Real Platform Research Articles

Energy-Aware Scenario-Based Mapping of Deep Learning Applications Onto Heterogeneous Processors Under Real-Time Constraints

To cope with the increasing demand for deep learning applications in embedded systems, emerging embedded devices tend to equip multiple heterogeneous processors, including GPU and deep learning hardware accelerator, called neural processing unit (NPU). It becomes popular to run multiple deep learning (DL) applications simultaneously to provide several functionalities. In this work, we assume that applications have real-time constraints that may vary at run time. While extensive studies have been conducted recently to find an efficient mapping of multiple DL applications on various hardware platforms, they do not consider the constraints imposed by the NPU and the associated software development kit (SDK) in a real embedded platform. In this paper, we propose a novel energy-aware mapping methodology of multiple DL applications onto a real embedded system that has multiple heterogeneous processors. The objective is to minimize energy consumption while satisfying the real-time constraints of all applications. In the proposed scheme, we first select Pareto-optimal mapping solutions for each application. Then mapping combination is explored, considering the scenario that indicates the dynamism of applications while satisfying the constraints. Also, we reduce energy consumption by tuning the frequency of processors. We could satisfy up to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$40\%$</tex-math></inline-formula> higher deadline constraints and reduce the energy consumption by <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$22\%$</tex-math></inline-formula> <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\sim$</tex-math></inline-formula> 31% compared to the static mapping methods with real-life applications and different scenarios on a real platform.

Design and evaluation of a skin-on-a-chip pumpless microfluidic device

The development of microfluidic culture technology facilitates the progress of study of cell and tissue biology. This technology expands the understanding of pathological and physiological changes. A skin chip, as in vitro model, consisting of normal skin tissue with epidermis and dermis layer (full thickness) was developed. Polydimethylsiloxane microchannels with a fed-batched controlled perfusion feeding system were used to create a full-thick ex-vivo human skin on-chip model. The design of a novel skin-on-a-chip model was reported, in which the microchannel structures mimic the architecture of the realistic vascular network as nutrients transporter to the skin layers. Viabilities of full-thick skin samples cultured on the microbioreactor and traditional tissue culture plate revealed that a precise controlled condition provided by the microfluidic enhanced tissue viability at least for seven days. Several advantages in skin sample features under micro-scale-controlled conditions were found such as skin mechanical strength, water adsorption, skin morphology, gene expression, and biopsy longevity. This model can provide an in vitro environment for localizing drug delivery and transdermal drug diffusion studies. The skin on the chip can be a valuable in vitro model for representing the interaction between drugs and skin tissue and a realistic platform for evaluating skin reaction to pharmaceutical materials and cosmetic products.

In Vitro Cell Transformation Assays: A Valuable Approach for Carcinogenic Potentiality Assessment of Nanomaterials.

This review explores the application of in vitro cell transformation assays (CTAs) as a screening platform to assess the carcinogenic potential of nanomaterials (NMs) resulting from continuously growing industrial production and use. The widespread application of NMs in various fields has raised concerns about their potential adverse effects, necessitating safety evaluations, particularly in long-term continuous exposure scenarios. CTAs present a realistic screening platform for known and emerging NMs by examining their resemblance to the hallmark of malignancy, including high proliferation rates, loss of contact inhibition, the gain of anchorage-independent growth, cellular invasion, dysregulation of the cell cycle, apoptosis resistance, and ability to form tumors in experimental animals. Through the deliberate transformation of cells via chronic NM exposure, researchers can investigate the tumorigenic properties of NMs and the underlying mechanisms of cancer development. This article examines NM-induced cell transformation studies, focusing on identifying existing knowledge gaps. Specifically, it explores the physicochemical properties of NMs, experimental models, assays, dose and time requirements for cell transformation, and the underlying mechanisms of malignancy. Our review aims to advance understanding in this field and identify areas for further investigation.

