Search results for: agent systems

Authors: Hyeongbok Kim, Lingling Zhao, Xiaohong Su

Abstract:

Deep reinforcement learning has been applied to address various problems in robotics, such as autonomous driving and unmanned aerial vehicle. However, because of the sparse reward penalty for a collision with obstacles during the navigation mission, the agent fails to learn the optimal policy or requires a long time for convergence. Therefore, using obstacles and enemy agents, in this paper, we present a curriculum-based boost learning method to effectively train compound skills during multi-agent reinforcement learning. First, to enable the agents to solve challenging tasks, we gradually increased learning difficulties by adjusting reward shaping instead of constructing different learning environments. Then, in a benchmark environment with static obstacles and moving enemy agents, the experimental results showed that the proposed curriculum learning strategy enhanced cooperative navigation and compound collision avoidance skills in uncertain environments while improving learning efficiency.

Keywords: curriculum learning, hard exploration, multi-agent reinforcement learning, robotic navigation, sparse reward

Procedia PDF Downloads 66

Authors: Assem El-Ansary

Abstract:

This paper illustrates the event-oriented Behavioral Pattern Analysis (BPA) modeling approach using the Healthcare Multi-Agent System. The Event defined in BPA is a real-life conceptual entity that is unrelated to any implementation. The major contributions of this research are: The Behavioral Pattern Analysis (BPA) modeling methodology. The development of an interactive software tool (DECISION), which is based on a combination of the Analytic Hierarchy Process (AHP) and the ELECTRE Multi-Criteria Decision Making (MCDM) methods.

Keywords: analysis, modeling methodology, software modeling, event-oriented, behavioral pattern, use cases, Healthcare Multi-Agent System

Procedia PDF Downloads 521

Authors: Daniia Nigmatullina, Vlada Kugurakova, Maxim Talanov

Abstract:

We present a methodology and our plans of anthropomorphic social agent visualization. That includes creation of three-dimensional model of the virtual companion's head and its facial expressions. Talking Head is a cross-disciplinary project of developing of the human-machine interface with cognitive functions. During the creation of a realistic humanoid robot or a character, there might be the ‘uncanny valley’ problem. We think about this phenomenon and its possible causes. We are going to overcome the ‘uncanny valley’ by increasing of realism. This article discusses issues that should be considered when creating highly realistic characters (particularly the head), their facial expressions and speech visualization.

Keywords: anthropomorphic social agent, facial animation, uncanny valley, visualization, 3D modeling

Procedia PDF Downloads 263

Authors: Assem El-Ansary

Abstract:

This paper illustrates the event-oriented Behavioral Pattern Analysis (BPA) modeling approach in developing an Intelligent Agent Reservation System (IARS). The Event defined in BPA is a real-life conceptual entity that is unrelated to any implementation. The major contributions of this research are developing the Behavioral Pattern Analysis (BPA) modeling methodology, and developing an interactive software tool (DECISION) which is based on a combination of the Analytic Hierarchy Process (AHP) and the ELECTRE Multi-Criteria Decision Making (MCDM) methods.

Keywords: analysis, intelligent agent, reservation system, modeling methodology, software modeling, event-oriented, behavioral pattern, use cases

Procedia PDF Downloads 456

Authors: Xiao Yihong, Yu Kexin, Burra Venkata Durga Kumar

Abstract:

With the accelerating process of urbanization, the problem of urban road congestion is becoming more and more serious. Intelligent transportation system combining distributed and artificial intelligence has become a research hotspot. As the core development direction of the intelligent transportation system, Cooperative Intelligent Transportation System (C-ITS) integrates advanced information technology and communication methods and realizes the integration of humans, vehicle, roadside infrastructure, and other elements through the multi-agent distributed system. By analyzing the system architecture and technical characteristics of C-ITS, the report proposes a distributed multi-agent C-ITS. The system consists of Roadside Sub-system, Vehicle Sub-system, and Personal Sub-system. At the same time, we explore the scalability of the C-ITS and put forward incorporating local rewards in the centralized training decentralized execution paradigm, hoping to add a scalable value decomposition method. In addition, we also suggest introducing blockchain to improve the safety of the traffic information transmission process. The system is expected to improve vehicle capacity and traffic safety.

