Hasil untuk "Information technology"

B.S. Prashanth, Manoj Kumar, Ariful Hoque et al.

The development of online banking has brought about an increase in fraudulent operations, which is a major problem for banks. This study delves into the urgent requirement for interpretable, scalable, and top-notch fraud detection systems by using TabNet, an adaptable deep learning framework, on a Kaggle dataset consisting of actual bank transactions in India. Maximizing operational risk management by improving the accuracy of transaction anomaly detection and ensuring regulatory compliance through transparent models is the goal.We utilize a supervised learning pipeline that incorporates the Synthetic Minority Over-sampling Technique (SMOTE) to ensure that classes are balanced. Subsequently, we conduct thorough exploratory data analysis (EDA) to identify patterns of fraud, both during specific times and across behaviors. On this dataset, five different deep learning architectures are tested: DNN, GRU, LSTM, CNN1D, and TabNet. Assessment of predictive performance was carried out using a 3-fold cross-validation framework. With a ROC-AUC of 0.9739 and an accuracy of 97.39 %, TabNet considerably outperformed the competition. The method of sparse feature selection used improved interpretability, generalized better on tabular data, and produced fewer false positives and negatives.Critical insights for operational fraud detection systems and a contribution to the broader literature on explainable AI (XAI) in financial decision-making are offered by the findings. Goals 8 and 16 of the Sustainable Development Agenda are supported by this study, which promotes inclusive economic growth and institutional transparency. Supporting strong, policy-compliant, and interpretable decision-support systems, it also offers practical use for real-time implementation in banking infrastructure.

Somayyeh Asgari, Tapio Fabritius

Abstract This paper presents a novel terahertz (THz) graphene-based tunable metamaterial that operates as a frequency-multiplexed logic device. The structure consists of a gold layer, a dielectric substrate, and an array of graphene resonators formed by two circular ring resonators per unit cell. The metamaterial is simulated and designed in CST Software. The equivalent circuit model (ECM) for the metamaterial is obtained using MATLAB code. Logical input values are set by adjusting the Fermi levels of graphene-based circular resonators, while output logic states are determined by analyzing the reflection spectrum. The proposed device operates within the THz range, enabling the realization of OR, XNOR, and NAND logic gates at three distinct frequencies. Additionally, the working frequencies of these gates can be tuned by modifying the graphene’s Fermi level. The highest extinction ratios (ERs) achieved for the OR, XNOR, and NAND gates are 36.93, 65.66, and 22.38 dB, respectively. Owing to its simple design and versatility, this metamaterial shows strong potential for use in THz digital systems.

Fei Li, Qinye Zhang, Yuntong Lu et al.

IntroductionCodon usage bias (CUB) can influence host-microbe interactions and stress adaptation. In this study, we aimed to investigate how codon usage bias (CUB) similarity between Arabidopsis thaliana and Bacillus amyloliquefaciens influences their interaction and contributes to the adaptation of A. thaliana to high calcium stress.MethodsThe CUB indices of both species were computed, and genes with high correlations were identified. The transcriptome sequencing data of gene expression in A. thaliana cultured under normal and high calcium conditions, with and without B. amyloliquefaciens treatment was used to analyze the expression of A. thaliana genes with CUB similar to that of B. amyloliquefaciens in relation with the adaptation of A. thaliana to high calcium stress and the interaction between both organisms.ResultsWe identified 19210 A. thaliana genes with CUB similar to B. amyloliquefaciens and 95 B. amyloliquefaciens-responsive and calcium-responsive genes in A. thaliana, which were involved in transport, carbohydrate metabolism, and response to chemical, and cellular homeostasis. Differential expression analysis showed a total of 733 A. thaliana genes with CUB similar to B. amyloliquefaciens to be dysregulated, among which 47 changed when A. thaliana was cultivated in the presence of the B. amyloliquefaciens LZ04 strain, 643 under high calcium condition and 43 with calcium treatment and the presence of the B. amyloliquefaciens LZO4 strain. The gene ontology (GO) biological processes termed among others of response to endogenous stimulus, response to oxygen containing compound, response to organic substance, response to abiotic and biotic stimuli, response to stress, and response to light stimulus, regulation of hormone levels, response to nutrient levels, post-embryonic plant morphogenesis, metabolic process, cell growth.DiscussionThese findings highlight the importance of CUB in the interaction between A. thaliana and B. amyloliquefaciens as well as in the adaptation of A. thaliana to high calcium stress. They also show the underlying regulatory role of B. amyloliquefaciens, which could help develop new tactics for improving A. thaliana growth and yield in karst regions. A more elaborate analysis of the value of CUB in the interaction of these two organisms could assist in engineering host- sensitive micro-organism strains and enhance the microbial-based approaches for the improvement of A. thaliana growth and yield in such areas and for managing abiotic stress in crops.

