In recent years,Speech Emotion Recognition(SER)has developed into an essential instrument for interpreting human emotions from auditory data.The proposed research focuses on the development of a SER system employing d...In recent years,Speech Emotion Recognition(SER)has developed into an essential instrument for interpreting human emotions from auditory data.The proposed research focuses on the development of a SER system employing deep learning and multiple datasets containing samples of emotive speech.The primary objective of this research endeavor is to investigate the utilization of Convolutional Neural Networks(CNNs)in the process of sound feature extraction.Stretching,pitch manipulation,and noise injection are a few of the techniques utilized in this study to improve the data quality.Feature extraction methods including Zero Crossing Rate,Chroma_stft,Mel⁃scale Frequency Cepstral Coefficients(MFCC),Root Mean Square(RMS),and Mel⁃Spectogram are used to train a model.By using these techniques,audio signals can be transformed into recognized features that can be utilized to train the model.Ultimately,the study produces a thorough evaluation of the models performance.When this method was applied,the model achieved an impressive accuracy of 94.57%on the test dataset.The proposed work was also validated on the EMO⁃BD and IEMOCAP datasets.These consist of further data augmentation,feature engineering,and hyperparameter optimization.By following these development paths,SER systems will be able to be implemented in real⁃world scenarios with greater accuracy and resilience.展开更多
The emergence of different computing methods such as cloud-,fog-,and edge-based Internet of Things(IoT)systems has provided the opportunity to develop intelligent systems for disease detection.Compared to other machin...The emergence of different computing methods such as cloud-,fog-,and edge-based Internet of Things(IoT)systems has provided the opportunity to develop intelligent systems for disease detection.Compared to other machine learning models,deep learning models have gained more attention from the research community,as they have shown better results with a large volume of data compared to shallow learning.However,no comprehensive survey has been conducted on integrated IoT-and computing-based systems that deploy deep learning for disease detection.This study evaluated different machine learning and deep learning algorithms and their hybrid and optimized algorithms for IoT-based disease detection,using the most recent papers on IoT-based disease detection systems that include computing approaches,such as cloud,edge,and fog.Their analysis focused on an IoT deep learning architecture suitable for disease detection.It also recognizes the different factors that require the attention of researchers to develop better IoT disease detection systems.This study can be helpful to researchers interested in developing better IoT-based disease detection and prediction systems based on deep learning using hybrid algorithms.展开更多
Many datasets in E-commerce have rich information about items and users who purchase or rate them. This information can enable advanced machine learning algorithms to extract and assign user sentiments to various aspe...Many datasets in E-commerce have rich information about items and users who purchase or rate them. This information can enable advanced machine learning algorithms to extract and assign user sentiments to various aspects of the items thus leading to more sophisticated and justifiable recommendations. However, most Collaborative Filtering (CF) techniques rely mainly on the overall preferences of users toward items only. And there is lack of conceptual and computational framework that enables an understandable aspect-based AI approach to recommending items to users. In this paper, we propose concepts and computational tools that can sharpen the logic of recommendations and that rely on users’ sentiments along various aspects of items. These concepts include: The sentiment of a user towards a specific aspect of a specific item, the emphasis that a given user places on a specific aspect in general, the popularity and controversy of an aspect among groups of users, clusters of users emphasizing a given aspect, clusters of items that are popular among a group of users and so forth. The framework introduced in this study is developed in terms of user emphasis, aspect popularity, aspect controversy, and users and items similarity. Towards this end, we introduce the Aspect-Based Collaborative Filtering Toolbox (ABCFT), where the tools are all developed based on the three-index sentiment tensor with the indices being the user, item, and aspect. The toolbox computes solutions to the questions alluded to above. We illustrate the methodology using a hotel review dataset having around 6000 users, 400 hotels and 6 aspects.展开更多
The widespread and growing interest in the Internet of Things(IoT)may be attributed to its usefulness in many different fields.Physical settings are probed for data,which is then transferred via linked networks.There ...The widespread and growing interest in the Internet of Things(IoT)may be attributed to its usefulness in many different fields.Physical settings are probed for data,which is then transferred via linked networks.There are several hurdles to overcome when putting IoT into practice,from managing server infrastructure to coordinating the use of tiny sensors.When it comes to deploying IoT,everyone agrees that security is the biggest issue.This is due to the fact that a large number of IoT devices exist in the physicalworld and thatmany of themhave constrained resources such as electricity,memory,processing power,and square footage.This research intends to analyse resource-constrained IoT devices,including RFID tags,sensors,and smart cards,and the issues involved with protecting them in such restricted circumstances.Using lightweight cryptography,the information sent between these gadgets may be secured.In order to provide a holistic picture,this research evaluates and contrasts well-known algorithms based on their implementation cost,hardware/software efficiency,and attack resistance features.We also emphasised how essential lightweight encryption is for striking a good cost-to-performance-to-security ratio.展开更多
