Hasil untuk "Computer Science"

R. Kupferman

G. Huet, D. Oppen

Norbert Wiener

Wenbin Ye, YanZhou Duan, Jun Yuan et al.

Abstract In the field of engineering, the utilization of surrogate models to replace computationally intensive simulation software has become a widely adopted approach. However, when addressing complex engineering problems, the costs of simulations can escalate significantly, making it challenging for simulation data to fulfill the training requirements of surrogate models. Recognizing that designers accumulate valuable design knowledge throughout the design process, this knowledge inherently governs the mapping rules between design parameters and performance metrics. This paper introduces a novel method for constructing surrogate models by integrating limited simulation data with engineering knowledge through Bayesian neural networks (B-DaKnow). In B-DaKnow, neural networks employ variational inference and automatic differentiation to amalgamate simulation data and engineering knowledge while optimizing weights and biases via evolutionary algorithms. The proposed methodology is validated using ten benchmark functions and three engineering cases. The experimental results demonstrate that: (1) the incorporation of diverse engineering knowledge enhances prediction accuracy in B-DaKnow to varying degrees; (2) in tackling complex engineering challenges, B-DaKnow exhibits superior performance compared to alternative algorithms; (3) B-DaKnow demonstrates commendable robustness, as evidenced by only slight fluctuations in prediction results across different problems.

Meisya Syahtira, Nurdin Nurdin, Fajriana Fajriana

Energi listrik merupakan kebutuhan vital bagi masyarakat dan menjadi penunjang utama dalam berbagai sektor, termasuk rumah tangga, bisnis, hingga industri. Seiring meningkatnya permintaan listrik setiap tahunnya, PT. PLN (Persero) ULP Lhokseumawe dituntut mampu melakukan perencanaan distribusi dan kapasitas daya yang akurat. Prediksi yang kurang tepat dapat menimbulkan ketidakseimbangan antara pasokan dan kebutuhan energi. Penelitian ini membandingkan dua metode peramalan, yaitu Single Exponential Smoothing (SES) dan Double Exponential Smoothing (DES), untuk memprediksi konsumsi energi listrik di wilayah Lhokseumawe. Data yang digunakan berupa konsumsi listrik bulanan per kecamatan periode 2022–2024, dengan proyeksi prediksi hingga tahun 2027. Tahapan penelitian meliputi pengumpulan data, pra-processing, penerapan metode SES dan DES, evaluasi akurasi menggunakan MAPE, serta perancangan sistem berbasis web menggunakan Python dan Flask. Hasil penelitian menunjukkan bahwa metode SES memiliki tingkat akurasi lebih tinggi dengan nilai MAPE sebesar 5,85%, sedangkan metode DES memperoleh nilai MAPE sebesar 7,87%. Hal ini menegaskan bahwa SES lebih sesuai digunakan untuk data dengan pola fluktuatif acak. Sebaliknya, DES lebih cocok diterapkan pada data dengan pola tren. Melalui perbandingan nilai MAPE, diperoleh gambaran metode mana yang lebih optimal digunakan dalam konteks prediksi konsumsi listrik di Lhokseumawe. Penelitian ini diharapkan dapat memberikan kontribusi praktis bagi PT. PLN (Persero) ULP Lhokseumawe dalam menyusun strategi distribusi energi listrik yang lebih efektif dan efisien.

Francisco-Jose Alvarado-Alcon, Rafael Asorey-Cacheda, Antonio-Javier Garcia-Sanchez et al.

The Internet of Things (IoT) is gaining significant attention for its ability to digitally transform various sectors by enabling seamless connectivity and data exchange. However, deploying these networks is challenging due to the need to tailor configurations to diverse application requirements. To date, there has been limited focus on examining and enhancing the carbon footprint (CF) associated with these network deployments. In this study, we present an optimization framework leveraging machine learning techniques to minimize the CF associated with IoT multi-hop network deployments by varying the placement of the required gateways. Additionally, we establish a direct comparison between our proposed machine learning method and the integer linear program (ILP) approach. Our findings reveal that placing gateways using neural networks can achieve a 14% reduction in the CF for simple networks compared to those not using optimization for gateway placement. The ILP method could reduce the CF by 16.6% for identical networks, although it incurs a computational cost more than 250 times higher, which has its own environmental impact. Furthermore, we highlight the superior scalability of machine learning techniques, particularly advantageous for larger networks, as discussed in our concluding remarks.

