检索结果-内蒙古大学图书馆

IEEE TRANSACTIONS ON RADAR SYSTEMS 2024年 2卷 471-481页

作者： Aubry, Augusto De Maio, Antonio Pallotta, Luca Univ Napoli Federico II Dept Elect Engn & Informat Technol DIETI I-80125 Naples Italy Natl Inter Univ Consortium Telecommun I-43124 Parma Italy Univ Basilicata Sch Engn I-85100 Potenza Italy

The modern battlefield scenario is strongly influenced by the innovative capabilities of multifunction phased array radars (MPARs), which can perform a plethora of sensing and communication (COM) activities sequentially or in parallel. In fact, the MPAR can functionally cluster its phased array into bespoke subapertures implementing different tasks. Accordingly, a portion of the other available resources, e.g., bandwidth, power-aperture product (PAP), and time, is also assigned to each subaperture, and the grand challenge is the definition of strategies for optimal scheduling of the tasks to be executed. In this respect, a rule-based algorithm for task scheduling is proposed in this article. In a nutshell, in each time window, the procedure first allocates the radar tasks (viz., volume search, cued search, update, and confirmation tracking) and then utilizes the COM looks to fill the empty intraslot time left by the radar tasks. When there are two concurrent looks, the allocation is performed according to their priorities. Moreover, if the bandwidth and PAP are sufficient, some of them can be also scheduled in parallel. Interesting results in terms of bandwidth and time occupancy efficiency are observed from simulations conducted in challenging scenarios comprising also multiple maneuvering targets.

关键词： Task analysis Radar Radar tracking Resource management Bandwidth Sensors Phased arrays Dynamic resource allocation multifunction phased array radar (MPAR) rule-based algorithm task scheduling

来源：评论

学校读者我要写书评

暂无评论

Multi-disease Classification of CT Reports using Traditional Natural Language Processing and a Lightweight Foundation Model

Multi-disease Classification of CT Reports using Traditional...

引用

2025 Conference on Medical Imaging

作者： Garcia-Alcoser, Michael E. Tushar, Fakrul Islam Nejad, Mobina Ghojogh Rubin, Geoffrey D. Lo, Joseph Y. Duke Univ Sch Med Ctr Virtual Imaging Trials Carl E Ravin Adv Imaging LabsDept Radiol Durham NC 27706 USA Univ Arizona Dept Med Imaging Coll Med Tucson AZ USA

ISBN: (纸本)9781510686007;9781510686014

Natural language processing (NLP) methods can annotate free-text radiology reports to create large datasets at the scale of an entire health system or beyond. Generalizing the disease classification across multiple organ systems inherently requires a complex, robust, and accurate classification model. Concurrently, NLP methods have significantly improved and become more sophisticated. This study compares two traditional NLP methods, a rule-based algorithm (RBA) and a Bidirectional Long Short-Term Memory network (BiLSTM), with a lightweight variant of the Large Language Model Meta AI (Llama) model. Our goal is to analyze the capabilities and limitations of each model in accurately classifying diseases encountered within the chest, abdominal, and pelvic computed tomography (CT) exams of the body. rule-based algorithms (RBAs) were used to extract disease labels from the "findings" section of CT radiology reports, creating the training, validation, and testing datasets. Disease labels were made for three organ systems: the lungs/pleura, liver/gallbladder, and kidneys/ureters. A BiLSTM network with an attention mechanism was trained on 151,431 cases and tested on 85,987 cases. The BiLSTM and Meta's Llama3.1-8B model was evaluated on the RBA-test set and a manually annotated dataset. On the smaller, manually labeled test set, the RBA model achieved the highest macro F1 score (0.94), followed by the BiLSTM (0.91) and then Llama (0.89). In contrast, on the larger RBA-labeled test set, the BiLSTM maintained high performance (average AUC > 0.98;macro F1 = 0.95), while Llama's macro F1 dropped to 0.65. Manual spot checking of reports where Llama disagreed with RBA/BiLSTM revealed numerous instances in which Llama was actually correct, indicating flaws with the previous RBA labeling. This study emphasizes the limitations of rule-based approaches and the need to consider clinical context in ambiguous scenarios. Llama3.1-8B exhibits the potential to outperform rule-based methods,

关键词： Foundation Model LLM Llama Natural Language Processing BiLSTM rule-based algorithm Computed Tomography

来源：评论

学校读者我要写书评

暂无评论

A 3-phase combined wheel slip and acceleration threshold algorithm for anti-lock braking in heavy commercial road vehicles

引用

VEHICLE SYSTEM DYNAMICS 2022年第7期60卷 2312-2333页

作者： Challa, Akhil Ramakrushnan, Karthik Gaurkar, Pavel Vijay Subramanian, Shankar C. Vivekanandan, Gunasekaran Sivaram, Sriram Indian Inst Technol Madras Chennai Tamil Nadu India Madras Engn Ind Pvt Ltd Chennai Tamil Nadu India