Electric vehicles are pivotal in the global shift toward decarbonizing road transport,with lithium-ion batteries at the heart of this technological evolution.However,the pursuit of batteries capable of extremely fast ...Electric vehicles are pivotal in the global shift toward decarbonizing road transport,with lithium-ion batteries at the heart of this technological evolution.However,the pursuit of batteries capable of extremely fast charging that also satisfy high energy and safety criteria,poses a significant challenge to current lithium-ion batteries technologies.Additionally,the increasing demand for aluminum(Al)and copper(Cu)in electrification,solar energy technologies,and vehicle light-eighting is driving these metals toward near-critical status in the medium term.This study introduces metalized polythylene terephthalate(mPET)polymer films by depositing an Al or Cu thin layer onto two sides of a polyethylene terephthalate film—named mPET/Al and mPET/Cu,as lightweight,cost-effective alternatives to traditional metal current collectors in lithium-ion batteries.We have fabricated current collectors that significantly reduce weight(by 73%),thickness(by 33%),and cost(by 85%)compared with traditional metal foil counterparts.These advancements have the potential to enhance energy density to 280 Wh kg^(-1) at the electrode level under 10-min charging at 6 C.Through testing,including a novel extremely fast charging protocol across various C-rates and long-term cycling(up to 1000 cycles)in different cell configurations,the superior performance of these metalized polymer films has been demonstrated.Notably,mPET/Cu and mPET/Al films exhibited comparable capacities to conventional cells under extremely fast charging,with the mPET cells showing a 27%improvement in energy density at 6 C and maintaining significant energy density after 1000 cycles.This study underscores the potential of mPET films to revolutionize the roll-to-roll battery manufacturing process and significantly advance the performance metrics of lithium-ion batteries in electric vehicles applications.展开更多
In the era of exponential growth of digital information,recommender algorithms are vital for helping users navigate vast data to find relevant items.Traditional approaches such as collaborative filtering and contentba...In the era of exponential growth of digital information,recommender algorithms are vital for helping users navigate vast data to find relevant items.Traditional approaches such as collaborative filtering and contentbasedmethods have limitations in capturing complex,multi-faceted relationships in large-scale,sparse datasets.Recent advances in Graph Neural Networks(GNNs)have significantly improved recommendation performance by modeling high-order connection patterns within user-item interaction networks.However,existing GNN-based models like LightGCN and NGCF focus primarily on single-type interactions and often overlook diverse semantic relationships,leading to reduced recommendation diversity and limited generalization.To address these challenges,this paper proposes a dual multi-relational graph neural network recommendation algorithm based on relational interactions.Our approach constructs two complementary graph structures:a User-Item Interaction Graph(UIIG),which explicitly models direct user behaviors such as clicks and purchases,and a Relational Association Graph(RAG),which uncovers latent associations based on user similarities and item attributes.The proposed Dual Multi-relational Graph Neural Network(DMGNN)features two parallel branches that perform multi-layer graph convolutional operations,followed by an adaptive fusion mechanism to effectively integrate information from both graphs.This design enhances the model’s capacity to capture diverse relationship types and complex relational patterns.Extensive experiments conducted on benchmark datasets—including MovieLens-1M,Amazon-Electronics,and Yelp—demonstrate thatDMGNN outperforms state-of-the-art baselines,achieving improvements of up to 12.3%in Precision,9.7%in Recall,and 11.5%in F1 score.Moreover,DMGNN significantly boosts recommendation diversity by 15.2%,balancing accuracy with exploration.These results highlight the effectiveness of leveraging hierarchical multi-relational information,offering a promising solution to the challenges of data sparsity and relation heterogeneity in recommendation systems.Our work advances the theoretical understanding of multi-relational graph modeling and presents practical insights for developing more personalized,diverse,and robust recommender systems.展开更多
In recent years, network traffic data have become larger and more complex, leading to higher possibilities of network intrusion. Traditional intrusion detection methods face difficulty in processing high-speed network...In recent years, network traffic data have become larger and more complex, leading to higher possibilities of network intrusion. Traditional intrusion detection methods face difficulty in processing high-speed network data and cannot detect currently unknown attacks. Therefore, this paper proposes a network attack detection method combining a flow calculation and deep learning. The method consists of two parts: a real-time detection algorithm based on flow calculations and frequent patterns and a classification algorithm based on the deep belief network and support vector machine(DBN-SVM). Sliding window(SW) stream data processing enables real-time detection, and the DBN-SVM algorithm can improve classification accuracy. Finally, to verify the proposed method, a system is implemented.Based on the CICIDS2017 open source data set, a series of comparative experiments are conducted. The method's real-time detection efficiency is higher than that of traditional machine learning algorithms. The attack classification accuracy is 0.7 percentage points higher than that of a DBN, which is 2 percentage points higher than that of the integrated algorithm boosting and bagging methods. Hence, it is suitable for the real-time detection of high-speed network intrusions.展开更多
We assessed nutrient characteristics, distributions and fractions within the disturbed and undisturbed sediments at four sampling sites within the mainstream of Haihe River. The river sediments contained mostly sand ...We assessed nutrient characteristics, distributions and fractions within the disturbed and undisturbed sediments at four sampling sites within the mainstream of Haihe River. The river sediments contained mostly sand （ 60%）. The fraction of clay was 3%. Total nitrogen （TN） and total phosphorus （TP） concentrations ranged from 729 to 1922 mg/kg and from 692 to 1388 mg/kg, respectively. Nutrient concentrations within the sediments usually decreased with increasing depth. The TN and TP concentrations within the fine sand were higher than for that within silt. Sediment phosphorus fractions were between 2.99% and 3.37% Ex-P （exchangeable phosphorus）, 7.89% and 13.71% Fe/Al-P （Fe, Al oxides bound phosphorus）, 61.32% and 70.14% Ca-P （calcium-bound phosphorus）, and 17.03% and 22.04% Org-P （organic phosphorus）. Nitrogen and phosphorus release from sediment could lead to the presence of 21.02 mg N/L and 3.10 mg P/L within the water column. A river restoration project should address the sediment nutrient stock.展开更多