Keywords: distributed system, artificial intelligence, multi-agent, cooperative intelligent transportation system

Procedia PDF Downloads 183

Authors: Natsumi Murakami, Jae-Ho Kim, Susumu Yonezawa

Abstract:

The calcium fluorosilicate (CaSiF₆) was prepared from calcium silicate (CaSiO₃) with fluorine gas at 25 ~ 200 ℃ and 760 Torr for 1~24 h. Especially, the pure CaSiF₆ could be prepared at 25 ℃ for 24 h with F₂ gas from the results of X-ray diffraction. Increasing temperature to higher than 100 ℃, the prepared CaSiF₆ was decomposed into CaF₂ and SiF₄. The release of SiF₄ gas was confirmed by the results of gas-phase infrared spectroscopy. In this study, we tried to modify the surface of polycarbonate (PC) resin using the SiF₄ gas released from CaSiF₆ particles. By using the prepared CaSiF₆, the surface roughness of fluorinated PC samples was approximately four times larger than that (1.4 nm) of the untreated sample. The results of X-ray photoelectron spectroscopy indicated the formation of fluorinated bonds (e.g., -CFx) on the surface of PC after surface fluorination. Consequently, the CaSiF₆ particles can be useful for a new fluorinating agent.

Keywords: calcium fluorosilicate, fluorinating agent, polycarbonate, surface fluorination

Procedia PDF Downloads 89

Authors: Zhdanova A. O., Volkov R. S., Kuznetsov G. V., Strizhak P. A.

Abstract:

Fires in different types of facilities are a serious problem worldwide.It is still an unaccomplished science and technology objective to establish the minimum number and type of sensors in automatic systems of compartment fire suppression which would turn the fire-extinguishing agent spraying on and off in real time depending on the state of the fire, minimize the amount of agent applied, delay time in fire suppression and system response, as well as the time of combustion suppression. Based on the results of experimental studies, the conclusion was made that it is reasonable to use a gas analysis system and heat sensors (in the event of their prior activation) to determine the effectiveness of fire suppression (fire-extinguishing composition interacts with the fire). Thus, the concentration of CO in the interaction of the firefighting liquid with the fire increases to 0.7–1.2%, which indicates a slowdown in the flame combustion, and heat sensors stop responding at a gas medium temperature below 80 ºC, which shows a gradual decrease in the heat release from the fire. The evidence from this study suggests that the information received from the video recording equipment (video camera) should be used in real time as an additional parameter confirming fire suppression. Research was supported by Russian Science Foundation (project No 21-19-00009, https://rscf.ru/en/project/21-19-00009/).

Keywords: compartment fires, fire suppression, continuous control of fire behavior, feedback systems

Procedia PDF Downloads 106

Authors: M. Rahimi, F. Corman

Abstract:

This paper study the travel behavior of passengers in a public transport disruption under information provision strategies. We develop a within-day approach for multi-agent simulation to evaluate the behavior of the agents, under comprehensive scenarios through various information exposure, equilibrium, and non-equilibrium scenarios. In particular, we quantify the effects of information strategies in disruption situation on passengers’ satisfaction, number of involved agents, and the caused delay. An agent-based micro-simulation model (MATSim) is applied for the city of Zürich, Switzerland, for the purpose of activity-based simulation in a multimodal network. Statistic outcome is analysed for all the agents who may be involved in the disruption. Agents’ movement in the public transport network illustrates agents’ adaptations to available information about the disruption. Agents’ delays and utility reveal that information significantly affects agents’ satisfaction and delay in public transport disruption. Besides, while the earlier availability of the information causes the fewer consequent delay for the involved agents, however, it also leads to more amount of affected agents.

Keywords: agent-based simulation, disruption management, passengers’ behavior simulation, public transport

Procedia PDF Downloads 114

Authors: H. Benmoussa, A. A. El Kalam, A. Ait Ouahman

Abstract:

The design and implementation of intrusion detection systems (IDS) remain an important area of research in the security of information systems. Despite the importance and reputation of the current intrusion detection systems, their efficiency and effectiveness remain limited as they should include active defense approach to allow anticipating and predicting intrusions before their occurrence. Consequently, they must be readapted. For this purpose we suggest a new generation of distributed intrusion detection system based on preventive detection approach and using intelligent and mobile agents. Our architecture benefits from mobile agent features and addresses some of the issues with centralized and hierarchical models. Also, it presents advantages in terms of increasing scalability and flexibility.

