Hasil untuk "Electronic computers. Computer science"

Chen Gao, Chi Liu, Zhengquan Luo et al.

Large language models (LLMs) are increasingly applied in computer science education for tasks such as tutoring, content generation, and code assessment. However, systematic evaluations aligned with formal curricula and certification standards remain limited. This study benchmarked four recent models, including GPT-5, DeepSeek-R1, Qwen-Plus, and Llama-3.3-70B-Instruct, using a dataset of 1,068 questions derived from six certification exams covering networking, office applications, and Java programming. We evaluated performance across language (Chinese vs. English), cognitive levels based on Bloom's Taxonomy, domain knowledge, confidence-accuracy alignment, and robustness to input masking. Results showed that GPT-5 performed best on English-language certifications, while Qwen-Plus performed better in Chinese contexts. DeepSeek-R1 achieved the most balanced cross-lingual performance, whereas Llama-3.3 showed clear limitations in higher-order reasoning and robustness. All models performed worse on more complex tasks. These findings provide empirical support for the integration of LLMs into computer science education and offer practical implications for curriculum design and assessment.

Andruid Kerne

We develop a conceptualization of ideology, in which a system of ideas represents social, economic, and political relationships. We use ideology as a lens for understanding and critiquing intersecting social, economic, and political aspects of how 'AI' technologies are being developed. We observe ideological shifts. We question that the present tangling of corporate and university objectives is beneficial to labor, particularly computer science students, and the general public. Corporations and computer science have a history of marketing the ideology of computing as empowerment. However, with intensification of the production of 'AI', contradictions emerge. We ask, "Who is being empowered?"

Rahul Karmakar, Akhil Kumar Das, Debapriya Sarkar et al.

This paper explores the application of stacking models for breast cancer detection, integrating key techniques such as data balancing, hyperparameter tuning, and feature selection. We implemented five different stacking configurations. Initially, Logistic Regression (LR) was used as the meta-classifier, while the base estimators included Decision Tree (DT), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Random Forest (RF) classifiers. In the second configuration, we reversed the roles: DT acted as the meta-classifier, with SVM, KNN, RF, and LR serving as the base estimators. In a third setup, SVM was used as the meta-classifier, with DT, LR, KNN, and RF as the base learners. Fourth, we implemented KNN as the stacking classifier, with LR, DT, SVM, and RF as the base estimators. Finally, in the fifth configuration, RF was the meta-classifier, supported by LR, DT, KNN, and SVM as base learners. The evaluation of stacking models was conducted in five phases, starting with a baseline with no adjustments, followed by applying data balancing alone, then adding hyperparameter tuning, applying Chi-square feature selection with data balancing, and finally using correlation-based feature selection with data balancing, all systematically excluding certain elements to analyze their individual impact. Among all cases, the stacking model with LR delivers the best performance, achieving an accuracy of 97.63%, precision of 97.68%, recall of 97.63%, and an F-measure of 97.63%, showcasing its exceptional reliability and balanced effectiveness. All models were evaluated using 10-fold cross-validation.

Talita Santos de Arruda, Rayssa Bruna Holanda Lima, Karla Luciana Magnani Seki et al.

Ultrasound has become an important tool that offers clinical and practical benefits in the intensive care unit (ICU). Its real-time imaging provides immediate information to support prognostic evaluation and clinical decision-making. This study used ultrasound assessment to investigate the impact of hospitalization on muscle properties in neurocritical patients and analyze the relationship between peripheral muscle changes and motor sequelae. A total of 43 neurocritical patients admitted to the ICU were included. The inclusion criteria were patients with acute brain injuries with or without motor sequelae. Muscle ultrasonography assessments were performed during ICU admission and hospital discharge. Measurements included muscle thickness, cross-sectional area, and echogenicity of the biceps brachii, quadriceps femoris, and rectus femoris. Statistical analyses were used to compare muscle properties between time points (hospital admission vs. discharge) and between groups (patients with vs. without motor sequelae). Significance was set at 5%. Hospitalization had a significant effect on muscle thickness, cross-sectional area, and echogenicity in patients with and without motor sequelae (<i>p</i> < 0.05, effect sizes between 0.104 and 0.475). Patients with motor sequelae exhibited greater alterations in muscle echogenicity than those without (<i>p</i> < 0.05, effect sizes between 0.182 and 0.211). Changes in muscle thickness and cross-sectional area were similar between the groups (<i>p</i> > 0.05). Neurocritical patients experience significant muscle deterioration during hospitalization. Future studies should explore why echogenicity is more markedly affected than muscle thickness and cross-sectional area in patients with motor sequelae compared to those without.

Yaping Fu, Fuquan Wang, Zhengyuan Li et al.