Quantum correlations in dissipative gain–loss systems across exceptional points

We investigate the behavior of correlations dynamics in a dissipative gain-loss system. First, we consider a setup made of two coupled lossy oscillators, with one of them subject to a local gain. This provides a more realistic platform to implement parity-time (PT) symmetry circumventing the implementation of a pure gain. We show how the qualitative dynamics of correlations resembles that for a pure-gain-loss setup. The major quantitative effect is that quantum correlations are reduced, while total ones are enhanced. Second, we study the behavior of these correlations across an exceptional point (EP) outside of the PT-symmetric regime of parameters, observing how different behaviors across the EP occur only in the transient dynamics. This shows how PT symmetry plays a relevant role at large times.

“Classes beyond the walls” – A reexploring method of teaching in ayurveda education over conventional approach

BackgroundGurukula system of Ayurveda education is a complete comprehensive approach. Institutionalization of this traditional system of education has its own limitations. Though the Ayurveda education is been institutionalized, some part of it deliberately needs to be learnt in real platform, in an integrated way to make learning process more engaging and relevant. Conventional method of teaching (CMT) has its own limitations and adoption of innovative methods is need of the hour. MethodsStudy was conducted on II Professional BAMS students in two groups: classes beyond the walls (CBW) group and CMT group. Integrated collaborative CBW teaching in medicinal plant garden and CMT in regular classrooms of institutional set up were conducted. Comparative learning experience was assessed based on open ended questionnaire. The effectiveness of CBW teaching was evaluated using five-point likert scale. Pre and Post tests were conducted using a google forms comprising of ten subject related questions to compare learning outcomes. Analysis of statistical parameters were done using SPSS software (Between the groups Mann - Whitney U test and within the groups Wilcoxon matched pairs signed rank test). ResultsThe learning significance within the both groups are demonstrated by the statistical findings based on the pre and posttest scores. Pretest scores between the groups are not significant with a P value 0.76, however the posttest results between the groups demonstrate a substantial learning improvement with a P value of < 0.0001. ConclusionThis demonstrates learning beyond the class is an important supportive component along with conventional method.

Managing Concurrent Queues for Efficient In- Vehicle Gateways

In modern vehicles, electrical control units communicate over multiple in-vehicle networks via domainor zone-oriented gateway architectures. This work examines efficient frame transfer across incoming and outgoing Controller Area Network (CAN) interfaces at a gateway. In our embedded platform prototype, each CAN interface of a CAN-to-CAN gateway is controlled independently by a corresponding Portable Operating System Interface (POSIX) thread. Inter-thread communication and synchronization are implemented using shared data structures, either lock-free concurrent queues or traditional lock-based circular queues that embody single-producer single-consumer (SPSC) principles. Our experimental framework provides a realistic open automotive platform that integrates multiple CAN interfaces. An Odroid XU3 device acts as a gateway, providing two Universal Asynchronous Receiver- Transmitter (UART) to CAN interfaces that lead to Raspberry Pi 3B nodes (connected to CAN via Serial Peripheral Interface (SPI)). To increase communication reliability and performance by minimizing frame loss and improving the egress CAN frame rate, low-level parameters at the gateway are optimized, especially the inter-character delay of the UART-to-CAN interfaces. Our experiments show that the frame waiting time in the queue is shorter for the concurrent queue, while relaying messages is equally fast, reaching a maximum output rate of ~380 frames/s for large enqueue rates near saturation. Power consumption is almost four times higher for the concurrent queue implementation.

Data-Driven and Compliance-Based Fault-Tolerance for a Flexible and Extendable Robotic Implant Coupled to a Growing Tissue

Robotic implants for real-time and long-term monitoring and therapies are being researched and could open new frontiers in the medical field. For these devices to see widespread adoption, though, key challenges still need to be overcome, including reliability. Over the years, many computational techniques have been developed to impart fault-tolerance to robots and industrial plants. However, the application of these approaches to robotic implants is still challenging, due to the lack of information about the complex behavior of soft tissue (e.g. growth, viscoelasticity) and robot-tissue interaction. In this paper, a novel fault detection framework for a flexible extendable robotic implant is presented. Based on Canonical Correlation Analysis, the approach exploits the flexibility of the robot to extrapolate information for fault identification purposes. The experiments are conducted with a soft tissue simulator, which can emulate the viscoelastic properties of tissue as well as its growth, providing a realistic testing platform. The experiments prove the reliability of the flexible extendable robotic implant and its robustness to system-level external disturbances. Long-term tests are also presented, where the implant extends 80 mm, to its full length, counteracting simulated hardware faults over a 24-hour period, and provide a promising basis for future in-vivo trials.