Phishing is a type of cybercrime in which cyber-attackers pose themselves as authorized persons or entities and hack the victims’sensitive data.E-mails,instant messages and phone calls are some of the common modes us...Phishing is a type of cybercrime in which cyber-attackers pose themselves as authorized persons or entities and hack the victims’sensitive data.E-mails,instant messages and phone calls are some of the common modes used in cyberattacks.Though the security models are continuously upgraded to prevent cyberattacks,hackers find innovative ways to target the victims.In this background,there is a drastic increase observed in the number of phishing emails sent to potential targets.This scenario necessitates the importance of designing an effective classification model.Though numerous conventional models are available in the literature for proficient classification of phishing emails,the Machine Learning(ML)techniques and the Deep Learning(DL)models have been employed in the literature.The current study presents an Intelligent Cuckoo Search(CS)Optimization Algorithm with a Deep Learning-based Phishing Email Detection and Classification(ICSOA-DLPEC)model.The aim of the proposed ICSOA-DLPEC model is to effectually distinguish the emails as either legitimate or phishing ones.At the initial stage,the pre-processing is performed through three stages such as email cleaning,tokenization and stop-word elimination.Then,the N-gram approach is;moreover,the CS algorithm is applied to extract the useful feature vectors.Moreover,the CS algorithm is employed with the Gated Recurrent Unit(GRU)model to detect and classify phishing emails.Furthermore,the CS algorithm is used to fine-tune the parameters involved in the GRU model.The performance of the proposed ICSOA-DLPEC model was experimentally validated using a benchmark dataset,and the results were assessed under several dimensions.Extensive comparative studies were conducted,and the results confirmed the superior performance of the proposed ICSOA-DLPEC model over other existing approaches.The proposed model achieved a maximum accuracy of 99.72%.展开更多
Free transverse vibration of monolayer graphene, boron nitride (BN), and silicon carbide (SiC) sheets is investigated by using molecular dynamics finite element method. Eigenfrequencies and eigenmodes of these three s...Free transverse vibration of monolayer graphene, boron nitride (BN), and silicon carbide (SiC) sheets is investigated by using molecular dynamics finite element method. Eigenfrequencies and eigenmodes of these three sheets in rectangular shape are studied with different aspect ratios with respect to various boundary conditions. It is found that aspect ratios and boundary conditions affect in a similar way on natural frequencies of graphene, BN, and SiC sheets. Natural frequencies in all modes decrease with an increase of the sheet’s size. Graphene exhibits the highest natural frequencies, and SiC sheet possesses the lowest ones. Missing atoms have minor effects on natural frequencies in this study.展开更多
Multi-target agents against tyrosine kinases and topoisomerases are potentially useful for the effective treatment of cancers.Discovery of new multi-target scaffolds are important for developing such agents. A series ...Multi-target agents against tyrosine kinases and topoisomerases are potentially useful for the effective treatment of cancers.Discovery of new multi-target scaffolds are important for developing such agents. A series of five novel acridine analogues,LXL 1-5,were synthesized and their antiproliferative activity against HepC-2 cell lines were evaluated,among which the 9-benzyloxyacridine analogue,LXL-5, showed inhibitory activity against tyrosine kinases,VEGFR-2 and Src.The results of UV-visible absorption spectra and fluorescence emission spectra,as well as DNA topoisomerase I inhibition assay, indicated topoisomerase I inhibitory activity.Our study suggested that acridine scaffold,previously shown to have no multi-target kinase and topoisomerase inhibitory activity,might be potentially developed as a multi-target inhibitor of tyrosine kinases and topoisomerase I.展开更多
In Wireless Body Area Networks(WBANs)with respect to health care,sensors are positioned inside the body of an individual to transfer sensed data to a central station periodically.The great challenges posed to healthca...In Wireless Body Area Networks(WBANs)with respect to health care,sensors are positioned inside the body of an individual to transfer sensed data to a central station periodically.The great challenges posed to healthcare WBANs are the black hole and sink hole attacks.Data from deployed sensor nodes are attracted by sink hole or black hole nodes while grabbing the shortest path.Identifying this issue is quite a challenging task as a small variation in medicine intake may result in a severe illness.This work proposes a hybrid detection framework for attacks by applying a Proportional Coinciding Score(PCS)and an MK-Means algorithm,which is a well-known machine learning technique used to raise attack detection accuracy and decrease computational difficulties while giving treatments for heartache and respiratory issues.First,the gathered training data feature count is reduced through data pre-processing in the PCS.Second,the pre-processed features are sent to the MK-Means algorithm for training the data and promoting classification.Third,certain attack detection measures given by the intrusion detection system,such as the number of data packages trans-received,are identified by the MK-Means algorithm.This study demonstrates that the MK-Means framework yields a high detection accuracy with a low packet loss rate,low communication overhead,and reduced end-to-end delay in the network and improves the accuracy of biomedical data.展开更多
In this paper, we theoretically investigate the effect of noise on the photoionization, the generation of the high-order harmonic and the attosecond pulse irradiated from a model He＋ ion. It shows that by properly ad...In this paper, we theoretically investigate the effect of noise on the photoionization, the generation of the high-order harmonic and the attosecond pulse irradiated from a model He＋ ion. It shows that by properly adding noise fields, such as Gaussian white noise, random light or colored noise, both the ionization probabilities （IPs） and the harmonic yields can be enhanced by several orders of magnitude. Further, by tuning the noise intensity, a stochastic resonance-like curve is observed, showing the existence of an optimal noise in the ionization enhancement process. Finally, by superposing a properly selected harmonic, an intense attosecond pulse with a duration of 67 as is directly generated.展开更多
