RESUMEN
Doppler-radar-based continuous human motion recognition recently has attracted extensive attention, which is a favorable choice for privacy and personal security. Existing results of continuous human motion recognition (CHMR) using mmWave FMCW Radar are not considered the continuous human motion with the high similarity problem. In this paper, we proposed a new CHMR algorithm with the consideration of the high similarity (HS) problem, called as CHMR-HS, by using the modified Transformer-based learning model. As far as we know, this is the first result in the literature to investigate the continuous HMR with the high similarity. To obtain the clear FMCW radar images, the background and target signals of the detected human are separated through the background denoising and the target extraction algorithms. To investigate the effects of the spectral-temporal multi-features with different dimensions, Doppler, range, and angle signatures are extracted as the 2D features and range-Doppler-time and range-angle-time signatures are extracted as the 3D features. The 2D/3D features are trained into the adjusted Transformer-encoder model to distinguish the difference of the high-similarity human motions. The conventional Transformer-decoder model is also re-designed to be Transformer-sequential-decoder model such that Transformer-sequential-decoder model can successfully recognize the continuous human motions with the high similarity. The experimental results show that the accuracy of our proposed CHMR-HS scheme are 95.2% and 94.5% if using 3D and 2D features, the simulation results also illustrates that our CHMR-HS scheme has advantages over existing CHMR schemes.
Asunto(s)
Radar , Procesamiento de Señales Asistido por Computador , Humanos , Movimiento (Física) , Algoritmos , Ultrasonografía DopplerRESUMEN
In this paper, we present a new AI (Artificial Intelligence) edge platform, called "MiniDeep", which provides a standalone deep learning platform based on the cloud-edge architecture. This AI-Edge platform provides developers with a whole deep learning development environment to set up their deep learning life cycle processes, such as model training, model evaluation, model deployment, model inference, ground truth collecting, data pre-processing, and training data management. To the best of our knowledge, such a whole deep learning development environment has not been built before. MiniDeep uses Amazon Web Services (AWS) as the backend platform of a deep learning tuning management model. In the edge device, the OpenVino enables deep learning inference acceleration at the edge. To perform a deep learning life cycle job, MiniDeep proposes a mini deep life cycle (MDLC) system which is composed of several microservices from the cloud to the edge. MiniDeep provides Train Job Creator (TJC) for training dataset management and the models' training schedule and Model Packager (MP) for model package management. All of them are based on several AWS cloud services. On the edge device, MiniDeep provides Inference Handler (IH) to handle deep learning inference by hosting RESTful API (Application Programming Interface) requests/responses from the end device. Data Provider (DP) is responsible for ground truth collection and dataset synchronization for the cloud. With the deep learning ability, this paper uses the MiniDeep platform to implement a recommendation system for AI-QSR (Quick Service Restaurant) KIOSK (interactive kiosk) application. AI-QSR uses the MiniDeep platform to train an LSTM (Long Short-Term Memory)-based recommendation system. The LSTM-based recommendation system converts KIOSK UI (User Interface) flow to the flow sequence and performs sequential recommendations with food suggestions. At the end of this paper, the efficiency of the proposed MiniDeep is verified through real experiments. The experiment results have demonstrated that the proposed LSTM-based scheme performs better than the rule-based scheme in terms of purchase hit accuracy, categorical cross-entropy, precision, recall, and F1 score.
Asunto(s)
Inteligencia Artificial , Aprendizaje Profundo , Programas InformáticosRESUMEN
Indoor localization is an important issue for indoor location-based services. As opposed to the other indoor localization approaches, the radio frequency (RF) based approaches are low-energy solutions with simple implementation. The kernel learning has been used for the RF-based indoor localization in 2D environment. However, the kernel learning has not been used in 3D environment. Hence, this paper proposes a multi-kernel learning scheme for 3D indoor localization. Based on the signals collected in the area of interest, the WiFi signals with better quality and closer to the user are selected so as to reduce the multipath effect and the external interference. Through the construction of multi-kernel, the localization accuracy can be improved as opposed to the localization based on the single kernel. We build multiple kernels to get the user's location by collecting wireless received signal strengths (RSS) and signal-to-noise ratios (SNR). The kernel learning maps data to high dimension space and uses the optimization process to find the surface where the data are mapped. By multi-kernel training, the surface is fine-tuned and eventually converges to form the location database during the mapping process. The proposed localization scheme is verified by the real RSS and SNR collected from multiple wireless access points (AP) in a building. The experimental results verify that the proposed multi-kernel learning scheme performs better than the multi-DNN scheme and the existing kernel-based localization schemes in terms of localization accuracy and error in 3D indoor environment.
