DHSEGATs:distance and hop-wise structures encoding enhanced graph attention networks

Numerous works prove that existing neighbor-averaging graph neural networks(GNNs)cannot efficiently catch structure features,and many works show that injecting structure,distance,position,or spatial features can significantly improve the performance of GNNs,however,injecting high-level structure and distance into GNNs is an intuitive but untouched idea.This work sheds light on this issue and proposes a scheme to enhance graph attention networks(GATs)by encoding distance and hop-wise structure statistics.Firstly,the hop-wise structure and distributional distance information are extracted based on several hop-wise ego-nets of every target node.Secondly,the derived structure information,distance information,and intrinsic features are encoded into the same vector space and then added together to get initial embedding vectors.Thirdly,the derived embedding vectors are fed into GATs,such as GAT and adaptive graph diffusion network(AGDN)to get the soft labels.Fourthly,the soft labels are fed into correct and smooth(C&S)to conduct label propagation and get final predictions.Experiments show that the distance and hop-wise structures encoding enhanced graph attention networks(DHSEGATs)achieve a competitive result.

Information in the Universal Triangle of Reality for Non-living/Living Structures:From Philosophy to Neuro/Life Sciences

With the purpose to understand better the role of information not only in communication systems,but actually in our environmental reality,this paper presented the model of Universal Triangle of Reality,composed by Matter,Energy and Information,as fundamental constitutive components of this reality.Arguments coming from the field of physics,both at the cosmic and microparticles scale are presented,showing undoubtable conclusions that information is a fundamental component of reality in our material world.At the cosmic level,where the unusual high concentration of mass in the black holes constitutes a special state of matter,suitable for analysis of their special properties,the problem of the conservation principle of information is discussed.At the quantum level,the special unusual characteristics derived from the non-localization principle are also highlighted,together with information-involved problems and solutions.The Universal Triangle of Reality in the living systems reveals the high role of the involved information,both as the informational common organization on the entire evolution scale,and as the info-dynamics processes inside of own structure and resulted from interaction with the environment.The relevant advances in the approaching and understanding of the functionality of the living systems from informational point of view are highlighted,showing the high contribution of information concepts in understanding/solving of various older/recent problems in philosophy,neuroscience/neurology/psychiatry,neuro-physics/neuropsychology/behavior sciences,geriatrics/gerontology,biology and life sciences.

Information-Body Relation and Information as a Solution of the Consciousness Problem in the Biological Structures

This paper approaches two main philosophical questions concerning the biological structures,from unicellular to multicellular organisms:one of them(i),referred to the information-body relation,as an extension of the mind-body relation at human,and another one(ii),to the consciousness problem,concerning the existence and nature of consciousness(if any),at the inferior organisms on the complexity scale,as this concept is known at humans.As philosophy benefits of the privilege to use data/concepts from other sciences to obtain philosophical conclusions,there were included detailed descriptions of some key biologic mechanisms,analyzed from informational perspective,necessary just to support/demonstrate/reinforce the informational nature/substrate of the mentioned relations.The analysis of the close relation between information and body,related to the structuration and functional properties of the biological organisms,from cells to multicellular structures,shows that all of them are able to“embody/disembody”information during/by structuration/destructuration processes of matter,in particular that of DNA/RNA/proteins,their functions appearing as a result of their informational capabilities to internally manage the inter-connection with environment,primarily due to their permanent dependence on the food resources and adaptation/survival needs.The experimental and theoretical studies,revealing/documenting on one hand the automatic management of maintenance metabolic processes,the reproduction,and growth/development,and on the other hand the adaptive decision-making/sentient processes as a responsive reaction to the environmental cues,show/support the consistency of the informational model of the human body and living structures on the entire biological scale,providing support to the informational solution of the stated problems(i)and(ii).A distinct attention is paid to plants,which are organisms without nervous system,but which show/manifest also informational capabilities to detect/react to information and to modulate their behavior accordingly.The question if the living organisms possess a pseudo/proto-consciousness level as a consequence of the informational activity of their body,distinct from human,but active in any biological structure under certain conditions is furthermore discussed,and a reliable definition of rudimentary pseudo/proto-consciousness level is given/described and compared with other empirical/theoretical concepts.