The Healthcare monitoring on a clinical base involves many implicit communication between the patient and the care takers. Any misinterpretation leads to adverse effects. A simple wearable system can precisely interpr...The Healthcare monitoring on a clinical base involves many implicit communication between the patient and the care takers. Any misinterpretation leads to adverse effects. A simple wearable system can precisely interpret the implicit communication to the care takers or to an automated support device. Simple and obvious hand movements can be used for the above purpose. The proposed system suggests a novel methodology simpler than the existing sign language interpretations for such implicit communication. The experimental results show a well-distinguished realization of different hand movement activities using a wearable sensor medium and the interpretation results always show significant thresholds.展开更多
The effects of two different amino acid catalysts on the stereoselectivities in the direct Mannich reactions of cyclohexanone,p-anisidine and p-nitrobenzaldehyde were studied with the aid of density functional theory....The effects of two different amino acid catalysts on the stereoselectivities in the direct Mannich reactions of cyclohexanone,p-anisidine and p-nitrobenzaldehyde were studied with the aid of density functional theory.Transition states of the stereo-determining C ＂C bond-forming step with the addition of enamine intermediate to the imine for the L-proline（·-amino acid） and （R）-3-pyrrolidinecarboxylic acid（·-amino acid）-catalyzed processes were reported.B3LYP/6-31G calculations provide a good explanation for the opposite syn vs.anti diastereoselectivities of these two different kinds of catalysts（syn-selectivity for the ·-amino acid catalysts,anti-selectivity for the ·-amino acid catalysts）.Calculated and observed diastereomeric ratio and enantiomeric excess values are in reasonable agreement.展开更多
The excited-state double-proton transfer （ESDPT） mechanism of 2-amino-3-methoxypyridine and acetic acid com- plex is studied by the density functional theory （DFT） and time-dependent DFT with CAM-B3LYP functional....The excited-state double-proton transfer （ESDPT） mechanism of 2-amino-3-methoxypyridine and acetic acid com- plex is studied by the density functional theory （DFT） and time-dependent DFT with CAM-B3LYP functional. The complex is connected through two different types of inter-molecular hydrogen bonds. After photo-excitation, both hydrogen bonds get strengthened, which can facilitate the ESDPT reaction. The scanned potential energy curve along the proton transfer coordinate indicates that the ESDPT reaction proceeds in a stepwise pattern.展开更多
The stereodynamic properties of the F ＋ HO （v, j） reaction are explored by quasi-classical trajectory （QCT） calculations performed on the 1At and 3At potential energy surfaces （PESs）. Based on the polarization-...The stereodynamic properties of the F ＋ HO （v, j） reaction are explored by quasi-classical trajectory （QCT） calculations performed on the 1At and 3At potential energy surfaces （PESs）. Based on the polarization-dependent differential cross sections （PDDCSs） and the angular distributions of the product angular momentum with the reactant at different values of initial v or j, the results show that the product scattering and product polarization have strong links with initial vibrationalrotational numbers of v and j. The significant manifestation of the normal DCSs is that the forward scattering gradually becomes predominant with the initial vibrational excitation increasing, and the scattering angle of the HF product taking place on the 3At potential energy surface is found to be more sensitive to the initial value of v. The product orientation and alignment are strongly dependent on the initial rovibrational excitation effect. With enhancement in the initial rovibrational excitation effect, there is an overall decrease in the product orientation as well as in the product alignment either perpendicular to the reagent relative velocity vector k or along the direction of the y axis, for which the initial rotational excitation effect is much more noticeable than the vibrational excitation effect. Moreover, the initial rovibrational excitation effect on the product polarization is more pronounced for the 3At potential energy surface than for the 1At potential energy surface.展开更多
To figure out the influence of isotope effect on product polarizations of the N（2D）＋D2 reactive system and its isotope variants, quasi-classical trajectory（QCT） calculation was performed on Ho＇s potential energy...To figure out the influence of isotope effect on product polarizations of the N（2D）＋D2 reactive system and its isotope variants, quasi-classical trajectory（QCT） calculation was performed on Ho＇s potential energy surface（PES） of 2A″ state. Product polarizations such as product distributions of P（θr）, P（φr） and P（θr,φr）, as well as the generalized polarization-dependent differential cross sections（PDDCSs） were discussed and compared in detail among the four product channels of the title reactions. Both the intermolecular and intramolecular isotope effects were proved to be influential on product polarizations.展开更多
The Mobile Ad-hoc Network(MANET)is a dynamic topology that provides a variety of executions in various disciplines.The most sticky topic in organizationalfields was MANET protection.MANET is helpless against various t...The Mobile Ad-hoc Network(MANET)is a dynamic topology that provides a variety of executions in various disciplines.The most sticky topic in organizationalfields was MANET protection.MANET is helpless against various threats that affect its usability and accessibility.The dark opening assault is considered one of the most far-reaching dynamic assaults that deteriorate the organi-zation's execution and reliability by dropping all approaching packages via the noxious node.The Dark Opening Node aims to deceive any node in the company that wishes to connect to another node by pretending to get the most delicate ability to support the target node.Ad-hoc On-demand Distance Vector(AODV)is a responsive steering convention with no corporate techniques to locate and destroy the dark opening center.We improved AODV by incorporating a novel compact method for detecting and isolating lonely and collaborative black-hole threats that utilize clocks and baits.The recommended method allows MANET nodes to discover and segregate black-hole network nodes over dynamic changes in the network topology.We implement the suggested method's performance with the help of Network Simulator(NS)-3 simulation models.Furthermore,the proposed approach comes exceptionally near to the original AODV,absent black holes in terms of bandwidth,end-to-end latency,error rate,and delivery ratio.展开更多
