检索结果-南通市图书馆

Science China(Information Sciences) 2021年第3期64卷 149-166页

作者： ameer hamza khan Shuai LI Xinwei CAO Department of Computing Hong Kong Polytechnic University Department of Electronics and Electrical Engineering Swansea University School of Management Shanghai University

In this paper, we propose a recurrent neural network(RNN) for the tracking control of surgical robots while satisfying remote center-of-motion(RCM) constraints. RCM constraints enforce rules suggesting that the surgical tip should not go beyond the region of incision while tracking the commands of the surgeon.Violations of RCM constraints can result in serious injury to the patient. We unify the RCM constraints with the tracing control by formulating a single constrained optimization problem using a penalty-term approach.The penalty-term actively rewards the optimizer for satisfying the RCM constraints. We then propose an RNN-based metaheuristic optimization algorithm called "Beetle Antennae Olfactory Recurrent Neural Network(BAORNN)" for solving the formulated optimization problem in real time. The proposed control framework can track the surgeon’s commands and satisfy the RCM constraints simultaneously. Theoretical analysis is performed to demonstrate the stability and convergence of the BAORNN algorithm. Simulations using LBR IIWA14, a 7-degree-of-freedom robotic arm, are performed to analyze the performance of the proposed framework.

关键词： tracking control surgical robots RCM constraints metaheuristic optimization recurrent neural network RNN redundant manipulator

Which is the Best PID Variant for Pneumatic Soft Robots?An Experimental Study

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2020年第2期7卷 451-460页

作者： ameer hamza khan Zili Shao Shuai Li Qixin Wang Nan Guan Department of Computing Hong Kong Polytechnic UniversityHong KongChina Department of Computer Science and Engineering Chinese University of Hong KongHong KongChina Department of Electronics and Electrical Engineering Swansea UniversitySwansea SA18ENUK

This paper presents an experimental study to compare the performance of model-free control strategies for pneumatic soft robots.Fabricated using soft materials,soft robots have gained much attention in academia and industry during recent years because of their inherent safety in human interaction.However,due to structural flexibility and compliance,mathematical models for these soft robots are nonlinear with an infinite degree of freedom(DOF).Therefore,accurate position(or orientation)control and optimization of their dynamic response remains a challenging task.Most existing soft robots currently employed in industrial and rehabilitation applications use model-free control algorithms such as PID.However,to the best of our knowledge,there has been no systematic study on the comparative performance of model-free control algorithms and their ability to optimize dynamic response,i.e.,reduce overshoot and settling time.In this paper,we present comparative performance of several variants of model-free PID-controllers based on extensive experimental results.Additionally,most of the existing work on modelfree control in pneumatic soft-robotic literature use manually tuned parameters,which is a time-consuming,labor-intensive task.We present a heuristic-based coordinate descent algorithm to tune the controller parameter automatically.We presented results for both manual tuning and automatic tuning using the Ziegler-Nichols method and proposed algorithm,respectively.We then used experimental results to statistically demonstrate that the presented automatic tuning algorithm results in high accuracy.The experiment results show that for soft robots,the PID-controller essentially reduces to the PI controller.This behavior was observed in both manual and automatic tuning experiments;we also discussed a rationale for removing the derivative term.

关键词： Automatic tuning algorithm model-free control PID soft robotics

维普期刊数据库

BAS-ADAM:An ADAM Based Approach to Improve the Performance of Beetle Antennae Search Optimizer

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2020年第2期7卷 461-471页

作者： ameer hamza khan Xinwei Cao Shuai Li Vasilios N.Katsikis Liefa Liao Department of Computing Hong Kong Polytechnic UniversityHong KongChina School of Management Shanghai UniversityShanghai 201900China Department of Electronics and Electrical Engineering Swansea UniversitySwansea SA18ENUK Department of Economics Division of Mathematics and InformaticsNational and Kapodistrian University of AthensAthens 10679Greece School of Information Engineering Jiangxi University of Science and TechnologyGanzhou 341000China

In this paper,we propose enhancements to Beetle Antennae search(BAS)algorithm,called BAS-ADAIVL to smoothen the convergence behavior and avoid trapping in localminima for a highly noin-convex objective function.We achieve this by adaptively adjusting the step-size in each iteration using the adaptive moment estimation(ADAM)update rule.The proposed algorithm also increases the convergence rate in a narrow valley.A key feature of the ADAM update rule is the ability to adjust the step-size for each dimension separately instead of using the same step-size.Since ADAM is traditionally used with gradient-based optimization algorithms,therefore we first propose a gradient estimation model without the need to differentiate the objective function.Resultantly,it demonstrates excellent performance and fast convergence rate in searching for the optimum of noin-convex functions.The efficiency of the proposed algorithm was tested on three different benchmark problems,including the training of a high-dimensional neural network.The performance is compared with particle swarm optimizer(PSO)and the original BAS algorithm.