Keywords: Intrusion Detection System (IDS), preventive detection, mobile agents, distributed architecture

Procedia PDF Downloads 551

Authors: Yamileth P. Herrera, Ronald R. Gutierrez, Carlos, Pacheco-Bustos

Abstract:

This research aims at the numerical modeling of a rectangular contact tank in order to improve the hydrodynamic behavior and the retention time of the water to be treated with the disinfecting agent. The methodology to be followed includes a hydraulic analysis of the tank to observe the fluid velocities, which will allow evidence of low-speed areas that may generate pathogenic agent incubation or high-velocity areas, which may decrease the optimal contact time between the disinfecting agent and the microorganisms to be eliminated. Based on the results of the numerical model, the efficiency of the tank under the geometric and hydraulic conditions considered will be analyzed. This would allow the performance of the tank to be improved before starting a construction process, thus avoiding unnecessary costs.

Keywords: contact tank, numerical models, hydrodynamic modeling, residence time

Procedia PDF Downloads 138

Authors: H. Yousefnia, N. Amraee, M. Hosntalab, S. Zolghadri, A. Bahrami-Samani

Abstract:

The aim of this study was the preparation of a new agent for bone marrow ablation in patients with multiple myeloma. 166Ho was produced at Tehran research reactor via 165Ho(n,γ)166Ho reaction. Complexion of Ho‐166 with BPAMD was carried out by the addition of about 200µg of BPAMD in absolute water to 1 mci of 166HoCl3 and warming up the mixture 90 0C for 1 h. 166Ho-BPAMD was prepared successfully with radio chemical purity of 95% which was measured by ITLC method. The final solution was injected to wild-type mice and bio distribution was determined up to 48 h. SPECT images were acquired after 2 and 48 h post injection. Both the bio distribution studies and SPECT imaging indicated high bone uptake, while accumulation in other organs was approximately negligible. The results show that 166Ho-BPAMD has suitable characteristics and can be used as a new bone marrow ablative agent.

Keywords: bone marrow ablation, BPAMD, 166Ho, SPECT

Procedia PDF Downloads 483

Authors: I. Nanako, Mariko Era, Hiroshi Morita

Abstract:

Objectives: Japanese uses TATAMI rather than flooring at home. Igusa ( Juncus effuses var. decipiens ), which is commonly known in the forms of TATAMI. Juncus spp. grow at a relatively high humidity area (Japan, China and Southeast Asia ). Yatsushiro region in the southern part of Kumamoto prefecture is major produing area of Igusa. Igusa found to have honeycomb structure and was also shown to have the ability to control humidity. And Igusa has been used as a medicinal herb for diuretic and antiphlogistic agent. In previous study, we investigated antimicrobial effects of Igusa, and showed high antimicrobial activity against food poisoning bacteria. Therefore, the food trays blended Igusa can be kept clean by antimicrobial activity of Igusa. We focus on ‘Igusa foam materials’. In this study, we investigated the antibacterial and antifungal activity of Igusa, and new application to foam materials for food industry. Materials and method: We used Igusa foam materials (3 × 3 × 3 cm) as a sample. We set about fifteen types of samples combined with a commercial antibacterial agent A, a commercial antibacterial agent B, potassium laurate (C12K) and a commercial antifungal agent C, a commercial antifungal agent D and a commercial antifungal agent E. We selected four bacteria strains (Escherichia coli NBRC 3972, Staphylococus aureus NBRC 12732, Salmonella typhimurium NBRC 13245, Bacillus subtilis NBRC 3335 ) and three fungus strains (Penicillium pinophilum NBRC 6345, Cladosporium cladosporioides NBRC 30314, Aspergillus oryzae NBRC 5238 ). The fungus was cultured at 30 °C on Igusa foam materials after inoculation of the fungus for fourteen days. The bacteria was cultured at 30 °C on Igusa foam materials after inoculation of the bacteria for three days. And the Igusa foam materials were washed with 10 mL normal saline after three days. The normal saline washed Igusa foam materials plated the NA medium. After, It was cultured at 30 °C and used colony counting method. Result and Conclusion: The fifteen types of sample of Igusa foam materials had antifungal activity against C. cladosporioides, A. oryzae and P. pinophilum for fourteen days. The four types of sample contained potassium laurate and antibacterial agent A, sample contained antibacterial agent B and antifungal agent D, sample contained A and antifungal agent E, sample contained B and E had antibacterial activity against B. subtilis. The three types of sample contained potassium laurate and A, sample contained B and D, sample contained A and E had antibacterial activity against S. typhimurium. The five types of sample contained potassium laurate and A, sample contained B and D, sample contained A and E, sample contained B and E, sample contained B and antifungal agent C had antibacterial activity against E. coli and S. aureus. These results indicate that Igusa of Igusa foam materials had high antifungal activity. In addition, Igusa foam materials combined with a commercial antibacterial agent had antibacterial activity. In the future, we consider that use of Igusa foam materials may be spread from food industry.