V05-11 DEVELOPMENT OF PERFUSED ROBOT-ASSISTED PARTIAL NEPHRECTOMY PROCEDURAL SIMULATION PLATFORM FOR SINGLE PORT, RETROPERITONEAL APPROACHES

You have accessJournal of UrologyCME1 Apr 2023V05-11 DEVELOPMENT OF PERFUSED ROBOT-ASSISTED PARTIAL NEPHRECTOMY PROCEDURAL SIMULATION PLATFORM FOR SINGLE PORT, RETROPERITONEAL APPROACHES Nathan Schuler, Lauren Shepard, Craig Rogers, Riccardo Autorino, Sammy Elsamara, Simone Crivellaro, Jean Joseph, and Ahmed Ghazi Nathan SchulerNathan Schuler More articles by this author , Lauren ShepardLauren Shepard More articles by this author , Craig RogersCraig Rogers More articles by this author , Riccardo AutorinoRiccardo Autorino More articles by this author , Sammy ElsamaraSammy Elsamara More articles by this author , Simone CrivellaroSimone Crivellaro More articles by this author , Jean JosephJean Joseph More articles by this author , and Ahmed GhaziAhmed Ghazi More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000003263.11AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Retroperitoneal robot assisted partial nephrectomy (RAPN) has shown restricted diffusion, limited to experienced surgeons at select institutions]. However, the recent introduction of the da Vinci single port (SP) surgical platform for RAPN with its slender profile is ideal for navigating narrow spaces. We have previously developed and validated a realistic, perfused hydrogel platform for transperitoneal RAPN robotic surgery as an adequate training tool. Our objective was to develop a similar platform using the same methodology. METHODS: A contoured box was designed to replicate the intraabdominal space surrounding the kidney, emphasizing realistic responses to initial incisions, balloon dilatation, and robot docking, then subsequently 3D printed. Patient-specific renal tissue phantoms and supporting structures were created using previously validated methods. Previous work with tensile testing on PVA hydrogels validated their ability to mimic the physical properties of renal tissue. The phantom was wrapped in a simulated Gerota’s Fascia, attached to a PVA “muscle” sheet, and connected to a hydrogel AA and IVC. The completed model was fixed to the inner contour of the 3D printed body cavity section, which was then covered with a hydrogel abdominal wall with a simulated peritoneal pouch, containing simulated bowels. Experts at the University of Rochester, Cleveland clinic and Henry ford hospitals tested the model during scheduled simulation events. 6 experts with >50 case experience in Single port robotic surgery and >1000 multiport robotic cases completed a survey to evaluate the realism and educational effectiveness of this model. RESULTS: Respondents completed surveys on the novelty and effectiveness of the platform. Agreement on simulator novelty was unanimously positive (100% agree or better) (Figure 1a). Performance evaluations reached a minimum of 80% agreement for all categories, with 100% of feedback rated as neutral or better. (Figure 1b). CONCLUSIONS: This realistic simulation procedural platform for robot assisted single port retroperitoneal renal surgery provides a suitable training medium for training and experienced urologists to improve the skills required to adopt this approach. Source of Funding: None © 2023 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 209Issue Supplement 4April 2023Page: e427 Advertisement Copyright & Permissions© 2023 by American Urological Association Education and Research, Inc.MetricsAuthor Information Nathan Schuler More articles by this author Lauren Shepard More articles by this author Craig Rogers More articles by this author Riccardo Autorino More articles by this author Sammy Elsamara More articles by this author Simone Crivellaro More articles by this author Jean Joseph More articles by this author Ahmed Ghazi More articles by this author Expand All Advertisement PDF downloadLoading ...