Evolution and Development of the Information Concept in Biological Systems: From Empirical Description to Informational Modeling of the Living Structures

With the purpose to smooth the way of a correct understanding of information concepts and their evolution,in this paper,is discussed the evolution and development of the concept of information in biological systems,showing that this concept was intuitively perceived even since ancient times by our predecessors,and described according to their language level of that times,but the crystallization of the real meaning of information is an achievement of our nowadays,by successive contribution of various scientific branches and personalities of the scientific community of the world,leading to a modern description/modeling of reality,in which information plays a fundamental role.It is shown that our reality can be understood as a contribution of matter/energy/information and represented/discussed as the model of the Universal Triangle of Reality(UTR),where various previous models can be suggestively inserted,as a function of their basic concern.The modern concepts on information starting from a theoretic experiment which would infringe the thermodynamics laws and reaching the theory of information and modern philosophic concepts on the world structuration allow us to show that information is a fundamental component of the material world and of the biological structures,in correlation with the structuration/destructuration processes of matter,involving absorption/release of information.Based on these concepts,is discussed the functionality of the biologic structures and is presented the informational model of the human body and living structures,as a general model of info-organization on the entire biological scale,showing that a rudimentary proto-consciousness should be operative even at the low-scale biological systems,because they work on the same principles,like the most developed bio-systems.The operability of biologic structures as informational devices is also pointed out.

Informational Structure of the Living Systems: From Philosophy to Informational Modeling

In this paper,there are discussed the informational functions of the living structures,analyzing the properties of the simplest eukaryotic cell as an example of a structural unit of the living unicellular and multicellular systems.The initiation of this analysis starts from an older example of an imaginary mechanism,particularly that described by the Maxwell’s demon experiment,which along the history of the information development concepts accompanied the philosophic vision on the structuration of matter and of the living entities,showing that these are actually the result of the intervention of information on the matter available substrate.Particularly,it is shown that the deoxyribonucleic acid(DNA)structure is appropriate to store a large quantity of structural information,allowing the transfer of this information by transcription and translation mechanisms to proteins,which act as(re)structuration/transmission informational agents,or the generation of a new cellular daughter structure by a replication process.On the basis of the theory of information in communication channels,applicable also in biological systems,it was discussed the followed line for the evaluation of the quantity of structural information in various cells,demonstrating the evolution of organism complexity by the increase of the structural information quantity from unicellular(bacterium)to human cell.Applying a natural strategy of entropy lowering mainly by heat elimination,folding protein structuration and compartmentalization on the evolutionary scale,the living structures act as dynamic entities assuring their self-organizational structure by a permanent change of matter,energy and information with the environment in an efficient way,following a negative entropic process by internal structuration,similarly with Maxwell’s demon work.It is shown that to assure such a communication with external and internal intracellular structure,it was necessary the development of an own info-operational system of communication and decision,in which the operational“Yes/No”decisional binary(Bit)unit is essential.These revolutionary results show that the cell unit complies with the similar informational functions like the multicellular structure of the human body,organized in seven-type informational components,allowing the informational modeling of the activity of the living biologic structures and the opening of a shortcutting way to mimic the biologic functions in artificial cells.

Qualitative analysis of aromatic compounds via 1D TOCSY techniques

The aromatic compounds,including o-xylene,m-xylene,p-xylene,and ethylbenzene,primarily originate from the catalytic reforming of crude oil,and have a wide variety of applications.However,because of similar physical and chemical properties,these compounds are difficult to be identified by gas chromatography(GC)without standard samples.With the development of modern nuclear magnetic resonance(NMR)techniques,NMR has emerged as a powerful and efficient tool for the rapid analysis of complex and crude mixtures without purification.In this study,the parameters of one-dimensional(1D)total correlation spectroscopy(TOCSY)NMR techniques,including 1D selective gradient TOCSY and 1D chemicalshift-selective filtration(CSSF)with TOCSY,were optimized to obtain comprehensive molecular structure information.The results indicate that the overlapped signals in NMR spectra of nonpolar aromatic compounds(including o-xylene,m-xylene,p-xylene and ethylbenzene),polar aromatic compounds(benzyl alcohol,benzaldehyde,benzoic acid),and aromatic compounds with additional conjugated bonds(styrene)can be resolved in 1D TOCSY.More importantly,full molecular structures can be clearly distinguished by setting appropriate mixing time in 1D TOCSY.This approach simplifies the NMR spectra,provides structural information of entire molecules,and can be applied for the analysis of other structural isomers.

