检索结果-南通市图书馆

Detecting anomalies in blockchain transactions using machine learning classifiers and explainability analysis

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

BLOCKCHAIN-RESEARCH AND APPLICATIONS 2024年第3期5卷 106-122页

作者： Hasan, mohammad rahman, mohammad Shahriar Janicke, Helge Sarker, Iqbal H. Premier Univ Dept Comp Sci & Engn Chitagong 4000 Bangladesh United Int Univ Dept Comp Sci & Engn Dhaka 1212 Bangladesh Cyber Secur Cooperat Res Ctr Perth 6027 Australia Edith Cowan Univ Ctr Securing Digital Futures Perth 6027 Australia

As the use of blockchain for digital payments continues to rise, it becomes susceptible to various malicious attacks. Successfully detecting anomalies within blockchain transactions is essential for bolstering trust in digital payments. However, the task of anomaly detection in blockchain transaction data is challenging due to the infrequent occurrence of illicit transactions. Although several studies have been conducted in the field, a limitation persists: the lack of explanations for the model's predictions. This study seeks to overcome this limitation by integrating explainable artificial intelligence (XAI) techniques and anomaly rules into tree-based ensemble classifiers for detecting anomalous Bitcoin transactions. The shapley additive explanation (SHAP) method is employed to measure the contribution of each feature, and it is compatible with ensemble models. Moreover, we present rules for interpreting whether a Bitcoin transaction is anomalous or not. Additionally, we introduce an under-sampling algorithm named XGBCLUS, designed to balance anomalous and non-anomalous transaction data. This algorithm is compared against other commonly used under-sampling and over-sampling techniques. Finally, the outcomes of various tree-based single classifiers are compared with those of stacking and voting ensemble classifiers. Our experimental results demonstrate that: (i) XGBCLUS enhances true positive rate (TPR) and receiver operating characteristic-area under curve (ROC-AUC) scores compared to state-of-the-art under-sampling and over-sampling techniques, and (ii) our proposed ensemble classifiers outperform traditional single tree-based machine learning classifiers in terms of accuracy, TPR, and false positive rate (FPR) scores.

关键词： Anomaly detection Blockchain Bitcoin transactions Data imbalance Data sampling Explainable AI Machine learning Decision tree Anomaly rules

Intelligent Vehicle for Urban Road Traffic Recognition System Using Deep Learning Algorithm

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Intelligent Vehicle for Urban Road Traffic Recognition Syste...

作者： ASHIKUR rahman mohammad 重庆交通大学

学位级别：硕士

城市道路的目标识别和监测技术是计算机视觉领域的关键研究途径,在日常生活中得到了广泛应用。人类探测作为主要焦点,具有独特的特征,将目标的典型属性与无与伦比的可变性相结合。因此,与行人检测和跟踪相关的技术挑战超过了普通目标所... 详细信息

