Conductive hydrogels have shown great prospects as wearable flexible sensors.Nevertheless,it is still a challenge to construct hydrogel-based sensor with great mechanical strength and high strain sensitivity.Herein,an...Conductive hydrogels have shown great prospects as wearable flexible sensors.Nevertheless,it is still a challenge to construct hydrogel-based sensor with great mechanical strength and high strain sensitivity.Herein,an ion-conducting hydrogel was fabricated by introducing gelatin-dialdehydeβ-cyclodextrin(Gel-DACD)into polyvinyl alcohol-borax(PVA-borax)hydrogel network.Natural Gel-DACD network acted as mechanical deformation force through non-covalent cross-linking to endow the polyvinyl alcoholborax/gelatin-dialdehydeβ-cyclodextrin hydrogel(PGBCDH)with excellent mechanical stress(1.35 MPa),stretchability(400%),toughness(1.84 MJ/m3)and great fatigue resistance(200%strain for 100 cycles).Surprisingly,PGBCDH displayed good conductivity of 0.31 S/m after adding DACD to hydrogel network.As sensor,it showed rapid response(168 ms),high strain sensitivity(gage factor(GF)=8.57 in the strain range of 200%-250%)and reliable sensing stability(100%strain for 200 cycles).Importantly,PGBCDHbased sensor can accurately monitor complex body movements(knee,elbow,wrist and finger joints)and large-scale subtle movements(speech,swallow,breath and facial expressions).Thus,PGBCDH shows great potential for human monitoring with high precision.展开更多
In the past decade,recommender systems have been widely used to provide users with personalized products and services.However,most traditional recommender systems are still facing a challenge in dealing with the huge ...In the past decade,recommender systems have been widely used to provide users with personalized products and services.However,most traditional recommender systems are still facing a challenge in dealing with the huge volume,complexity,and dynamics of information.To tackle this challenge,many studies have been conducted to improve recommender system by integrating deep learning techniques.As an unsupervised deep learning method,autoencoder has been widely used for its excellent performance in data dimensionality reduction,feature extraction,and data reconstruction.Meanwhile,recent researches have shown the high efficiency of autoencoder in information retrieval and recommendation tasks.Applying autoencoder on recommender systems would improve the quality of recommendations due to its better understanding of users,demands and characteristics of items.This paper reviews the recent researches on autoencoder-based recommender systems.The differences between autoencoder-based recommender systems and traditional recommender systems are presented in this paper.At last,some potential research directions of autoencoder-based recommender systems are discussed.展开更多
基金supported by National Key R&D Program of China(Nos.2019YFC1905500 and 2021ZD0201604)National Natural Science Foundation of China(Nos.U20A20261,31870948,31971250 and 21922409)Seed Foundation of Tianjin University(No.2022XYY-0009)。
文摘Conductive hydrogels have shown great prospects as wearable flexible sensors.Nevertheless,it is still a challenge to construct hydrogel-based sensor with great mechanical strength and high strain sensitivity.Herein,an ion-conducting hydrogel was fabricated by introducing gelatin-dialdehydeβ-cyclodextrin(Gel-DACD)into polyvinyl alcohol-borax(PVA-borax)hydrogel network.Natural Gel-DACD network acted as mechanical deformation force through non-covalent cross-linking to endow the polyvinyl alcoholborax/gelatin-dialdehydeβ-cyclodextrin hydrogel(PGBCDH)with excellent mechanical stress(1.35 MPa),stretchability(400%),toughness(1.84 MJ/m3)and great fatigue resistance(200%strain for 100 cycles).Surprisingly,PGBCDH displayed good conductivity of 0.31 S/m after adding DACD to hydrogel network.As sensor,it showed rapid response(168 ms),high strain sensitivity(gage factor(GF)=8.57 in the strain range of 200%-250%)and reliable sensing stability(100%strain for 200 cycles).Importantly,PGBCDHbased sensor can accurately monitor complex body movements(knee,elbow,wrist and finger joints)and large-scale subtle movements(speech,swallow,breath and facial expressions).Thus,PGBCDH shows great potential for human monitoring with high precision.
基金This work was supported by Beijing Advanced Inno vation Center for Future Internet Technology(110000546617001).
文摘In the past decade,recommender systems have been widely used to provide users with personalized products and services.However,most traditional recommender systems are still facing a challenge in dealing with the huge volume,complexity,and dynamics of information.To tackle this challenge,many studies have been conducted to improve recommender system by integrating deep learning techniques.As an unsupervised deep learning method,autoencoder has been widely used for its excellent performance in data dimensionality reduction,feature extraction,and data reconstruction.Meanwhile,recent researches have shown the high efficiency of autoencoder in information retrieval and recommendation tasks.Applying autoencoder on recommender systems would improve the quality of recommendations due to its better understanding of users,demands and characteristics of items.This paper reviews the recent researches on autoencoder-based recommender systems.The differences between autoencoder-based recommender systems and traditional recommender systems are presented in this paper.At last,some potential research directions of autoencoder-based recommender systems are discussed.
