Hasil untuk "Instruments and machines"

Ivaxi Sheth, Zhijing Jin, Bryan Wilder et al.

In the presence of confounding between an endogenous variable and the outcome, instrumental variables (IVs) are used to isolate the causal effect of the endogenous variable. Identifying valid instruments requires interdisciplinary knowledge, creativity, and contextual understanding, making it a non-trivial task. In this paper, we investigate whether large language models (LLMs) can aid in this task. We perform a two-stage evaluation framework. First, we test whether LLMs can recover well-established instruments from the literature, assessing their ability to replicate standard reasoning. Second, we evaluate whether LLMs can identify and avoid instruments that have been empirically or theoretically discredited. Building on these results, we introduce IV Co-Scientist, a multi-agent system that proposes, critiques, and refines IVs for a given treatment-outcome pair. We also introduce a statistical test to contextualize consistency in the absence of ground truth. Our results show the potential of LLMs to discover valid instrumental variables from a large observational database.

Jonas Hein, Lilian Calvet, Matthias Seibold et al.

Purpose: Accurate detection and 6D pose estimation of surgical instruments are crucial for many computer-assisted interventions. However, supervised methods lack flexibility for new or unseen tools and require extensive annotated data. This work introduces a training-free pipeline for accurate multi-view 6D pose estimation of unseen surgical instruments, which only requires a textured CAD model as prior knowledge. Methods: Our pipeline consists of two main stages. First, for detection, we generate object mask proposals in each view and score their similarity to rendered templates using a pre-trained feature extractor. Detections are matched across views, triangulated into 3D instance candidates, and filtered using multi-view geometric consistency. Second, for pose estimation, a set of pose hypotheses is iteratively refined and scored using feature-metric scores with cross-view attention. The best hypothesis undergoes a final refinement using a novel multi-view, occlusion-aware contour registration, which minimizes reprojection errors of unoccluded contour points. Results: The proposed method was rigorously evaluated on real-world surgical data from the MVPSP dataset. The method achieves millimeter-accurate pose estimates that are on par with supervised methods under controlled conditions, while maintaining full generalization to unseen instruments. These results demonstrate the feasibility of training-free, marker-less detection and tracking in surgical scenes, and highlight the unique challenges in surgical environments. Conclusion: We present a novel and flexible pipeline that effectively combines state-of-the-art foundational models, multi-view geometry, and contour-based refinement for high-accuracy 6D pose estimation of surgical instruments without task-specific training. This approach enables robust instrument tracking and scene understanding in dynamic clinical environments.

Arokia Pratheesha S V, Annapoorna M S, Radha R et al.

Hamacher operators are extensively utilized in multicriteria attribute group decision-making (MAGDM) problems due to their remarkable adaptability provided by an adjustable parameter. Here, the Hamacher T-norm and T-conorm operations for two QSVNRNs are formulated.Using these Hamacher operations, we present the quadripartitioned single-valued neutrosophic refined Hamacher weighted averaging (QSVNRHWA) operators within the QSVNR framework and analyze their properties.Finally, we explore a TOPSIS-based approach for multi-attribute decision-making problems that employs the QSVNRHWA operators, demonstrating its application in evaluating practical scenarios related to converting solid waste into energy.

Bo Feng, Yangrui Zhang, Chao Zhang et al.

Abstract Cloud storage systems in smart grids face dual challenges: ensuring data integrity while maintaining real-time responsiveness when managing large-scale power data. Conventional static key management strategies, due to their fixed update patterns, are prone to predictability. Meanwhile, standalone data integrity verification mechanisms often introduce substantial computational and communication overhead, rendering them unsuitable for real-time grid monitoring requirements. To address these issues, this study proposes a collaborative anti-tampering strategy that integrates reinforcement learning with dynamic hash chains. The approach employs a deep Q-network (DQN) to dynamically optimize the update timing and strategy of Advanced Encryption Standard (AES) keys, thereby enhancing the adaptability of key management. Simultaneously, by constructing a dynamic hash chain, it achieves chain-style cross-verification between data blocks to ensure traceability and rapid localization of tampering incidents. Simulation results demonstrate that, compared with conventional key rotation and Secure Hash Algorithm (SHA)-based methods, the proposed scheme improves the tamper detection rate by 67.2%, reduces the average system latency by 38.5 ms, and significantly decreases computational and communication overhead by 52% and 88%, respectively. This study provides an effective technical pathway for addressing dynamic security challenges in smart grid cloud storage environments.

Shreyan Banerjee, Luna Gava, Aasifa Rounak et al.