Solution to the Mind-Body Relation Problem: Information

In this paper it is analyzed from the informational perspective the relation between mind and body, an ancientphilosophic issue defined as a problem, which still did not receive up to date an adequate solution. Byintroducing/using the concept of information, it is shown that this concept includes two facets, one of themreferring to the common communications and another one referring to a hidden/structuring matter-relatedinformation, effectively acting in the human body and in the living systems, which determines the dynamicinter-change of information between specific structures of the organism by electric/electronic/chemical agents andgenetic/epigenetic processes. It is shown that the maintenance of body, permanently and obligatory depending onthe external matter (foods, air, water) resources, needed to provide both the structuring/restructuring basic materialand energy, determines the necessary existence of an info-managing system, administrating the internalmechano-chemical/physical processes. As a natural consequence, such a system should organize and assure ownsurvival by an effective informational operability to detect the external food resources, to select the appropriateinterest information and to decide as a function of circumstances. One important component in such aninformational system is memory, allowing to dispose of the reference informational data for analysis/comparisonand the selection between good and bad binary possible decisions. The memory receives and stores thereforesignals from external reality and from the body itself, referring to the emotional reaction, digestion status, creation,and inherited predilections, within specific info-neural communication circuits between the brain and bodyexecution/sensitive organs, the human body appearing as an integrated info-matter self-managed dynamic system.The specific body components memorize information with different degrees of info-integration: short/long-termintegration, emotive/action reaction, info-abilities, culminating with the integration in the chromosomal structuresby epigenetic processes. The new acquired information is transgenerationally transmissible, and is manifested asnew traits, showing the adaptation capability of the human and close relation between mind and body. Analyzingthe results of such a mind-body informational model in comparison with the earlier assumed/proposed/assertedarchaic, Greek and Occidental philosophies, which represent only partial aspects of this relation, it is shown thatthis informational model, elaborated in terms of information on the basis of scientific reasons and arguments,constitutes a general, realist, and coherent model of the mind-body relation, able to integrate and/or explain most ofthe others.

Information Space and Information Process: Genesis and Evolution

In this article,the phenomenon of“information space”and its methods of study,its types,elementary structure and qualitative characteristics are discussed,the author’s definition of the concept of“information”is given,the structure of the information process,and the phases,which are the basis for the evolution of the information space and the universe of human activity,are considered.

Set pair three-way overlapping community discovery algorithm for weighted social internet of things

There are many problems in Social Internet of Things(IoTs),such as complex topology information,different degree of association between nodes and overlapping communities.The idea of set pair information grain computing and clustering is introduced to solve the above problems so as to accurately describe the similarity between nodes and fully explore the multi-community structure.A Set Pair Three-Way Overlapping Community Discovery Algorithm for Weighted Social Internet of Things(WSIoT-SPTOCD)is proposed.In the local network structure,which fully considers the topological information between nodes,the set pair connection degree is used to analyze the identity,difference and reverse of neighbor nodes.The similarity degree of different neighbor nodes is defined from network edge weight and node degree,and the similarity measurement method of set pair between nodes based on the local information structure is proposed.According to the number of nodes'neighbors and the connection degree of adjacent edges,the clustering intensity of nodes is defined,and an improved algorithm for initial value selection of k-means is proposed.The nodes are allocated according to the set pair similarity between nodes and different communities.Three-way community structures composed of a positive domain,boundary domain and negative domain are generated iteratively.Next,the overlapping node set is generated according to the calculation results of community node membership.Finally,experiments are carried out on artificial networks and real networks.The results show that WSIoT-SPTOCD performs well in terms of standardized mutual information,overlapping community modularity and F1.

Leveraging Structured Information from a Passage to Generate Questions

Question Generation(QG)is the task of utilizing Artificial Intelligence(AI)technology to generate questions that can be answered by a span of text within a given passage.Existing research on QG in the educational field struggles with two challenges:the mainstream QG models based on seq-to-seq fail to utilize the structured information from the passage;the other is the lack of specialized educational QG datasets.To address the challenges,a specialized QG dataset,reading comprehension dataset from examinations for QG(named RACE4QG),is reconstructed by applying a new answer tagging approach and a data-filtering strategy to the RACE dataset.Further,an end-to-end QG model,which can exploit the intra-and inter-sentence information to generate better questions,is proposed.In our model,the encoder utilizes a Gated Recurrent Units(GRU)network,which takes the concatenation of word embedding,answer tagging,and Graph Attention neTworks(GAT)embedding as input.The hidden states of the GRU are operated with a gated self-attention to obtain the final passage-answer representation,which will be fed to the decoder.Results show that our model outperforms baselines on automatic metrics and human evaluation.Consequently,the model improves the baseline by 0.44,1.32,and 1.34 on BLEU-4,ROUGE-L,and METEOR metrics,respectively,indicating the effectivity and reliability of our model.Its gap with human expectations also reflects the research potential.

