Hasil untuk "Instruments and machines"

Ye Wang, Yaling Deng, Ge Wang et al.

Modern Large Language Models (LLMs) exhibit complexity and granularity similar to humans in the field of natural language processing, challenging the boundaries between humans and machines in language understanding and creativity. However, whether the semantic network of LLMs is similar to humans is still unclear. We examined the representative closed-source LLMs, GPT-3.5-Turbo and GPT-4, with open-source LLMs, LLaMA-2-70B, LLaMA-3-8B, LLaMA-3-70B using semantic fluency tasks widely used to study the structure of semantic networks in humans. To enhance the comparability of semantic networks between humans and LLMs, we innovatively employed role-playing to generate multiple agents, which is equivalent to recruiting multiple LLM participants. The results indicate that the semantic network of LLMs has poorer interconnectivity, local association organization, and flexibility compared to humans, which suggests that LLMs have lower search efficiency and more rigid thinking in the semantic space and may further affect their performance in creative writing and reasoning.

Tanweer Alam, Ruchi Gupta

In the social media environment, fake news is a significant issue. It might be online or offline, depending on the field of journalism. Concerns have been expressed by media and publishing houses, who are looking for solutions to the problem. One of the solutions the industry has to offer in this area is Blockchain. It could be digital security trading, source or identity verification, or quotes following a certain news piece, photo, or video. It's miles of shared document generation to deliver timely files, and it's done with the help of a specific article, video, or image that has been addressed. This will no longer assist the fact abuser in verifying the details. This will help the fact abuser confirm the details, but it will also offer documentation of metadata generated at all phases. It allows you to cut the expense of disseminating false information by forwarding and explicit disclosure to persons who have first-hand knowledge of the subject. The proposed structure for acquiring fake news is supported by the blockchain age, which allows news organizations to deliver their content to their subscribers transparently. This framework was created for journalists and can be integrated into any current platform to publish a news piece and include asset statistics.

Jiajun Guo, Qingge Ji, Guangwei Shan

Abstract Current skeleton‐based action recognition methods usually assume the input skeleton is complete and noise‐free. However, it is inevitable that the captured skeletons are incomplete due to occlusions or noisy due to changes in the environment. When dealing with these data, even State Of The Art (SOTA) recognition backbones experience significant degradation in recognition accuracy. Though a few methods have been proposed to address this issue, they still lack flexibility, efficiency and interpretability. In this work, an overcomplete Graph Convolutional Denoising Autoencoder (GCDAE) is proposed which can act as a flexible preprocessing module for pretrained recognition backbones and improve their robustness. Taking advantages of the overcomplete and fully graph convolutional structure, GCDAE is able to rectify noisy joints while keeping information of unspoiled details efficiently. On two large scale skeleton datasets NTU RGB+D 60 and 120, the introducing of GCDAE brings significant robustness improvements to SOTA backbones towards different types of noises.

Kei Nishihara, Masaya Nakata

Abstract In the field of expensive optimization, numerous papers have proposed surrogate-assisted evolutionary algorithms (SAEAs) for a few thousand or even hundreds of function evaluations. However, in reality, low-cost simulations suffice for a lot of real-world problems, in which the number of function evaluations is moderately restricted, e.g., to several thousands. In such moderately restricted scenario, SAEAs become unnecessarily time-consuming and tend to struggle with premature convergence. In addition, tuning the SAEA parameters becomes impractical under the restricted budgets of function evaluations—in some cases, inadequate configuration may degrade performance instead. In this context, this paper presents a fast and auto-tunable evolutionary algorithm for solving moderately restricted expensive optimization problems. The presented algorithm is a variant of adaptive differential evolution (DE) algorithms, and is called emulation-based adaptive DE or EBADE. The primary aim of EBADE is to emulate the principle of sample-efficient optimization, such as that in SAEAs, by adaptively tuning the DE parameter configurations. Specifically, similar to Expected Improvement-based sampling, EBADE identifies parameter configurations that may produce expected-to-improve solutions, without using function evaluations. Further, EBADE incepts a multi-population mechanism and assigns a parameter configuration to each subpopulation to estimate the effectiveness of parameter configurations with multiple samples carefully. This subpopulation-based adaptation can help improve the selection accuracy of promising parameter configurations, even when using an expected-to-improve indicator with high uncertainty, by validating with respect to multiple samples. The experimental results demonstrate that EBADE outperforms modern adaptive DEs and is highly competitive compared to SAEAs with a much shorter runtime.