This research presents a rule-based Anti-lock Braking System (ABS) algorithm towards active vehicle safety in Heavy Commercial Road Vehicles (HCRVs). Wheel Slip Regulation (WSR) algorithms, that are constituents of an ABS, are typically either model-based or rule-based. Model-based algorithms (MBAs) utilise mathematical models that characterise vehicle dynamics and are intensive in their demand for real-time information. On the other hand, rule-based algorithms (RBAs) operate on set rules with pre-defined thresholds and utilise data from sensors that are typically available on the vehicle. A great deal of advancement has been reported in literature related to MBAs. However, most commercially available RBAs are proprietary in nature and the finer details are seldom revealed. Hence, this work proposes an RBA, which is a combined Slip and Wheel Acceleration Threshold algorithm (SWATA), including a framework for identifying the importance of thresholds and their magnitudes. SWATA was tested on a Hardware-in-Loop (HiL) setup across varying road and loading conditions, and it provided a maximum of 36% braking distance improvement compared to a case where it was inactive. An adaptive version - ASWATA - is also proposed that can adapt the thresholds according to the particular tyre-road interface. Additionally, a quantitative comparison of the proposed RBA with a Sliding Mode Control (SMC) based MBA, which was developed and tested on the same HiL setup, is presented. It was observed that the performance of the RBA was on par with that of the MBA for most test cases, but with minimal data requirements.

关键词： Active vehicle safety anti-lock braking rule-based algorithm wheel slip regulation

来源：评论

学校读者我要写书评

暂无评论

A Multi-Level rule Model for Selecting Post-Quantum Cryptography in 5G Application and beyond

A Multi-Level Rule Model for Selecting Post-Quantum Cryptogr...

引用

2024 IEEE International Conference on Consumer Electronics, ICCE 2024

作者： Ojetunde, Babatunde Kurihara, Takuya Yano, Kazuto Sakano, Toshikazu Yokoyama, Hiroyuki Wave Engineering Laboratories Japan Advanced Telecommunications Research Institute International Soraku Kyoto Seika Japan Adaptive Communications Research Laboratories Japan

ISBN: (纸本)9798350324136

The Post Quantum Cryptography (PQC) is promising in enhancing the security needed in the next-generation network. However, migrating the PQC to the network comes with a cost such as increased computational cost, larger key sizes, etc., which may affect the processing time and the Quality of Service (QoS) that is required in these networks. Therefore, a method to effectively and efficiently selects PQC algorithm is necessary. This paper proposes a method of selecting a suitable PQC algorithm based on the network QoS requirements and the PQC algorithms, key exchange mechanism performance. In particular, a three-level selection model for the selecting a suitable PQC algorithm is introduced. The first level model rules are based on the general IF-THEN rule while the second model uses fuzzy logic rule. A default rule based on Euclidean distance is introduced at the third level. Thereafter, the PQC selection process is presented. The performance of the proposed method is evaluated by experimenting with PQC algorithm using a client-server connection. The evaluation results show that the proposed selection model is effective in selecting a PQC algorithm based on the network condition. It is confirmed that the PQC algorithm can be selected with up to 97-99% certainty factor in all selected PQC algorithm. © 2024 IEEE.

关键词： 5G 5QI application fuzzy logic Post quantum cryptography post-quantum key exchange rule-based algorithm

来源：评论

学校读者我要写书评

暂无评论

Battery Energy Storage Systems in Different Countries for Arbitrage Services 11

Battery Energy Storage Systems in Different Countries for Ar...

引用

11th International Conference on Smart Grid (IcSmartGrid)

作者： Cetinkaya, Umit Demirbas, Sevki Ayik, Samet Bayindir, Ramazan Gazi Univ Dept Elect & Elect Engn Ankara Turkiye

ISBN: (纸本)9798350310665

This paper explores the feasibility and profitability of battery energy storage systems in different countries for arbitrage services. The study utilizes an improved algorithm designed to analyze and optimize battery energy storage systems deployment for energy arbitrage in diverse energy markets. The algorithm considers various factors such as energy prices, demand, battery cycling costs, and efficiency. The analysis focuses on quantifying the arbitrage profit in distinct countries, taking into account their unique energy market structures and electricity price dynamics. The conclusion drawn from this comprehensive study is that energy storage arbitrage facilitated by battery energy storage systems can indeed be profitable. This profitability, however, is contingent on the specific market conditions and regulatory frameworks in different countries. The findings of this paper underscore the potential of battery energy storage systems as a viable and lucrative solution for energy arbitrage, contributing significantly to the evolving discourse on energy storage and grid flexibility.