V02-07 DEVELOPMENT AND VALIDATION OF A BENCHTOP SIMULATOR FOR ULTRASOUND GUIDED PERCUTANEOUS NEPHROLITHOTOMY TRAINING USING 3D PRINTING AND HYDROGEL MOLDING

You have accessJournal of UrologyCME1 Apr 2023V02-07 DEVELOPMENT AND VALIDATION OF A BENCHTOP SIMULATOR FOR ULTRASOUND GUIDED PERCUTANEOUS NEPHROLITHOTOMY TRAINING USING 3D PRINTING AND HYDROGEL MOLDING Lauren Shepard, Nathan Schuler, Aaron Saxton, Patrick Saba, Andrew Cook, Tyler Holler, Karen Stern, David Tzou, Helena Chang, Justin Ahn, Thomas Tailly, Thomas Chi, and Ahmed Ghazi Lauren ShepardLauren Shepard More articles by this author , Nathan SchulerNathan Schuler More articles by this author , Aaron SaxtonAaron Saxton More articles by this author , Patrick SabaPatrick Saba More articles by this author , Andrew CookAndrew Cook More articles by this author , Tyler HollerTyler Holler More articles by this author , Karen SternKaren Stern More articles by this author , David TzouDavid Tzou More articles by this author , Helena ChangHelena Chang More articles by this author , Justin AhnJustin Ahn More articles by this author , Thomas TaillyThomas Tailly More articles by this author , Thomas ChiThomas Chi More articles by this author , and Ahmed GhaziAhmed Ghazi More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000003232.07AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Ultrasound-guided percutaneous nephrolithotomy (US-PCNL) is an effective and safe approach for management of large renal stones, yet adoption has been limited. The vast majority of US-PCNL are performed in the prone position vs supine position (80% vs 20%); however, there is a need for a safe, realistic procedural training platform for both approaches. We have previously demonstrated the ability of similar hydrogel simulations to improve operative outcomes during fluoroscopic PCNL training. Our objective was the development of a benchtop, non-biohazardous US-PCNL simulator using 3D printing and hydrogel molding and its validation using educational theory. METHODS: Consensus among 12 experts was reached regarding the essential aspects of an ideal US-PCNL model and an associated evaluation checklist using a Delphi consensus methodology. Segmentation software was used to generate a 3D model from an approved patient computed tomography (CT) scan, including kidney, pelvicalyceal system, stone, spine and ribs, abdominal wall, and iliac crest. Post-processing generated 3D printed casts into which hydrogel formulations replicating various anatomical and tissue mechanical properties of the structures were created according to the consensus statement. A prototype was fabricated for expert approval, after which 20 experts and 28 novices performed US-PCNL with performance assessed using the developed checklist. RESULTS: The simulator fulfilled all criteria established in the consensus statement, including external and ultrasound appearance mimicking in vivo appearance, a watertight pelvicalyceal system containing a functional stone that is distensible with retrograde instillation, and realistic tactile feedback during puncture. Experts agreed the simulator provides a safe training alternative (100%), bridges gaps between classroom and clinic (95.7%), and allows trainee performance evaluation (100%) in a risk free environment that can be modified for variable anatomy (88.9%). Highly significant differences were found between expert and novices using the checklist developed (93.4% vs 42.3%, p<0.001). In addition, novice performance improved with repeated practice (p<.001). A similar process was utilized to develop a supine version for US-PCNL simulation. CONCLUSIONS: We have successfully developed and validated a high-fidelity benchtop simulator for both Prone and Supine US-PCNL that can be easily tailored to varying anatomy. Further studies evaluating the transfer of skill are still required. Source of Funding: None © 2023 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 209Issue Supplement 4April 2023Page: e170 Advertisement Copyright & Permissions© 2023 by American Urological Association Education and Research, Inc.MetricsAuthor Information Lauren Shepard More articles by this author Nathan Schuler More articles by this author Aaron Saxton More articles by this author Patrick Saba More articles by this author Andrew Cook More articles by this author Tyler Holler More articles by this author Karen Stern More articles by this author David Tzou More articles by this author Helena Chang More articles by this author Justin Ahn More articles by this author Thomas Tailly More articles by this author Thomas Chi More articles by this author Ahmed Ghazi More articles by this author Expand All Advertisement PDF downloadLoading ...