城市道路的目标识别和监测技术是计算机视觉领域的关键研究途径,在日常生活中得到了广泛应用。人类探测作为主要焦点,具有独特的特征,将目标的典型属性与无与伦比的可变性相结合。因此,与行人检测和跟踪相关的技术挑战超过了普通目标所面临的挑战,这使得这一主题变得特别复杂和苛刻。对这一主题的探索不仅具有科学研究意义,而且具有相当大的社会应用价值。智能汽车技术的快速发展导致了解决城市道路交通复杂性的范式转变。本文介绍了新能源智能汽车领域内交通识别系统的一种开创性方法,利用最先进的深度学习算法。本研究强调YOLO v8(You Only Look Once)和DETR(Detection Transformer)的融合,推动了物体检测的前沿,特别是在自动驾驶汽车的背景下。使用深度学习算法进行城市道路交通监测面临着一些挑战,包括高计算需求、实时处理要求、多样化和复杂的城市环境,以及对物体检测和分类的高精度要求。像Faster R-CNN这样的传统模型虽然准确,但计算密集且速度较慢,因此不太适合实时应用。DETR以其基于转换器的架构提供了稳健的特征提取,但可能会在速度和复杂性方面遇到困难。YOLO模型效率高、速度快,适用于实时检测,但它们可能会为速度牺牲一些准确性。所提出的DETR-YOLO v8n融合模型旨在通过将DETR的鲁棒特征提取的优势与YOLO v8n的实时检测能力相结合来解决这些问题。这种融合利用注意力机制来突出相关特征,在不显著影响速度的情况下提高准确性。通过集成这些方法,DETR-YOLO v8n Fusion模型提供了一个平衡的解决方案,可以提高检测精度,保持实时处理,并有效地导航城市道路环境的复杂性,从而改善整体交通监控和管理。这项研究错综复杂地探索了YOLO v8的细微改进,展示了其在城市道路交通场景中的卓越性能。细化的锚盒预测细化了空间定位,而特征金字塔网络增强了模型在不同尺度上辨别物体的能力。先进的主干架构增强了特征提取,从而增强了网络的整体辨别能力。所提出的系统以YOLO v8和DETR的融合为基础,强调了其在复杂交通环境中显著提高新能源智能汽车安全性和有效性的潜力。这项研究不仅有助于新兴的智能交通解决方案领域,而且有助于不断完善自动驾驶汽车的目标检测机制。这些发现强调了接受YOLO v8进化改进的关键性,为追求智能和响应能力强的城市交通系统的先进识别系统树立了新的基准。近年来,深度学习的出现在计算机视觉方面取得了重大进展,特别是在目标检测精度方面。然而,深度模型的复杂性阻碍了检测速度的提高,再加上硬件需求的提高,从而阻碍了其对行人检测和跟踪的适用性。因此,本文对行人检测与跟踪进行了全面的研究。这项研究的高潮涉及对峰值响应和目标损失之间相关性的检查。在本文中,我们使用最新的YOLO v8升级了这三项改进,用于城市道路的交通监控。*** v8引入了精细的锚盒预测,增强了空间定位,以更精确地识别对象位置。这一改进对于智能汽车在复杂城市环境中的精确导航至关重要。2.在YOLO v8中引入特征金字塔网络解决了多尺度检测中的挑战。这种增强使该模型能够有效地识别和分类不同大小的对象,确保在不同的交通场景中具有强大的检测能力。*** v8的高级骨干架构提高了特征提取效率,捕捉了复杂的细节和上下文信息。这一改进提高了模型的鉴别力,特别是在具有挑战性的城市道路交通条件下,从而提高了物体检测任务的整体性能。在我之前的研究中,我使用Tensor Flow深度学习框架,来完成网络模型的设计与训练。为了验证本文提出模型的可行性与检测效果,将本文算法的检测实验结果与当前常见的目标检测算法进行对比分析,对比的算法包括SSD、YOLO V3和GANet(Guided Attention Net Work),在相同数据集进行对比,检测准确率结果如下:SSD模型的平均查准率为68.2%,YOLO V3网络模型的平均查准率为73.8%,GANet网络模型的平均查准率为76.8%:而本文采用的Faster R-CNN平均查准率为86.3%。由此可知,Faster R-CNN网络模型在城市道路目标检测准确.在智能汽车自动驾驶道路智能识别实验中,本文改进了DETR(Detection Transformer)网络结构,并与其他常见的识别算法,如Faster R-CNN、YOLO(You Only Look Once)和SSD(Single Shot Multi Box Detector)进行了对比。在我之前的研究中,它的结果如下,以评价指标的数据说明:(1)准确率(Precision):指模型检测到的物体中真实物体的比例。综合了测试集上的准确率结果,DETR网络达到了90%的准确率,超过了Faster R-CNN和YOL