Malte Högemann, Malte Högemann, Laura Hein et al.

Generative artificial intelligence (GenAI) is rapidly diffusing into the workplace and is expected to substantially reshape roles, workflows, and skill requirements, particularly for young professionals as early adopters who are highly exposed to these tools. While GenAI is widely regarded as a means to increase productivity, its adoption may simultaneously introduce new challenges, including various forms of technostress. Drawing on 15 semi-structured interviews with young professionals in research and development (R&D), IT, finance, and marketing in organizations piloting or using GenAI, we conducted a structured qualitative content analysis guided by established technostress dimensions. Our findings indicate that classic technostress dimensions remain relevant but manifest differently across sectors and contexts. Moreover, additional GenAI-specific stressors emerged, such as regulatory and compliance ambiguity, data protection and copyright concerns, perceived dependency, potential skill degradation, doubts about the reliability and controllability of AI outputs, and a shift towards more monitoring and conceptual work. At the same time, participants reported techno-eustress in the form of efficiency gains, learning opportunities, and enhanced intrinsic motivation. Overall, the study extends existing technostress frameworks and underscores the importance of AI literacy, clear organizational governance, and supportive work design to mitigate negative technostress while enabling the productive use of GenAI.

Wei Xia, Feifei Song, Zimeng Peng

With the widespread application of small quadcopter drones in the military and civilian fields, the security challenges they face are gradually becoming apparent. Especially in dynamic environments, the rapidly changing conditions make the flight of drones more complex. To address the computational limitations of small quadcopter drones and meet the demands of obstacle perception in dynamic environments, a LiDAR-based obstacle perception algorithm is proposed. First, accumulation, filtering, and clustering processes are carried out on the LiDAR point cloud data to complete the segmentation and extraction of point cloud obstacles. Then, an obstacle motion/static discrimination algorithm based on three-dimensional point motion attributes is developed to classify dynamic and static point clouds. Finally, oriented bounding box (OBB) detection is employed to simplify the representation of the spatial position and shape of dynamic point cloud obstacles, and motion estimation is achieved by tracking the OBB parameters using a Kalman filter. Simulation experiments demonstrate that this method can ensure a dynamic obstacle detection frequency of 10 Hz and successfully detect multiple dynamic obstacles in the environment.

Aijaz H. Lone, Daniel N. Rahimi, Meng Tang et al.

Spintronic-based neuron devices for neural network hardware are gaining increasing attention. However, the majority of these devices are designed to replicate a highly simplified neuronal model known as the leaky integrate-and-fire (LIF) neuron. We present a domain wall motion-based magnetic tunnel junction (DW-MTJ) device that emulates the more bio-plausible FitzHugh–Nagumo neuron model. The neuron characteristics are realized using spin–orbit torque (SOT) driven DW motion in a circular nano-pillar. We obtain sustained magnetization relaxation oscillations in the presence of a DC charge current. The shape, frequency, and phase of the FitzHugh–Nagumo oscillations are controlled by SOT and voltage. A thorough parametric analysis of the proposed neuron device structure is done to assess the device viability with different material systems and environmental conditions. The device consumes energy per spike in the range from 9 to 47.5 fJ, depending upon the parameters. Furthermore, we map the device characteristics to the FitzHugh–Nagumo neuron model by tuning the parameters. The device model is integrated into a fully connected, 3-layer spiking neural network (SNN) framework to classify the MNIST handwritten digit images dataset. We train and test the network under different device conditions. The SNN achieves a classification accuracy of more than 98% in all cases, showcasing its potential for efficient, bio-plausible neuromorphic systems.