Persuading Risk-Conscious Agents: A Geometric Approach

A Convex Programming Framework for Information Design Under Realistic Human Behavior Platform markets and services typically have additional relevant information in comparison with their users. Information design studies how the sharing of this information can be leveraged by the platform to influence user behavior and obtain desirable outcomes. Previous research has studied information design assuming that the users act to maximize their expected utility, but this assumption does not always hold in reality. Instead, people often exhibit biases and deviations from expected utility maximization. In “Persuading Risk-Conscious Agents: A Geometric Approach,” Anunrojwong, Iyer, and Lingenbrink study information design with “risk-conscious” agents whose utility functions may depend nonlinearly on their beliefs. They provide a convex programming approach for solving for the optimal persuasion mechanism and establish their structural properties in different settings. They illustrate their approach in an application involving the sharing of waiting-time information in a queueing system. Overall, this work contributes to the study of information design under realistic models of human behavior.

A comprehensive data-driven assessment scheme for power battery of large-scale electric vehicles in cloud platform

In cloud platform with power battery data from large-scale electric vehicles (EVs), cloud battery management system needs to achieve various monitoring tasks, including safety, degradation, and variation analysis. The unstable data quality and deployment conditions limit the full usage of existing methods, such as model-based estimation method and machine learning algorithm. This paper presents a comprehensive data-driven assessment scheme, named as ComDAS, to improve the multi-tasks realization for cloud platform. The proposed ComDAS can be fast deployed for lithium-ion batteries of EVs, and integrates three mainly concerned aspects: capacity estimation, anomaly detection, and variation evaluation. Neural network is applied for calibration of capacity estimation to achieve higher accuracy. A risk scoring method is proposed to achieve long-scale statistics filtering in time dimension, and weeks-early risk pre-warning for anomaly detection. Considering weak labels or even no labels of cloud EV data, correlation analysis among capacity, anomaly, and variation are also calculated to conduct cross validations and reveal the coupling evolution mechanism among the three aspects. Based on the designed monitoring process for large-scale EVs, ComDAS has been deployed to a realistic cloud big-data platform in Sichuan, China. The working ComDAS can hold the capacity error within 4.5 %, obtain the risk pre-warning more than one week earlier, and maintain the variation score of all EVs into 0–100 for further detection. Hence, it proves that ComDAS can maintain satisfying real-time performance for both large-scale EV statistics and specific detection of risky EV.

SchedGuard++: Protecting against Schedule Leaks Using Linux Containers on Multi-Core Processors

Timing correctness is crucial in a multi-criticality real-time system, such as an autonomous driving system. It has been recently shown that these systems can be vulnerable to timing inference attacks, mainly due to their predictable behavioral patterns. Existing solutions like schedule randomization cannot protect against such attacks, often limited by the system’s real-time nature. This article presents “ SchedGuard++ ”: a temporal protection framework for Linux-based real-time systems that protects against posterior schedule-based attacks by preventing untrusted tasks from executing during specific time intervals. SchedGuard++ supports multi-core platforms and is implemented using Linux containers and a customized Linux kernel real-time scheduler. We provide schedulability analysis assuming the Logical Execution Time (LET) paradigm, which enforces I/O predictability. The proposed response time analysis takes into account the interference from trusted and untrusted tasks and the impact of the protection mechanism. We demonstrate the effectiveness of our system using a realistic radio-controlled rover platform. Not only is “ SchedGuard++ ” able to protect against the posterior schedule-based attacks, but it also ensures that the real-time tasks/containers meet their temporal requirements.

Intrusion Detection Scheme With Dimensionality Reduction in Next Generation Networks

Due to millions of heterogeneous physical nodes, multiple-vendor and multi-tenant domains, and technologies etc., 5G has greatly expanded the threat landscape. Particularly from the high rate of traffic and ultra-low latency requirement of applications in 5G networks, the detection of the network traffic anomalies in real-time is critical. The conventional security approaches lack compatibility with modern network designs and are not much effective in 5G settings. We propose a two-stage network traffic anomaly detection system compatible with ETSI-NFV standard 5G architecture. Our architecture consists of two modules, i.e., (a) Dimensionality Reduction to compress the sample size at the edge of 5G networks and (b) Deep Neural Network classifier (DNN) that detects traffic anomalies. We have conducted our experiments using OMNET++ and ETSI-NFV (OSM MANO) 5G orchestration real platform deployed on AWS cloud systems. We have used the UNSW-NB15 data set and have shown that at dimensionality reduction factor of 81% the detection accuracy obtained is 98%. The proposal is compared with other recent approaches to show the overall merit of the architecture.