Optimizing the performance of composite structures is a real-world application with significant benefits.In this paper,a high-fidelity finite element method(FEM)is combined with the iterative improvement capability of...Optimizing the performance of composite structures is a real-world application with significant benefits.In this paper,a high-fidelity finite element method(FEM)is combined with the iterative improvement capability of metaheuristic optimization algorithms to obtain optimized composite plates.The FEM module comprises of ninenode isoparametric plate bending element in conjunction with the first-order shear deformation theory(FSDT).A recently proposed memetic version of particle swarm optimization called RPSOLC is modified in the current research to carry out multi-objective Pareto optimization.The performance of the MO-RPSOLC is found to be comparable with the NSGA-III.This work successfully highlights the use of FEM-MO-RPSOLC in obtaining highfidelity Pareto solutions considering simultaneous maximization of the fundamental frequency and frequency separation in laminated composites by optimizing the stacking sequence.展开更多
文摘In recent years,Speech Emotion Recognition(SER)has developed into an essential instrument for interpreting human emotions from auditory data.The proposed research focuses on the development of a SER system employing deep learning and multiple datasets containing samples of emotive speech.The primary objective of this research endeavor is to investigate the utilization of Convolutional Neural Networks(CNNs)in the process of sound feature extraction.Stretching,pitch manipulation,and noise injection are a few of the techniques utilized in this study to improve the data quality.Feature extraction methods including Zero Crossing Rate,Chroma_stft,Mel⁃scale Frequency Cepstral Coefficients(MFCC),Root Mean Square(RMS),and Mel⁃Spectogram are used to train a model.By using these techniques,audio signals can be transformed into recognized features that can be utilized to train the model.Ultimately,the study produces a thorough evaluation of the models performance.When this method was applied,the model achieved an impressive accuracy of 94.57%on the test dataset.The proposed work was also validated on the EMO⁃BD and IEMOCAP datasets.These consist of further data augmentation,feature engineering,and hyperparameter optimization.By following these development paths,SER systems will be able to be implemented in real⁃world scenarios with greater accuracy and resilience.
文摘The emergence of different computing methods such as cloud-,fog-,and edge-based Internet of Things(IoT)systems has provided the opportunity to develop intelligent systems for disease detection.Compared to other machine learning models,deep learning models have gained more attention from the research community,as they have shown better results with a large volume of data compared to shallow learning.However,no comprehensive survey has been conducted on integrated IoT-and computing-based systems that deploy deep learning for disease detection.This study evaluated different machine learning and deep learning algorithms and their hybrid and optimized algorithms for IoT-based disease detection,using the most recent papers on IoT-based disease detection systems that include computing approaches,such as cloud,edge,and fog.Their analysis focused on an IoT deep learning architecture suitable for disease detection.It also recognizes the different factors that require the attention of researchers to develop better IoT disease detection systems.This study can be helpful to researchers interested in developing better IoT-based disease detection and prediction systems based on deep learning using hybrid algorithms.
文摘Many datasets in E-commerce have rich information about items and users who purchase or rate them. This information can enable advanced machine learning algorithms to extract and assign user sentiments to various aspects of the items thus leading to more sophisticated and justifiable recommendations. However, most Collaborative Filtering (CF) techniques rely mainly on the overall preferences of users toward items only. And there is lack of conceptual and computational framework that enables an understandable aspect-based AI approach to recommending items to users. In this paper, we propose concepts and computational tools that can sharpen the logic of recommendations and that rely on users’ sentiments along various aspects of items. These concepts include: The sentiment of a user towards a specific aspect of a specific item, the emphasis that a given user places on a specific aspect in general, the popularity and controversy of an aspect among groups of users, clusters of users emphasizing a given aspect, clusters of items that are popular among a group of users and so forth. The framework introduced in this study is developed in terms of user emphasis, aspect popularity, aspect controversy, and users and items similarity. Towards this end, we introduce the Aspect-Based Collaborative Filtering Toolbox (ABCFT), where the tools are all developed based on the three-index sentiment tensor with the indices being the user, item, and aspect. The toolbox computes solutions to the questions alluded to above. We illustrate the methodology using a hotel review dataset having around 6000 users, 400 hotels and 6 aspects.
基金supported by project TRANSACT funded under H2020-EU.2.1.1.-INDUSTRIAL LEADERSHIP-Leadership in Enabling and Industrial Technologies-Information and Communication Technologies(Grant Agreement ID:101007260).
文摘The widespread and growing interest in the Internet of Things(IoT)may be attributed to its usefulness in many different fields.Physical settings are probed for data,which is then transferred via linked networks.There are several hurdles to overcome when putting IoT into practice,from managing server infrastructure to coordinating the use of tiny sensors.When it comes to deploying IoT,everyone agrees that security is the biggest issue.This is due to the fact that a large number of IoT devices exist in the physicalworld and thatmany of themhave constrained resources such as electricity,memory,processing power,and square footage.This research intends to analyse resource-constrained IoT devices,including RFID tags,sensors,and smart cards,and the issues involved with protecting them in such restricted circumstances.Using lightweight cryptography,the information sent between these gadgets may be secured.In order to provide a holistic picture,this research evaluates and contrasts well-known algorithms based on their implementation cost,hardware/software efficiency,and attack resistance features.We also emphasised how essential lightweight encryption is for striking a good cost-to-performance-to-security ratio.