Kawuryan Megandaru Widhi, Fahlevvi Mohammad Rezza, Putri Titis Sari et al.

This study examines the combination of governance and green technology to facilitate the sustainable development of tourism in Cirebon City, Indonesia. Employing a qualitative case study design, data were collected through document analysis, participatory observation, and interviews with 21 informants from the community, local government, and tourism enterprise. The findings reveal that the achievements and challenges in Cirebon's tourism are insufficient infrastructure, inefficient use of ICT, and inadequate environmental regulations. The study also offers strategic recommendations, including infrastructure development, utilization of digital platforms, and enhanced public participation. The study is contextual to Cirebon, yet the findings yield valuable lessons on sustainable tourism elsewhere in similar settings. This study contributes a strategic plan integrating the Triple Bottom Line framework with the emphasis on economic, social, and environmental perspectives for sustainable development of tourism.

Jürgen Soom, Isabel Boavida, Renan Leite et al.

The need for efficient approaches to track and assess fish behavior in rivers impacted by hydropeaking is increasing. Nonetheless, employing an automated camera system for underwater monitoring requires that the algorithms function under highly variable environmental conditions, which affect the ability to detect and assess fish size. Additionally, there is a lack of openly accessible freshwater fish classification and size estimation datasets. To address these limitations, we propose a binocular underwater fish monitoring system capable of real-time fish detection and size estimation. The system was deployed and tested over one week in two Portuguese rivers affected by hydropeaking. The week-long analysis also provided new insights regarding wild fish behavior in rivers affected by hydropeaking. Results indicate that hydropeaking strongly influences how fish may use instream flow refuges during hydropeaking. Fish were less frequently detected in the flow refuge during peak flow events, suggesting that the flow conditions created habitat instability and difficulty accessing the flow refuge. In contrast, fish in the non-hydropeaking river consistently used refuge areas, reinforcing their importance as shelter during natural flow variations. This study demonstrates the potential of a computer vision-based pipeline for real-time, fully automated fish monitoring of hydropeaking’s impacts on riverine fish. Additionally, we provide PTFish, an open dataset with 18,523 manually annotated frames featuring infrared and color video frames. These findings emphasize that automated, camera-based solutions for hydropeaking monitoring can be used to develop evidence-based mitigation strategies to sustain fish populations in rivers impacted by hydropeaking.

Haoliang Wang, Zarina Shukur, Khairul Akram Zainol Ariffin et al.

Abstract In recent years, online examinations have been widely adopted because of their flexibility, but the covert and diverse nature of cheating behaviour poses a serious challenge to the fairness and integrity of examinations. Existing anti-cheating techniques are deficient in detecting diverse cheating behaviours in real-time and ensuring the credibility of evidence. To address this problem, this paper proposes an integrated solution for online exam cheating detection based on the lightweight YOLOv12 model and blockchain trusted depository. Firstly, we made targeted lightweight improvements to the benchmark YOLOv12n model by removing the computationally intensive Attention mechanism from the backbone network and simplifying the module structure (modifying the A2C2f module), as well as replacing the computationally heavy C3k2 module in the head network with the efficient C3Ghost module. These modifications aim to reduce the model’s computational complexity and number of parameters, increasing inference speed, thus making it more suitable for real-time detection tasks. Secondly, to address the issue of credible evidence preservation concerning cheating, we constructed a evidence preservation system based on the Hyperledger Fabric consortium blockchain, combined with IPFS distributed storage technology. Key screenshots of suspected cheating behaviors are stored on IPFS, and their content identifier (CID) along with detection metadata (such as timestamp, detection type, confidence, etc.) is recorded on the blockchain through smart contracts, ensuring the originality, integrity, and immutability of the evidence. Experiments conducted on an online exam cheating dataset containing categories of ’person’ and ’electronic devices’ demonstrate that the proposed lightweight YOLOv12NoAttn model exhibits competitive detection performance (with slight improvements in mAP50 and Recall) while showing higher efficiency by significantly reducing parameters (approximately 28%) and GFLOPs (approximately 13%). Ablation experiments further verify the effectiveness of the lightweight improvements made to both the backbone and head networks. This research provides an efficient, accurate, and trustworthy solution for cheating detection and evidence management in online examinations, contributing to the maintenance of fairness and integrity in online assessments.