EXPLORING CROWDFUNDING POTENTIAL FOR SUPPORTING COMMUNITY- BASED TOURISM IN MALAYSIA

This paper discovers the potential of the Islamic crowdfunding model for supporting community-based tourism in developing states Malaysia in particular. Community-based tourism has provided a great opportunity for rural areas to empower the socio-economy of local people to earn main or additional income, and crowdfunding is seen as a potential fund for supporting community-based tourism. This study applies a library research method as its data are collected through literature related to community-based tourism and crowdfunding topics. The special model of Islamic crowdfunding proposed by this study can potentially support community-based tourism if it is applied to a real platform. As a result, it can reduce the burden of the government in providing funds for tourism. While crowdfunding creates an alternative opportunity for community and tourism-based projects, it promotes job opportunities and economic growth within society including business and services. However, this approach could be challenging to apply because of awareness among people. Nevertheless, a suitable Islamic crowdfunding model with a proper campaign can be a practical solution for funding community-based tourism projects. As this study is conceptual, the outcomes may not be limited. However, it still provides a substantial contribution in terms of offering a practical model of Islamic crowdfunding in Malaysia.

Higher-order topological corner states induced solely by on-site potentials with mirror symmetry

Higher-order topological insulators have triggered a great deal of interest because they exhibit nontrivial bulk topology on lower-dimensional boundaries such as corners and hinges. While such interesting phases have been investigated in a plethora of systems by tuning staggered tunneling strength or manipulating existing topological phases, here we show that a higher-order topological phase can be driven solely by mirror-symmetric on-site potentials. We start with a chain model, and we show that it has nonzero edge states due to the lack of internal symmetries such as chiral and particle-hole symmetries. We then generalize the model to two dimensions, and we demonstrate the emergence of topological corner modes. These corner modes are an intrinsic manifestation of nontrivial bulk band topology protected by mirror symmetry, and thus they are robust against symmetry-preserved perturbations. Our model only requires the tuning of on-site energies, and it provides a realistic platform for studying a class of higher-order topological insulators using state-of-the-art experiment techniques.

Breaking the Action‐Reaction Principle of Light Interactions Under a Stroboscopic Nonlinearity

AbstractThe action–reaction principle is proven violated in multitudes of physical systems under certain circumstances, but such a violation is rarely reported in the interplay (via nonlinearity) of optical fields, particularly in experiment. Here a realistic optical platform is demonstrated for realizing light interactions that break the law of action–reaction. Under a stroboscopic nonlinearity where self‐focusing and ‐defocusing effects come to play the role periodically, two optical beams are judiciously trimmed temporally to experience the two inverted nonlinear effects. During their interaction, they show deflections toward the same direction. The underlying physics is in sharp contrast to that in the attraction/repulsion or diametric drive behavior commonly seen in all previous experiments. In addition, the wave dynamics introduce an extra feature that has no counterpart in particle interactions breaking the action–reaction principle. The counterintuitive interplay realized here in optics may bring about new ways for light manipulation.

BARM: A Batch-Aware Resource Manager for Boosting Multiple Neural Networks Inference on GPUs With Memory Oversubscription

Modern intelligent devices usually execute multiple neural networks to improve service quality. However, system performance degrades significantly when the working set exceeds the physical memory capability, a phenomenon called memory oversubscription. To support the execution of multiple independent neural networks with limited physical memory, this article explores resource management in GPUs with unified virtual memory and demand paging. We first analyze the relationship between the simultaneous execution of multiple neural networks from streaming multiprocessors (SM) assignment and page fault overhead from memory thrashing. To boost performance by reducing the page fault penalty, we propose a batch-aware resource management approach, BARM, including (1) batch-aware SM resource allocation to increase the batch size and (2) thrashing-preventing memory allocation to eliminate run-time thrashing. The performance of the proposed method was evaluated using a series of workloads, and response latency is reduced significantly over the state-of-the-art page fault prefetcher and batch-aware TLP management. The proposed framework was also implemented on the real platform and evaluated by a case study, and impressive results were obtained.

