Hasil untuk "Computer Science"

Cristian Valero-Abundio, Emilio Sansano-Sansano, Raúl Montoliu et al.

Handling geometric transformations, particularly rotations, remains a challenge in deep learning for computer vision. Standard neural networks lack inherent rotation invariance and typically rely on data augmentation or architectural modifications to improve robustness. Although effective, these approaches increase computational demands, require specialised implementations, or alter network structures, limiting their applicability. This paper introduces General Intensity Direction (GID), a preprocessing method that improves rotation robustness without modifying the network architecture. The method estimates a global orientation for each image and aligns it to a canonical reference frame, allowing standard models to process inputs more consistently across different rotations. Unlike moment-based approaches that extract invariant descriptors, this method directly transforms the image while preserving spatial structure, making it compatible with convolutional networks. Experimental evaluation on the rotated MNIST dataset shows that the proposed method achieves higher accuracy than state-of-the-art rotation-invariant architectures. Additional experiments on the CIFAR-10 dataset, confirm that the method remains effective under more complex conditions.

Ming Han, Ge Sun, Paul F. Nealey et al.

Abstract Machine learning (ML) offers considerable promise for the design of new molecules and materials. In real-world applications, the design problem is often domain-specific, and suffers from insufficient data, particularly labeled data, for ML training. In this study, we report a data-efficient, deep-learning framework for molecular discovery that integrates a coarse-grained functional-group representation with a self-attention mechanism to capture intricate chemical interactions. Our approach exploits group-contribution concepts to create a graph-based intermediate representation of molecules, serving as a low-dimensional embedding that substantially reduces the data demands typically required for training. Using a self-attention mechanism to learn the subtle but highly relevant chemical context of functional groups, the method proposed here consistently outperforms existing approaches for predictions of multiple thermophysical properties. In a case study focused on adhesive polymer monomers, we train on a limited dataset comprising only 6,000 unlabeled and 600 labeled monomers. The resulting chemistry prediction model achieves over 92% accuracy in forecasting properties directly from SMILES strings, exceeding the performance of current state-of-the-art techniques. Furthermore, the latent molecular embedding is invertible, enabling the design pipeline to automatically generate new monomers from the learned chemical subspace. We illustrate this functionality by targeting several properties, including high and low glass transition temperatures (Tg), and demonstrate that our model can identify new candidates with values that surpass those in the training set. The ease with which the proposed framework navigates both chemical diversity and data scarcity offers a promising route to accelerate and broaden the search for functional materials.

Muhammad Aamir, Ziaur Rahman, Uzair Aslam Bhatti et al.

Abstract The precise and timely diagnosis of brain tumors is essential for accelerating patient recovery and preserving lives. Brain tumors exhibit a variety of sizes, shapes, and visual characteristics, requiring individualized treatment strategies for each patient. Radiologists require considerable proficiency to manually detect brain malignancies. However, tumor recognition remains inefficient, imprecise, and labor-intensive in manual procedures, underscoring the need for automated methods. This study introduces an effective approach for identifying brain lesions in magnetic resonance imaging (MRI) images, minimizing dependence on manual intervention. The proposed method improves image clarity by combining guided filtering techniques with anisotropic Gaussian side windows (AGSW). A morphological analysis is conducted prior to segmentation to exclude non-tumor regions from the enhanced MRI images. Deep neural networks segment the images, extracting high-quality regions of interest (ROIs) and multiscale features. Identifying salient elements is essential and is accomplished through an attention module that isolates distinctive features while eliminating irrelevant information. An ensemble model is employed to classify brain tumors into different categories. The proposed technique achieves an overall accuracy of 99.94% and 99.67% on the publicly available brain tumor datasets BraTS2020 and Figshare, respectively. Furthermore, it surpasses existing technologies in terms of automation and robustness, thereby enhancing the entire diagnostic process.