Abstract Remanufacturing has become a mainstream sustainable manufacturing paradigm for energy conservation and environmental protection. Disassembly and reprocessing operations are two main activities in remanufacturing. This work proposes multiobjective integrated scheduling of disassembly and reprocessing operations considering product structures and random processing time. First, a stochastic programming model is developed to minimize maximum completion time and total tardiness. Second, a reinforcement learning-based multiobjective evolutionary algorithm is devised considering problem-specific knowledge. Three search strategy combinations are formed: crossover and mutation, crossover and key product-based iterated local search, mutation and key product-based iterated local search. At each iteration, a Q-learning method is devised to intelligently choose a combination of premium strategies. A stochastic simulation is incorporated to evaluate the objective values of the searched solutions. Finally, the formulated model and method are compared with an exact solver, CPLEX, and three well-known metaheuristics from the literature on a set of test instances. The results confirm the excellent competitiveness of the developed model and algorithm for solving the considered problem.

Haley Lepp, Daniel Scott Smith

LLMs have been celebrated for their potential to help multilingual scientists publish their research. Rather than interpret LLMs as a solution, we hypothesize their adoption can be an indicator of existing linguistic exclusion in scientific writing. Using the case study of ICLR, an influential, international computer science conference, we examine how peer reviewers critique writing clarity. Analyzing almost 80,000 peer reviews, we find significant bias against authors associated with institutions in countries where English is less widely spoken. We see only a muted shift in the expression of this bias after the introduction of ChatGPT in late 2022. To investigate this unexpectedly minor change, we conduct interviews with 14 conference participants from across five continents. Peer reviewers describe associating certain features of writing with people of certain language backgrounds, and such groups in turn with the quality of scientific work. While ChatGPT masks some signs of language background, reviewers explain that they now use ChatGPT "style" and non-linguistic features as indicators of author demographics. Authors, aware of this development, described the ongoing need to remove features which could expose their "non-native" status to reviewers. Our findings offer insight into the role of ChatGPT in the reproduction of scholarly language ideologies which conflate producers of "good English" with producers of "good science."

Jelena Jovanovic

A.G. Catalano, S.M. Giampaolo, O. Morsch et al.

We propose to use a quantum spin chain as a device to store and release energy coherently and we investigate the interplay between its internal correlations and outside decoherence. We employ the quantum Ising chain in a transverse field and our charging protocol consists of a sudden global quantum quench in the external field to take the system out of equilibrium. Interactions with the environment and decoherence phenomena can dissipate part of the work that the chain can supply after being charged, measured by the ergotropy. We find that overall, the system shows remarkably better performance, in terms of resilience, charging time, and energy storage, when topological frustration is introduced by setting antiferromagnetic interactions with an odd number of sites and periodic boundary conditions. Moreover, we show that in a simple discharging protocol to an external spin, only the frustrated chain can transfer work and not just heat.

Carlos Alberto Espinosa-Pinos, Paúl Bladimir Acosta-Pérez, Camila Alessandra Valarezo-Calero

This article investigates the factors that affect the job satisfaction of university teachers for which 400 teachers from 4 institutions (public and private) in Ecuador were stratified, resulting in a total of 1600 data points collected through online forms. The research was of a cross-sectional design and quantitative and used machine learning techniques of classification and prediction to analyze variables such as ethnic identity, field of knowledge, gender, number of children, job burnout, perceived stress, and occupational risk. The results indicate that the best classification model is neural networks with a precision of 0.7304; the most significant variables for predicting the job satisfaction of university teachers are: the number of children they have, scores related to perceived stress, professional risk, and burnout, province of the university at which the university teacher surveyed works, and city where the teacher works. This is in contrast to marital status, which does not contribute to its prediction. These findings highlight the need for inclusive policies and effective strategies to improve teacher well-being in the university academic environment.

Rahmahtrisilvia Rahmahtrisilvia, Rudi Setiawan, Asep Ahmad Sopandi et al.

Early Intervention Behavioral Therapy as a method has been shown to aid children diagnosed with Autism in adjusting behavior through Applied Behavior Analysis. While there are three levels of ABA, EIBI does not provide a concrete metric of what separates between the individual levels. The current study focuses on differentiating the electrical patterns found in EEG in children and plans to explore how EIBI can serve across the ABA spectrum. The electrodes F3, F4, C3, C4, P3, P4, O1, and O2 were used to capture the EEG signals and were utilized in estimating the power, spectral density using the Welch method. It was observed during the statistical examination that there existed differences in the results of power across the frequency band amongst the groups. The higher levels of Alpha lead us to believe that there was better emotional management. The chronic group was shown to have more prominent Delta power reflecting weakened control. Comparatively, beginning level’s theta power was found to be higher across all groups showcasing change in attention requiring tasks. Due to greater focus being placed on the lower range frequency activity there existed no noteworthy changes in the Beta and Gamma portions. These findings highlight the role of EIBI in neuromodulation in the Alpha and Delta bands, and its application in the enhancement of emotional and neurological stability. EEG is an effective measure as it quantifies EIBI outcomes. Further studies should examine the long-term effects and enhance curriculum concepts to increase the efficacy of the interventions.