Gianluca Aguzzi, Roberto Casadei, Mirko Viroli

Swarm behaviour engineering is an area of research that seeks to investigate methods and techniques for coordinating computation and action within groups of simple agents to achieve complex global goals like pattern formation, collective movement, clustering, and distributed sensing. Despite recent progress in the analysis and engineering of swarms (of drones, robots, vehicles), there is still a need for general design and implementation methods and tools that can be used to define complex swarm behaviour in a principled way. To contribute to this quest, this article proposes a new field-based coordination approach, called MacroSwarm, to design and program swarm behaviour in terms of reusable and fully composable functional blocks embedding collective computation and coordination. Based on the macroprogramming paradigm of aggregate computing, MacroSwarm builds on the idea of expressing each swarm behaviour block as a pure function, mapping sensing fields into actuation goal fields, e.g., including movement vectors. In order to demonstrate the expressiveness, compositionality, and practicality of MacroSwarm as a framework for swarm programming, we perform a variety of simulations covering common patterns of flocking, pattern formation, and collective decision-making. The implications of the inherent self-stabilisation properties of field-based computations in MacroSwarm are discussed, which formally guarantee some resilience properties and guided the design of the library.

Behnam Faghih, Amin Shoari Nejad, Joseph Timoney

Abstract Performing musical notes correctly does not mean that all the performers will play the notes at the exact same pitch and duration. However, it does imply that they are performing the notes within acceptable psychoacoustic ranges. Therefore, this article aims to find the range of a note’ duration and pitch according to its position in a piece of music by analysing several parameters in trained-professional singers’ behaviours in singing notes. To achieve the goal, the variations of eight variables on 2688 solo singing recorded files by trained professional singers were investigated to find the relationships between a performed note’s F0 and duration with these variables. The variables considered in this study are the interval to the following and previous notes, the existence of rest before or after the note, the note’s MIDI pitch code and duration in a music score, and the particular singing technique applied. The Bayesian hierarchical model was used to find the effect of the variables on the pitch and duration of a note sung by professionals, mainly in opera style, singers. The investigation confirms that these parameters affect the pitch and duration of notes performed by professional singers. Finally, this paper proposes formulas to calculate the pitch frequency and duration of the notes according to the variables to simulate the behaviour of the trained-professional singers in performing notes’ pitches and duration.

TAN Ruoqi, DONG Minggang, ZHAO Weixiao, WU Tianhao

Holding non-motorized vehicles accountable for legal violations effectively enhances urban traffic safety. Non-motorized vehicle license plates are characterized by small size, dense distribution, and ease of being obscured, which leads to significant feature information loss during the detection process in traditional deep learning-based methods. A non-motorized vehicle license plate recognition and localization method based on semantic alignment and hierarchical optimization is proposed. In this method, a semantic alignment module is designed for the underlying information fusion. During the upsampling process, low-level target information is used to guide the fusion of high-level semantics downwards, addressing the loss of small target features caused by conflicts between high- and low-level semantics. Subsequently, a hierarchical optimization module is constructed within the CSP structure to replace the deep ELAN module. This module uses a stack of a few convolutional kernel modules to extract the target information, reducing the number of network layers and preventing the loss of feature information at deeper levels. In the final stage, the K-Means++ algorithm is employed to cluster and obtain the initial anchor boxes suitable for non-motorized license plates to reduce the matching error during the training process. This approach aims to improve the accuracy of small-object recognition and localization. The experimental results demonstrate that the proposed method achieves a recognition and localization accuracy of 90.95% on a non-motorized vehicle license plate dataset. Compared with representative methods such as YOLOv7 and YOLOv8, it improves the accuracy by at least 3.58%. The proposed approach is effective for non-motorized vehicle license plate recognition and localization.

Тураева Н.М.