Songmei Yu, Andrew Zagula

Collaborative group projects are integral to computer science education, fostering teamwork, problem-solving, and industry-relevant skills. However, assessing individual contributions within group settings remains challenging. Traditional approaches, including equal grade distribution and subjective peer evaluations, often lack fairness, objectivity, and scalability, particularly in large classrooms. We propose TRACE, a semi-automated AI-assisted framework for assessing collaborative software projects that evaluates both project quality and individual contributions using repository mining, communication analytics, and AI-assisted analytics. A pilot deployment in a software engineering course demonstrated high alignment with instructor assessments, increased student satisfaction, and reduced instructor grading effort. The results suggest that AI-assisted analytics can improve the transparency and scalability of collaborative project assessment in computer science education.

Gabriel Nicolae Popa, Corina Maria Diniș

Among many other applications, electronic converters can be used with sensors with analogue outputs (DC voltage). This article presents an analogue computation converter with two DC voltages at the inputs (one input changes the frequency of the output signal, another input changes the amplitude of the output signal) that provide a periodic sinusoidal signal (with variable frequency and amplitude) at the output. On the basis of the analogue computation converter is a nonhomogeneous second-order linear ordinary differential equation which is solved analogically. The analogue computation converter consists of analogue multipliers and operational amplifiers, composed of seven function circuits: two analogue multiplication circuits, two analogue addition circuits, one non-inverting amplifier, and two integration circuits (with RC time constants). At the output of an oscillator is a sinusoidal signal which depends on the DC voltages applied on two inputs (0 ÷ 10 V): at one input, a DC voltage is applied to linearly change the sinusoidal frequency output (up to tens of kHz, according to two time constants), and at the other input, a DC voltage is applied to linearly change the amplitude of the oscillator output signal (up to 10 V). It can be used with sensors which have a DC output voltage and must be converted to a sine wave signal with variable frequency and amplitude with the aim of transmitting information over longer distances through wires. This article presents the detailed theory of the functioning, simulations, and experiments of the analogue computation converter.

Pablo Sala, Sara Murciano, Yue Liu et al.

Entanglement, measurement, and classical communication together enable teleportation of quantum states between distant parties, in principle, with perfect fidelity. To what extent do correlations and entanglement of a many-body wave function transfer under imperfect teleportation protocols? We address this question for the case of an imperfectly teleported quantum critical wave function, focusing on the ground state of a critical Ising chain. We demonstrate that imperfections, e.g., in the entangling gate adopted for a given protocol, effectively manifest as weak measurements acting on the otherwise pristinely teleported critical state. Armed with this perspective, we leverage and further develop the theory of measurement-altered quantum criticality to quantify the resilience of critical-state teleportation. We identify classes of teleportation protocols for which imperfection (i) preserves both the universal long-range entanglement and correlations of the original quantum critical state, (ii) weakly modifies these quantities away from their universal values, and (iii) obliterates long-range entanglement altogether while preserving power-law correlations, albeit with a new set of exponents. We also show that mixed states describing the average over a series of sequential imperfect teleportation events retain pristine power-law correlations due to a “built-in” decoding algorithm, though their entanglement structure measured by the negativity depends on errors similarly to individual protocol runs. These results may allow one to design teleportation protocols that optimize against errors—highlighting a potential practical application of measurement-altered criticality.

MingHui Zhong, YePing Zhou

Abstract With the rapid development of information technology, new educational models using virtual reality technology have received widespread attention from relevant researchers. In the field of vocational education, vocational colleges and training institutions can effectively mobilize students' learning initiative and improve their learning efficiency by using virtual reality technology. This study details the development process and system evaluation of a bespoke virtual reality system that offers a solution to the issues of uncertainty regarding hazards, high teaching expenses, and spatial constraints inherent in the practical training of elevator maintenance. By establishing a virtual environment that is highly reproducible and designing abundant interaction methods, this system facilitates students in attaining mastery over the structural make‐up of elevators, the principles of their operation, and the techniques involved in calibrating elevator governors. The system underwent testing by multiple users, and the satisfaction level of the system was ascertained through a questionnaire study, while the effectiveness of the system was evaluated using independent samples t test for data statistics concerning students' performance. The results of the study indicate that the system gained widespread praise among users, and it notably enhanced the students' learning drive, practical abilities, and on‐site adaptability.

Ahatesham Bhuiyan, Eftekhar Hossain, Mohammed Moshiul Hoque et al.