关键词： Adaptive moment estimation(ADAM) Beetle antennae search(BAM) gradient estimation metaheuristic optimization nature-inspired algorithms neural network

维普期刊数据库

Modelling of debris-flow susceptibility and propagation: a case study from Northwest Himalaya

在线全文

学校读者我要写书评

暂无评论

Journal of Mountain Science 2024年第1期21卷 200-217页

作者： hamza DAUD Javed Iqbal TANOLI Sardar Muhammad ASIF Muhammad QASIM Muhammad ALI Junaid khan Zahid Imran BHATTI Ishtiaq Ahmad khan JADOON Badong National Observation and Research Station of Geohazards China University of GeosciencesWuhan 430074China Department of Earth Sciences COMSATS University IslamabadAbbottabad Campus 22010Pakistan Department of Earth Sciences Sultan Qaboos UniversityAl-KhoudMascat 123Oman Faculty of Engineering China University of Geosciences(Wuhan)Wuhan 430074China Department of Earth Sciences Abbottabad University of Science and TechnologyHavelian 22500Pakistan

The geological and geographical position of the Northwest Himalayas makes it a vulnerable area for mass movements particularly landslides and debris flows. Mass movements have had a substantial impact on the study area which is extending along Karakorum Highway(KKH) from Besham to Chilas. Intense seismicity, deep gorges, steep terrain and extreme climatic events trigger multiple mountain hazards along the KKH, among which debris flow is recognized as the most destructive geohazard. This study aims to prepare a field-based debris flow inventory map at a regional scale along a 200 km stretch from Besham to Chilas. A total of 117 debris flows were identified in the field, and subsequently, a point-based debris-flow inventory and catchment delineation were performed through Arc GIS analysis. Regional scale debris flow susceptibility and propagation maps were prepared using Weighted Overlay Method(WOM) and Flow-R technique sequentially. Predisposing factors include slope, slope aspect, elevation, Topographic Roughness Index(TRI), Topographic Wetness Index(TWI), stream buffer, distance to faults, lithology rainfall, curvature, and collapsed material layer. The dataset was randomly divided into training data(75%) and validation data(25%). Results were validated through the Receiver Operator Characteristics(ROC) curve. Results show that Area Under the Curve(AUC) using WOM model is 79.2%. Flow-R propagation of debris flow shows that the 13.15%, 22.94%, and 63.91% areas are very high, high, and low susceptible to debris flow respectively. The propagation predicated by Flow-R validates the naturally occurring debris flow propagation as observed in the field surveys. The output of this research will provide valuable input to the decision makers for the site selection, designing of the prevention system, and for the protection of current infrastructure.

关键词： North Pakistan Debris flow Flow-R Propagation Susceptibility mapping Debris-flow inventory Weighted Overlay Method

维普期刊数据库

Turning teawaste particles into magnetic bio-sorbents particles for arsenic removal from wastewater:Isotherm and kinetic studies

在线全文

学校读者我要写书评

暂无评论

Particuology 2024年第4期87卷 179-193页

作者： Mary McGeogh hamza Annath Chirangano Mangwandi School of Chemistry and Chemical Engineering Queen's University BelfastDavid Kier BuildingBT95AGUnited Kingdorm Department of Chermnistry Lancaster UniversityBailrigsLancasterLA14YBUnited Kingdom

The primary objective of this research was to assess the potential of magnetic bleached biochar(MBBC)as a cost-effective adsorbent for arsenic removal.To achieve this,locally collected tea wastes underwent meticulous cleaning,bleaching,and modifications via thermal and chemical treatments.Both non-magnetic and magnetic biochar adsorbents were thoroughly characterized using Fourier transform-infrared spectroscopy(FT-IR)and thermo-gravimetric analysis(TGA).Subsequently,the adsorptive performance of MBBC in removing arsenic from wastewater samples was investigated,considering various crucial parameters such as adsorbent-adsorbate contact time,concentration of As,temperature,adsorbent dosage,and the regeneration-ability of the adsorbent.The experimental data for the adsorption process were best represented by the Langmuir isotherm,indicating its suitability for the MBBC adsorbent.Remarkably,the MBBC demonstrated a maximum Langmuir adsorption capacity of approximately 714 mg/g at room temperature,highlighting its efficiency as an arsenic adsorbent.Furthermore,the Lagergren's Pseudo-second order kinetic model proved to be the most suitable for describing the adsorption kinetics,confirming the chemisorption nature of the process.The results also indicated that the adsorption process is endothermic and feasible,suggesting its viability for practical applications.Taking all findings into account,the comprehensive analysis strongly supports the potential use of MBBC as a highly promising and cost-effective adsorbent for efficiently removing arsenic from aqueous samples.This research contributes valuable insights to the field of wastewater treatment and offers a sustainable and environmentally friendly solution for tackling arsenic contamination in water sources.

