Identifying human actions and interactions finds its use in manyareas, such as security, surveillance, assisted living, patient monitoring, rehabilitation,sports, and e-learning. This wide range of applications has at...
详细信息
Identifying human actions and interactions finds its use in manyareas, such as security, surveillance, assisted living, patient monitoring, rehabilitation,sports, and e-learning. This wide range of applications has attractedmany researchers to this field. Inspired by the existing recognition systems,this paper proposes a new and efficient human-object interaction recognition(HOIR) model which is based on modeling human pose and scene featureinformation. There are different aspects involved in an interaction, includingthe humans, the objects, the various body parts of the human, and the backgroundscene. Themain objectives of this research include critically examiningthe importance of all these elements in determining the interaction, estimatinghuman pose through image foresting transform (IFT), and detecting the performedinteractions based on an optimizedmulti-feature vector. The proposedmethodology has six main phases. The first phase involves preprocessing theimages. During preprocessing stages, the videos are converted into imageframes. Then their contrast is adjusted, and noise is removed. In the secondphase, the human-object pair is detected and extracted from each image *** third phase involves the identification of key body parts of the detectedhumans using IFT. The fourth phase relates to three different kinds of featureextraction techniques. Then these features are combined and optimized duringthe fifth phase. The optimized vector is used to classify the interactions in thelast phase. TheMSRDaily Activity 3D dataset has been used to test this modeland to prove its efficiency. The proposed system obtains an average accuracyof 91.7% on this dataset.
Embedded Systems Operations (ESOps) introduces a feature-driven development pipeline for next-generation embedded system, leveraging domain-specific Large Language Models (LLMs) to expedite the development process. Ta...
详细信息
In this paper, we first introduce a new text representation method to convert a textual document into a tensor space model named TextCuboid, which can preserve various meanings of polysemy. Based upon the new model, w...
详细信息
The current limiting control is commonly used in grid-forming (GFM) inverters to protect semiconductor devices during grid faults. However, it can lead to abnormal post-fault scenarios, such as continuous operation in...
详细信息
This paper proposes a nulling steering beamforming-based isolation optimization scheme to mitigate the Tx-Rx self-interference in full-duplex massive MIMO systems. By searching the optimal nulling angles in both the u...
详细信息
This paper introduces the Correlation-Diversified Conditional Generative Adversarial Network (CDC-GAN), a new model that automates and speeds up electric machine (E-machine) design exploration. Traditional methods in ...
详细信息
This study developed a small, low-profile magneto-electric dipole antenna with wideband characteristics by adding a capacitively loaded loop (CLL) structure and stubs. The proposed antenna consists of an electric dipo...
详细信息
Providing a reliable and rapid energy supply to Pelagic Oceanic Islands (POIs) is a critical challenge due to their remote geographical locations. This study addresses this challenge by introducing the innovative conc...
详细信息
ISBN:
(纸本)9798331507565
Providing a reliable and rapid energy supply to Pelagic Oceanic Islands (POIs) is a critical challenge due to their remote geographical locations. This study addresses this challenge by introducing the innovative concept of Oceanic Mobile electrical Storage (OMES), which aims to ensure energy reliability while minimizing environmental impact. OMES systems are electrically powered, floating Microgrids (MGs) equipped with Battery electrical Storage Packs (BESPs). These MGs integrate Oceanic Biodiesel Generators (OBMDGs) and Oceanic Distributed Energy Resources (ODERs), such as Flywheel Energy Storage Systems (FESS), Proton Exchange Membrane Fuel Cells (PEMFCs), and OMES-Mounted Photovoltaics (OMES-MPVs). The study focuses on enhancing the frequency stability of the OMES Isolated Microgrid (OMESIM) by proposing a novel control topology: The IPD-2DOF-TID (Proportional-Derivative with Two Degrees of Freedom-Tilt Integral Derivative) cascode hybrid controller. This controller is optimized using the Greylag Goose Optimization (GGO) algorithm, a swarm intelligence technique inspired by the natural behaviors of Greylag Geese. The main contribution of this research is the development of the IPD-2DOF-TID/GGO control scheme, which provides a robust framework for the design and performance evaluation of Load Frequency Control (LFC) controllers. The proposed control scheme is benchmarked against established meta-heuristic algorithms, including the Mountaineering Team-Based Optimization (MTBO) and Corona Virus Search Optimizer (CVSO) algorithms, using the Integral of Squared Time multiplied by Absolute Error (ISTSE) as the primary objective function. Additional evaluation metrics include the Integral of Squared Error (ISE) and the Integral of Time multiplied by Squared Error (ITSE). The results demonstrate that the IPD-2DOF-TID/GGO control strategy offers significant performance improvements over alternative schemes, with superior response speed, substantial reductions in maximum
In this paper, we consider reinforcement learning (RL) techniques to systematically analyze and enhance the levels of disagreement and polarization within social media ecosystems. The proposed methodology employs a Do...
This paper presents a design for a novel single-layer, dual-wideband linear-to-circular polarization converter. The unit cell features two identical, diagonally oriented C-shaped metallic strips, integrated with four ...
详细信息
暂无评论