关键词：深度学习 YOLOv8模型交通检测 DETR Faster R-CNN 自动驾驶

Surface Morphology and Thermo-Electrical Energy Analysis of Polyaniline (PANI) Incorporated Cotton Fabric

同方学位论文库评论

在线全文

同方学位论文库

学校读者我要写书评

暂无评论

Energy Engineering 2024年第1期121卷 1-12页

作者： Md.Shohan Parvez Md.Mustafizur rahman Mahendran Samykano mohammad Yeakub Ali Automotive Engineering Research Group Faculty of Mechanical and Automotive Engineering TechnologyUniversiti Malaysia Pahang Al-Sultan AbdullahPekanMalaysia Department of Textile Engineering Khulna University of Engineering&Technology(KUET)KhulnaBangladesh Centre for Research in Advanced Fluid and Processes(CARIFF) Universiti Malaysia Pahang Al-Sultan AbdullahLebuhraya Tun RazakGambangMalaysia Mechanical Engineering Programme Area Faculty of EngineeringUniversiti Teknologi BruneiBruneiDarussalam

With the exponential development in wearable electronics,a significant paradigm shift is observed from rigid electronics to flexible wearable ***(PANI)is considered as a dominant material in this sector,as it is endowed with the optical properties of both metal and ***,its widespread application got delineated because of its irregular rigid form,level of conductivity,and precise choice of *** PANI in textile materials can generate promising functionality for wearable *** research work employed a straightforward in-situ chemical oxidative polymerization to synthesize PANI on Cotton fabric surfaces with varying dopant(HCl)***-treatment using NaOH is implemented to improve the conductivity of the fabric surface by increasing the monomer *** research explores the morphological and structural analysis employing SEM,FTIR and *** surface resistivity was measured using a digital multimeter,and thermal stability is measured using *** successful polymerization,a homogenous coating layer is *** is revealed that the simple pre-treatment technique significantly reduces the surface resistivity of Cotton fabric to 1.27 kΩ/cm with increasing acid concentration and thermal *** electro-thermal energy can also reach up to 38.2°C within 50 s with a deployed voltage of 15 *** modified fabric is anticipated to be used in thermal regulation,supercapacitor,sensor,UV shielding,antimicrobial and other prospective functional applications.

关键词： Polyaniline cotton in-situ polymerization SEM TGA heating fabric

Urban Freight Consolidation Model for Post-Hauler Planning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Transportation Technologies 2024年第2期14卷 255-272页

作者： mohammad Anwar rahman School of Engineering Science & Technology Central Connecticut State University New Britain USA

Freight transportation in urban areas has increased significantly in a shorter period due to the widespread use of e-commerce, fast delivery, and population growth. Recently, a noticeable government initiative aimed at creating an effective, acceptable, and sustainable city logistics policy. This paper examines freight consolidation as a transportation strategy for optimizing last-mile delivery costs. Freight consolidation involves combining smaller shipments from various origins into a single, larger shipment for more efficient transportation to a common destination. This approach is particularly beneficial for last-mile delivery, where frequent deliveries of smaller quantities are frequently visible. Finally, we provide an illustrative example targeting urban freight stakeholders for practicing possible consolidation methodology. The result in the illustrative example shows that freight with 3-day consolidation, despite the delay penalty, is cheaper than daily shipping, and both are cheaper than 2-day consolidated shipping. The study will benefit urban businesses and freight services.