RESUMEN
Human activity recognition without equipment plays a vital role in smart home applications, freeing humans from the shackles of wearable devices. In this paper, by using the channel state information (CSI) of the WiFi signal, semi-supervised transfer learning with dynamic associate domain adaptation is proposed for human activity recognition. In order to improve the CSI quality and denoising of CSI, we carried out missing packet filling, burst noise removal, background estimation, feature extraction, feature enhancement, and data augmentation in the data pre-processing stage. This paper considers the problem of environment-independent human activity recognition, also known as domain adaptation. The pre-trained model is trained from the source domain by collecting a complete labeled dataset of all of the CSI of human activity patterns. Then, the pre-trained model is transferred to the target environment through the semi-supervised transfer learning stage. Therefore, when humans move to different target domains, a partial labeled dataset of the target domain is required for fine-tuning. In this paper, we propose a dynamic associate domain adaptation called DADA. By modifying the existing associate domain adaptation algorithm, the target domain can provide a dynamic ratio of labeled dataset/unlabeled dataset, while the existing associate domain adaptation algorithm only allows target domains with the unlabeled dataset. The advantage of DADA is that it provides a dynamic strategy to eliminate different effects on different environments. In addition, we further designed an attention-based DenseNet model, or AD, as our training network, which is modified by an existing DenseNet by adding the attention function. The solution we proposed was simplified to DADA-AD throughout the paper. The experimental results show that for domain adaptation in different domains, the accuracy of human activity recognition of the DADA-AD scheme is 97.4%. It also shows that DADA-AD has advantages over existing semi-supervised learning schemes.
Asunto(s)
Aprendizaje Automático Supervisado , Dispositivos Electrónicos Vestibles , Aclimatación , Algoritmos , Actividades Humanas , HumanosRESUMEN
During the training phase of the supervised learning, it is not feasible to collect all the datasets of labelled data in an outdoor environment for the localization problem. The semi-supervised transfer learning is consequently used to pre-train a small number of labelled data from the source domain to generate a kernel knowledge for the target domain. The kernel knowledge is transferred to a target domain to transfer some unlabelled data into the virtual labelled data. In this paper, we have proposed a new outdoor localization scheme using a semi-supervised transfer learning for LoRaWANs. In the proposed localization algorithm, a grid segmentation concept is proposed so as to generate a number of virtual labelled data through learning by constructing the relationship of labelled and unlabelled data. The labelled-unlabelled data relationship is repeatedly fine-tuned by correctly adding some more virtual labelled data. Basically, the more the virtual labelled data are added, the higher the location accuracy will be obtained. In the real implementation, three types of signal features, RSSI, SNR, and timestamps, are used for training to improve the location accuracy. The experimental results illustrate that the proposed scheme can improve the location accuracy and reduce the localization error as opposed to the existing outdoor localization schemes.
RESUMEN
Mobility management for supporting the location tracking and location-based service (LBS) is an important issue of smart city by providing the means for the smooth transportation of people and goods. The mobility is useful to contribute the innovation in both public and private transportation infrastructures for smart cities. With the assistance of edge/fog computing, this paper presents a fully new mobility management using the proposed follow-me cloud-cloudlet (FMCL) approach in fog-computing-based radio access networks (Fog-RANs) for smart cities. The proposed follow-me cloud-cloudlet approach is an integration strategy of follow-me cloud (FMC) and follow-me edge (FME) (or called cloudlet). A user equipment (UE) receives the data, transmitted from original cloud, into the original edge cloud before the handover operation. After the handover operation, an UE searches for a new cloud, called as a migrated cloud, and a new edge cloud, called as a migrated edge cloud near to UE, where the remaining data is migrated from the original cloud to the migrated cloud and all the remaining data are received in the new edge cloud. Existing FMC results do not have the property of the VM migration between cloudlets for the purpose of reducing the transmission latency, and existing FME results do not keep the property of the service migration between data centers for reducing the transmission latency. Our proposed FMCL approach can simultaneously keep the VM migration between cloudlets and service migration between data centers to significantly reduce the transmission latency. The new proposed mobility management using FMCL approach aims to reduce the total transmission time if some data packets are pre-scheduled and pre-stored into the cache of cloudlet if UE is switching from the previous Fog-RAN to the serving Fog-RAN. To illustrate the performance achievement, the mathematical analysis and simulation results are examined in terms of the total transmission time, the throughput, the probability of packet loss, and the number of control messages.
