In the last decade, technical advancements and faster Internet speeds have also led to an increasing number ofmobile devices and users. Thus, all contributors to society, whether young or old members, can use these mo...
详细信息
In the last decade, technical advancements and faster Internet speeds have also led to an increasing number ofmobile devices and users. Thus, all contributors to society, whether young or old members, can use these mobileapps. The use of these apps eases our daily lives, and all customers who need any type of service can accessit easily, comfortably, and efficiently through mobile apps. Particularly, Saudi Arabia greatly depends on digitalservices to assist people and visitors. Such mobile devices are used in organizing daily work schedules and services,particularly during two large occasions, Umrah and Hajj. However, pilgrims encounter mobile app issues such asslowness, conflict, unreliability, or user-unfriendliness. Pilgrims comment on these issues on mobile app platformsthrough reviews of their experiences with these digital services. Scholars have made several attempts to solve suchmobile issues by reporting bugs or non-functional requirements by utilizing user ***, solving suchissues is a great challenge, and the issues still exist. Therefore, this study aims to propose a hybrid deep learningmodel to classify and predict mobile app software issues encountered by millions of pilgrims during the Hajj andUmrah periods from the user perspective. Firstly, a dataset was constructed using user-generated comments fromrelevant mobile apps using natural language processing methods, including information extraction, the annotationprocess, and pre-processing steps, considering a multi-class classification problem. Then, several experimentswere conducted using common machine learning classifiers, Artificial Neural Networks (ANN), Long Short-TermMemory (LSTM), and Convolutional Neural Network Long Short-Term Memory (CNN-LSTM) architectures, toexamine the performance of the proposed model. Results show 96% in F1-score and accuracy, and the proposedmodel outperformed the mentioned models.
The technology of facial expression reconstruction has paved the way for various face-centric applications such as virtual reality (VR) modeling, human-computer interaction, and affective computing. Existing vision-ba...
详细信息
The subsynchronous oscillations(SSOs)related to renewable generation seriously affect the stability and safety of the power *** realize the dynamic monitoring of SSOs by utilizing the high computational efficiency and...
详细信息
The subsynchronous oscillations(SSOs)related to renewable generation seriously affect the stability and safety of the power *** realize the dynamic monitoring of SSOs by utilizing the high computational efficiency and noise-resilient features of the matrix pencil method(MPM),this paper propos es an improved MPM-based parameter identification with syn *** MPM is enhanced by the angular frequency fitting equations based on the characteristic polynomial coeffi cients of the matrix pencil to ensure the accuracy of the identi fied parameters,since the existing eigenvalue solution of the MPM ignores the angular frequency conjugation constraints of the two fundamental modes and two oscillation ***,the identification and recovery of bad data are proposed by uti lizing the difference in temporal continuity of the synchropha sors before and after noise *** proposed parameter identification is verified with synthetic,simulated,and actual measured phase measurement unit(PMU)*** with the existing MPM,the improved MPM achieves better accuracy for parameter identification of each component in SSOs,better real-time performance,and significantly reduces the effect of bad data.
This paper presents a novel supervised learning framework for real-time optimization of multi-parametric mixed-integer quadratic programming (mp-MIQP) problems. The framework utilizes a multi-layer perceptron (MLP) mo...
详细信息
Federated learning is widely accepted as a privacy-preserving paradigm for training a shared global model across multiple client devices in a collaborative fashion. However, in practice, the significantly limited comp...
详细信息
Federated learning is widely accepted as a privacy-preserving paradigm for training a shared global model across multiple client devices in a collaborative fashion. However, in practice, the significantly limited computational power on client devices has been a major barrier when we wish to train large models with potentially hundreds of millions of parameters. In this paper, we propose a new architecture, referred to as Infocomm, that incorporates locally supervised learning in federated learning. With locally supervised learning, the disadvantages of split learning can be avoided by using a more flexible way to offload training from resource constrained clients to a more capable server. Infocomm enables parallel training of different modules of the neural network in both the server and clients in a gradient-isolated fashion. The efficacy in reducing both training time and communication time is supported by our theoretical analysis and empirical results. In the scenario involving larger models and fewer available local data, Infocomm has been observed to reduce the elapsed time per round by over 37% without sacrificing accuracy compared to both conventional federated learning or directly combining federated learning and split learning, which showcases the advantages of Infocomm under power-constrained IoT scenarios. IEEE
To maximize conversion efficiency,photovoltaic(PV)systems generally operate in the maximum power point tracking(MPPT)***,due to the increasing penetra tion level of PV systems,there is a need for more developed contro...
