tailored to specific datasets, making it challenging to adapt to new dialog scenarios. In this work, we propose ESAinsTOD, a unified End-to-end Schema-Aware Instruction-tuning framework for general Task-Oriented Dialog modeling. This framework introduces a structured methodology to go beyond simply fine-tuning Large Language Models (LLMs), enabling flexible adaptation to various dialogue task flows and schemas. Specifically, we leverage full-parameter fine-tuning of LLMs and introduce two alignment mechanisms to make the resulting system both instruction-aware and schema-aware: (i) instruction alignment, which ensures that the system faithfully follows task instructions to complete various task flows from heterogeneous TOD datasets; and (ii) schema alignment, which encourages the system to make predictions adhering to the specified schema. In addition, we employ session-level end-to-end modeling, which allows the system to access the results of previously executed task flows within the dialogue history, to bridge the gap between the instruction-tuning paradigm and the real-world application of TOD systems. Empirical results show that while a fine-tuned LLM serves as a strong baseline, our structured approach provides significant additional benefits. In particular, our findings indicate that: (i) ESAinsTOD outperforms state-of-the-art models by a significant margin on end-to-end task-oriented dialog modeling benchmarks: CamRest676, In-Car and MultiWOZ; (ii) more importantly, it exhibits superior generalization capabilities across various low-resource settings, with the proposed alignment mechanisms significantly enhancing zero-shot performance; and (iii) our instruction-tuning paradigm substantially improves the model's robustness against data noise and cascading errors.

Shahram Ghahremani, Uyen Trang Nguyen

We propose an attention-based LSTM model for predicting forex rates (ALFA). The prediction process consists of three stages. First, an LSTM model captures temporal dependencies within the forex time series. Next, an attention mechanism assigns different weights (importance scores) to the features of the LSTM model’s output. Finally, a fully connected layer generates predictions of forex rates. We conducted comprehensive experiments to evaluate and compare the performance of ALFA against several models used in previous work and against state-of-the-art deep learning models such as temporal convolutional networks (TCN) and Transformer. Experimental results show that ALFA outperforms the baseline models in most cases, across different currency pairs and feature sets, thanks to its attention mechanism that filters out irrelevant or redundant data to focus on important features. ALFA consistently ranks among the top three of the seven models evaluated and ranks first in most cases. We validated the effectiveness of ALFA by applying it to actual trading scenarios using several currency pairs. In these evaluations, ALFA achieves estimated annual return rates comparable to those of professional traders.

Adela Bâra, Irina Alexandra Georgescu, Simona-Vasilica Oprea

The paper examines the price volatility, key determinants, and autoregressive distributed lag (ARDL) framework of Romania’s Intraday Continuous Market (IDC) during the summer months. The stability of the ARDL-ECM coefficients is assessed using the cumulative sum (CUSUM) test. We explore the interaction between IDC and Day-Ahead Market (DAM) prices, alongside the influence of economic and environmental variables, including traded volumes, consumption, export/import and the generation mix. Using hourly data and econometric techniques, we identify significant short- and long-run relationships between IDC prices and their drivers. DAM prices exhibit a strong positive impact on IDC prices, reflecting tight market integration. Higher shares of Renewable Energy Sources (RES) such as wind and solar are associated with increased IDC prices, highlighting challenges in integrating intermittent resources. Conventional sources, particularly coal and oil/gas, also elevate prices due to higher marginal costs. Conversely, electricity consumption is negatively related to IDC prices, suggesting that anticipated demand patterns may contribute to system stability. The findings carry implications for policymakers, indicating a need for enhanced forecasting, flexible resources and improved inter-market coordination to ensure price stability and efficient integration of RES.