RESUMEN
CONCLUSIONS: Nasal epithelial cells are constitutively equipped with all Toll-like receptors (TLRs) which are essential for innate immunity. Both mRNA and protein levels of TLR3 expression increased in more differentiated nasal epithelial cells. Considering that the ligand for TLR3 is viral dsRNA, this result is in good accordance with previous reports demonstrating that more differentiated airway epithelial cells have increased resistance to rhinovirus infection. OBJECTIVE: Nasal epithelial cells use innate immune responses to combat inspired potential pathogens. TLRs are receptors that recognize pathogen-associated molecular patterns of microbes. Therefore, we investigated the expression of TLRs in cultured nasal epithelial cells obtained from nasal polyps. MATERIALS AND METHODS: Submerged single layer (SSL) and air-liquid interface (ALI) nasal epithelial cell cultures with or without 10(-7) M retinoid acid (+/- RA) were created. RESULTS: ALI + RA culture developed ciliary differentiation as observed by light and scanning electron microscopic examination in 3 weeks. It had higher interleukin (IL)-8 basal secretion (21.9 vs 0.82-1.45 ng/ml) and transepithelial potential (-20.4 mV). TLR1-10 mRNA expression in cultured nasal epithelial cells was determined by RT-PCR. Only TLR3 mRNA significantly increased at day 20 vs day 1 (n=5, p=0.02) in ALI + RA cell culture. Higher TLR3 protein was also expressed at day 20 in ALI + RA cell culture but not in SSL culture by western blotting.
Asunto(s)
Células Epiteliales/metabolismo , Mucosa Nasal/metabolismo , Receptores Toll-Like/genética , Western Blotting , Diferenciación Celular/genética , Células Cultivadas , Ensayo de Inmunoadsorción Enzimática , Células Epiteliales/inmunología , Expresión Génica , Humanos , Inmunidad Innata/genética , Interleucina-8/metabolismo , Potenciales de la Membrana/fisiología , Microscopía Electrónica de Rastreo , Mucosa Nasal/inmunología , ARN Mensajero/genética , Reacción en Cadena de la Polimerasa de Transcriptasa Inversa , Receptor Toll-Like 3/genética , Tretinoina/farmacologíaRESUMEN
BACKGROUND: A nasal polyp usually is characterized by eosinophil infiltration. Eosinophil-fibroblast interaction is an important event of persistent inflammation in airways. We have found abundant connexin 43 (Cx43) expression in subepithelial fibroblasts of nasal mucosa. Thus, we aim to analyze the relationship of Cx43 expression and eosinophil in nasal polyps. METHODS: In 25 nasal polyps and 19 inferior turbinates, indirect immunofluorescent and hematoxylin and eosin staining were performed in adjacent sections. We calculated the density of Cx43 staining and eosinophil individually by fluorescent and light microscope. RESULTS: Positive Cx43 staining under confocal microscope was shown as punctated spots on cell margin. The density of Cx43 and eosinophil staining was significantly different between groups of inferior turbinate and nasal polyp (p = 0.01 and 0.03, respectively). Decreased Cx43 expression in the subepithelial fibroblast was correlated with eosinophil infiltration in nasal polyps. Spearman rank order coefficient was equal to -0.43 (p < 0.05). CONCLUSION: This is the first demonstration of decreased Cx43 expression related to eosinophil infiltration. To the best of our knowledge, interleukin-8 may be a link between Cx43 and eosinophil and orchestrating both in developing nasal polyps.