Keywords: antibacterial, antifungal, foam materials, Igusa

Procedia PDF Downloads 215

Authors: Azimeh Rajaee, Lingyun Zhao, Shi Wang, Yaqiang Liu

Abstract:

In recent years many studies have been focused on bismuth-based nanoparticles as radiosensitizer and contrast agent in radiation therapy and imaging due to the high atomic number (Z = 82), high photoelectric absorption, low cost, and low toxicity. This study aims to introduce a new multifunctional bismuth-based nanoparticle as a theranostic agent for radiotherapy, computed tomography (CT) and magnetic resonance imaging (MRI). We synthesized bismuth ferrite (BFO, BiFeO3) nanoparticles by sol-gel method and surface of the nanoparticles were modified by Polyethylene glycol (PEG). After proved biocompatibility of the nanoparticles, the ability of them as contract agent in Computed tomography (CT) and magnetic resonance imaging (MRI) was investigated. The relaxation time rate (R2) in MRI and Hounsfield unit (HU) in CT imaging were increased with the concentration of the nanoparticles. Moreover, the effect of nanoparticles on dose enhancement in low energy was investigated by clonogenic assay. According to clonogenic assay, sensitizer enhancement ratios (SERs) were obtained as 1.35 and 1.76 for nanoparticle concentrations of 0.05 mg/ml and 0.1 mg/ml, respectively. In conclusion, our experimental results demonstrate that the multifunctional nanoparticles have the ability to employ as multimodal imaging and therapy to enhance theranostic efficacy.

Keywords: molecular imaging, nanomedicine, radiotherapy, theranostics

Procedia PDF Downloads 285

Authors: Niklas Panten, Eberhard Abele

Abstract:

This paper presents a novel approach for real-time and near-optimal control of industrial smart grids by deep reinforcement learning (DRL). To achieve highly energy-efficient factory systems, the energetic linkage of machines, technical building equipment and the building itself is desirable. However, the increased complexity of the interacting sub-systems, multiple time-variant target values and stochastic influences by the production environment, weather and energy markets make it difficult to efficiently control the energy production, storage and consumption in the hybrid industrial smart grids. The studied deep reinforcement learning approach allows to explore the solution space for proper control policies which minimize a cost function. The deep neural network of the DRL agent is based on a multilayer perceptron (MLP), Long Short-Term Memory (LSTM) and convolutional layers. The agent is trained within multiple Modelica-based factory simulation environments by the Advantage Actor Critic algorithm (A2C). The DRL controller is evaluated by means of the simulation and then compared to a conventional, rule-based approach. Finally, the results indicate that the DRL approach is able to improve the control performance and significantly reduce energy respectively operating costs of industrial smart grids.

Keywords: industrial smart grids, energy efficiency, deep reinforcement learning, optimal control

Procedia PDF Downloads 169

Authors: Mallikarjun B. Channappagoudar, Pallapa Venkataram

Abstract:

The dynamic nature of Mobile adhoc network (MANET) due to mobility and disconnection of mobile nodes, leads to various problems in predicting the movement of nodes and their location information updation, for efficient interaction among the application specific nodes. Location management is one of the main challenges to be considered for an efficient service provision to the applications of a MANET. In this paper, we propose a location management protocol, for locating the nodes of a MANET and to maintain uninterrupted high-quality service for distributed applications by intelligently anticipating the change of location of its nodes. The protocol predicts the node movement and application resource scarcity, does the replacement with the chosen nodes nearby which have less mobility and rich in resources, with the help of both static and mobile agents, and maintains the application continuity by providing required network resources. The protocol has been simulated using Java Agent Development Environment (JADE) Framework for agent generation, migration and communication. It consumes much less time (response time), gives better location accuracy, utilize less network resources, and reduce location management overhead.

Keywords: mobile agent, location management, distributed applications, mobile adhoc network

Procedia PDF Downloads 364

Authors: Ibtissem Daoudi, Raoudha Chebil, Wided Lejouad Chaari

Abstract:

Serious games constitute actually a recent and attractive way supposed to replace the classical boring courses. However, the choice of the adapted serious game to a specific learning environment remains a challenging task that makes teachers unwilling to adopt this concept. To fill this gap, we present, in this paper, a multi-agent-based simulator allowing to predict the impact of a serious game integration in a learning environment given several game and players characteristics. As results, the presented tool gives intensities of several emotional aspects characterizing learners reactions to the serious game adoption. The presented simulator is tested to predict the effect of basing a coding course on the serious game ”CodeCombat”. The obtained results are compared with feedbacks of using the same serious game in a real learning process.