The emerging field of neuromorphic computing for edge control applications poses the need to quantitatively estimate and limit the number of spiking neurons, to reduce network complexity and optimize the number of neurons per core and hence, the chip size, in an application-specific neuromorphic hardware. While rate-encoding for spiking neurons provides a robust way to encode signals with the same number of neurons as an ANN, it often lacks precision. To achieve the desired accuracy, a population of neurons is often needed to encode the complete range of input signals. However, using population encoding immensely increases the total number of neurons required for a particular application, thus increasing the power consumption and on-board resource utilization. A transition from two neurons to a population of neurons for the linear quadratic regulator (LQR) control of a cartpole is shown in this work. The near-linear behavior of a leaky-integrate-and-fire neuron can be exploited to achieve the LQR control of a cartpole system. This has been shown in simulation, followed by a demonstration on a single-neuron hardware, known as Lu.i. The improvement in control performance is then demonstrated by using a population of varying numbers of neurons for similar control in the Nengo neural engineering framework (NEF), on CPU and on Intel’s Loihi neuromorphic chip. Finally, linear control is demonstrated for four multi-linked pendula on cart systems, using a population of neurons in Nengo, followed by an implementation of the same on Loihi. This study compares LQR control in the NEF using 7 control and 7 neuromorphic performance metrics, followed by a comparison with other conventional spiking and non-spiking controllers.

Reshma Devi, Keith T. Butler, Gopalakrishnan Sai Gautam

Abstract A pathway to overcome limited data availability in materials science is to use the framework of transfer learning, where a pre-trained (PT) machine learning model (on a larger dataset) can be fine-tuned (FT) on a target (smaller) dataset. We systematically explore the effectiveness of various PT/FT strategies to learn and predict material properties and create generalizable models by PT on multiple properties (MPT) simultaneously. Specifically, we leverage graph neural networks (GNNs) to PT/FT on seven diverse curated materials datasets, with sizes ranging from 941 to 132,752. Besides identifying optimal PT/FT strategies and hyperparameters, we find our pair-wise PT-FT models to consistently outperform models trained from scratch on target datasets. Importantly, our MPT models outperform pair-wise models on several datasets and, more significantly, on a 2D material band gap dataset that is completely out-of-domain. Finally, we expect our PT/FT and MPT frameworks to accelerate materials design and discovery for various applications.

Yin-Jyun Luo, Kin Wai Cheuk, Woosung Choi et al.

Existing work on pitch and timbre disentanglement has been mostly focused on single-instrument music audio, excluding the cases where multiple instruments are presented. To fill the gap, we propose DisMix, a generative framework in which the pitch and timbre representations act as modular building blocks for constructing the melody and instrument of a source, and the collection of which forms a set of per-instrument latent representations underlying the observed mixture. By manipulating the representations, our model samples mixtures with novel combinations of pitch and timbre of the constituent instruments. We can jointly learn the disentangled pitch-timbre representations and a latent diffusion transformer that reconstructs the mixture conditioned on the set of source-level representations. We evaluate the model using both a simple dataset of isolated chords and a realistic four-part chorales in the style of J.S. Bach, identify the key components for the success of disentanglement, and demonstrate the application of mixture transformation based on source-level attribute manipulation.

Shah Rukh Qasim, Patrick Owen, Nicola Serra

We present a case for the use of Reinforcement Learning (RL) for the design of physics instrument as an alternative to gradient-based instrument-optimization methods. It's applicability is demonstrated using two empirical studies. One is longitudinal segmentation of calorimeters and the second is both transverse segmentation as well longitudinal placement of trackers in a spectrometer. Based on these experiments, we propose an alternative approach that offers unique advantages over differentiable programming and surrogate-based differentiable design optimization methods. First, Reinforcement Learning (RL) algorithms possess inherent exploratory capabilities, which help mitigate the risk of convergence to local optima. Second, this approach eliminates the necessity of constraining the design to a predefined detector model with fixed parameters. Instead, it allows for the flexible placement of a variable number of detector components and facilitates discrete decision-making. We then discuss the road map of how this idea can be extended into designing very complex instruments. The presented study sets the stage for a novel framework in physics instrument design, offering a scalable and efficient framework that can be pivotal for future projects such as the Future Circular Collider (FCC), where most optimized detectors are essential for exploring physics at unprecedented energy scales.

D. Lubin Balasubramanian, V. Govindasamy

A wireless sensor network (WSN) encompasses a huge set of sensor nodes employed to collect data and transmit it to a base station (BS). Due to its compact, inexpensive, and scalable nature of sensors, WSN finds its applicability in diverse real-time applications. The battery-operated sensor nodes necessitate the design of a multi-hop routing protocol for the effective utilization of available energy in the network. Routing can be considered an optimization problem and can be solved by the design of bioinspired algorithms. This study introduces an improved deer hunting optimization-enabled multihop routing (IDHO-MHR) protocol for WSN. The major intention of the IDHO-MHR approach is to optimally find the routes to the destination in WSN. The IDHO algorithm is initially derived by the incorporation of the Nelder Mead (NM) concept into the traditional DHO algorithm. In addition, the IDHO-MHR technique primarily derives a fitness function with the inclusion of two major variables, namely residual energy (RE) and distance. The nodes with higher RE and minimum distance have the probability of becoming optimal routes from the networks. The performance validation of the IDHO-MHR approach is performed, and the outcomes are inspected in various aspects. The experimental outcomes reported the supremacy of the IDHO-MHR protocol over the other recent approaches.