Structure and property of metal melt Ⅱ—Evolution of atomic clusters in the not high temperature range above liquidus

Based on the theory of micro-inhomogeneity of liquid metal,a calculation model is established for the quantitative description of the structural information of metal melts.Only by thermophysical property parameters and basic structural parameters of solid metal,can this model produce the main information of melt structure,including the relative concentration of active atoms,size of atomic clusters and number of short-range order atoms.Based on this model,the main structural information of Al and Ni melts in the not high range above the liquidus is calculated,with results in good agreement with experimental values.Besides,analyzed is the influence of superheating temperature and atomic number on the melt structural information of the first (IA) and second main group (IIA) elements.With temperature increasing,melt structural information regularly changes for both IA and IIA elements.With the atomic number increasing,melt structural information of IA elements changes regularly,for the crystal structures of the IA elements are all of bcc lattice type.However,no notable regular change of melt structural information for IIA elements has been found,mainly because the lattice type of IIA elements is of hcp-fcc-bcc transition.The present work presents an effective way for better understanding metal melt structure and for forecasting the change of the physical property of metal melts.

Feedback Stackelberg Solution for Mean-Field Type Stochastic Systems with Multiple Followers

This paper discusses feedback Stackelberg strategies for the continuous-time mean-field type stochastic systems with multiple followers in infinite horizon.First,optimal control problems of the followers are studied in the sense of Nash equilibrium.With the help of a set of generalized algebraic Riccati equations(GAREs),sufficient conditions for the solvability are put forward.Then,the leader faces a constrained optimal control problem by transforming the cost functional into a trace criterion.Employing the Karush-Kuhn-Tucker(KKT)conditions,necessary conditions are presented in term of the solvability of the cross-coupled stochastic algebraic equations(CSAEs).Moreover,feedback Stackelberg strategies are obtained based on the solutions of the CSAEs.In addition,an iterative scheme is introduced to obtain efficiently the solutions of the CSAEs.Finally,an example is given to shed light on the effectiveness of the proposed results.

JFinder:A novel architecture for java vulnerability identification based quad self-attention and pre-training mechanism

Software vulnerabilities pose significant risks to computer systems,impacting our daily lives,productivity,and even our health.Identifying and addressing security vulnerabilities in a timely manner is crucial to prevent hacking and data breaches.Unfortunately,current vulnerability identification methods,including classical and deep learning-based approaches,exhibit critical drawbacks that prevent them from meeting the demands of the contemporary software industry.To tackle these issues,we present JFinder,a novel architecture for Java vulnerability identification that leverages quad self-attention and pre-training mechanisms to combine structural information and semantic representations.Experimental results demonstrate that JFinder outperforms all baseline methods,achieving an accuracy of 0.97 on the CWE dataset and an F1 score of 0.84 on the PROMISE dataset.Furthermore,a case study reveals that JFinder can accurately identify four cases of vulnerabilities after patching.

Fast code recommendation via approximate sub-tree matching

Software developers often write code that has similar functionality to existing code segments.A code recommendation tool that helps developers reuse these code fragments can significantly improve their efficiency.Several methods have been proposed in recent years.Some use sequence matching algorithms to find the related recommendations.Most of these methods are time-consuming and can leverage only low-level textual information from code.Others extract features from code and obtain similarity using numerical feature vectors.However,the similarity of feature vectors is often not equivalent to the original code’s similarity.Structural information is lost during the process of transforming abstract syntax trees into vectors.We propose an approximate sub-tree matching based method to solve this problem.Unlike existing tree-based approaches that match feature vectors,it retains the tree structure of the query code in the matching process to find code fragments that best match the current query.It uses a fast approximation sub-tree matching algorithm by transforming the sub-tree matching problem into the match between the tree and the list.In this way,the structural information can be used for code recommendation tasks that have high time requirements.We have constructed several real-world code databases covering different languages and granularities to evaluate the effectiveness of our method.The results show that our method outperforms two compared methods,SENSORY and Aroma,in terms of the recall value on all the datasets,and can be applied to large datasets.

A two-stage restoration of distorted underwater images using compressive sensing and image registration

Imaging through a time-varying water surface exhibits severe non-rigid geometric distortions and motion blur.Theoretically,although the water surface possesses smoothness and temporal periodicity,random fluctuations are inevitable in an actual video sequence.Meanwhile,considering the distribution of information,the image structure contributes more to the restoration.In this paper,a new two-stage restoration method for distorted underwater video sequences is presented.During the first stage,salient feature points,which are selected through multiple methods,are tracked across the frames,and the motion fields at all pixels are estimated using a compressive sensing solver to remove the periodic distortions.During the second stage,the combination of a guided filter algorithm and an image registration method is applied to remove the structural-information-oriented residual distortions.Finally,the experiment results show that the method outperforms other state-of-the-art approaches in terms of the recovery effect and time.