Keywords: emotion, learning process, multi-agent simulation, serious games

Procedia PDF Downloads 381

Authors: Abdulwakeel B. Raji

Abstract:

This paper introduces a concept of an intelligent virtual learning environment that involves communication between learners and an artificially intelligent teaching agent in an attempt to replicate classroom learning interactions. The benefits of this technology over current e-learning practices is that it creates a virtual classroom where real time adaptive learning interactions are made possible. This is a move away from the static learning practices currently being adopted by e-learning systems. Over the years, artificial intelligence has been applied to various fields, including and not limited to medicine, military applications, psychology, marketing etc. The purpose of e-learning applications is to ensure users are able to learn outside of the classroom, but a major limitation has been the inability to fully replicate classroom interactions between teacher and students. This study used comparative surveys to gain information and understanding of the current learning practices in Nigerian universities and how they compare to these practices compare to the use of a developed e-learning system. The study was conducted by attending several lectures and noting the interactions between lecturers and tutors and as an aftermath, a software has been developed that deploys the use of an artificial intelligent teaching-agent alongside an e-learning system to enhance user learning experience and attempt to create the similar learning interactions to those found in classroom and lecture hall settings. Dialogflow has been used to implement a teaching-agent, which has been developed using JSON, which serves as a virtual teacher. Course content has been created using HTML, CSS, PHP and JAVASCRIPT as a web-based application. This technology can run on handheld devices and Google based home technologies to give learners an access to the teaching agent at any time. This technology also implements the use of definite clause grammars and natural language processing to match user inputs and requests with defined rules to replicate learning interactions. This technology developed covers familiar classroom scenarios such as answering users’ questions, asking ‘do you understand’ at regular intervals and answering subsequent requests, taking advanced user queries to give feedbacks at other periods. This software technology uses deep learning techniques to learn user interactions and patterns to subsequently enhance user learning experience. A system testing has been undergone by undergraduate students in the UK and Nigeria on the course ‘Introduction to Database Development’. Test results and feedback from users shows that this study and developed software is a significant improvement on existing e-learning systems. Further experiments are to be run using the software with different students and more course contents.

Keywords: virtual learning, natural language processing, definite clause grammars, deep learning, artificial intelligence

Procedia PDF Downloads 112

Authors: Myungkyu Park, Minkun Kim, Sunghoon Kim, Samgon Ryu

Abstract:

Recently, research for reactive fabrics which have the characteristics of CWA (Chemical Warfare Agent) decomposition is being performed actively. The performance level of decomposition for CWA decomposition in various environmental condition is one of the critical factors in applicability as protective materials for NBC (Nuclear, Biological, and Chemical) protective clothing. In this study, results of performance test for CWA decomposition by reactive fabric made of electrospinning web and reactive particle are presented. Currently, the MOF (metal organic framework) type of UiO-66-NH₂ is frequently being studied as material for decomposing CWA especially blister agent HD [Bis(2-chloroethyl) sulfide]. When we test decomposition rate with electrospinning web made of PVB (Polyvinyl Butiral) polymer and UiO-66-NH₂ particle, we can get very high protective performance than the case other particles are applied. Furthermore, if the repellant surface fabric is added on reactive material as the component of protective fabric, the performance of layer by layered reactive fabric could be approached to the level of current NBC protective fabric for HD decomposition rate. Reactive fabric we used in this study is manufactured by electrospinning process of polymer which contains the reactive particle of UiO-66-NH₂, and we performed crystalizing process once again on that polymer fiber web in solvent systems as a second step for manufacturing reactive fabric. Three kinds of polymer materials are used in this process, but PVB was most suitable as an electrospinning fiber polymer considering the shape of product. The density of particle on fiber web and HD decomposition rate is enhanced by secondary crystallization compared with the results which are not processed. The amount of HD penetration by 24hr AVLAG (Aerosol Vapor Liquid Assessment Group) swatch test through the reactive fabrics with secondary crystallization and without crystallization is 24 and 146μg/cm² respectively. Even though all of the reactive fiber webs for this test are combined with repellant surface layer at outer side of swatch, the effects of secondary crystallization of particle for the reactive fiber web are remarkable.