Özgün Akalın, Gülfem Isiklar Alptekin

Alexander Ek, Michelle Blom, Philip B. Stark et al.

AWAIRE is one of two extant methods for conducting risk-limiting audits of instant-runoff voting (IRV) elections. In principle AWAIRE can audit IRV contests with any number of candidates, but the original implementation incurred memory and computation costs that grew superexponentially with the number of candidates. This paper improves the algorithmic implementation of AWAIRE in three ways that make it practical to audit IRV contests with 55 candidates, compared to the previous 6 candidates. First, rather than trying from the start to rule out all candidate elimination orders that produce a different winner, the algorithm starts by considering only the final round, testing statistically whether each candidate could have won that round. For those candidates who cannot be ruled out at that stage, it expands to consider earlier and earlier rounds until either it provides strong evidence that the reported winner really won or a full hand count is conducted, revealing who really won. Second, it tests a richer collection of conditions, some of which can rule out many elimination orders at once. Third, it exploits relationships among those conditions, allowing it to abandon testing those that are unlikely to help. We provide real-world examples with up to 36 candidates and synthetic examples with up to 55 candidates, showing how audit sample size depends on the margins and on the tuning parameters. An open-source Python implementation is publicly available.

James Boerkoel, Mehmet Ergezer

Despite an increasing number of successful interventions designed to broaden participation in computing research, there is still significant attrition among historically marginalized groups in the computing research pipeline. This experience report describes a first-of-its-kind Undergraduate Consortium (UC) that addresses this challenge by empowering students with a culmination of their undergraduate research in a conference setting. The UC, conducted at the AAAI Conference on Artificial Intelligence (AAAI), aims to broaden participation in the AI research community by recruiting students, particularly those from historically marginalized groups, supporting them with mentorship, advising, and networking as an accelerator toward graduate school, AI research, and their scientific identity. This paper presents our program design, inspired by a rich set of evidence-based practices, and a preliminary evaluation of the first years that points to the UC achieving many of its desired outcomes. We conclude by discussing insights to improve our program and expand to other computing communities.

YE Han, LI Xin, SUN Haichun

The adequacy of the entity information directly affects the applications that depend on textual entity information,while conventional entity recognition models can only identify the existing entities.The task of the entity missing detection,defined as a sequence labeling task,aims at finding the location where the entity is missing.In order to construct training dataset,three corres-ponding methods are proposed.We introduce an entity missing detection method combining the convolutional neural network with the gated mechanism and the pre-trained language model.Experiments show that the F1 scores of this model are 80.45% for the PER entity,83.02% for the ORG entity,and 86.75% for the LOC entity.The model performance exceeds the other LSTM-based named entity recognition model.It is found that there is a correlation between the accuracy of the model and the word frequency of the annotated characters.

Nardine Osman, Mark d'Inverno

In the diverse array of work investigating the nature of human values from psychology, philosophy and social sciences, there is a clear consensus that values guide behaviour. More recently, a recognition that values provide a means to engineer ethical AI has emerged. Indeed, Stuart Russell proposed shifting AI's focus away from simply ``intelligence'' towards intelligence ``provably aligned with human values''. This challenge -- the value alignment problem -- with others including an AI's learning of human values, aggregating individual values to groups, and designing computational mechanisms to reason over values, has energised a sustained research effort. Despite this, no formal, computational definition of values has yet been proposed. We address this through a formal conceptual framework rooted in the social sciences, that provides a foundation for the systematic, integrated and interdisciplinary investigation into how human values can support designing ethical AI.

Xingyu Zhao

Prior to the COVID-19 pandemic, the adoption of live polling and real-time feedback tools gained traction in higher education to enhance student engagement and learning outcomes. Integrating live polling activities has been shown to boost attention, participation, and understanding of course materials. However, recent changes in learning behaviours due to the pandemic necessitate a reevaluation of these active learning technologies. In this context, our study focuses on the Computer Science (CS) domain, investigating the impact of Live Polling Quizzes (LPQs) in undergraduate CS lectures. These quizzes comprise fact-based, formally defined questions with clear answers, aiming to enhance engagement, learning outcomes, and overall perceptions of the course module. A survey was conducted among 70 undergraduate CS students, attending CS modules with and without LPQs. The results revealed that while LPQs contributed to higher attendance, other factors likely influenced attendance rates more significantly. LPQs were generally viewed positively, aiding comprehension and maintaining student attention and motivation. However, careful management of LPQ frequency is crucial to prevent overuse for some students and potential reduced motivation. Clear instructions for using the polling software were also highlighted as essential.