Nisrina Hanifa Setiono, Yunita Sari

Social media, particularly Twitter, has become a key platform for communication and opinion-sharing, where code mixing, the blending of multiple languages in a single sentence, is common. In Indonesia, Indonesian-English code mixing is widely used, especially in urban areas. However, sentiment analysis on code-mixed text poses challenges in natural language processing (NLP) due to the informal nature of the data and the limitations of models trained on formal text. This study applies back translation to address these challenges and optimize BERT-based sentiment analysis. The method is tested on the INDONGLISH dataset, consisting of 5,067 labeled tweets. Results show that applying back translation directly to raw tweets yields better performance by preserving original meaning, improving model accuracy. However, when back translation follows monolingual translation, accuracy declines due to semantic distortions. Repeated translation modifies sentence structure and sentiment labels, reducing reliability. These findings indicate that each additional translation step risks decreasing sentiment analysis accuracy, particularly for code-mixed datasets, which are highly sensitive to linguistic shifts. Back translation proves to be an effective approach for formalizing data while maintaining contextual integrity, enhancing sentiment analysis performance on code-mixed text

Zdenek Slanina, Lukas Danys, Rene Jaros et al.

This paper investigates the potential of visible light communication (VLC) for autonomous railway vehicles (ARVs) engaged in nuclear waste disposal. The research focuses on designing an ARV system equipped with VLC technology to ensure safe, reliable communication in hazardous environments, such as deep geological repositories. Initial testing demonstrated that VLC can effectively maintain communication between ARV components over distances of up to 30 m, even when operating at limiting angles. In this study, angles of 60° and 75° were tested, corresponding to the angles of the curves of the tested route. With 4-QAM modulation it was possible to measure at a distance of approximately 5.5 m with an angle of 75°. The system has shown promise in addressing key challenges, such as high radiation levels and confined spaces, where traditional RF-based communication systems may fail. The results indicate that VLC could significantly improve the safety and efficiency of ARV operations in nuclear waste disposal, offering advantages in terms of robustness and reliability. Future work will focus on integrating VLC more deeply into ARV control systems, further testing in real-world environments, and exploring its application nuclear waste management.

Ahmed Rashad Sayed, Mohamed Helmy Khafagy, Mostafa Ali et al.

Adaptive learning systems focus on improving the performance of educational processes by adapting them to different students. One of the factors which require this adaptation is the preferred way of students to learn, which is at times considered as a blend of visual, auditory, kinesthetic, (VAK) etc. Knowing such things, not only helps the teacher to improve the delivery of the content, but also assists in improving assessment methods to suit each student. The primary motivation of this research is to analyze students’ engagement characteristics in Virtual Learning Environments (VLE) and determine their prevalent instructional preference and learning style and recommend the best learning assessment tools. To accomplish this goal, we have proposed an integrated system which encompasses the use of machine learning (ML) algorithms. This hybrid model is aimed at linking various activities to VAK model of learning and hence place students in their various class learning preferences derived from their activities and the patterns created during the learning processes. We used the Open University Learning Analytics Dataset (OULAD)to assess the efficiency of the proposed system. Multiple tests were performed by different machine learning classifiers, mainly in predicting learning style and recommending an assessment methodology. Our results show that the Random Forest algorithm achieved the highest accuracy with 98 %.This research shows how machine learning techniques embedded in learning analytics could expand the functionalities of VLEs toward greater personalization and effectiveness, with every student receiving the best educational experience that suits their learning styles.

Ansei Yonezawa, Heisei Yonezawa, Shuichi Yahagi et al.

The sparse identification of nonlinear dynamics (SINDy) approach can discover the governing equations of dynamical systems based on measurement data, where the dynamical model is identified as the sparse linear combination of the given basis functions. A major challenge in SINDy is the design of a library, which is a set of candidate basis functions, as the appropriate library is not trivial for many dynamical systems. To overcome this difficulty, this study proposes SINDy with library optimization mechanism (SINDy-LOM), which is a combination of the sparse regression technique and the novel learning strategy of the library. In the proposed approach, the basis functions are parametrized. The SINDy-LOM approach involves a two-layer optimization architecture: the inner-layer, in which the data-driven model is extracted as the sparse linear combination of the candidate basis functions, and the outer-layer, in which the basis functions are optimized from the viewpoint of the recursive long-term (RLT) prediction accuracy; thus, the library design is reformulated as the optimization of the parametrized basis functions. The dynamical model obtained by SINDy-LOM has good interpretability and usability, as this approach yields a parsimonious closed-form model. The library optimization mechanism significantly reduces user burden. The RLT perspective improves the reliability of the resulting model compared with the traditional SINDy approach that can only ensure the one-step-ahead prediction accuracy. The effectiveness of the proposed approach is verified through numerical experiments.