关键词： Battery energy storage systems Energy arbitrage Energy prices Arbitrage profit rule-based algorithm

来源：评论

学校读者我要写书评

暂无评论

Information Processing and Retrieval on WSNs for Plant Monitoring Using Natural Language 5

Information Processing and Retrieval on WSNs for Plant Monit...

引用

5th IEEE Eurasia Conference on IOT, Communication and Engineering, ECICE 2023

作者： Co, Justin Miguel A. Justo, James Ryan A. Yumang, Analyn N. Padilla, Dionis A. Mapúa University School of Electrical Electronics and Computer Engineering Manila Philippines

ISBN: (纸本)9798350314694

Technology has improved so that everyone can obtain the information they need from a single prompt. Most data is contained in a database, and exploring the data we need in these databases requires the language and the database, which most users do not know. We created an NLP system that allows farmers to access their databases' information with simple prompts and queries. By entering natural language queries into the system, they are converted to structured language queries to access the database information. We used pre-processing techniques such as tokenization, lemmatization, parts of speech tagging, and parsing on the natural language, and a rule-based algorithm was created to translate the query. 106 queries from random respondents were used to test the algorithm. The developed system showed an accuracy of 91.51%. We converted simple queries to structured language queries and provided output from the database. © 2023 IEEE.

关键词： natural language processing POS-tagging rule-based algorithm structured query language WSNs

来源：评论

学校读者我要写书评

暂无评论

Real-time Sleep Prediction algorithm using Commercial Off the Shelf Wearable Devices 9

Real-time Sleep Prediction Algorithm using Commercial Off th...

引用

9th IEEE Smart World Congress, SWC 2023

作者： Pugliese, Luigi Violante, Massimo Groppo, Riccardo Politecnico di Torino Dept. of Control and Computer Engineering Turin Italy Sleep Advice Technologies S.r.l. Turin Italy

ISBN: (纸本)9798350319804

As reported by the American National Highway Traffic Safety Administration (NHTSA), sleep while driving is one of the most influential factors in fatal vehicle crashes, along with excessive vehicle speed and alcohol consumption. Physiologically speaking, driving for more than two hours in a nocturnal environment produces a driving impairment like a blood alcohol concentration of 0.05%. In this work, we present an innovative and patented sleep prediction method based on the analysis of the Autonomic Nervous System (ANS) (and its subsystems) that monitors the actions happening during the transition from awake to sleep onset. The prediction method processes the Heart Rate (HR) and the Heart Rate Variability (HRV) as collected by a wearable device on the subject wrist. Using a sliding window approach that operates on 20 seconds of samples (acquired at 1 Hz), the trend of the variance of HR and HRV is used to classify the subject condition according to a reduced Karolinska Sleepiness Scale (rKSS) that comprises five stages: Calibration, Awake, Low Drowsiness level, Medium Drowsiness level, High Drowsiness level. The prediction method has been validated experimentally using a set of recordings acquired in a realistic environment (AVL dynamic car simulator, in Graz (AT)). During the experiments, 15 subjects performed several rounds of the Maintenance Wakefulness Test (MWT). Each subject was equipped with a wearable device and apolysomnography medical equipment to gather both the data processed by the proposed approach, and the data set that constituted the ground truth under the supervision of a sleep expert medical doctor. A further experimental section has been conducted, involving the Italian truck company Chrono Express. 15 different drivers have utilized the built-up system for more than 13000 km. The proposed method is sensor agnostic, as it has been proven through preliminary activities with contactless Radio Frequency (RF) sensors. The output produced by the propos

关键词： Drowsiness Heart Rate Heart Rate Variability IOT Physiological data Real-time rule-based algorithm Sleep

来源：评论

学校读者我要写书评

暂无评论

An intelligent and interpretable rule-based metaheuristic approach to task scheduling in cloud systems

引用

KNOWLEDGE-based SYSTEMS 2024年 284卷

作者： Barut, Cebrail Yildirim, Gungor Tatar, Yetkin Firat Univ Dept Continuing Educ Ctr Elazig Turkiye Firat Univ Dept Comp Engn Elazig Turkiye

Metaheuristic algorithms can be very successful in solving scheduling problems. However, these methods can be slow for time-critical applications due to the iterative stochastic processes they perform. This problem becomes even more pronounced in dynamic environments such as cloud systems. This paper proposes an interpretable rule-based solution to minimize this problem. Combining metaheuristic task scheduling solutions and machine learning techniques, this method uses a two-phase mechanism, semi-offline and online. In the semi-offline phase, we first archive metaheuristic solutions to previously randomly generated or encountered task-scheduling problems. The basic idea of the proposed method is to reuse these previously obtained successful metaheuristic solution patterns for future similar problems. Finding similar solution patterns from this extensive archive dataset is done by automatically extracting rule sets through machine learning techniques. These interpretable rule sets are used to identify the type of task scheduling problem encountered in the online phase and to find the optimal solution pattern. The performance of this method, which dramatically reduces execution time and enables the use of metaheuristics in time-critical applications, has been tested and proven for various cloud task-scheduling scenarios.