Bartłomiej Jacek Kubica

Taoufiq El Moussaoui, Loqman Chakir

A. Fenwick, G. Molnar

Abstract One of the biggest challenges in Artificial Intelligence (AI) development and application is the lack of consideration for human enhancement as a cornerstone for its operationalization. Nor is there a universally accepted approach that guides best practices in this field. However, the behavioral science field offers suggestions on how to develop a sustainable and enriching relationship between humans and intelligent machines. This paper provides a three-level (micro, meso and macro) framework on how to humanize AI with the intention of enhancing human properties and experiences. It argues that humanizing AI will help make intelligent machines not just more efficient but will also make their application more ethical and human-centric. Suggestions to policymakers, organizations, and developers are made on how to implement this framework to fix existing issues in AI and create a more symbiotic relationship between humans and machines moving into the future.

Akshara Rai, Suyash Sangwan, Tushar Goel et al.

Ihor Butko

У статті запропоновано модель та метод прийняття управлінських рішень на основі аналізу геопросторової інформації. Метою статті є удосконалення моделі та методу прийняття управлінських рішень на основі аналізу геопросторової інформації. Результати: запропоновано алгоритм процесу прийняття управлінського рішення, який складається з ситуаційної та концептуальної частини; запропоновано алгоритм дій керівника організації на основі розробленої моделі прийняття управлінського рішення; розглянута ситуація, коли якість рішення залежить від зовнішніх факторів, на які орган прийняття рішення не впливає; наведена загальна схема методу прийняття управлінських рішень на основі аналізу геопросторової інформації. Використовуваними методами є: методи системного аналізу, теорії прийняття рішень, обробки інформації, оптимальних рішень, теорії ймовірності. Висновки. Удосконалено модель прийняття управлінських рішень, яка, на відміну від відомих, є динамічною і базується на відборі рішень, що є оптимальними за комбінованим критерієм, при цьому використовується прогнозні значення імовірностей станів середовища, що забезпечує обґрунтованість управлінських рішень. Отримав подальший розвиток метод прийняття управлінських рішень на основі аналізу геопросторової інформації, який базується на моделях прогнозування даних та прийняття управлінських рішень і використовує метод семантичної сегментації видових зображень для оцінки апріорних імовірностей станів середовища, що забезпечує можливість прийняття рішення в умовах ризику та невизначенності. Напрямком подальших досліджень є розробка інформаційної технології прийняття управлінських рішень на основі аналізу геопросторової інформації.

Hritik Soni, Pranjal Arora, D. Rajeswari

As of late, the uses of advanced mobile phones are expanding relentlessly and furthermore development of Android application clients are expanding. Because of development of Android application client, some gatecrashers are making vindictive android application as instrument to take the delicate information and data for fraud and misrepresentation portable bank, versatile wallets. There are such a large number of malevolent applications discovery instruments and programming’s are accessible. Be that as it may, a viably and productively vindictive application recognition device expected to handle and deal with new complex pernicious applications made by interloper or programmers. This paper Utilizing Machine Learning approaches for distinguishing the malignant android application. First, dataset of past pernicious applications has to be obtained with the assistance of Help vector machine calculation and choice tree calculation make up correlation with preparing dataset. The prepared dataset can foresee the malware android applications up to 93.2 % obscure/new malware portable application.

P. K. Shreevathsa, M. Harshith, Abhishek Rao M et al.

In this is modern era, everyone listens to and plays music. Music is diverse across the globe. It is a language that speaks by itself and is the fulcrum of all the arts. We can say that rich legacy of this flawless art is infinity and beyond. It has the ability to mesmerise one and all. If there was a way in which we could get to know the instruments that are being played in the music, it would be more interesting. So, we can classify the music based on certain instruments. In last two decades, researchers are actively associated with human perception towards the study of Musical Instruments. Our work is based on designing an application that recognizes the instruments that are present in a given Music. It is no hidden fact anymore that neural network in general are dominating every single aspect and application in this world. The fact that a neural network can do a task that can be done by a human brain efficiently if we train them properly tells us a lot about their advancement in the day to day world. Thus, we make use of neural networks for the recognition of an instrument in a piece of music. Hence, we make use of ANN (Artificial Neural Network) and CNN(Convolutional Neural Network). We've considered eight different music instruments. The models thus built play a major role in finding the music instruments being played. Various features are extracted in the process and the result is found.

Salima khaoula Reguieg, Z. Ghemari, T. Benslimane et al.

Dan Zhao, Y. Bi, Y. Ke

Baran Balkan, Patrick Essay, V. Subbian

Clinical scoring systems have been developed for many specific applications, yet they remain underutilized for common reasons such as model inaccuracy and difficulty of use. For intensive care units specifically, the Acute Physiology and Chronic Health Evaluation (APACHE) score is used as a decision-making tool and hospital efficacy measure. In an attempt to alleviate the general underlying limitations of scoring instruments and demonstrate the utility of readily available medical databases, machine learning techniques were used to evaluate APACHE IV and IVa prediction measures in an open-source, teleICU research database. The teleICU database allowed for large-scale evaluation of APACHE IV and IVa predictions by comparing predicted values to the actual, recorded patient outcomes along with preliminary exploration of new predictive models for patient mortality and length of stay in both the hospital and the ICU. An increase in performance was observed in the newly developed models trained on the APACHE input variables highlighting avenues of future research and illustrating the utility of teleICU databases for model development and evaluation.