Laurentiu-Nicolae PRICOPE, Valentin-Marian ANTOHI, Romeo-Victor IONESCU et al.

Amid the increasingly acute need for systematization and urban social management, Romanian cities are facing transformation attempts, their desideratum being to reach a new level of comfort and safety offered to citizens. All these aspects are in line with the sustainable development goals through the need to create the least polluted cities that offer a healthy standard of living to citizens. Starting from the sustainable development desideratum obtained by orienting urban areas to the needs of the citizen and the community, we intend to analyze through the dispersion method the level of smart cities development in Romania. The mainly resuls consist in the realization of a ranking of the Romanian smart cities.

Fengming Sun, Junjie Cui, Xia Yuan et al.

Abstract Fully convolutional neural networks‐based salient object detection has recently achieved great success with its performance benefits from the effective use of multi‐layer features. Based on this, most of the existing saliency detectors designed complex network structures to fuse the multi‐level features generated by the backbone network. However, the variable scale and complex shape of the target are always a great challenge for saliency detection tasks. In this paper, the authors propose a Rich‐scale Feature Fusion Network (RFFNet) for salient object detection. The authors design a rich‐scale feature interactive fusion module to obtain more efficient features from the multi‐scale features. Moreover, the global feature enhance module is used to extract features with better characterization for the final saliency prediction. Extensive experiments performed on five benchmark datasets demonstrate that the proposed method can achieve satisfactory results on different evaluation metrics compared to other state‐of‐the‐art salient object detection approaches.

Meri Azmi, Deni Satria, Farhan Rinsky Mulya et al.

The industrial sector's growth has led to an increase in the number of industrial products available in the market. However, this has made it more challenging for retail merchants to choose which items to sell due to the overwhelming number of options. The seller must carefully consider various factors such as the type, quality, and probability of selling the goods to turn a profit. This research proposes a group decision support system to assist retail sellers in selecting the products to sell. The system is designed to process various information on comparing retail products against specific criteria, enabling sellers to make quick and accurate decisions. To achieve optimal results, this study combines three methods in the decision-making calculation process: Fuzzy Logic, EDAS, and Borda methods. The Fuzzy Logic method is used to assign a value to an unclear criterion, followed by the EDAS method ranking process, and ending with the combination of the decision-making results using the Borda method. The group decision support system is web-based and has been proven to provide effective solutions for retail business actors to increase sales and reduce losses. By using this system, retail sellers can make informed decisions about their products, enabling them to optimize their profits and reduce their risks. In conclusion, the increase in the number of industrial products has created challenges for retail merchants, but this research proposes a solution in the form of a group decision support system. Combining Fuzzy Logic, EDAS, and Borda methods results in an effective decision-making process that allows retail sellers to make informed decisions and achieve their business goals.

Freeman J. Dyson

A gravitational machine is defined as an arrangement of gravitating masses from which useful energy can be extracted. It is shown that such machines may exist if the masses are of normal astronomical size. A simple example of a gravitational machine, consisting of a double star with smaller masses orbiting around it, is described. It is shown that an efficient gravitational machine will also be an emitter of gravitational radiation. The emitted radiation sets a limit on the possible performance of gravitational machines, and also provides us with a possible means for detecting such machines if they exist.

Ryo Fujiwara, Ryoma Fukuhara, Tsubasa Ebiko et al.

Renewable energy is an essential factor in guaranteeing the sustainability of society. In Japan, there have been developments to harness energy from the ocean. The Tsugaru strait, in the northern region of Japan, is an area that has attracted attention for this purpose. We propose a tidal/ocean power generator utilizing a Flaring Flanged Diffuser (FFD) to harness the power. However, for the power generators utilizing FFD to generate power at the optimal condition, design values based on the stream regimes need to be determined. In this paper, the objective is to forecast the design values of tidal/ocean power generators utilizing FFD. We are especially interested in the dimensions of the diffuser shape that relate to effective factors for increasing flow velocity. Fluid field data around FFD is obtained by experimentation. The fluid field data is measured by particle image velocimetry (PIV). The trained deep neural network can forecast design values from a given fluid field. Moreover, we can recognize correlations between the changes in design values and the increase of fluid velocity.

Israa Al-Badarneh, Maria Habib, Ibrahim Aljarah et al.