详细信息
To maximize conversion efficiency,photovoltaic(PV)systems generally operate in the maximum power point tracking(MPPT)***,due to the increasing penetra tion level of PV systems,there is a need for more developed control functions in terms of frequency support services and voltage control to maintain the reliability and stability of the power ***,flexible active power control is a manda tory task for grid-connected PV systems to meet part of the grid ***,a significant number of flexible pow er point tracking(FPPT)algorithms have been introduced in the existing *** purpose of such algorithms is to real ize a cost-effective method to provide grid support functional ities while minimizing the reliance on energy storage *** paper provides a comprehensive overview of grid support functionalities that can be obtained with the FPPT control of PV systems such as frequency support and volt-var *** of these grid support functionalities necessitates PV sys tems to operate under one of the three control strategies,which can be provided with FPPT *** three control strate gies are classified as:①constant power generation control(CP GC),②power reserve control(PRC),and③power ramp rate control(PRRC).A detailed discussion on available FPPT algo rithms for each control strategy is also *** paper can serve as a comprehensive review of the state-of-the-art FPPT algorithms that can equip PV systems with various grid support functionalities.
This study addresses the critical need for robust safeguarding of sensitive data stored on personal computing devices and during data transmissions, alongside the increasing need for secure digital interactions. Conve...
详细信息
Optoelectronic devices are advantageous in in-memory light sensing for visual information processing,recognition,and storage in an energy-efficient ***,in-memory light sensors have been proposed to improve the energy,...
详细信息
Optoelectronic devices are advantageous in in-memory light sensing for visual information processing,recognition,and storage in an energy-efficient ***,in-memory light sensors have been proposed to improve the energy,area,and time efficiencies of neuromorphic computing *** study is primarily focused on the development of a single sensing-storage-processing node based on a two-terminal solution-processable MoS2 metal-oxide-semiconductor(MOS)charge-trapping memory structure—the basic structure for charge-coupled devices(CCD)—and showing its suitability for in-memory light sensing and artificial visual *** memory window of the device increased from 2.8 V to more than 6V when the device was irradiated with optical lights of different wavelengths during the program ***,the charge retention capability of the device at a high temperature(100 ℃)was enhanced from 36 to 64%when exposed to a light wavelength of 400 *** larger shift in the threshold voltage with an increasing operating voltage confirmed that more charges were trapped at the Al_(2)O_(3)/MoS_(2) interface and in the MoS_(2) layer.A small convolutional neural network was proposed to measure the optical sensing and electrical programming abilities of the *** array simulation received optical images transmitted using a blue light wavelength and performed inference computation to process and recognize the images with 91%*** study is a significant step toward the development of optoelectronic MOS memory devices for neuromorphic visual perception,adaptive parallel processing networks for in-memory light sensing,and smart CCD cameras with artificial visual perception capabilities.
The rapid growth of digital data necessitates advanced natural language processing(NLP)models like BERT(Bidi-rectional Encoder Representations from Transformers),known for its superior performance in text ***,BERT’s ...
详细信息
The rapid growth of digital data necessitates advanced natural language processing(NLP)models like BERT(Bidi-rectional Encoder Representations from Transformers),known for its superior performance in text ***,BERT’s size and computational demands limit its practicality,especially in resource-constrained *** research compresses the BERT base model for Bengali emotion classification through knowledge distillation(KD),pruning,and quantization *** Bengali being the sixth most spoken language globally,NLP research in this area is *** approach addresses this gap by creating an efficient BERT-based model for Bengali *** have explored 20 combinations for KD,quantization,and pruning,resulting in improved speedup,fewer parameters,and reduced memory *** best results demonstrate significant improvements in both speed and *** instance,in the case of mBERT,we achieved a 3.87×speedup and 4×compression ratio with a combination of Distil+Prune+Quant that reduced parameters from 178 to 46 M,while the memory size decreased from 711 to 178 *** results offer scalable solutions for NLP tasks in various languages and advance the field of model compression,making these models suitable for real-world applications in resource-limited environments.
Direct training of Spiking Neural Networks (SNNs) is a challenging task because of their inherent temporality. Added to it, the vanilla Back-propagation based methods are not applicable either, due to the non-differen...
详细信息
Direct training of Spiking Neural Networks (SNNs) is a challenging task because of their inherent temporality. Added to it, the vanilla Back-propagation based methods are not applicable either, due to the non-differentiability of the spikes in SNNs. Surrogate-Derivative based methods with Backpropagation Through Time (BPTT) address these direct training challenges quite well;however, such methods are not neuromorphic-hardware friendly for the On-chip training of SNNs. Recently formalized Three-Factor based Rules (TFR) for direct local-training of SNNs are neuromorphic-hardware friendly;however, they do not effectively leverage the depth of the SNN architectures (we show it empirically here), thus, are limited. In this work, we present an improved version of a conventional three-factor rule, for local learning in SNNs which effectively leverages depth - in the context of learning features hierarchically. Taking inspiration from the Back-propagation algorithm, we theoretically derive our improved, local, three-factor based learning method, named DALTON (Deep LocAl Learning via local WeighTs and SurrOgate-Derivative TraNsfer), which employs weights and surrogate-derivative transfer from the local layers. Along the lines of TFR, our proposed method DALTON is also amenable to the neuromorphic-hardware implementation. Through extensive experiments on static (MNIST, FMNIST, & CIFAR10) and event-based (N-MNIST, DVS128-Gesture, & DVSCIFAR10) datasets, we show that our proposed local-learning method DALTON makes effective use of the depth in Convolutional SNNs, compared to the vanilla TFR implementation. IEEE
暂无评论