Tuhin Bera, Nirmal Kumar Mahapatra

In this paper, the concept of connectedness and compactness on neutrosophic soft topological space have been introduced along with the investigation of their several characteristics. Some related theorems have been established also. Then, the notion of neutrosophic soft continuous mapping on a neutrosophic soft topological space and it’s properties are developed here.

AnnetteM.C. Ficker, FritsC.R. Spieksma, GerhardJ. Woeginger

An instance of a balanced optimization problem with vector costs consists of a ground set X, a cost-vector for every element of X, and a system of feasible subsets over X. The goal is to find a feasible subset that minimizes the so-called imbalance of values in every coordinate of the underlying vector costs. Balanced optimization problems with vector costs are equivalent to the robust optimization version of balanced optimization problems under the min-max criterion. We regard these problems as a family of optimization problems; one particular member of this family is the known balanced assignment problem. We investigate the complexity and approximability of robust balanced optimization problems in a fairly general setting. We identify a large family of problems that admit a 2-approximation in polynomial time, and we show that for many problems in this family this approximation factor 2 is best-possible (unless P = NP). We pay special attention to the balanced assignment problem with vector costs and show that this problem is NP-hard even in the highly restricted case of sum costs. We conclude by performing computational experiments for this problem.

Alireza Haji Fathaliyan, Xiaoyu Wang, Veronica J. Santos

Human–robot collaboration could be advanced by facilitating the intuitive, gaze-based control of robots, and enabling robots to recognize human actions, infer human intent, and plan actions that support human goals. Traditionally, gaze tracking approaches to action recognition have relied upon computer vision-based analyses of two-dimensional egocentric camera videos. The objective of this study was to identify useful features that can be extracted from three-dimensional (3D) gaze behavior and used as inputs to machine learning algorithms for human action recognition. We investigated human gaze behavior and gaze–object interactions in 3D during the performance of a bimanual, instrumental activity of daily living: the preparation of a powdered drink. A marker-based motion capture system and binocular eye tracker were used to reconstruct 3D gaze vectors and their intersection with 3D point clouds of objects being manipulated. Statistical analyses of gaze fixation duration and saccade size suggested that some actions (pouring and stirring) may require more visual attention than other actions (reach, pick up, set down, and move). 3D gaze saliency maps, generated with high spatial resolution for six subtasks, appeared to encode action-relevant information. The “gaze object sequence” was used to capture information about the identity of objects in concert with the temporal sequence in which the objects were visually regarded. Dynamic time warping barycentric averaging was used to create a population-based set of characteristic gaze object sequences that accounted for intra- and inter-subject variability. The gaze object sequence was used to demonstrate the feasibility of a simple action recognition algorithm that utilized a dynamic time warping Euclidean distance metric. Averaged over the six subtasks, the action recognition algorithm yielded an accuracy of 96.4%, precision of 89.5%, and recall of 89.2%. This level of performance suggests that the gaze object sequence is a promising feature for action recognition whose impact could be enhanced through the use of sophisticated machine learning classifiers and algorithmic improvements for real-time implementation. Robots capable of robust, real-time recognition of human actions during manipulation tasks could be used to improve quality of life in the home and quality of work in industrial environments.

Tao Li, Hui Zhao, Yu Chang

This paper addresses the stability problem of uncalibrated image-based visual servoing robotic systems. Both the visual feedback delay and the uncalibrated visual parameters can be the sources of instability for visual servoing robotic systems. To eliminate the negative effects caused by kinematic uncertainties and delays, we propose an adaptive controller including the delay-affected Jacobian matrix and design an adaptive law accordingly. Besides, the delay-dependent stability conditions are provided to show the relationship between the system stability and the delayed time in order to obtain less conservative results. A Lyapunov-Krasovskii functional is constructed, and a rigorously mathematic proof is given. Finally, the simulation results are presented to show the effectiveness of the proposed control scheme.

R. Fiebrink

ZHANG Zhiyuan,YANG Hongjing,ZHAO Yue

Mining the probability distribution of topic words in document collection can make a summary understanding of the document content.Further exploring the connection relationship between words in a given topic not only riches the meaning of topic words,but also reveals the hierarchy and aggregation of topics.For the labeled document collection,this paper proposes a method to compute the conditional probability of two words under a given topic based on Gibbs sampling outputs of labeled Latent Dirichlet Allocation(LDA),and a topical text network is also constructed.Compared with Pointwise Labeled-LDA(PL-LDA) model,this method does not extend the original document and needs less computation cost and shorter time.Experiments on the data set of aviation safety reports show that,for topics with many labeled words,this method can better display the distribution of subject words and the complex relationship between them.