文摘Electric vehicles are pivotal in the global shift toward decarbonizing road transport,with lithium-ion batteries at the heart of this technological evolution.However,the pursuit of batteries capable of extremely fast charging that also satisfy high energy and safety criteria,poses a significant challenge to current lithium-ion batteries technologies.Additionally,the increasing demand for aluminum(Al)and copper(Cu)in electrification,solar energy technologies,and vehicle light-eighting is driving these metals toward near-critical status in the medium term.This study introduces metalized polythylene terephthalate(mPET)polymer films by depositing an Al or Cu thin layer onto two sides of a polyethylene terephthalate film—named mPET/Al and mPET/Cu,as lightweight,cost-effective alternatives to traditional metal current collectors in lithium-ion batteries.We have fabricated current collectors that significantly reduce weight(by 73%),thickness(by 33%),and cost(by 85%)compared with traditional metal foil counterparts.These advancements have the potential to enhance energy density to 280 Wh kg^(-1) at the electrode level under 10-min charging at 6 C.Through testing,including a novel extremely fast charging protocol across various C-rates and long-term cycling(up to 1000 cycles)in different cell configurations,the superior performance of these metalized polymer films has been demonstrated.Notably,mPET/Cu and mPET/Al films exhibited comparable capacities to conventional cells under extremely fast charging,with the mPET cells showing a 27%improvement in energy density at 6 C and maintaining significant energy density after 1000 cycles.This study underscores the potential of mPET films to revolutionize the roll-to-roll battery manufacturing process and significantly advance the performance metrics of lithium-ion batteries in electric vehicles applications.
文摘In the era of exponential growth of digital information,recommender algorithms are vital for helping users navigate vast data to find relevant items.Traditional approaches such as collaborative filtering and contentbasedmethods have limitations in capturing complex,multi-faceted relationships in large-scale,sparse datasets.Recent advances in Graph Neural Networks(GNNs)have significantly improved recommendation performance by modeling high-order connection patterns within user-item interaction networks.However,existing GNN-based models like LightGCN and NGCF focus primarily on single-type interactions and often overlook diverse semantic relationships,leading to reduced recommendation diversity and limited generalization.To address these challenges,this paper proposes a dual multi-relational graph neural network recommendation algorithm based on relational interactions.Our approach constructs two complementary graph structures:a User-Item Interaction Graph(UIIG),which explicitly models direct user behaviors such as clicks and purchases,and a Relational Association Graph(RAG),which uncovers latent associations based on user similarities and item attributes.The proposed Dual Multi-relational Graph Neural Network(DMGNN)features two parallel branches that perform multi-layer graph convolutional operations,followed by an adaptive fusion mechanism to effectively integrate information from both graphs.This design enhances the model’s capacity to capture diverse relationship types and complex relational patterns.Extensive experiments conducted on benchmark datasets—including MovieLens-1M,Amazon-Electronics,and Yelp—demonstrate thatDMGNN outperforms state-of-the-art baselines,achieving improvements of up to 12.3%in Precision,9.7%in Recall,and 11.5%in F1 score.Moreover,DMGNN significantly boosts recommendation diversity by 15.2%,balancing accuracy with exploration.These results highlight the effectiveness of leveraging hierarchical multi-relational information,offering a promising solution to the challenges of data sparsity and relation heterogeneity in recommendation systems.Our work advances the theoretical understanding of multi-relational graph modeling and presents practical insights for developing more personalized,diverse,and robust recommender systems.
基金supported by the National Key Research and Development Program of China(2017YFB1401300,2017YFB1401304)the National Natural Science Foundation of China(61702211,L1724007,61902203)+3 种基金Hubei Provincial Science and Technology Program of China(2017AKA191)the Self-Determined Research Funds of Central China Normal University(CCNU)from the Colleges’Basic Research(CCNU17QD0004,CCNU17GF0002)the Natural Science Foundation of Shandong Province(ZR2017QF015)the Key Research and Development Plan–Major Scientific and Technological Innovation Projects of Shandong Province(2019JZZY020101)。
文摘In recent years, network traffic data have become larger and more complex, leading to higher possibilities of network intrusion. Traditional intrusion detection methods face difficulty in processing high-speed network data and cannot detect currently unknown attacks. Therefore, this paper proposes a network attack detection method combining a flow calculation and deep learning. The method consists of two parts: a real-time detection algorithm based on flow calculations and frequent patterns and a classification algorithm based on the deep belief network and support vector machine(DBN-SVM). Sliding window(SW) stream data processing enables real-time detection, and the DBN-SVM algorithm can improve classification accuracy. Finally, to verify the proposed method, a system is implemented.Based on the CICIDS2017 open source data set, a series of comparative experiments are conducted. The method's real-time detection efficiency is higher than that of traditional machine learning algorithms. The attack classification accuracy is 0.7 percentage points higher than that of a DBN, which is 2 percentage points higher than that of the integrated algorithm boosting and bagging methods. Hence, it is suitable for the real-time detection of high-speed network intrusions.
基金supported by the National Natural Sci- ence Foundation of China (No. 51079068)the Natural Science Foundation of Tianjin (No. 09ZCGYSF00400, 08FDZDSF03402)+1 种基金the National Key-Projects of Water Pollution Control and Prevention (No. 2008ZX07314-005- 001, 2009ZX07209-001)funded by The Royal Society
文摘We assessed nutrient characteristics, distributions and fractions within the disturbed and undisturbed sediments at four sampling sites within the mainstream of Haihe River. The river sediments contained mostly sand （ 60%）. The fraction of clay was 3%. Total nitrogen （TN） and total phosphorus （TP） concentrations ranged from 729 to 1922 mg/kg and from 692 to 1388 mg/kg, respectively. Nutrient concentrations within the sediments usually decreased with increasing depth. The TN and TP concentrations within the fine sand were higher than for that within silt. Sediment phosphorus fractions were between 2.99% and 3.37% Ex-P （exchangeable phosphorus）, 7.89% and 13.71% Fe/Al-P （Fe, Al oxides bound phosphorus）, 61.32% and 70.14% Ca-P （calcium-bound phosphorus）, and 17.03% and 22.04% Org-P （organic phosphorus）. Nitrogen and phosphorus release from sediment could lead to the presence of 21.02 mg N/L and 3.10 mg P/L within the water column. A river restoration project should address the sediment nutrient stock.