Image captioning, the process of generating natural language descriptions based on image content, has garnered attention in AI research for its implications in scene understanding and human-computer interaction. While much prior research has focused on caption generation for English, addressing low-resource languages like Bengali presents challenges, particularly in producing coherent captions linking visual objects with corresponding words. This paper proposes a context-aware attention mechanism over semantic attention to accurately diagnose objects for image captioning in Bengali. The proposed architecture consists of an encoder and a decoder block. We chose ResNet-50 over the other pre-trained models for encoding the image features due to its ability to solve the vanishing gradient problem and recognize complex object features. For decoding generated captions, a bidirectional Gated Recurrent Unit (GRU) architecture combined with an attention mechanism captures contextual dependencies in both directions, resulting in more accurate captions. The paper also highlights the challenge of transferring knowledge between domains, especially with culturally specific images. Evaluation of three Bengali benchmark datasets, namely BAN-Cap, BanglaLekhaImageCaption, and Bornon, demonstrates significant performance improvement in METEOR score over existing methods by approximately 30%, 18%, and 45%, respectively. The proposed context-aware, attention-based image captioning system significantly outperforms current state-of-the-art models in Bengali caption generation despite limitations in reference captions on certain datasets.

Changhee Yun, Bomi Eom, Sungjun Park et al.

In the medical field, it is delicate to anticipate good performance in using deep learning due to the lack of large-scale training data and class imbalance. In particular, ultrasound, which is a key breast cancer diagnosis method, is delicate to diagnose accurately as the quality and interpretation of images can vary depending on the operator’s experience and proficiency. Therefore, computer-aided diagnosis technology can facilitate diagnosis by visualizing abnormal information such as tumors and masses in ultrasound images. In this study, we implemented deep learning-based anomaly detection methods for breast ultrasound images and validated their effectiveness in detecting abnormal regions. Herein, we specifically compared the sliced-Wasserstein autoencoder with two representative unsupervised learning models autoencoder and variational autoencoder. The anomalous region detection performance is estimated with the normal region labels. Our experimental results showed that the sliced-Wasserstein autoencoder model outperformed the anomaly detection performance of others. However, anomaly detection using the reconstruction-based approach may not be effective because of the occurrence of numerous false-positive values. In the following studies, reducing these false positives becomes an important challenge.

Sachita Nishal, Jasmine Sinchai, Nicholas Diakopoulos

Science and technology journalists today face challenges in finding newsworthy leads due to increased workloads, reduced resources, and expanding scientific publishing ecosystems. Given this context, we explore computational methods to aid these journalists' news discovery in terms of time-efficiency and agency. In particular, we prototyped three computational information subsidies into an interactive tool that we used as a probe to better understand how such a tool may offer utility or more broadly shape the practices of professional science journalists. Our findings highlight central considerations around science journalists' agency, context, and responsibilities that such tools can influence and could account for in design. Based on this, we suggest design opportunities for greater and longer-term user agency; incorporating contextual, personal and collaborative notions of newsworthiness; and leveraging flexible interfaces and generative models. Overall, our findings contribute a richer view of the sociotechnical system around computational news discovery tools, and suggest ways to improve such tools to better support the practices of science journalists.

Wilmer Contreras Sepúlveda, Ángel David Torres-Palencia, José Javier Sánchez Mondragón et al.

Quantum computing is a rapidly emerging and promising field that has the potential to revolutionize numerous research domains, including drug design, network technologies and sustainable energy. Due to the inherent complexity and divergence from classical computing, several major quantum computing libraries have been developed to implement quantum algorithms, namely IBM Qiskit, Amazon Braket, Cirq, PyQuil, and PennyLane. These libraries allow for quantum simulations on classical computers and facilitate program execution on corresponding quantum hardware, e.g., Qiskit programs on IBM quantum computers. While all platforms have some differences, the main concepts are the same. QInterpreter is a tool embedded in the Quantum Science Gateway QubitHub using Jupyter Notebooks that translates seamlessly programs from one library to the other and visualizes the results. It combines the five well-known quantum libraries: into a unified framework. Designed as an educational tool for beginners, Qinterpreter enables the development and execution of quantum circuits across various platforms in a straightforward way. The work highlights the versatility and accessibility of Qinterpreter in quantum programming and underscores our ultimate goal of pervading Quantum Computing through younger, less specialized, and diverse cultural and national communities.

