Associative Tasks Computing Offloading Scheme in Internet of Medical Things with Deep Reinforcement Learning

The Internet of Medical Things(Io MT) is regarded as a critical technology for intelligent healthcare in the foreseeable 6G era. Nevertheless, due to the limited computing power capability of edge devices and task-related coupling relationships, Io MT faces unprecedented challenges. Considering the associative connections among tasks, this paper proposes a computing offloading policy for multiple-user devices(UDs) considering device-to-device(D2D) communication and a multi-access edge computing(MEC)technique under the scenario of Io MT. Specifically,to minimize the total delay and energy consumption concerning the requirement of Io MT, we first analyze and model the detailed local execution, MEC execution, D2D execution, and associated tasks offloading exchange model. Consequently, the associated tasks’ offloading scheme of multi-UDs is formulated as a mixed-integer nonconvex optimization problem. Considering the advantages of deep reinforcement learning(DRL) in processing tasks related to coupling relationships, a Double DQN based associative tasks computing offloading(DDATO) algorithm is then proposed to obtain the optimal solution, which can make the best offloading decision under the condition that tasks of UDs are associative. Furthermore, to reduce the complexity of the DDATO algorithm, the cacheaided procedure is intentionally introduced before the data training process. This avoids redundant offloading and computing procedures concerning tasks that previously have already been cached by other UDs. In addition, we use a dynamic ε-greedy strategy in the action selection section of the algorithm, thus preventing the algorithm from falling into a locally optimal solution. Simulation results demonstrate that compared with other existing methods for associative task models concerning different structures in the Io MT network, the proposed algorithm can lower the total cost more effectively and efficiently while also providing a tradeoff between delay and energy consumption tolerance.

DISCRETE BIDIRECTIONAL ASSOCIATIVE MEMORY WITH LEARNING FUNCTION

In this paper we propose a new discrete bidirectional associative memory (DBAM) which is derived from our previous continuous linear bidirectional associative memory (LBAM). The DBAM performs bidirectionally the optimal associative mapping proposed by Kohonen. Like LBAM and NBAM proposed by one of the present authors,the present BAM ensures the guaranteed recall of all stored patterns,and possesses far higher capacity compared with other existing BAMs,and like NBAM, has the strong ability to suppress the noise occurring in the output patterns and therefore reduce largely the spurious patterns. The derivation of DBAM is given and the stability of DBAM is proved. We also derive a learning algorithm for DBAM,which has iterative form and make the network learn new patterns easily. Compared with NBAM the present BAM can be easily implemented by software.

THAPE: A Tunable Hybrid Associative Predictive Engine Approach for Enhancing Rule Interpretability in Association Rule Learning for the Retail Sector

Association rule learning(ARL)is a widely used technique for discovering relationships within datasets.However,it often generates excessive irrelevant or ambiguous rules.Therefore,post-processing is crucial not only for removing irrelevant or redundant rules but also for uncovering hidden associations that impact other factors.Recently,several post-processing methods have been proposed,each with its own strengths and weaknesses.In this paper,we propose THAPE(Tunable Hybrid Associative Predictive Engine),which combines descriptive and predictive techniques.By leveraging both techniques,our aim is to enhance the quality of analyzing generated rules.This includes removing irrelevant or redundant rules,uncovering interesting and useful rules,exploring hidden association rules that may affect other factors,and providing backtracking ability for a given product.The proposed approach offers a tailored method that suits specific goals for retailers,enabling them to gain a better understanding of customer behavior based on factual transactions in the target market.We applied THAPE to a real dataset as a case study in this paper to demonstrate its effectiveness.Through this application,we successfully mined a concise set of highly interesting and useful association rules.Out of the 11,265 rules generated,we identified 125 rules that are particularly relevant to the business context.These identified rules significantly improve the interpretability and usefulness of association rules for decision-making purposes.

A Novel Multivalued Associative Memory System

Globally coupled map (GCM) model can evolve through chaotic searching into several stable periodic orbits under properly controlled parameters. This can be exploited in information processing such as associative memory and optimization. In this paper, we propose a novel covariance learning rule for multivalue patterns and apply it in memorization of gray scale images based on modified GCM model (S GCM). Analysis of retrieval results are given finally.