Training an Artificial Neural Network (ANN) algorithm is not trivial, which requires optimizing a set of weights and biases that increase dramatically with the increasing capacity of the neural network resulting in such hard optimization problems. Essentially, over recent decades, stochastic search algorithms have shown remarkable abilities for addressing hard optimization problems. On the other hand, pragmatically, abundant real-world problems suffer from the imbalance problem, where the distribution of data varies considerably among classes resulting in more training biases and variances which degrades the performance of the learning algorithm. This paper introduces three stochastic and metaheuristic algorithms for training the Multilayer Perceptron (MLP) neural network to solve the problem of imbalanced classifications. The utilized algorithms are the Grey Wolf Optimization (GWO), Particle Swarm Optimization (PSO), and the Salp Swarm Algorithm (SSA). The proposed GWO-MLP, PSO-MLP, and SSA-MLP are trained based on different objective functions; accuracy, f1-score, and g-mean. Whereas, it is evaluated based on 10 benchmark imbalanced datasets. The results show an advantage for f1-score, and g-mean fitness functions over the accuracy when the datasets are imbalanced.

Firdews A.Alsalman, Shler Khorshid, Amira Sallow

Machine learning and deep learning algorithms have become increasingly important in the medical field, especially for diagnosing disease using medical databases. Techniques developed within these two fields are now used to classify different diseases. Although the number of Machine Learning algorithms is vast and increasing, the number of frameworks and libraries that implement them is also vast and growing.  TensorFlow is a well-known machine learning library that has been used by several researchers in the field of disease classification. With the help of TensorFlow (Google's framework), a complex calculation can be addressed effectively by modeling it as a graph and properly mapping the graph segments to the machine in the form of a cluster. In this review paper, the role of the TensorFlow-Python framework- for disease classification is discussed.

SUNWenbing(孙文兵), XIEWenping(谢文平)

构造了一个带参数的Riemann-Liouville分数阶积分恒等式，得到几个关于h-预不变凸函数的带参数的分数阶积分不等式。当参数取特殊值时，分别得到了“中点型”“梯形型”和“Simpson型”积分不等式。利用构建的不等式得到了几个经典数值积分的误差估计式。

Hans-Christoph Burmeister, Manfred Constapel

In this survey, results from an investigation on collision avoidance and path planning methods developed in recent research are provided. In particular, existing methods based on Artificial Intelligence, data-driven methods based on Machine Learning, and other Data Science approaches are investigated to provide a comprehensive overview of maritime collision avoidance techniques applicable to Maritime Autonomous Surface Ships. Relevant aspects of those methods and approaches are summarized and put into suitable perspectives. As autonomous systems are expected to operate alongside or in place of conventionally manned vessels, they must comply with the COLREGs for robust decision-support/-making. Thus, the survey specifically covers how COLREGs are addressed by the investigated methods and approaches. A conclusion regarding their utilization in industrial implementations is drawn.

ZHANG Haobo, XUE Feng, LIU Kai

To effectively use the user-item interaction history and auxiliary information in recommendation systems,this paper proposes an improved collaborative filtering recommendation algorithm.Based on semi-autoencoder,the features of auxiliary information of users and items are extracted,and then mapped into the Matrix Factorization(MF) model.By using the back propagation algorithm,the semi-autoencoder and the matrix factorization model are jointly updated to improve the recommendation performance.Experimental results on the public datasets of MovieLens-100K and Book-Crossing show that the proposed algorithm provides better recommendation effects than the traditional recommendation algorithms,including the Biased Singular Value Decomposition(Biased SVD) and the Probabilistic Matrix Factorization(PMF) algorithm.

Giulia Perugia, Maike Paetzel-Prüsmann, Madelene Alanenpää et al.

Over the past years, extensive research has been dedicated to developing robust platforms and data-driven dialog models to support long-term human-robot interactions. However, little is known about how people's perception of robots and engagement with them develop over time and how these can be accurately assessed through implicit and continuous measurement techniques. In this paper, we explore this by involving participants in three interaction sessions with multiple days of zero exposure in between. Each session consists of a joint task with a robot as well as two short social chats with it before and after the task. We measure participants' gaze patterns with a wearable eye-tracker and gauge their perception of the robot and engagement with it and the joint task using questionnaires. Results disclose that aversion of gaze in a social chat is an indicator of a robot's uncanniness and that the more people gaze at the robot in a joint task, the worse they perform. In contrast with most HRI literature, our results show that gaze toward an object of shared attention, rather than gaze toward a robotic partner, is the most meaningful predictor of engagement in a joint task. Furthermore, the analyses of gaze patterns in repeated interactions disclose that people's mutual gaze in a social chat develops congruently with their perceptions of the robot over time. These are key findings for the HRI community as they entail that gaze behavior can be used as an implicit measure of people's perception of robots in a social chat and of their engagement and task performance in a joint task.