基金This research was supported in part by Basic Science Research Program through the National Research Foundation of Korea(NRF),funded by the Ministry of Education(NRF-2021R1A6A1A03039493)in part by the NRF grant funded by the Korea government(MSIT)(NRF-2022R1A2C1004401).
文摘Phishing is a type of cybercrime in which cyber-attackers pose themselves as authorized persons or entities and hack the victims’sensitive data.E-mails,instant messages and phone calls are some of the common modes used in cyberattacks.Though the security models are continuously upgraded to prevent cyberattacks,hackers find innovative ways to target the victims.In this background,there is a drastic increase observed in the number of phishing emails sent to potential targets.This scenario necessitates the importance of designing an effective classification model.Though numerous conventional models are available in the literature for proficient classification of phishing emails,the Machine Learning(ML)techniques and the Deep Learning(DL)models have been employed in the literature.The current study presents an Intelligent Cuckoo Search(CS)Optimization Algorithm with a Deep Learning-based Phishing Email Detection and Classification(ICSOA-DLPEC)model.The aim of the proposed ICSOA-DLPEC model is to effectually distinguish the emails as either legitimate or phishing ones.At the initial stage,the pre-processing is performed through three stages such as email cleaning,tokenization and stop-word elimination.Then,the N-gram approach is;moreover,the CS algorithm is applied to extract the useful feature vectors.Moreover,the CS algorithm is employed with the Gated Recurrent Unit(GRU)model to detect and classify phishing emails.Furthermore,the CS algorithm is used to fine-tune the parameters involved in the GRU model.The performance of the proposed ICSOA-DLPEC model was experimentally validated using a benchmark dataset,and the results were assessed under several dimensions.Extensive comparative studies were conducted,and the results confirmed the superior performance of the proposed ICSOA-DLPEC model over other existing approaches.The proposed model achieved a maximum accuracy of 99.72%.
文摘Free transverse vibration of monolayer graphene, boron nitride (BN), and silicon carbide (SiC) sheets is investigated by using molecular dynamics finite element method. Eigenfrequencies and eigenmodes of these three sheets in rectangular shape are studied with different aspect ratios with respect to various boundary conditions. It is found that aspect ratios and boundary conditions affect in a similar way on natural frequencies of graphene, BN, and SiC sheets. Natural frequencies in all modes decrease with an increase of the sheet’s size. Graphene exhibits the highest natural frequencies, and SiC sheet possesses the lowest ones. Missing atoms have minor effects on natural frequencies in this study.
基金supports from the Ministry of Science and Technology of China(Nos. 2012ZX09506001-010,2012AA020305 and 2011DFA30620)the National Natural Science Foundation of China(Nos.21272134 and 20902053)Shenzhen Sci & Tech Bureau(No. JCYJ20120831165730905)
文摘Multi-target agents against tyrosine kinases and topoisomerases are potentially useful for the effective treatment of cancers.Discovery of new multi-target scaffolds are important for developing such agents. A series of five novel acridine analogues,LXL 1-5,were synthesized and their antiproliferative activity against HepC-2 cell lines were evaluated,among which the 9-benzyloxyacridine analogue,LXL-5, showed inhibitory activity against tyrosine kinases,VEGFR-2 and Src.The results of UV-visible absorption spectra and fluorescence emission spectra,as well as DNA topoisomerase I inhibition assay, indicated topoisomerase I inhibitory activity.Our study suggested that acridine scaffold,previously shown to have no multi-target kinase and topoisomerase inhibitory activity,might be potentially developed as a multi-target inhibitor of tyrosine kinases and topoisomerase I.
基金funded by Stefan cel Mare University of Suceava,Romania.
文摘In Wireless Body Area Networks(WBANs)with respect to health care,sensors are positioned inside the body of an individual to transfer sensed data to a central station periodically.The great challenges posed to healthcare WBANs are the black hole and sink hole attacks.Data from deployed sensor nodes are attracted by sink hole or black hole nodes while grabbing the shortest path.Identifying this issue is quite a challenging task as a small variation in medicine intake may result in a severe illness.This work proposes a hybrid detection framework for attacks by applying a Proportional Coinciding Score(PCS)and an MK-Means algorithm,which is a well-known machine learning technique used to raise attack detection accuracy and decrease computational difficulties while giving treatments for heartache and respiratory issues.First,the gathered training data feature count is reduced through data pre-processing in the PCS.Second,the pre-processed features are sent to the MK-Means algorithm for training the data and promoting classification.Third,certain attack detection measures given by the intrusion detection system,such as the number of data packages trans-received,are identified by the MK-Means algorithm.This study demonstrates that the MK-Means framework yields a high detection accuracy with a low packet loss rate,low communication overhead,and reduced end-to-end delay in the network and improves the accuracy of biomedical data.
基金Project supported by the National Natural Science Foundations of China(Grant Nos.10874096 and 20633070)
文摘In this paper, we theoretically investigate the effect of noise on the photoionization, the generation of the high-order harmonic and the attosecond pulse irradiated from a model He＋ ion. It shows that by properly adding noise fields, such as Gaussian white noise, random light or colored noise, both the ionization probabilities （IPs） and the harmonic yields can be enhanced by several orders of magnitude. Further, by tuning the noise intensity, a stochastic resonance-like curve is observed, showing the existence of an optimal noise in the ionization enhancement process. Finally, by superposing a properly selected harmonic, an intense attosecond pulse with a duration of 67 as is directly generated.
