Social collaborative filtering using local dynamic overlapping community detection

The Journal of Supercomputing - Recommender systems play an important role in dealing with the problems caused by the great and growing amount of information, and the collaborative filtering method...     

Experience classification for transfer learning in traffic signal control

In recent years, due to the drastic rise in the number of vehicles and the lack of sufficient infrastructure, traffic jams, air pollution, and fuel consumption have increased in cities. The optimization of timing for traffic lights is one of the solutions for the mentioned problems. Many methods have been introduced to deal with these problems, including reinforcement learning. Although a great number of learning-based methods have been used in traffic signal control, they suffer from poor performance and slow learning convergence. In this paper, a transfer learning-based method for traffic signal control has been proposed. Multi-agent system has also been used for modelling the traffic network and transfer learning has been used to make reinforcement learning agents transfer their experience to each other. Furthermore, a classifier has been utilized to classify the transferred experiences. The results show that using the proposed method leads to a significant improvement on average delay time and convergence time of the learning process.

     

Bidirectional teleportation of a pure EPR state by using GHZ states

In the present paper, a novel bidirectional quantum teleportation protocol is proposed. By using entanglement swapping technique, two GHZ states are shared as a quantum channel between Alice and Bob as legitimate users. In this scheme, based on controlled-not operation, single-qubit measurement, and appropriate unitary operations, two users can simultaneously transmit a pure EPR state to each other, While, in the previous protocols, the users can just teleport a single-qubit state to each other via more than four-qubit state. Therefore, the proposed scheme is economical compared with previous protocols.     

Harnessing Normal and Engineered Mesenchymal Stem Cells Derived Exosomes for Cancer Therapy: Opportunity and Challenges

There remains a vital necessity for new therapeutic approaches to combat metastatic cancers, which cause globally over 8 million deaths per year. Mesenchymal stem cells (MSCs) display aptitude as new therapeutic choices for cancer treatment. Exosomes, the most important mediator of MSCs, regulate tumor progression. The potential of harnessing exosomes from MSCs (MSCs-Exo) in cancer therapy is now being documented. MSCs-Exo can promote tumor progression by affecting tumor growth, metastasis, immunity, angiogenesis, and drug resistance. However, contradictory evidence has suggested that MSCs-Exo suppress tumors through several mechanisms. Therefore, the exact association between MSCs-Exo and tumors remains controversial. Accordingly, the applications of MSCs-Exo as novel drug delivery systems and standalone therapeutics are being extensively explored. In addition, engineering MSCs-Exo for targeting tumor cells has opened a new avenue for improving the efficiency of antitumor therapy. However, effective implementation in the clinical trials will need the establishment of standards for MSCs-Exo isolation and characterization as well as loading and engineering methods. The studies outlined in this review highlight the pivotal roles of MSCs-Exo in tumor progression and the promising potential of MSCs-Exo as therapeutic drug delivery vehicles for cancer treatment.     

Towards bridging the neuro-symbolic gap: deep deductive reasoners

Applied Intelligence - Symbolic knowledge representation and reasoning and deep learning are fundamentally different approaches to artificial intelligence with complementary capabilities. The...     

Preparation of Janus-type superparamagnetic iron oxide nanoparticles modified with functionalized PCL/PHEMA via photopolymerization for dual drug delivery

In this study, superparamagnetic iron oxide nanoparticles (SPIONs) were synthesized by the coprecipitation of FeCl₂˙4H₂O and FeCl₃˙6H₂O and applied as a core for preparation of Janus nanoparticles. Accordingly, freshly modified methacrylated iron oxide nanoparticles were reacted with two functionalized polymers. Acrylated poly(ε-caprolactone) (PCL) and acrylated poly(2-hydroxyethyl methacrylate) (PHEMA) were synthesized via ring-opening and free-radical polymerization, respectively, and subsequent modification with acryloyl chloride. Acrylated PCL as the hydrophobic part and acrylated PHEMA as the hydrophilic domain were grafted on the surface of methacrylated iron oxide nanoparticles with two morphologies. Pickering emulsion and solution photopolymerization reactions were used to prepare nanoparticles with “Janus” and “mixed” morphologies, respectively. The products were characterized in each step using Fourier-transform infrared spectroscopy (FT-IR), Proton nuclear magnetic resonance (¹H-NMR), thermogravimetric analysis (TGA), dynamic light scaterring (DLS), transmission electron microscope (TEM), vibrating-sample magnetometer (VSM), energy dispersive X-ray (EDX), and ultraviolet–visible spectroscopy (UV-Vis). Quercetin and 5-FU (as two anticancer drugs) were loaded in the mentioned nanoparticles, and the drug loading capacity and encapsulation efficiency (EE) of these nanoparticles were calculated. in vitro release behavior at two pH values (5.8 and 7.4) and at 37°C demonstrated that morphology can affect the release profile. Finally, rat C6 cell viability was determined by 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazoliumbromide (MTT) assay for drug-free and drug-loaded nanoparticles.     

Study of the synergism effect of a binary carbon system in the nanostructure of the gas diffusion electrode (GDE) of a proton exchange membrane fuel cell

We report on the use of dual carbon supports activated charcoal (AC) and Vulcan XC-72R (VC) as catalysts for the fabrication of a gas diffusion electrode. The electrocatalytic properties for the oxygen reduction reaction were evaluated in a sulfuric acid electrolyte using polarization curves and electrochemical impedance spectroscopy. The water uptake and oxygen permeability were also obtained, as were the performances of electrodes in a membrane electrode assembly. A binary support electrode exhibits better performance than the usual single support electrode, with the best performance being obtained when the mass ratio of the two carbons is 50:50.     

A trust-based bio-inspired approach for credit lending decisions

Credit scoring computation essentially involves taking into account various financial factors and the previous behavior of the credit requesting person. There is a strong degree of correlation between the compliance level and the credit score of a given entity. The concept of trust has been widely used and applied in the existing literature to determine the compliance level of an entity. However it has not been studied in the context of credit scoring literature. In order to address this shortcoming, in this paper we propose a six-step bio-inspired methodology for trust-based credit lending decisions by credit institutions. The proposed methodology makes use of an artificial neural network-based model to classify the (potential) customers into various categories. To show the applicability and superiority of the proposed algorithm, it is applied to a credit-card dataset obtained from the UCI repository. Due to the varying spectrum of trust levels, we are able to solve the problem of binary credit lending decisions. A trust-based credit scoring approach allows the financial institutions to grant credit-based on the level of trust in potential customers.