The Processing Mechanism of Associative Meaning Under the Cognitive Context Based on Culture

Cognitive context is the cognitionalized context of language, situation and context of culture by the individual which is stored and stimulated in individual＇s mind when meaning is processed. The focus of this article is on context of culture cognitionalized by individuals. Cognitive context based on culture is the inner force of the processing of associative meaning. Cognitive context reflects the similarities and differences of the understanding of different cultural communities towards the world around them.

BIDIRECTIONAL ASSOCIATIVE MEMORY ENSEMBLE

The multiple classifier system （MCS）, composed of multiple diverse classifiers or feed-forward neural networks, can significantly improve the classification or generalization ability of a single classifier. Enlightened by the fundamental idea of MCS, the ensemble is introduced into the quick learning for bidirectional associative memory （QLBAM） to construct a BAM ensemble, for improving the storage capacity and the error-correction capability without destroying the simple structure of the component BAM. Simulations show that, with an appropriate ＂overproduce and choose＂ strategy or ＂thinning＂ algorithm, the proposed BAM ensemble significantly outperforms the single QLBAM in both storage capacity and noise-tolerance capability.

Cultural Context and Associative Meaning of Words in Cross-culture Communication

Language is the vehicle of culture, vocabulary is the most active part of a language. This article compares and analyses the relationship of cultural context and the associative meaning of words in three aspects—associative meaning overlap, associative meaning mismatch and associative meaning gap, revealing its importance in the cross-cultural communication.

Associative Meanings of Colors in Chinese and English Cultures

Colors are endowed into many different associative meanings by different peoples and countries under the various cultural backgrounds and people make it express testimonial and depreciated meaning. There is not only the same aspect, but also the differences. Moreover, some factors such as geographical environment, public sentiment custom, thinking mode, religious belief, and national psychology also influence it. Each kind of color is regarded the difference for every nation's person. This article analyzes and investigates the associative meaning of the color in the Chinese and English cultures. And then it will let the reader learn well and more the associative meaning under the different cultural background.

STABILITY OF BIDIRECTIONAL ASSOCIATIVE MEMORY NEURAL NETWORKS WITH DELAYS

In this paper the globally asymptotic stability of more general two-layer nonlinear feedback associative memory neural networks with time delays is examined. The sufficient conditions of existence, uniqueness and globally asymptotic stability of the equilibrum position are given. Finally, two interesting examples to illustrate the theory are given.

Paired associative stimulation improves synaptic plasticity and functional outcomes after cerebral ischemia

Paired associative stimulation is a relatively new non-invasive brain stimulation technique that combines transcranial magnetic stimulation and peripheral nerve stimulation. The effects of paired associative stimulation on the excitability of the cerebral cortex can vary according to the time interval between the transcranial magnetic stimulation and peripheral nerve stimulation. We established a model of cerebral ischemia in rats via transient middle cerebral artery occlusion. We administered paired associative stimulation with a frequency of 0.05 Hz 90 times over 4 weeks. We then evaluated spatial learning and memory using the Morris water maze. Changes in the cerebral ultra-structure and synaptic plasticity were assessed via transmission electron microscopy and a 64-channel multi-electrode array. We measured mRNA and protein expression levels of brain-derived neurotrophic factor and N-methyl-D-aspartate receptor 1 in the hippocampus using a real-time polymerase chain reaction and western blot assay. Paired associative stimulation treatment significantly improved learning and memory in rats subjected to cerebral ischemia. The ultra-structures of synapses in the CA1 area of the hippocampus in rats subjected to cerebral ischemia were restored by paired associative stimulation. Long-term potentiation at synapses in the CA3 and CA1 regions of the hippocampus was enhanced as well. The protein and mRNA expression of brain-derived neurotrophic factor and N-methyl-D-aspartate receptor 1 increased after paired associative stimulation treatment. These data indicate that paired associative stimulation can protect cog-nition after cerebral ischemia. The observed effect may be mediated by increases in the mRNA and protein expression of brain-derived neurotrophic factor and N-methyl-D-aspartate receptor 1, and by enhanced synaptic plasticity in the CA1 area of the hippocampus. The animal experiments were approved by the Animal Ethics Committee of Tongji Medical College, Huazhong University of Science & Technology, China(approval No. TJ-A20151102) on July 11, 2015.