Mohammad Ebrahim Hajiabadi, Mahdi Samadi, Mohammad Hassan Nikkhah et al.

Abstract One of the primary challenges faced by generation companies (GenCos), which operate multiple generation units within the electricity market, is the determination of the optimal bid price for these units to maximize profit. This paper proposes a novel approach to ascertain the optimal bid price direction for GenCos by leveraging the gradient vector of the profit function within the constraints of the electricity market. First, the Jacobian matrix of unit profits is computed using the electricity market structural decomposition method. This matrix highlights how the profit of generation units is affected by market input parameters, including the bid prices of the units. Then, the gradient vector of the GenCos' profit function and the optimal bid price direction are derived from the Jacobian matrix. The methodology is applied to a 24‐bus IEEE network, with results validated against those from a simulation method to confirm the efficacy of the proposed approach. The simulation results show that the highest and lowest profit changes with a step increase of 0.1$/MWh are observed for GenCo 4 and GenCo 6 with values of 60.28 and 2.20 $/h, respectively. The proposed approach can be effective in the changes of bid direction of the units of a GenCo to achieve the highest possible profit.

Yuqing Ye, Guoliang Yun, Yuanrong He et al.

Urbanization is a crucial indicator which reflects the socio-economic development of a country or region. The regions across the Taiwan Strait (TSR) have garnered attention worldwide as being representative of typical urbanization development along the southeastern coast. Currently, research in the TSR predominantly focuses on individual regions, with limited academic achievements comparing urbanization paths across the strait. In particular, the domain of comparative analysis of the spatiotemporal characteristics of urbanization dynamics in TSR by using long time series of nighttime light data remains largely underexplored. Therefore, this study focused on comparing the urbanization paths in the TSR and analyzing the spatiotemporal characteristics of urbanization by using the long-term nighttime light data from 1992 to 2020. Additionally, some methods such as Theil–Sen median trend analysis, Mann–Kendall significance test, Hurst exponent, spatial statistics, and time series were used to quantitatively analyze the spatial distribution patterns and temporal trends of nighttime lights in the TSR since 1992. The results were as follows: (1) From 1992 to 2020, the spatial distribution of nighttime light data in TSR exhibited significant spatial heterogeneity, with high-value areas mainly located in southeastern Fujian and northwestern Taiwan, while low-value areas were concentrated in Fujian’s inland regions; (2) During this period, nighttime lighting data increased from 729,863 in 1992 to 2,729,052 in 2020, and the percentage of its high-value (40–063) increased from 2.59% in 1992 to 12.22% in 2020; (3) Comparison of nighttime light data across representative cities from Taiwan (Taipei, Hsinchu) and Fujian (Xiamen, Fuzhou) uncovered distinct growth patterns—while Taiwanese cities had a high initial brightness value (the lowest value in the last 30 years was 518,379.4), their growth was relatively slow (average growth rate of 17%); Fujian cities, on the other hand, started from lower initial brightness value (the lowest value in the last 30 years was 35,123.1), but displayed substantial growth vigor (average growth rate of 222%); (4) During the study period, the nighttime light data of the vast majority of cities in the TSR demonstrated a significant increasing trend, particularly in coastal areas and urban centers; (5) Predictions of future trend variation suggest that the significantly increasing trend of cities surrounding Taiwan’s primary metropolitan areas will intensify, whereas metropolitan regions such as Keelung may witness a decline in future trend variations. However, only a mere 0.03% of the nighttime light data show a significant decreasing trend. Additionally, there are distinct differences in the urbanization development stages of the TSR. Fujian is currently undergoing rapid urbanization, while Taiwan’s urbanization has entered a stable stage. The study reveals that factors such as geographical location, natural resources, transportation infrastructure, population size, and industrial structure collectively influence the urbanization characteristics of the TSR. This research bears substantial significance for deepening the comprehension of the patterns and processes of urbanization development in the TSR and provides valuable insights for urban construction and development across the strait.