Matteo Gavazzoni, Nicola Ferro, Simona Perotto et al.

We present a new algorithm to design lightweight cellular materials with required properties in a multi-physics context. In particular, we focus on a thermo-elastic setting by promoting the design of unit cells characterized both by an isotropic and an anisotropic behavior with respect to mechanical and thermal requirements. The proposed procedure generalizes the microSIMPATY algorithm to a thermo-elastic framework by preserving all the good properties of the reference design methodology. The resulting layouts exhibit non-standard topologies and are characterized by very sharp contours, thus limiting the post-processing before manufacturing. The new cellular materials are compared with the state-of-art in engineering practice in terms of thermo-elastic properties, thus highlighting the good performance of the new layouts which, in some cases, outperform the consolidated choices.

Ayşegül Bozdoğan, Latife Görkemli Aykut, Neslihan Demirel

Abstract The supply chain is a dynamic and uncertain system consisting of material, information, and fund flows between different organizations, from the acquisition of the raw materials to the delivery of the finished products to the end customers. Closed-loop supply chains do not end with the delivery of the finished products to the end customers, the process continues until economic value is obtained from the returned products or they are disposed properly in landfills. Incorporating reverse flows in supply chains increases the uncertainty and complexity, as well as complicating the management of supply chains that are already composed of different actors and have a dynamic structure. Since agent-based modeling and simulation is a more efficient method of handling the dynamic and complex nature of supply chains than the traditional analytical methods, in this study agent-based modeling methodology has been used to model a generic closed-loop supply chain network design problem with the aims of integrating customer behavior into the network, coping with the dynamism, and obtaining a more realistic structure by eliminating the required assumptions for solving the model with analytical methods. The actors in the CLSC network have been defined as agents with goals, properties and behaviors. In the proposed model dynamic customer arrivals, the changing aspects of customers' purchasing preferences for new and refurbished products and the time, quantity and quality uncertainties of returns have been handled via the proposed agent-based architecture. To observe the behavior of the supply chain in several conditions various scenarios have been developed according to different parameter settings for the supplier capacities, the rate of customers being affected by advertising, the market incentive threshold values, and the environmental awareness of customers. From the scenarios, it has been concluded that the system should be fed in the right amounts for the new and refurbished products to increase the effectiveness of factors such as advertising, incentives, and environmental awareness for achieving the desired sales amounts and cost targets.

Hezi Zhang, Anbang Wu, Yuke Wang et al.

In this paper, we propose OneQ, the first optimizing compilation framework for one-way quantum computation towards realistic photonic quantum architectures. Unlike previous compilation efforts for solid-state qubit technologies, our innovative framework addresses a unique set of challenges in photonic quantum computing. Specifically, this includes the dynamic generation of qubits over time, the need to perform all computation through measurements instead of relying on 1-qubit and 2-qubit gates, and the fact that photons are instantaneously destroyed after measurements. As pioneers in this field, we demonstrate the vast optimization potential of photonic one-way quantum computing, showcasing the remarkable ability of OneQ to reduce computing resource requirements by orders of magnitude.

Gugus Wijonarko

Era digital secara konsep menuntut pemanfaatan teknologi pada seluruh aspek pekerjaan manusia, khususnya adanya sinergi dan hubungan antara teknologi dengan faktor manusia yang dianggap sebagai salah satu aset perusahaan. Tujuan penelitian ini adalah untuk mengukur dan mengetahui faktor-faktor yang membuat karyawan memutuskan untuk menggunakan aplikasi sistem informasi sumber daya manusia dalam rutinitas pekerjaan dengan melihat pada variabel penelitian manajemen SDM yaitu kinerja, disiplin, dan produktivitas kerja dalam mempengaruhi keputusan menggunakan aplikasi HRIS. Sampel penelitian ini adalah pengguna dari beberapa perusahaan di Surabaya yang menggunakan aplikasi HRIS dalam rutinitas operasional pekerjaan sehari-hari mereka. Pada penelitian ini ditemukan sampel penelitian sebanyak 55 responden dari berbagai perusahaan di Surabaya dan hasil tanggapan responden tersebut dilakukan pengolahan data menggunakan teknik analisis data regresi linear berganda dengan tingkat kepercayaan 95% dan pembuktian hipotesis menggunakan uji T dan uji F. Hasilnya adalah faktor kinerja karyawan dan faktor disiplin mempengaruhi secara signifikan keputusan pengguna menggunakan sistem informasi sumber daya manusia. Hal ini dikarenakan para responden merasa adanya urgensi terhadap proses pencatatan adminsitrasi yang lebih baik. Sedangkan untuk variabel produktivitas kerja tidak mempengaruhi keputusan penggunaan aplikasi SISDM dikarenakan aplikasi hanya dipandang sebagai alat penunjang operasional pekerjaan sehari hari.