关键词： Freight Consolidation Urban Transport Intermodal Last-Mile Delivery

Choosing Multimodal Freight Mix: An Integrated Multi-Objective Multicriteria Approach

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Transportation Technologies 2024年第3期14卷 402-422页

作者： mohammad Anwar rahman School of Engineering Science & Technology Central Connecticut State University New Britain CT USA

Multimodal freight transportation emerges as the go-to strategy for cost-effectively and sustainably moving goods over long distances. In a multimodal freight system, where a single contract includes various transportation methods, businesses aiming for economic success must make well-informed decisions about which modes of transport to use. These decisions prioritize secure deliveries, competitive cost advantages, and the minimization of environmental footprints associated with transportation-related pollution. Within the dynamic landscape of logistics innovation, various multicriteria decision-making (MCDM) approaches empower businesses to evaluate freight transport options thoroughly. In this study, we utilize a case study to demonstrate the application of the Technique for Order Preference by Similarity to the Ideal Solution (TOPSIS) algorithm for MCDM decision-making in freight mode selection. We further enhance the TOPSIS framework by integrating the entropy weight coefficient method. This enhancement aids in assigning precise weights to each criterion involved in mode selection, leading to a more reliable decision-making process. The proposed model provides cost-effective and timely deliveries, minimizing environmental footprint and meeting consumers’ needs. Our findings reveal that freight carbon footprint is the primary concern, followed by freight cost, time sensitivity, and service reliability. The study identifies the combination of Rail/Truck as the ideal mode of transport and containers in flat cars (COFC) as the next best option for the selected case. The proposed algorithm, incorporating the enhanced TOPSIS framework, benefits companies navigating the complexities of multimodal transport. It empowers making more strategic and informed transportation decisions. This demonstration will be increasingly valuable as companies navigate the ever-growing trade within the global supply chains.

关键词： Multimodal Freight Transport MCDM TOPSIS Entropy Technique COFC

Rhizobium Inoculation and Micronutrient Addition Influence the Growth,Yield,Quality and Nutrient Uptake of Garden Peas(Pisum sativum L.)

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Phyton-International Journal of Experimental Botany 2024年第5期93卷 901-922页

作者： MdAbdul Quddus MdAtaur rahman Razu Ahmed mohammad Eyakub Ali Khokan Kumer Sarker MdAlamgir Siddiky Mohibur rahman Lamya Ahmed Alkeridis Samy Sayed Ahmed Gaber Akbar Hossain Horticulture Research Centre Bangladesh Agricultural Research InstituteGazipur1701Bangladesh Soil Science Division Bangladesh Agricultural Research InstituteGazipur1701Bangladesh Irrigation and Water Management Division Bangladesh Agricultural Research InstituteGazipur1701Bangladesh Regional Agricultural Research Station Bangladesh Agricultural Research InstituteCumilla3500Bangladesh Department of Biology College of SciencePrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Science and Technology University College‑RanyahTaif UniversityP.O.Box 11099Taif21944Saudi Arabia Department of Economic Entomology and Pesticides Faculty of AgricultureCairo UniversityGiza12613Egypt Department of Genetics Faculty of AgricultureCairo UniversityGiza12613Egypt Department of Biology College of ScienceTaif UniversityTaif21944Saudi Arabia Division of Soil Science Bangladesh Wheat and Maize Research InstituteDinajpur5200Bangladesh

Garden pea productivity and qualities are hampered in zinc(Zn),boron(B),and molybdenum(Mo)deficient ***,the combination of micronutrients(i.e.,Zn,B,and Mo)and rhizobium is necessary to increase the productivity and quality of garden peas,since this management for garden peas is neglected in ***,the present study was made to assess the effectiveness of rhizobium inoculant singly or in combination with the micronutrients(i.e.,Zn,B,and Mo)on growth,yield,nutrient uptake,and quality of garden *** were:T_(1)=Control,T_(2)=Rhizobium inoculation at 50 g/kg seed,T_(3)=T_(2)+Zn_(3)Mo1,T_(4)=T_(2)+B_(2)Mo1,T_(5)=T_(2)+Zn_(3)B_(2),T_(6)=T_(2)+Zn_(3)B_(2)Mo1 and T_(7)=Zn_(3)B_(2)*** treatments were arranged in a randomized complete block design and repeated all treatments in three *** application of 3 kg Zn,2 kg B,and 1 kg Mo ha^(−1)with inoculation of Rhizobium at 50 g kg^(−1)seed(T_(6))facilitated to increase of 44.8%in the green pod and 29.7%seed yield over *** same treatment contributed to attaining the maximum nodulation(25.3 plant^(−1)),Vitamin C(43.5 mg 100 g^(−1)),protein content(22.2%),and nutrient uptake as well as accumulation in garden *** all treatment combinations,treatment T_(6)was found superior to others based on microbial activities,soil fertility,and *** results of the study found that the application of 3 kg Zn,2 kg B,and 1 kg Mo ha^(−1)in combination with Rhizobium inoculation(50 g kg^(−1)seed)can improve the yield and quality of garden *** results of the study have the potential for the areas,where there is no use of Rhizobium inoculant or Zn,B,and Mo fertilizer for cultivation of garden pea.