关键词： Arsenics Wastewater Adsorption Magnetic bio-char Teawaste

Secure android IoT mobile and collaborative machine learning for controlling the management of enterprise

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 Control and Decision 2024年第1期11卷 15-25页

作者： hamza Mohammed Ridha Al-Khafaji Refed Adnan Jaleel Biomedical Engineering Department Al-Mustaqbal University CollegeHillahIraq Information and Communication Engineering Department Al-Nahrain UniversityBaghdadIraq

There is a need for increased security measures because of wide variety of android Internet of Thing(IoT)mobile devices that can communicate with each other via networks for controlling the management of enterprise.Elliptic Curve Deffie Hellman(ECDH)and Rivest Shamir Adleman(RSA)are used to secure data in android IoT phones in efficient manner.Android mobile can store a lot of data,including sensitive data.Protecting data saved on mobile has become a critical problem.In android IoT,Collaborative Machine Learning describes a method for collaboratively mining data,which makes it easier to manage and lowers cost of maintenance.To increase security in IoT phones,suggested system uses ECDH,RSA,and CML algorithms,which have been considered novelty of this method.RSA and ECDH are computed using time of decryption,encryption,and key generation.Conclusions show ECDH beats other alternatives like RSA.Finally,all users of the network have been tested.

关键词： IoT ECDH RSA CML android encryption decryption

Wave Reflection by Rectangular Breakwaters for Coastal Protection

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Fluid Dynamics & Materials Processing 2024年第3期20卷 579-593页

作者： Hasna Akarni hamza Mabchour Laila El Aarabi Soumia Mordane Laboratory of Polymer Physics Mechanical Sciences and MaterialsFaculty of Sciences Ben M’SikHassan II University of CasablancaCasablanca20670Morocco

In this study,we focus on the numerical modelling of the interaction between waves and submerged structures in the presence of a uniform flow current.Both the same and opposite senses of wave propagation are considered.The main objective is an understanding of the effect of the current and various geometrical parameters on the reflection coefficient.The wave used in the study is based on potential theory,and the submerged structures consist of two rectangular breakwaters positioned at a fixed distance from each other and attached to the bottom of a wave flume.The numerical modeling approach employed in this work relies on the Boundary Element Method(BEM).The results are compared with experimental data to validate the approach.The findings of the study demonstrate that the double rectangular breakwater configuration exhibits superior wave attenuation abilities if compared to a single rectangular breakwater,particularly at low wavenumbers.Furthermore,the study reveals that wave mitigation is more pronounced when the current and wave propagation are coplanar,whereas it is less effective in the case of opposing current.

关键词： Wave current breakwaters Boundary Element Method(BEM) reflection coefficient

WebFLex:A Framework for Web Browsers-Based Peer-to-Peer Federated Learning Systems Using WebRTC

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3期78卷 4177-4204页

作者： Mai Alzamel hamza Ali Rizvi Najwa Altwaijry Isra Al-Turaiki Department of Computer Science College of Computer and Information SciencesKing Saud UniversityRiyadhKingdom of Saudi Arabia Department of Computer Science and Engineering Punjab Engineering CollegeChandigarhIndia

Scalability and information personal privacy are vital for training and deploying large-scale deep learning models.Federated learning trains models on exclusive information by aggregating weights from various devices and taking advantage of the device-agnostic environment of web browsers.Nevertheless,relying on a main central server for internet browser-based federated systems can prohibit scalability and interfere with the training process as a result of growing client numbers.Additionally,information relating to the training dataset can possibly be extracted from the distributed weights,potentially reducing the privacy of the local data used for training.In this research paper,we aim to investigate the challenges of scalability and data privacy to increase the efficiency of distributed training models.As a result,we propose a web-federated learning exchange(WebFLex)framework,which intends to improve the decentralization of the federated learning process.WebFLex is additionally developed to secure distributed and scalable federated learning systems that operate in web browsers across heterogeneous devices.Furthermore,WebFLex utilizes peer-to-peer interactions and secure weight exchanges utilizing browser-to-browser web real-time communication(WebRTC),efficiently preventing the need for a main central server.WebFLex has actually been measured in various setups using the MNIST dataset.Experimental results show WebFLex’s ability to improve the scalability of federated learning systems,allowing a smooth increase in the number of participating devices without central data aggregation.In addition,WebFLex can maintain a durable federated learning procedure even when faced with device disconnections and network variability.Additionally,it improves data privacy by utilizing artificial noise,which accomplishes an appropriate balance between accuracy and privacy preservation.