D. T. Gedenidze, A. V. Sinitsyn

Purpose. Maintaining approaches to designing a system for planned training of system integrator employees in relation to corporate infrastructure.Methods. The company’s internal processes related to employee training are considered, approaches to designing a  system of planned corporate training for employees in the field of the department’s technological infrastructure are proposed.Results. The need to develop our own system for planned corporate training of system integrator employees was substantiated, functional requirements were formed, the architecture of the software complex was designed, intersystem interaction was designed, algorithms for calculating user recommendations were proposed.Conclusions. Despite the availability of solutions for corporate training on the market, developing your own system is still the optimal solution for a large company, allowing you to satisfy all the needs of employees and managers in managing corporate training, as well as the most optimal way to integrate the system into the existing over many years, the company’s technological infrastructure, while avoiding the involvement of thirdparty specialists.

Faizan Ahmad, Jing Xiong, Zeyang Xia

Abstract Augmented reality (AR) is gaining traction in the field of computer‐assisted treatment (CAT). Head‐mounted display (HMD)‐based AR in CAT provides dentists with enhanced visualisation by directly overlaying a three‐dimensional (3D) model on a real patient during dental treatment. However, conventional AR‐based treatments rely on optical markers and trackers, which makes them tedious, expensive, and uncomfortable for dentists. Therefore, a markerless image‐to‐patient tracking system is necessary to overcome these challenges and enhance system efficiency. This paper proposes a novel feature‐based markerless calibration and navigation method for an HMD‐based AR visualisation system. The authors address three sub‐challenges: firstly, synthetic RGB‐D data for anatomical landmark detection is generated to train a deep convolutional neural network (DCNN); secondly, the HMD is automatically calibrated using detected anatomical landmarks, eliminating the need for user input or optical trackers; and thirdly, a multi‐iterative closest point (ICP) algorithm is developed for effective 3D‐3D real‐time navigation. The authors conduct several experiments on a commercially available HMD (HoloLens 2). Finally, the authors compare and evaluate the approach against state‐of‐the‐art methods that employ HoloLens. The proposed method achieves a calibration virtual‐to‐real re‐projection distance of (1.09 ± 0.23) mm and navigation projection errors and accuracies of approximately (0.53 ± 0.19) mm and 93.87%, respectively.

Raul Steinmetz, Victor A. Kich, Henrique Krever et al.

Deep learning, particularly Convolutional Neural Networks (CNNs), has gained significant attention for its effectiveness in computer vision, especially in agricultural tasks. Recent advancements in instance segmentation have improved image classification accuracy. In this work, we introduce a comprehensive dataset for training neural networks to detect weeds and soy plants through instance segmentation. Our dataset covers various stages of soy growth, offering a chronological perspective on weed invasion's impact, with 1,000 meticulously annotated images. We also provide 6 state of the art models, trained in this dataset, that can understand and detect soy and weed in every stage of the plantation process. By using this dataset for weed and soy segmentation, we achieved a segmentation average precision of 79.1% and an average recall of 69.2% across all plant classes, with the YOLOv8X model. Moreover, the YOLOv8M model attained 78.7% mean average precision (mAp-50) in caruru weed segmentation, 69.7% in grassy weed segmentation, and 90.1% in soy plant segmentation.