关键词： Cloud computing Task scheduling Metaheuristic rule-based algorithm

来源：评论

学校读者我要写书评

暂无评论

An Enhanced rule-based Approach for Optimizing Energy Costs and Battery Health in Microgrid Systems

引用

ELECTRIC POWER COMPONENTS AND SYSTEMS 2024年

作者： Bourezig, Sid Ahmed Benrabah, Abdeldjabar Khoucha, Farid Benmansour, Khelifa Benbouzid, Mohamed Ecole Mil Polytech UER ELT Algiers 16111 Algeria Univ Brest UMR CNRS IRDL 6026 Brest France Shanghai Maritime Univ Shanghai Peoples R China

Renewable energy resource systems have increased significantly as a result of the transition to microgrids. These systems require an effective energy management system (EMS) in order to optimize the flow of energy from the different sources. This paper proposes an enhanced rule-based EMS (EnRB-EMS) for a grid connected photovoltaic (PV)-battery system, in order to optimize the operation of the system to meet the escalating energy demand, minimize the cost of electricity, and increase the battery life by improving the power quality. The proposed strategy is based on a set of real-time information, such as the load demand, the state of charge (SoC) of the battery, and the cost of electricity. The performance of the proposed strategy is evaluated under different scenarios, demonstrating the effectiveness of the proposed strategy in achieving optimal energy management, reducing the electricity cost, and increasing the battery life.

关键词： energy management system rule-based algorithm PV system microgrid energy cost batteries

来源：评论

学校读者我要写书评

暂无评论

A rule-based energy management scheme for long-term optimal capacity planning of grid-independent microgrid optimized by multi-objective grasshopper optimization algorithm

引用

ENERGY CONVERSION AND MANAGEMENT 2020年 221卷 113161-113161页

作者： Bukar, Abba Lawan Tan, Chee Wei Yiew, Lau Kwan Ayop, Razman Tan, Wen-Shan Univ Teknol Malaysia UTM Fac Engn Sch Elect Engn Div Elect Power Engn Skudai 81310 Johor Malaysia Univ Teknol Malaysia UTM Fac Engn Sch Elect Engn Inst High Voltage & High Current Johor Baharu 81310 Malaysia Univ Maiduguri Fac Engn Dept Elect & Elect Engn PMB 1069 Maiduguri Borno State Nigeria Monash Univ Sch Engn Jalan Lagoon Bandar Sunway 47500 Selangor Malaysia Monash Univ Adv Engn Platform Jalan Lagoon Bandar Sunway 47500 Selangor Malaysia

Off-grid electrification of remote communities using sustainable energy systems (SESs) is a requisite for realizing sustainable development goals. Nonetheless, the capacity planning of the SESs is challenging as it needs to fulfil the fluctuating demand from a long-term perspective, in addition to the intermittency and unpredictable nature of renewable energy sources (RESs). Owing to the nonlinear and non-convex nature of the capacity planning problem, an efficient technique must be employed to achieve a cost-effective system. Existing techniques are, subject to some constraints on the derivability and continuity of the objective function, prone to premature convergence, computationally demanding, follows rigorous procedures to fine-tune the algorithm parameters in different applications, and often do not offer a fair balance during the exploitation and exploration phase of the optimization process. Furthermore, the literature review indicates that researchers often do not implement and examine the energy management scheme (EMS) of a microgrid while computing for the capacity planning problem of microgrids. This paper proposes a rule-based EMS (REMS) optimized by a nature-inspired grasshopper optimization algorithm (GOA) for long-term capacity planning of a grid-independent microgrid incorporating a wind turbine, a photovoltaic, a battery (BT) bank and a diesel generator (D-gen). In which, a rule-based algorithm is used to implement an EMS to prioritize the usage of RES and coordinate the power flow of the proposed microgrid components. Subsequently, an attempt is made to explore and confirm the efficiency of the proposed REMS incorporated with GOA. The ultimate goal of the objective function is to minimize the cost of energy (COE) and the deficiency of power supply probability (DPSP). The performance of the REMS is examined via a long-term simulation study to ascertain the REMS resiliency and to ensure the operating limit of the BT storage is not violated. The resu

关键词： Grasshopper optimization Energy management scheme rule-based algorithm PV Metaheuristic algorithms Pareto-optimal front

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：