关键词： Federated learning web browser privacy deep learning

Analysis of CH_(4) and H_(2) Adsorption on Heterogeneous Shale Surfaces Using aMolecular Dynamics 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

Fluid Dynamics & Materials Processing 2024年第1期20卷 31-44页

作者： Surajudeen Sikiru Hassan Soleimani Amir Rostami Mohammed Falalu hamza Lukmon Owolabi Afolabi Centre of Subsurface Imaging(CSI) Universiti Teknologi PETRONASTronohPerakMalaysia Department of Geosciences Universiti Teknologi PETRONASBandar Seri IskandarTronohPerakMalaysia Department of Pure&Industrial Chemistry Faculty of Physical SciencesBayero University KanoKanoNigeria Department of Mechanical Engineering Engineering Institute of TechnologyMelbourne Campus VictoriaMelbourneAustralia

Determining the adsorption of shale gas on complex surfaces remains a challenge in molecular simulation studies.Difficulties essentially stem from the need to create a realistic shale structure model in terms of mineral heterogeneityand multiplicity.Moreover,precise characterization of the competitive adsorption of hydrogen andmethane in shale generally requires the experimental determination of the related adsorptive capacity.In thisstudy,the adsorption of adsorbates,methane(CH_(4)),and hydrogen(H_(2))on heterogeneous shale surface modelsof Kaolinite,Orthoclase,Muscovite,Mica,C_(60),and Butane has been simulated in the frame of a moleculardynamic’s numerical technique.The results show that these behaviors are influenced by pressure and potentialenergy.On increasing the pressure from 500 to 2000 psi,the sorption effect for CH_(4)significantly increasesbut shows a decline at a certain stage(if compared to H_(2)).The research findings also indicate that raw shalehas a higher capacity to adsorb CH_(4)compared to hydrogen.However,in shale,this difference is negligible.

关键词： Shale gas adsorption methane hydrogen molecular dynamic sorption

Cocrystals of carbamazepine:Structure,mechanical properties,fluorescence properties,solubility,and dissolution rate

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Particuology 2024年第7期90卷 20-30页

作者： Jinbo Ouyang Lishan Liu Yin Li Mingyang Chen Limin Zhou Zhirong Liu Li Xu hamza Shehzad School of Chemistry and Materials Science East China University of TechnologyNanchang 330013China School of Physics and Materials Science Nanchang UniversityNanchang 330013China School of Chemical Engineering and Technology Tianjin UniversityTianjin 300072China

Carbamazepine(CBZ)is an anticonvulsant with very low water solubility,presenting as a white crystalline powder with poor mechanical properties and is hard to bend.To enhance CBZ's physicochemical properties,such as water solubility and mechanical properties,we selected six cocrystal coformers(CCFs):nicotinamide(NIC),benzamide(BZM),salicylic acid(SCA),fumaric acid(FMA),trimesic acid(TMA),and hesperetin(HPE).Six CBZ cocrystals were successfully prepared using the solution method.Fourier transform infrared spectroscopy(FT-IR),powder X-ray diffraction(PXRD),differential scanning calorimetry(DSC),and single crystal X-ray diffraction(SCXRD)were used to characterize the crystal structures and gain comprehensive insights into the six cocrystals.The mechanical,fluorescence,and solubility properties of the six cocrystals were tested.The results reveal that most of the prepared cocrystals exhibit improved water solubility and mechanical properties when compared to CBZ.Among them,the dissolution rate of cocrystals excluded from CBZ-HPE has increased by an average of 3 or 4 times compared to CBZ,while CBZ-HPE exhibits superior mechanical properties.Moreover,all six cocrystals possess better fluorescence performance than CBZ.We thoroughly evaluated the mechanical properties of the cocrystals through both experimental and theoretical approaches.This work provides a new direction for studying drug cocrystals to improve the physicochemical properties of drugs.

关键词： Carbamazepine Cocrystal Mechanical properties Fluorescence performance Dissolution rate