Ansei Yonezawa, Heisei Yonezawa, Itsuro Kajiwara

Inverse kinematics is an important and challenging problem in the operation of industrial manipulators. This study proposes a simple inverse kinematics calculation scheme for an industrial serial manipulator. The proposed technique can calculate appropriate values of the joint variables to realize the desired end-effector position and orientation while considering the motion costs of each joint. Two scalar functions are defined for the joint variables: one is to evaluate the end-effector position and orientation, whereas the other is to evaluate the motion efficiency of the joints. By combining the two scalar functions, the inverse kinematics calculation of the manipulator is formulated as a numerical optimization problem. Furthermore, a simple algorithm for solving the inverse kinematics via the aforementioned optimization is constructed on the basis of the simultaneous perturbation stochastic approximation with a norm-limited update vector (NLSPSA). The proposed scheme considers not only the accuracy of the position and orientation of the end-effector but also the efficiency of the robot movement. Therefore, it yields a practical result of the inverse problem. Moreover, the proposed algorithm is simple and easy to implement owing to the high calculation efficiency of NLSPSA. Finally, the effectiveness of the proposed method is verified through numerical examples using a redundant manipulator.

Muhammad Ahsan Mustafa, Yasheerah Yaqoot, Mikhail Martynov et al.

This paper discusses developments for a multi-limb morphogenetic UAV, MorphoGear, that is capable of both aerial flight and ground locomotion. A hybrid path planning algorithm based on the A* strategy has been developed, enabling seamless transition between air-to-ground navigation modes, thereby enhancing robot's mobility in complex environments. Moreover, precise path following is achieved during ground locomotion with a Model Predictive Control (MPC) architecture for its novel walking behaviour. Experimental validation was conducted in the Unity simulation environment utilizing Python scripts to compute control values. The algorithm's performance is validated by the Root Mean Squared Error (RMSE) of 0.91 cm and a maximum error of 1.85 cm, as demonstrated by the results. These developments highlight the adaptability of MorphoGear in navigation through cluttered environments, establishing it as a usable tool in autonomous exploration, both aerial and ground-based.

Nils Mandischer, Alexander Atanasyan, Michael Schluse et al.

Modern modelling approaches fail when it comes to understanding rather than pure supervision of human behavior. As humans become more and more integrated into human-to-anything interactions, the understanding of the human as a whole becomes critical. In this paper, we conduct a structured review of the human digital twin to indicate where modern paradigms fail to model the human agent. Particularly, the mechanistic viewpoint limits the usability of human and general digital twins. Instead, we propose a novel way of thinking about models, states, and their relations: Perspectives-Observer-Transparency. The modelling paradigm indicates how transparency - or whiteness - relates to the abilities of an observer, which again allows to model the penetration depth of a system model into the human psyche. The split in between the human's outer and inner states is described with a perspectives model, featuring the introperspective and the exteroperspective. We explore this novel paradigm by employing two recent scenarios from ongoing research and give examples to emphasize specific characteristics of the modelling paradigm.

Jia Quan Loh, Xuewen Luo, Fan Ding et al.

With the advancements of sensor hardware, traffic infrastructure and deep learning architectures, trajectory prediction of vehicles has established a solid foundation in intelligent transportation systems. However, existing solutions are often tailored to specific traffic networks at particular time periods. Consequently, deep learning models trained on one network may struggle to generalize effectively to unseen networks. To address this, we proposed a novel spatial-temporal trajectory prediction framework that performs cross-domain adaption on the attention representation of a Transformer-based model. A graph convolutional network is also integrated to construct dynamic graph feature embeddings that accurately model the complex spatial-temporal interactions between the multi-agent vehicles across multiple traffic domains. The proposed framework is validated on two case studies involving the cross-city and cross-period settings. Experimental results show that our proposed framework achieves superior trajectory prediction and domain adaptation performances over the state-of-the-art models.