В данной статье рассматривается математическая модель цифровой системы автоматического сопровождения цели по дальности, которая, в отличие от существующих, удовлетворяет по всем требованиям устойчивости и качеству системы измерения дальности и автоматического сопровождения цели. Также в статье показана структурная схема и построена математическая модель преобразователя «код-временная задержка», которая исследована на устойчивость и качество, определены допустимые области параметров цифрового управляющего устройства, обеспечивающие устойчивость работы построенной математической модели. Определены допустимые области параметров алгоритма работы цифрового управляющего устройства, при которых система автоматического сопровождения дальности соответствует своему предназначению.

Syed Rizvi, Akash Awasthi, Maria J. Peláez et al.

Abstract The COVID-19 pandemic affected countries across the globe, demanding drastic public health policies to mitigate the spread of infection, which led to economic crises as a collateral damage. In this work, we investigate the impact of human mobility, described via international commercial flights, on COVID-19 infection dynamics on a global scale. We developed a graph neural network (GNN)-based framework called Dynamic Weighted GraphSAGE (DWSAGE), which operates over spatiotemporal graphs and is well-suited for dynamically changing flight information updated daily. This architecture is designed to be structurally sensitive, capable of learning the relationships between edge features and node features. To gain insights into the influence of air traffic on infection spread, we conducted local sensitivity analysis on our model through perturbation experiments. Our analyses identified Western Europe, the Middle East, and North America as leading regions in fueling the pandemic due to the high volume of air traffic originating or transiting through these areas. We used these observations to propose air traffic reduction strategies that can significantly impact controlling the pandemic with minimal disruption to human mobility. Our work provides a robust deep learning-based tool to study global pandemics and is of key relevance to policymakers for making informed decisions regarding air traffic restrictions during future outbreaks.

S. Kirkpatrick, B. Selman

M. Kojima, N. Megiddo, Toshihito Noma et al.

Philip R. Cohen, Michael Johnston, David R. McGee et al.

Akanksha Arora, Hitendra Garg, Shivendra Shivani

The increase in information sharing in terms of digital images imposes threats to privacy and personal identity. Digital images can be stolen while in transfer and any kind of alteration can be done very easily. Thus, privacy protection of digital images from attackers becomes very important. Encryption, steganography, watermarking, and visual cryptography techniques to protect digital images have been proposed from time to time. The present paper is focused on the enhancement of privacy protection of digital images utilizing watermarking and a QR code-based expansion-free and meaningful visual cryptography approach which generates visually appealing QR codes for transmitting meaningful shares. The original secret image is processed with a watermark image (copyright logo, signature, and so on), and then halftoning of the watermarked image has been done to limit pixel expansion. Then, the halftoned image has been partitioned using VC into two shares. These shares are embedded with a QR code to make the shares meaningful. Lossless compression has been performed on the QR code-based shares. The compression method employed in visual cryptography would save space and time. The proposed approach keeps the beauty of visual cryptography, i.e., computation-free decryption, and the size of the recovered image the same as the original secret image. The experimental results confirm the effectiveness of the proposed approach.

Phillip RogawayyFebruary

LIU Baobao, WANG Heying, TAO Lu et al.

In order to tackle the problem of unbalanced distribution of educational resources in some regions, taking the real data of teachers and book resource allocation in 13 districts as example, an educational resource distribution model was proposed based on differential evolution (DE) algorithm, the effect of educational resource allocation model were compared and analyzed by simulation experiment. The results show that the model has similar allocation performance and the same time complexity, they can allocate educational resources reasonably and provide decision-making basis for education management departments, compared with the educational resource allocation model based on particle swarm (PSO) algorithm. However, with the increase of the amount of educational resources data, the model can obtain the optimal solution in fewer iterations, and the distribution result can effectively improve the problem of unbalanced distribution of educational resources. Finally, in order to verify the validity of the model, an educational resource allocation model based on artificial fish swarm algorithm is also proposed. The visualization of the distribution of educational resources data by three models is realized, which provides a certain theoretical basis for the statistics and distribution of educational resources.