Carolyn A Lin, Xihui Wang, Linda Dam

Extant research addressing the relations between TikTok videos and sustainable apparel consumption behavior is limited. This study explores these relations by testing the following theories and constructs: social consciousness, prior sustainable apparel purchasing, attitude toward TikTok videos (featuring sustainable apparel content), and theory of planned behavior. Results from an online survey supported the proposed conceptual framework, suggesting that cognitive, affective, and behavioral factors relevant to sustainable apparel consumption had a positive influence on sustainable apparel purchase intention.

MA Jing, CAO Du, MA Lili

Aero-engine´s characteristics vary with flight conditions and operating states. In complex operating environments, both model uncertainty and controller parameter variation exist simultaneously, which greatly affect the control performance in the whole flight envelope. Therefore, a robust elastic adaptive control method based on parameter perturbation model is proposed in this paper. The structural model of aero-engine parameter perturbation is established. Then, aiming at the uncertainty of the controlled object model and the perturbation of controller gain, the robust resilient adaptive control law is designed when the gain perturbation is bounded but the upper bound is unknown by using Lyapunov stability theory and linear matrix inequality constraints, and the controller design problem is transformed into a feasible solution problem of linear matrix inequalities. The controller design only depends on the existence of the solution matrix of linear matrix inequalities, and the stability of the algorithm is proved. On this basis, the control simulation of different operating states of the engine in the flight envelope is carried out. The simulation results show that the adjustment time is less than 1.8 s and the overshoot is less than 5%, which indicates good stability and control performance of the designed controller.

S. Graham

Mengmeng Tao, Jingfeng Ye, Xisheng Ye et al.

A thermal model concerning resonantly pumped high power Tm-doped fiber amplifiers is established with temperature dependent parameters taken into consideration. With this model, performance of resonantly pumped Tm-doped fiber amplifiers at 1 kW output is investigated. Comparisons with the traditional 793 nm LD pump scheme shows that, resonant pumping, especially the 1.9 μm pump, is more favorable for high power Tm-doped fiber systems, featuring high operation efficiency with low heat load, limited temperature rise, controllable beam compression and a relatively small laser intensity at the output end. Besides, the power scalability of resonantly pumped Tm-doped fiber systems with 25/250 double-clad fiber is also explored numerically with various thermal effects, optical damage and nonlinear effects taken in account. Simulations show that, for 1 GHz narrow linewidth output, outer cladding damage and stimulated Brillouin scattering are the two primary limiting factors for power scaling. And, the maximal output of a Tm-doped fiber amplifier could reach 5.1 kW and 6.8 kW for 1.6 μm pump and 1.9 μm pump, respectively. For systems with broad spectrum, output approaching 10 kW can be expected.

Xiao Wei, Xiao Wei, Hongbo Guo et al.

Cerenkov luminescence tomography (CLT) is a promising non-invasive optical imaging method with three-dimensional semiquantitative in vivo imaging capability. However, CLT itself relies on Cerenkov radiation, a low-intensity radiation, making CLT reconstruction more challenging than other imaging modalities. In order to solve the ill-posed inverse problem of CLT imaging, some numerical optimization or regularization methods need to be applied. However, in commonly used methods for solving inverse problems, parameter selection significantly influences the results. Therefore, this paper proposed a probabilistic energy distribution density region scaling (P-EDDRS) framework. In this framework, multiple reconstruction iterations are performed, and the Cerenkov source distribution of each reconstruction is treated as random variables. According to the spatial energy distribution density, the new region of interest (ROI) is solved. The size of the region required for the next operation was determined dynamically by combining the intensity characteristics. In addition, each reconstruction source distribution is given a probability weight value, and the prior probability in the subsequent reconstruction is refreshed. Last, all the reconstruction source distributions are weighted with the corresponding probability weights to get the final Cerenkov source distribution. To evaluate the performance of the P-EDDRS framework in CLT, this article performed numerical simulation, in vivo pseudotumor model mouse experiment, and breast cancer mouse experiment. Experimental results show that this reconstruction framework has better positioning accuracy and shape recovery ability and can optimize the reconstruction effect of multiple algorithms on CLT.

G. Dakin