Valeria Villani, Beatrice Capelli, Lorenzo Sabattini

The growing spread of robots for service and industrial purposes calls for versatile, intuitive and portable interaction approaches. In particular, in industrial environments, operators should be able to interact with robots in a fast, effective, and possibly effortless manner. To this end, reality enhancement techniques have been used to achieve efficient management and simplify interactions, in particular in manufacturing and logistics processes. Building upon this, in this paper we propose a system based on mixed reality that allows a ubiquitous interface for heterogeneous robotic systems in dynamic scenarios, where users are involved in different tasks and need to interact with different robots. By means of mixed reality, users can interact with a robot through manipulation of its virtual replica, which is always colocated with the user and is extracted when interaction is needed. The system has been tested in a simulated intralogistics setting, where different robots are present and require sporadic intervention by human operators, who are involved in other tasks. In our setting we consider the presence of drones and AGVs with different levels of autonomy, calling for different user interventions. The proposed approach has been validated in virtual reality, considering quantitative and qualitative assessment of performance and user's feedback.

Peng Tang, Zhiqiang Xu, Pengfei Wei et al.

We propose an efficient deep learning method for single image defocus deblurring (SIDD) by further exploring inverse kernel properties. Although the current inverse kernel method, i.e., kernel-sharing parallel atrous convolution (KPAC), can address spatially varying defocus blurs, it has difficulty in handling large blurs of this kind. To tackle this issue, we propose a Residual and Recursive Kernel-sharing Atrous Convolution (R$^2$KAC). R$^2$KAC builds on a significant observation of inverse kernels, that is, successive use of inverse-kernel-based deconvolutions with fixed size helps remove unexpected large blurs but produces ringing artifacts. Specifically, on top of kernel-sharing atrous convolutions used to simulate multi-scale inverse kernels, R$^2$KAC applies atrous convolutions recursively to simulate a large inverse kernel. Specifically, on top of kernel-sharing atrous convolutions, R$^2$KAC stacks atrous convolutions recursively to simulate a large inverse kernel. To further alleviate the contingent effect of recursive stacking, i.e., ringing artifacts, we add identity shortcuts between atrous convolutions to simulate residual deconvolutions. Lastly, a scale recurrent module is embedded in the R$^2$KAC network, leading to SR-R$^2$KAC, so that multi-scale information from coarse to fine is exploited to progressively remove the spatially varying defocus blurs. Extensive experimental results show that our method achieves the state-of-the-art performance.

Behzad Akbari, Ya-Jun Pan, Shiwei Liu et al.

Unmanned Surface Vehicles (USVs) in the ocean environment, considering various spatiotemporal factors such as ocean currents and other energy consumption factors. The paper uses Gaussian Process Motion Planning (GPMP2), a Bayesian optimization method that has shown promising results in continuous and nonlinear motion planning algorithms. The proposed work improves GPMP2 by incorporating a new spatiotemporal factor for tracking and predicting ocean currents using a spatiotemporal Bayesian inference. The algorithm is applied to the USV path planning and is shown to optimize for smoothness, obstacle avoidance, and ocean currents in a challenging environment. The work is relevant for practical applications in ocean scenarios where optimal path planning for USVs is essential for minimizing costs and optimizing performance.

Blaženka Divjak, Darko Grabar, Barbi Svetec et al.

We present a comprehensive learning design (LD) concept and tool, motivated by the needs identified by higher education (HE) practitioners. The concept and tool aim at implementing contemporary research findings and theory to support balanced LD planning (BDP). The student-centered BDP concept and tool provide innovation to LD planning by strongly focusing on learning outcomes (LOs) and student workload, aligning study program and course level LOs, ensuring constructive alignment and assessment validity, enhancing LD by using learning analytics, and enabling flexible use in different contexts and pedagogical approaches. The ongoing work has been done according to design science methodology, with positive first feedback from HE practitioners. We identify areas for further research and improvement, including testing the BDP tool in real-world HE contexts and its integration with learning management systems. This could help close the gap between intended (often innovative) LDs and their implementation in real teching and learning environments.