This paper presents a decentralized self-triggered tracking control method for modular reconfigurable robots (MRRs) via adaptive dynamic programming (ADP). The Newton-Euler form dynamic modeling method is used to mode...
详细信息
Aiming at bipedal modular robot (MR) system with strong coupling, a trajectory tracking method based on adaptive neural network (NN) is proposed to solve the gait coordination control issue, and the dynamic model of b...
详细信息
This study focuses on enhancing Natural Language Processing (NLP) in generative AI chatbots through the utilization of advanced pre-trained models. We assessed five distinct Large Language Models (LLMs): TRANSFORMER M...
详细信息
The Terminator, a specific DNA sequence, provides the transcriptional termination signal to RNA polymerase, making it a critical aspect of transcriptional regulation. This article proposes AMter, the first end-to-end ...
详细信息
This paper proposes a decentralized cooperative control for multi-reconfigurable manipulator (MRM) based on Adaptive Dynamic Programing (ADP). The control method can achieve both motion path tracking and control the f...
详细信息
In the field of medical images,pixel-level labels are time-consuming and expensive to acquire,while image-level labels are relatively easier to ***,it makes sense to learn more information(knowledge)from a small numbe...
详细信息
In the field of medical images,pixel-level labels are time-consuming and expensive to acquire,while image-level labels are relatively easier to ***,it makes sense to learn more information(knowledge)from a small number of hard-to-get pixel-level annotated images to apply to different tasks to maximize their usefulness and save time and training *** this paper,using Pixel-Level Labeled Images forMulti-Task Learning(PLDMLT),we focus on grading the severity of fundus images for Diabetic Retinopathy(DR).This is because,for the segmentation task,there is a finely labeled mask,while the severity grading task is without classification *** this end,we propose a two-stage multi-label learning weakly supervised algorithm,which generates initial classification pseudo labels in the first stage and visualizes heat maps at all levels of severity using Grad-Cam to further provide medical interpretability for the classification task.A multitask model framework with U-net as the baseline is proposed in the second stage.A label update network is designed to alleviate the gradient balance between the classification and segmentation *** experimental results show that our PLDMLTmethod significantly outperforms other stateof-the-art methods in DR segmentation on two public datasets,achieving up to 98.897%segmentation *** addition,our method achieves comparable competitiveness with single-task fully supervised learning in the DR severity grading task.
Preserving privacy is imperative in the new unmanned aerial vehicle(UAV)-assisted mobile edge computing(MEC)architecture to ensure that sensitive information is protected and kept secure throughout the ***,efficiency ...
详细信息
Preserving privacy is imperative in the new unmanned aerial vehicle(UAV)-assisted mobile edge computing(MEC)architecture to ensure that sensitive information is protected and kept secure throughout the ***,efficiency must be considered while developing such a privacy-preserving scheme because the devices involved in these architectures are resource *** study proposes a lightweight and efficient authentication scheme for *** proposed scheme is a hardware-based password-less authentication mechanism that is based on the fact that temporal and memory-related efficiency can be significantly improved while maintaining the data security by adopting a hardwarebased solution with a simple *** proposed scheme works in four stages:system initialization,EU registration,EU authentication,and session *** is implemented as a single hardware chip comprising registers and XOR gates,and it can run the entire process in one clock ***,the proposed scheme has significantly higher efficiency in terms of runtime and memory consumption compared to other prevalent methods in the *** are conducted to evaluate the proposed authentication *** results show that the scheme has an average execution time of 0.986 ms and consumes average memory of 34 *** hardware execution time is approximately 0.39 ns,which is a significantly less than the prevalent schemes,whose execution times range in ***,the security of the proposed scheme is examined,and it is resistant to brute-force *** 1.158×10^(77) trials are required to overcome the system’s security,which is not feasible using fastest available processors.
The unconventional photon blockade effect due to quantum interference in a second-order nonlinear system embedded with a two-level atom is studied. By performing analytical calculations, the approximate results are ob...
详细信息
This paper presents a standing balance control scheme for biped reconfigurable robots (BRRs) via neuro-dynamic programming (NDP) method. First, a global dynamic model of BRRs is established, in which the torso model i...
详细信息
Audio Deepfakes, which are highly realistic fake audio recordings driven by AI tools that clone human voices, With Advancements in Text-Based Speech Generation (TTS) and Vocal Conversion (VC) technologies have enabled...
详细信息
Audio Deepfakes, which are highly realistic fake audio recordings driven by AI tools that clone human voices, With Advancements in Text-Based Speech Generation (TTS) and Vocal Conversion (VC) technologies have enabled it easier to create realistic synthetic and imitative speech, making audio Deepfakes a common and potentially dangerous form of deception. Well-known people, like politicians and celebrities, are often targeted. They get tricked into saying controversial things in fake recordings, causing trouble on social media. Even kids’ voices are cloned to scam parents into ransom payments, etc. Therefore, developing effective algorithms to distinguish Deepfake audio from real audio is critical to preventing such frauds. Various Machine learning (ML) and Deep learning (DL) techniques have been created to identify audio Deepfakes. However, most of these solutions are trained on datasets in English, Portuguese, French, and Spanish, expressing concerns regarding their correctness for other languages. The main goal of the research presented in this paper is to evaluate the effectiveness of deep learning neural networks in detecting audio Deepfakes in the Urdu language. Since there’s no suitable dataset of Urdu audio available for this purpose, we created our own dataset (URFV) utilizing both genuine and fake audio recordings. The Urdu Original/real audio recordings were gathered from random youtube podcasts and generated as Deepfake audios using the RVC model. Our dataset has three versions with clips of 5, 10, and 15 seconds. We have built various deep learning neural networks like (RNN+LSTM, CNN+attention, TCN, CNN+RNN) to detect Deepfake audio made through imitation or synthetic techniques. The proposed approach extracts Mel-Frequency-Cepstral-Coefficients (MFCC) features from the audios in the dataset. When tested and evaluated, Our models’ accuracy across datasets was noteworthy. 97.78% (5s), 98.89% (10s), and 98.33% (15s) were remarkable results for the RNN+LSTM
暂无评论