关键词： Nodulation nutrient content Pisum sativum L. profitability rhizobium Zn B Mo

Comprehensive analysis of the role of ubiquitin-specific peptidases in colorectal cancer:A systematic review

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

World Journal of Gastrointestinal Oncology 2024年第1期16卷 197-213页

作者： Eman Al-Balushi Amina Al Marzouqi Shima Tavoosi Amir Hossein Baghsheikhi Arash Sadri Leyla Sharifi Aliabadi mohammad-Mahdi Salarabedi Syed Azizur rahman Nabeel Al-Yateem Alireza Mosavi Jarrahi Aram Halimi mohammad Ahmadvand Wael M Abdel-rahman College of Health Sciences University of SharjahSharjah 27272United Arab Emirates Department of Biology Faculty of SciencesUniversity of IsfahanIsfahan 81746-73441Iran Department of Biology Science and Research BranchIslamic Azad UniversityTehran 11365/4435Iran Students’Scientific Research Center Tehran University of Medical SciencesTehran ***Iran Cell Therapy and Hematopoietic Stem Cell Transplantation Research Center Research Institute for OncologyHematologyand Cell TherapyTehran University of Medical SciencesTehran ***Iran Student Research Committee School of MedicineShahid Beheshti University of Medical SciencesTehran ***Iran Department of Nursing University of SharjahSharjah 27272United Arab Emirates Cancer Research Centre Shahid Beheshti University of Medical SciencesTehran ***Iran Department of Medical Laboratory Sciences University of SharjahSharjah 27272United Arab Emirates

BACKGROUND Colorectal cancer(CRC)is the third most frequent and the second most fatal *** search for more effective drugs to treat this disease is ongoing.A better understanding of the mechanisms of CRC development and progression may reveal new therapeutic ***-specific peptidases(USPs),the largest group of the deubiquitinase protein family,have long been implicated in various *** have been numerous studies on the role of USPs in CRC;however,a comprehensive view of this role is *** To provide a systematic review of the studies investigating the roles and functions of USPs in *** We systematically queried the MEDLINE(via PubMed),Scopus,and Web of Science *** Our study highlights the pivotal role of various USPs in several processes implicated in CRC:Regulation of the cell cycle,apoptosis,cancer stemness,epithelial–mesenchymal transition,metastasis,DNA repair,and drug *** findings of this study suggest that USPs have great potential as drug targets and noninvasive biomarkers in *** dysregulation of USPs in CRC contributes to drug resistance through multiple *** Targeting specific USPs involved in drug resistance pathways could provide a novel therapeutic strategy for overcoming resistance to current treatment regimens in CRC.