文摘The Healthcare monitoring on a clinical base involves many implicit communication between the patient and the care takers. Any misinterpretation leads to adverse effects. A simple wearable system can precisely interpret the implicit communication to the care takers or to an automated support device. Simple and obvious hand movements can be used for the above purpose. The proposed system suggests a novel methodology simpler than the existing sign language interpretations for such implicit communication. The experimental results show a well-distinguished realization of different hand movement activities using a wearable sensor medium and the interpretation results always show significant thresholds.
基金Supported by the National Natural Science Foundation of China(Nos.20773071,20901043)the Natural Science Foundation of Shandong Province,China(No.ZR2010BM024)the Project of Shandong Province Higher Educational Science and Technology Program,China(No.J10LB06)
文摘The effects of two different amino acid catalysts on the stereoselectivities in the direct Mannich reactions of cyclohexanone,p-anisidine and p-nitrobenzaldehyde were studied with the aid of density functional theory.Transition states of the stereo-determining C ＂C bond-forming step with the addition of enamine intermediate to the imine for the L-proline（·-amino acid） and （R）-3-pyrrolidinecarboxylic acid（·-amino acid）-catalyzed processes were reported.B3LYP/6-31G calculations provide a good explanation for the opposite syn vs.anti diastereoselectivities of these two different kinds of catalysts（syn-selectivity for the ·-amino acid catalysts,anti-selectivity for the ·-amino acid catalysts）.Calculated and observed diastereomeric ratio and enantiomeric excess values are in reasonable agreement.
文摘The excited-state double-proton transfer （ESDPT） mechanism of 2-amino-3-methoxypyridine and acetic acid com- plex is studied by the density functional theory （DFT） and time-dependent DFT with CAM-B3LYP functional. The complex is connected through two different types of inter-molecular hydrogen bonds. After photo-excitation, both hydrogen bonds get strengthened, which can facilitate the ESDPT reaction. The scanned potential energy curve along the proton transfer coordinate indicates that the ESDPT reaction proceeds in a stepwise pattern.
基金supported by the National Natural Science Foundation of China (Grant Nos. 10874096 and 20633070)the Natural Science Foundation of Qingdao University,China (Grant No. 063-06300510)
文摘The stereodynamic properties of the F ＋ HO （v, j） reaction are explored by quasi-classical trajectory （QCT） calculations performed on the 1At and 3At potential energy surfaces （PESs）. Based on the polarization-dependent differential cross sections （PDDCSs） and the angular distributions of the product angular momentum with the reactant at different values of initial v or j, the results show that the product scattering and product polarization have strong links with initial vibrationalrotational numbers of v and j. The significant manifestation of the normal DCSs is that the forward scattering gradually becomes predominant with the initial vibrational excitation increasing, and the scattering angle of the HF product taking place on the 3At potential energy surface is found to be more sensitive to the initial value of v. The product orientation and alignment are strongly dependent on the initial rovibrational excitation effect. With enhancement in the initial rovibrational excitation effect, there is an overall decrease in the product orientation as well as in the product alignment either perpendicular to the reagent relative velocity vector k or along the direction of the y axis, for which the initial rotational excitation effect is much more noticeable than the vibrational excitation effect. Moreover, the initial rovibrational excitation effect on the product polarization is more pronounced for the 3At potential energy surface than for the 1At potential energy surface.
基金Supported by the National Natural Science Foundation of China(No.10874096)
文摘To figure out the influence of isotope effect on product polarizations of the N（2D）＋D2 reactive system and its isotope variants, quasi-classical trajectory（QCT） calculation was performed on Ho＇s potential energy surface（PES） of 2A″ state. Product polarizations such as product distributions of P（θr）, P（φr） and P（θr,φr）, as well as the generalized polarization-dependent differential cross sections（PDDCSs） were discussed and compared in detail among the four product channels of the title reactions. Both the intermolecular and intramolecular isotope effects were proved to be influential on product polarizations.
文摘The Mobile Ad-hoc Network(MANET)is a dynamic topology that provides a variety of executions in various disciplines.The most sticky topic in organizationalfields was MANET protection.MANET is helpless against various threats that affect its usability and accessibility.The dark opening assault is considered one of the most far-reaching dynamic assaults that deteriorate the organi-zation's execution and reliability by dropping all approaching packages via the noxious node.The Dark Opening Node aims to deceive any node in the company that wishes to connect to another node by pretending to get the most delicate ability to support the target node.Ad-hoc On-demand Distance Vector(AODV)is a responsive steering convention with no corporate techniques to locate and destroy the dark opening center.We improved AODV by incorporating a novel compact method for detecting and isolating lonely and collaborative black-hole threats that utilize clocks and baits.The recommended method allows MANET nodes to discover and segregate black-hole network nodes over dynamic changes in the network topology.We implement the suggested method's performance with the help of Network Simulator(NS)-3 simulation models.Furthermore,the proposed approach comes exceptionally near to the original AODV,absent black holes in terms of bandwidth,end-to-end latency,error rate,and delivery ratio.
文摘Optimizing the performance of composite structures is a real-world application with significant benefits.In this paper,a high-fidelity finite element method(FEM)is combined with the iterative improvement capability of metaheuristic optimization algorithms to obtain optimized composite plates.The FEM module comprises of ninenode isoparametric plate bending element in conjunction with the first-order shear deformation theory(FSDT).A recently proposed memetic version of particle swarm optimization called RPSOLC is modified in the current research to carry out multi-objective Pareto optimization.The performance of the MO-RPSOLC is found to be comparable with the NSGA-III.This work successfully highlights the use of FEM-MO-RPSOLC in obtaining highfidelity Pareto solutions considering simultaneous maximization of the fundamental frequency and frequency separation in laminated composites by optimizing the stacking sequence.