Effect of Paired Associative Stimulation on Motor Cortex Excitability in Rats

Paired associative stimulation (PAS),combining transcranial magnetic stimulation (TMS) with electrical peripheral nerve stimulation (PNS) in pairs with an optimal interstimulus interval (ISI)in between,has been shown to influence the excitability of the motor cortex (MC)in humans.However,the underlying mechanisms remain unclear.This study was designed to explore an optimal protocol of PAS,which can modulate the excitability of MC in rats,and to investigate the underlying mechanisms. The resting motor thresholds (RMTs) of TMS-elicited motor evoked potentials (MEPs) recorded from the gastrocnemius muscle and the latency of P1 component of somatosensory evoked potentials (SEPs) induced by electrical tibial nerve stimulation were determined in male Sprague-Dawley rats (n=10).Sixty rats were then randomly divided into 3 groups:a PAS group (further divided into 10 subgroups at various ISIs calculated by using the latency of P1,n=5,respectively),a TMS (only)group (n=5)and a PNS (only)group (n=5).Ninety repetitions of PAS,TMS and PNS were administered to the rats in the 3 groups,respectively,at the frequency of 0.05 Hz and the intensity of TMS at 120% RMT and that of PNS at 6 mA.RMTs and motor evoked potentials'amplitude (MEPamp)were recorded before and immediately after the interventions.It was found that the MEPamp significantly decreased after PAS at ISI of 5 ms (P<0.05),while the MEPamp significantly increased after PAS at ISI of 15ms,as compared with those before the intervention (P<0.05).However,the RMT did not change significantly after PAS at ISI of 5 ms or 15 ms (P>0.05).PAS at other ISis as well as the sole use of TMS and PNS induced no remarkable changes in MEPamp and RMT.In conclusion,PAS can influence motor cortex excitability in rats.Neither TMS alone nor PNS alone shows significant effect.

QUALITATIVE ANALYSIS OF BIDIRECTIONAL ASSOCIATIVE MEMORY NEURAL NETWORKS

In this paper, the global exponential stability of an equilibrium position for general bidirectional associative memory neural networks are studied. The sufficient conditions of existence and uniqueness of the equilibrium position are given. The method of energy function is examined. Two examples are given to illustrate the theory.

A novel associative latex thickener using ethoxylated behenyl methacrylate as functional monomer

Alkali-soluble associative latex thickeners modified with hydrophobic long chain alkyl groups were prepared using common acrylics and varying amount of a functional monomer,ethoxylated behenyl methacrylate(BEM),through emulsion polymerization.It was found that the size of the emulsion particle became larger with addition of BEM.The light transmittance of the thickener latex sharply increased with pH varied from 6 to 7.The associative latex thickener manifested a higher viscosity when solids in the latex thickeners were kept at 0.5 wt%or higher,and the optimal amount of BEM was found to be around 2.5 wt%,or 0.16 mol%.All thickener latexes modified with BEM have better shearing resistance than the BEM-free thickener.

Non-covalent associative structure of coal

The recent progress of non-covalent associative structure of coal, and the mechanisms of the CS2/NMP (1:1 by volume) mixed solvent and the additive addition enhancing the extraction yield of coals were reviewed, and the aggregation behavior of coal in solid and solution states were presented, and the aggregation behavior of coal in solid and solution states were introduced in this paper. Coal extraction and swelling in organic solvents at room temperature were the most useful methods to understand the associative structure of coal. CS2/NMP (1:1 by volume) is a unique solvent to give high extraction yields for some bituminous coals. Some additives can dissociate the stronger interactions among coal molecules and enhance the extraction yields of coal in the mixed solvent.