ChSO-DNFNet: Spam detection in Twitter using feature fusion and optimized Deep Neuro Fuzzy Network

The usage of social networking platforms for interaction and meeting has grown significantly. However, as social networks continue to expand, Twitter has emerged as a vital social media for real life and has become a major source of spam. To address the aforementioned problems, spam identification on social media becomes an increasingly crucial task. The features that are present in the high dimension data of social networks cannot be used effectively by the existing approaches. In order to filter the spam information in social media, a Chimp Sailfish Optimization-based Deep Neuro Fuzzy Network (ChSO-based DNFN) is proposed. The proposed method effectively performs well under high dimensional data in real platform environment using deep learning classifier. It is more robust and generates optimal result and also reduces the computational complexity problems. Additionally, the proposed approach demonstrated improved performance in terms of metrics like precision, recall, and F-measure, which were measured using a 5k continuous dataset and yielded values of 0.894, 0.903, and 0.898, respectively.

Simulation and Validation of Optimized PID Controller in AGV (Automated Guided Vehicles) Model Using PSO and BAS Algorithms.

Automated guided vehicles (AGVs) are popular subsets of robots that come in various shapes and sizes. The group's use in the industry ranges from applications for carrying pallets, carts, and utensils to helping the elderly or transporting medicine to hospitals. Even recently, they have been used in libraries to carry books on shelves. The main part of an AGV includes its body, motor, driver, processor, and sensors, which are more or less the same in all types of AGVs, and addons vary depending on the application and the work environment. The part that affects AGV performance is the control strategy, to which researchers have shown different approaches. Using various techniques and simulations to obtain a model is the key and can help to improve and evaluate the performance of the strategy of the robot. In this study, based on the actual design of the AGV system, all data and components are described, and the simulation is performed in MATLAB software. Then, for controlling the platform based on the PID controller tuning, four methods of Ziegler Nichols, empirical, Particle Swarm Optimization (PSO), and Beetle Antennae Searching (BAS) (optimizer) are discussed, and the results are compared in the four paths including the circle, ellipse, Spiral and 8-shaped paths by observing and testing the tuned PID parameters. Finally, a series of subsequent experiences were carried out in CoppeliaSim (VREP) as a famous robot simulator to overcome the environmental constraints for the same paths that were used in Matlab based on the extracted PID values. Based on the results, the empirical methods, PSO, and BAS errors are very close together. But in general, the BAS algorithm is the fastest, and the PSO had better performance. In general, the maximum error is linked to the path of 8 shapes and the minimum is related to circle shape one. Finally, the analysis of results in different paths in both simulators shows the same results. Therefore, concerning the limited test on the real platform and using the PID coefficients obtained from the simulation shows the model's ability for the researchers in robotic research.

Virtual-reality-based online simulator design with a virtual simulation system for the docking of unmanned underwater vehicle

The simulation of the docking process is an important solution for the control and navigation design of Unmanned Underwater Vehicle (UUV), which can be used to evaluate the reliability of the algorithm in an economic way. However, most of the existing simulations are offline, which cannot interact with the real sensors mounted on the UUV, and cannot visually simulate and display the immersive motion of the UUV in the underwater environment. Therefore, to address the aforementioned problem, an online simulator is designed in this paper, which provides a virtual simulation system for the docking task simulation of the UUV. Two modes are designed with one to provide the virtual simulation with simulated UUV model and sensor, while another to provide the real platform simulation with intuitive visualization of the real tasks achieved by the recorded data. The host and lower computers are designed to communicate and exchange the data. Namely, the lower computer can calculate the mathematical model, and simulate or interact with the real sensor during the docking process; The host computer can obtain the simulated or recorded data from the lower computer, and implement the navigation and control of the UUV, which can be finally displayed in the accurately created virtual docking scene. The fuzzy PID controller and four different navigation modes are designed to implement the experiment with the specific motion verification and underwater docking for the UUV, and the results verify the effectiveness of the online simulator for the underwater tasks simulation with lower cost.