关键词： Ubiquitin-specific peptidases Colorectal cancer Deubiquitinase protein family Drug target discovery Biomarker discovery

Bayesian Optimized LightGBM model for predicting the fundamental vibrational period of masonry infilled RC frames

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Structural and Civil Engineering 2024年第7期18卷 1084-1102页

作者： Taimur rahman Pengfei ZHENG Shamima SULTANA Department of Civil Engineering World University of BangladeshDhaka 1230Bangladesh School of Civil Engineering Zhengzhou UniversityZhengzhou 450001China Department of Computer Science&Engineering University of Asia PacificDhaka 1205Bangladesh

The precise prediction of the fundamental vibrational period for reinforced concrete(RC)buildings with infilled walls is essential for structural design,especially earthquake-resistant *** learning models from previous studies,while boasting commendable accuracy in predicting the fundamental period,exhibit vulnerabilities due to lengthy training times and inherent dependence on pre-trained models,especially when engaging with continually evolving data *** predicament emphasizes the necessity for a model that adeptly balances predictive accuracy with robust adaptability and swift data *** latter should include consistent re-training ability as demanded by realtime,continuously updated data *** research implements an optimized Light Gradient Boosting Machine(LightGBM)model,highlighting its augmented predictive capabilities,realized through the astute use of Bayesian Optimization for hyperparameter tuning on the FP4026 research data set,and illuminating its adaptability and efficiency in predictive *** results show that the R^(2) score of LightGBM model is 0.9995 and RMSE is 0.0178,while training speed is 23.2 times faster than that offered by XGBoost and 45.5 times faster than for Gradient ***,this study introduces a practical application through a streamlit-powered,web-based dashboard,enabling engineers to effortlessly utilize and augment the model,contributing data and ensuring precise fundamental period predictions,effectively bridging scholarly research and practical applications.

关键词： masonry-infilled RC frame fundamental period LightGBM FP4026 research dataset machine learning data-driven approach Bayesian Optimization

A Low Complexity ML-Based Methods for Malware Classification

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第9期80卷 4833-4857页

作者： Mahmoud E.Farfoura Ahmad Alkhatib Deema Mohammed Alsekait mohammad Alshinwan Sahar A.El-rahman Didi Rosiyadi Diaa Salama Abd Elminaam Cybersecurity Department Al-Zaytoonah University of JordanAmman11733Jordan Department of Computer Science and Information Technology Applied CollegePrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Faculty of Information Technology Applied Science Private UniversityAmman11931Jordan Computer Systems Program-Electrical Engineering Department Faculty of Engineering-ShoubraBenha UniversityCairo11629Egypt Research Center for Artificial Intelligence and Cybersecurity Electronics and Informatics OrganizationNational Research and Innovation Agency(BRIN)KST Samaun SamadikunBandung40135Republic of Indonesia Jadara Research Center Jadara UniversityIrbid21110Jordan MEU Research Unit Middle East UniversityAmman11831Jordan

The article describes a new method for malware classification,based on a Machine Learning(ML)model architecture specifically designed for malware detection,enabling real-time and accurate malware *** an innovative feature dimensionality reduction technique called the Interpolation-based Feature Dimensionality Reduction Technique(IFDRT),the authors have significantly reduced the feature space while retaining critical information necessary for malware *** technique optimizes the model’s performance and reduces computational *** proposed method is demonstrated by applying it to the BODMAS malware dataset,which contains 57,293 malware samples and 77,142 benign samples,each with a 2381-feature *** the IFDRT method,the dataset is transformed,reducing the number of features while maintaining essential data for accurate *** evaluation results show outstanding performance,with an F1 score of 0.984 and a high accuracy of 98.5%using only two reduced *** demonstrates the method’s ability to classify malware samples accurately while minimizing processing *** method allows for improving computational efficiency by reducing the feature space,which decreases the memory and time requirements for training and *** new method’s effectiveness is confirmed by the calculations,which indicate significant improvements in malware classification accuracy and *** research results enhance existing malware detection techniques and can be applied in various cybersecurity applications,including real-timemalware detection on resource-constrained *** and scientific contribution lie in the development of the IFDRT method,which provides a robust and efficient solution for feature reduction in ML-based malware classification,paving the way for more effective and scalable cybersecurity measures.

关键词： Malware detection ML-based models dimensionality reduction feature engineering