HYDROPHOBICALLY ASSOCIATING POLYACRYLAMIDES MODIFIED BY A NOVEL SELF-ASSOCIATIVE CATIONIC MONOMER

A series of hydrophobically associating polyacrylamides modified by small amounts （〈 3 mol%） of a self- associative cationic monomer 4-（2-（acryloyloxy） ethoxy） benzyl tri-ethyl ammonium bromide （AEBA） as hydrophobe were synthesized by radical copolymerization in aqueous solutions without external surfactants. The resulting eopolymers containing a multiblock structure exhibited a high tendency for hydrophobic association and a high thickening capacity. Solution properties and aggregation structures were investigated by viscometry and fluorescence technique. The high viscosity enhancement was found as the polymer concentration beyond a critical value c＊ and strongly depended on the copolymer microstructures. The number and length of hydrophobic microblocks within the copolymer backbones could be controlled by changing the AEBA concentration in copolymerization system. Addition of salt induced more hydrophobic association and viscosity enhancement. The synthesis method used was simple and environmentally friendly without any external surfactant contamination in comparison with the conventional micellar copolymerization.

Highly efficient subnanometer Ru-based catalyst for ammonia synthesis via an associative mechanism

The industrial manufacture of ammonia(NH_(3))using Fe-based catalyst works under rigorous conditions.For the goal of carbon-neutrality,it is highly desired to develop advanced catalyst for NH_(3)synthesis at mild conditions to reduce energy consumption and CO_(2)emissions.However,the main challenge of NH_(3)synthesis at mild conditions lies in the dissociation of steady N≡N triple bond.In this work,we report the design of subnanometer Ru clusters(0.8 nm)anchored on the hollow N-doped carbon spheres catalyst(Ru-SNCs),which effectively promotes the NH_(3)synthesis at mild conditions via an associative route.The NH_(3)synthesis rate over Ru-SNCs(0.49%(mass)Ru)reaches up to 11.7 mmol NH_(3)·(g cat)^(-1)·h^(-1) at 400℃ and 3 MPa,which is superior to that of 8.3 mmol NH_(3)·(g cat)^(-1)·h^(-1) over Ru nanoparticle catalyst(1.20%(mass)Ru).Various characterizations show that the N_(2)H_(4)species are the main intermediates for NH_(3)synthesis on Ru-SNCs catalyst.It demonstrates that Ru-SNCs catalyst can follow an associative route for N_(2)activation,which circumvents the direct dissociation of N_(2)and results in highly efficient NH_(3)synthesis at mild conditions.

Novel hydrophobically associative polyacrylamide with tunable viscosity

Hydrophobically associative polyacrylamide （HAPAM） were prepared in aqueous solution by radical copolymerization of novel cationic surface-active monomer, dimethylhexadecyl（3-acrylamidopropyl）ammonium bromide （DMHAB）, with acrylamide （AM） in the presence of DMHAB/CTAB mixed micelles. The length of hydrophobic microblock （NH） in HAPAM is controlled by the molar fraction of DMHAB in mixed micelles, which can be mediated by the ratio of CTAB to DMHAB. The results of steady-state fluorescence probe and viscometry experiments showed the ability of HAPAM association was determined by the length of the hydrophobic microblock. HAPAM with tunable association ability are promising materials for thickening agent.

Synthesization of high-capacity auto-associative memories using complex-valued neural networks

In this paper, a novel design procedure is proposed for synthesizing high-capacity auto-associative memories based on complex-valued neural networks with real-imaginary-type activation functions and constant delays. Stability criteria dependent on external inputs of neural networks are derived. The designed networks can retrieve the stored patterns by external inputs rather than initial conditions. The derivation can memorize the desired patterns with lower-dimensional neural networks than real-valued neural networks, and eliminate spurious equilibria of complex-valued neural networks. One numerical example is provided to show the effectiveness and superiority of the presented results.

Multi-Valued Associative Memory Neural Network

A novel learning method for multi-valued associative memory network is introduced, which is based on Hebb rule, but utilizes more information. According to the current probe vector, the connection weights matrix could be chosen dynamically. Double-valued and multi-valued associative memory are all realized in our simulation experiment. The experimental results show that the method could enhance the associative success rate.

ESTIMATION OF ATTRACTION DOMAIN AND EXPONENTIAL CONVERGENCE RATE OF CONTINUOUS FEEDBACK ASSOCIATIVE MEMORY AND ITS APPLICATIONS

The attraction domains of memory patterns and exponential convergence rate of the network trajectories to memory patterns for continuous feedback associative memory are estimated. These results can be used for evaluation of error-correction capability and the synthesis procedures for continuous-time associative memory neural networks.