Crosslinked poly(vinyl alcohol)(PVA)based composite films were prepared as polyelectrolyte membranes for low temperature direct ethanol fuel cells(DEFC).The membranes were functionalised by means of the addition of gr...Crosslinked poly(vinyl alcohol)(PVA)based composite films were prepared as polyelectrolyte membranes for low temperature direct ethanol fuel cells(DEFC).The membranes were functionalised by means of the addition of graphene oxide(GO)and sulfonated graphene oxide(SGO)and crosslinked with sulfosuccinic acid(SSA).The chemical structure was corroborated and suitable thermal properties were found.Although the addition of GO and SGO slightly decreased the proton conductivity of the membranes,a significant reduction of the ethanol solution swelling and crossover was encountered,more relevant for those functionalised with SGO.In general,the composite membranes were stable under simulated service conditions.The addition of GO and SGO particles permitted to buffer the loss and almost retain similar proton conductivity than prior to immersion.These membranes are alternative polyelectrolytes,which overcome current concerns of actual commercial membranes such as the high cost or the crossover phenomenon.展开更多
A blending strategy of virgin and reprocessed polylactide may be postulated as an alternative to reduce the material cost at industrial level,and as a valorization route to plastic waste management of production scrap...A blending strategy of virgin and reprocessed polylactide may be postulated as an alternative to reduce the material cost at industrial level,and as a valorization route to plastic waste management of production scraps.The performance of blends prepared from virgin polylactide and polylactide mechanically reprocessed up to two cycles(PLA-V/R)was assessed in terms of thermo-oxidative stability,morphology,viscoelasticity and thermal kinetics for energetic valorization.PLA-V/R blends showed appropriate thermo-oxidative stability.The amorphous nature of polylactide was preserved after blending.The viscoelastic properties showed an increment of the mechanical blend effectiveness,which suggested the feasibility of using PLA-V/R blends under similar mechanical conditions to those of virgin PLA goods.Finally,it was shown that the energetic valorization of PLA-V/R blends would result in a more feasible process,due to the lower required activation energy,thus highlighting the advantages of the energetic demand for the process.In conclusion,PLA-V/R blends showed similar processability,service performance and valorization routes as virgin PLA and therefore could be relevant in the sustainable circular industry of bioplastics.展开更多
The development of artificial intelligence(AI)and smart home technologies has driven the need for speech recognition-based solutions.This demand stems from the quest for more intuitive and natural interaction between ...The development of artificial intelligence(AI)and smart home technologies has driven the need for speech recognition-based solutions.This demand stems from the quest for more intuitive and natural interaction between users and smart devices in their homes.Speech recognition allows users to control devices and perform everyday actions through spoken commands,eliminating the need for physical interfaces or touch screens and enabling specific tasks such as turning on or off the light,heating,or lowering the blinds.The purpose of this study is to develop a speech-based classification model for recognizing human actions in the smart home.It seeks to demonstrate the effectiveness and feasibility of using machine learning techniques in predicting categories,subcategories,and actions from sentences.A dataset labeled with relevant information about categories,subcategories,and actions related to human actions in the smart home is used.The methodology uses machine learning techniques implemented in Python,extracting features using CountVectorizer to convert sentences into numerical representations.The results show that the classification model is able to accurately predict categories,subcategories,and actions based on sentences,with 82.99%accuracy for category,76.19%accuracy for subcategory,and 90.28%accuracy for action.The study concludes that using machine learning techniques is effective for recognizing and classifying human actions in the smart home,supporting its feasibility in various scenarios and opening new possibilities for advanced natural language processing systems in the field of AI and smart homes.展开更多
Diabetic retinopathy (DR) is a complication of diabetesmellitus thatappears in the retina. Clinitians use retina images to detect DR pathologicalsigns related to the occlusion of tiny blood vessels. Such occlusion bri...Diabetic retinopathy (DR) is a complication of diabetesmellitus thatappears in the retina. Clinitians use retina images to detect DR pathologicalsigns related to the occlusion of tiny blood vessels. Such occlusion brings adegenerative cycle between the breaking off and the new generation of thinnerand weaker blood vessels. This research aims to develop a suitable retinalvasculature segmentation method for improving retinal screening proceduresby means of computer-aided diagnosis systems. The blood vessel segmentationmethodology relies on an effective feature selection based on SequentialForward Selection, using the error rate of a decision tree classifier in theevaluation function. Subsequently, the classification process is performed bythree alternative approaches: artificial neural networks, decision trees andsupport vector machines. The proposed methodology is validated on threepublicly accessible datasets and a private one provided by Hospital Sant Joanof Reus. In all cases we obtain an average accuracy above 96% with a sensitivityof 72% in the blood vessel segmentation process. Compared with the state-ofthe-art, our approach achieves the same performance as other methods thatneed more computational power.Our method significantly reduces the numberof features used in the segmentation process from 20 to 5 dimensions. Theimplementation of the three classifiers confirmed that the five selected featureshave a good effectiveness, independently of the classification algorithm.展开更多
基金the support of the European Union through the European Regional Development Funds(ERDF)The Spanish Ministry of Economy,Industry and Competitiveness,is thanked for the research project POLYDECARBOCELL(ENE2017-86711-C3-1-R)The Spanish Ministry of Education,Culture and Sports is thanked for the FPU grant for O.Gil-Castell(FPU13/01916)。
文摘Crosslinked poly(vinyl alcohol)(PVA)based composite films were prepared as polyelectrolyte membranes for low temperature direct ethanol fuel cells(DEFC).The membranes were functionalised by means of the addition of graphene oxide(GO)and sulfonated graphene oxide(SGO)and crosslinked with sulfosuccinic acid(SSA).The chemical structure was corroborated and suitable thermal properties were found.Although the addition of GO and SGO slightly decreased the proton conductivity of the membranes,a significant reduction of the ethanol solution swelling and crossover was encountered,more relevant for those functionalised with SGO.In general,the composite membranes were stable under simulated service conditions.The addition of GO and SGO particles permitted to buffer the loss and almost retain similar proton conductivity than prior to immersion.These membranes are alternative polyelectrolytes,which overcome current concerns of actual commercial membranes such as the high cost or the crossover phenomenon.