Yuliya Shapovalova, Tom Heskes, Tjeerd Dijkstra

Abstract Background Understanding the synergetic and antagonistic effects of combinations of drugs and toxins is vital for many applications, including treatment of multifactorial diseases and ecotoxicological monitoring. Synergy is usually assessed by comparing the response of drug combinations to a predicted non-interactive response from reference (null) models. Possible choices of null models are Loewe additivity, Bliss independence and the recently rediscovered Hand model. A different approach is taken by the MuSyC model, which directly fits a generalization of the Hill model to the data. All of these models, however, fit the dose–response relationship with a parametric model. Results We propose the Hand-GP model, a non-parametric model based on the combination of the Hand model with Gaussian processes. We introduce a new logarithmic squared exponential kernel for the Gaussian process which captures the logarithmic dependence of response on dose. From the monotherapeutic response and the Hand principle, we construct a null reference response and synergy is assessed from the difference between this null reference and the Gaussian process fitted response. Statistical significance of the difference is assessed from the confidence intervals of the Gaussian process fits. We evaluate performance of our model on a simulated data set from Greco, two simulated data sets of our own design and two benchmark data sets from Chou and Talalay. We compare the Hand-GP model to standard synergy models and show that our model performs better on these data sets. We also compare our model to the MuSyC model as an example of a recent method on these five data sets and on two-drug combination screens: Mott et al. anti-malarial screen and O’Neil et al. anti-cancer screen. We identify cases in which the HandGP model is preferred and cases in which the MuSyC model is preferred. Conclusion The Hand-GP model is a flexible model to capture synergy. Its non-parametric and probabilistic nature allows it to model a wide variety of response patterns.

Nikolay Chepachenko, Marina Yudenko, Anna Gospodinova et al.

The current trend of globalization of the world economy necessitates the use of high-tech developments and innovations that allow achieving strategic goals at the national, regional, and sectoral levels. The prerequisites of the study are determined by the urgency of finding solutions to problematic issues of formation and implementation of priority strategic guidelines for the development of enterprises of the construction sector, designed to ensure an adequate contribution to the strategic vector of advanced industrial, technological and socio-economic development of the construction industry and the national economy. This determines the need to find a solution to the problem of forming and implementing priority strategic guidelines for the development of enterprises mainly by increasing technological and innovative potentials that form the economic potential of the development of enterprises by the type of activity "Construction". The purpose of the study is to identify strategic guidelines for the development of enterprises of the construction sector that meet the targets of the fourth scientific and technological revolution and the achievement of strategic goals for the development of national economies. The findings of the paper outline the key signs of development, inherent in the nature of the development of material objects and economic entities of the economy are revealed. This allowed us to propose a systematization of the formation of priority strategic guidelines for the economic development of construction enterprises, reflecting the relationship with the targets for achieving national goals and strategic objectives for the development of economies of various countries and meeting the targets of the fourth scientific and technological revolution Industry 4.0. The practical implications refer to enterprises of the construction sector.

Jiasui Cai, Jie Su

While China has made major social and economic breakthroughs, it has also raised the level of research, development, and application of science and technology, especially the application of digital technology. Combining digital technology with visual communication design to meet diversified design needs can maximize the level of innovation in visual communication design work. The effective use and continuous innovation of digital technology in visual communication design make visual information more intuitive and image . and constantly bring people a fresh and unique visual experience, and the development of visual communication design has been strongly promoted. This paper analyzes the advantages of the application of digital technology in visual communication design, focusing on the application of digital technology in visual communication design, and from different perspectives such as art space tools, it is extremely critical and important to apply and expand the theory of advanced innovation. From the aspects of artistry, diversification, and science and technology, the application of digital technology in visual communication design is discussed, and the application innovation strategy of digital technology in visual communication design is further discussed. We hope that this research can provide some useful references for the development of modern visual communication design.