文摘A blending strategy of virgin and reprocessed polylactide may be postulated as an alternative to reduce the material cost at industrial level,and as a valorization route to plastic waste management of production scraps.The performance of blends prepared from virgin polylactide and polylactide mechanically reprocessed up to two cycles(PLA-V/R)was assessed in terms of thermo-oxidative stability,morphology,viscoelasticity and thermal kinetics for energetic valorization.PLA-V/R blends showed appropriate thermo-oxidative stability.The amorphous nature of polylactide was preserved after blending.The viscoelastic properties showed an increment of the mechanical blend effectiveness,which suggested the feasibility of using PLA-V/R blends under similar mechanical conditions to those of virgin PLA goods.Finally,it was shown that the energetic valorization of PLA-V/R blends would result in a more feasible process,due to the lower required activation energy,thus highlighting the advantages of the energetic demand for the process.In conclusion,PLA-V/R blends showed similar processability,service performance and valorization routes as virgin PLA and therefore could be relevant in the sustainable circular industry of bioplastics.
基金supported by Generalitat Valenciana with HAAS(CIAICO/2021/039)the Spanish Ministry of Science and Innovation under the Project AVANTIA PID2020-114480RB-I00.
文摘The development of artificial intelligence(AI)and smart home technologies has driven the need for speech recognition-based solutions.This demand stems from the quest for more intuitive and natural interaction between users and smart devices in their homes.Speech recognition allows users to control devices and perform everyday actions through spoken commands,eliminating the need for physical interfaces or touch screens and enabling specific tasks such as turning on or off the light,heating,or lowering the blinds.The purpose of this study is to develop a speech-based classification model for recognizing human actions in the smart home.It seeks to demonstrate the effectiveness and feasibility of using machine learning techniques in predicting categories,subcategories,and actions from sentences.A dataset labeled with relevant information about categories,subcategories,and actions related to human actions in the smart home is used.The methodology uses machine learning techniques implemented in Python,extracting features using CountVectorizer to convert sentences into numerical representations.The results show that the classification model is able to accurately predict categories,subcategories,and actions based on sentences,with 82.99%accuracy for category,76.19%accuracy for subcategory,and 90.28%accuracy for action.The study concludes that using machine learning techniques is effective for recognizing and classifying human actions in the smart home,supporting its feasibility in various scenarios and opening new possibilities for advanced natural language processing systems in the field of AI and smart homes.
基金This work has been funded by the research project PI18/00169 from Instituto de Salud Carlos III&FEDER funds.University Rovira i.Virgili also provided funds with Project 2019PFR-B2-61.
文摘Diabetic retinopathy (DR) is a complication of diabetesmellitus thatappears in the retina. Clinitians use retina images to detect DR pathologicalsigns related to the occlusion of tiny blood vessels. Such occlusion brings adegenerative cycle between the breaking off and the new generation of thinnerand weaker blood vessels. This research aims to develop a suitable retinalvasculature segmentation method for improving retinal screening proceduresby means of computer-aided diagnosis systems. The blood vessel segmentationmethodology relies on an effective feature selection based on SequentialForward Selection, using the error rate of a decision tree classifier in theevaluation function. Subsequently, the classification process is performed bythree alternative approaches: artificial neural networks, decision trees andsupport vector machines. The proposed methodology is validated on threepublicly accessible datasets and a private one provided by Hospital Sant Joanof Reus. In all cases we obtain an average accuracy above 96% with a sensitivityof 72% in the blood vessel segmentation process. Compared with the state-ofthe-art, our approach achieves the same performance as other methods thatneed more computational power.Our method significantly reduces the numberof features used in the segmentation process from 20 to 5 dimensions. Theimplementation of the three classifiers confirmed that the five selected featureshave a good effectiveness, independently of the classification algorithm.