Keywords: CWA, Chemical Warfare Agent, gas decomposition, particle growth, protective clothing, reactive fabric, swatch test

Procedia PDF Downloads 265

Authors: Mert Turanli, Hakan Temeltas

Abstract:

In this paper, we present an adaptive controller for decentralized coordination problem of multiple non-holonomic agents. The performance of the presented Multi-Agent Bounded Gain Forgetting (BGF) Composite Adaptive controller is compared against the tracking error criterion with a Feedback Linearization controller. By using the method, the sensor nodes move and reconfigure themselves in a coordinated way in response to a sensed environment. The multi-agent coordination is achieved through Centroidal Voronoi Tessellations and Coverage Control. Also, a consensus protocol is used for synchronization of the parameter vectors. The two controllers are given with their Lyapunov stability analysis and their stability is verified with simulation results. The simulations are carried out in MATLAB and ROS environments. Better performance is obtained with BGF Adaptive Controller.

Keywords: adaptive control, centroidal voronoi tessellations, composite adaptation, coordination, multi robots

Procedia PDF Downloads 320

Authors: Hazleen Anuar, Nur Aimi Mohd Nasir

Abstract:

Durian skin is a newly explores natural fibre potentially reinforced polyolefin for diverse applications. In this work, investigation on the effect of coupling agent, maleic anhydride polypropylene (MAPP) on the mechanical, morphological and thermal properties of polypropylene (PP) reinforced with durian skin fibre (DSF) was conducted. The presence of 30 wt% DSF significantly reduced the tensile strength of PP-DSF composite. Interestingly, even though the same trend goes to PP-DSF with the presence of MAPP, the reduction is only about 4% relative to unreinforced PP and 18% higher than PP-DSF without MAPP (untreated composite or UTC). The used of MAPP in treated composite (TC) also increased the tensile modulus, flexural properties and degradation temperature. The enhanced mechanical properties are consistent with good interfacial interaction as evidenced under scanning electron microscopy.

Keywords: durian skin fiber, coupling agent, mechanical properties, thermogravimetry analysis

Procedia PDF Downloads 441

Authors: Lacramioara Ochiuz, Aurelia Vasile, Iulian Stoleriu, Cristina Ghiciuc, Maria Ignat

Abstract:

Topical administration of chemotherapeutic agents (eg. carmustine, bexarotene, mechlorethamine etc.) in local treatment of cutaneous T-cell lymphoma (CTCL) is accompanied by multiple side effects, such as contact hypersensitivity, pruritus, skin atrophy or even secondary malignancies. A known method of reducing the side effects of anticancer agent is the development of modified drug release systems using drug incapsulation in biocompatible nanoporous inorganic matrices, such as mesoporous MCM-41 silica. Mesoporous MCM-41 silica is characterized by large specific surface, high pore volume, uniform porosity, and stable dispersion in aqueous medium, excellent biocompatibility, in vivo biodegradability and capacity to be functionalized with different organic groups. Therefore, MCM-41 is an attractive candidate for a wide range of biomedical applications, such as controlled drug release, bone regeneration, protein immobilization, enzymes, etc. The main advantage of this material lies in its ability to host a large amount of the active substance in uniform pore system with adjustable size in a mesoscopic range. Silanol groups allow surface controlled functionalization leading to control of drug loading and release. This study shows (I) the amino-grafting optimization of mesoporous MCM-41 silica matrix by means of co-condensation during synthesis and post-synthesis using APTES (3-aminopropyltriethoxysilane); (ii) loading the therapeutic agent (carmustine) obtaining a modified drug release systems; (iii) determining the profile of in vitro carmustine release from these systems; (iv) assessment of carmustine release kinetics by fitting on four mathematical models. Obtained powders have been described in terms of structure, texture, morphology thermogravimetric analysis. The concentration of the therapeutic agent in the dissolution medium has been determined by HPLC method. In vitro dissolution tests have been done using cell Enhancer in a 12 hours interval. Analysis of carmustine release kinetics from mesoporous systems was made by fitting to zero-order model, first-order model Higuchi model and Korsmeyer-Peppas model, respectively. Results showed that both types of highly ordered mesoporous silica (amino grafted by co-condensation process or post-synthesis) are thermally stable in aqueous medium. In what regards the degree of loading and efficiency of loading with the therapeutic agent, there has been noticed an increase of around 10% in case of co-condensation method application. This result shows that direct co-condensation leads to even distribution of amino groups on the pore walls while in case of post-synthesis grafting many amino groups are concentrated near the pore opening and/or on external surface. In vitro dissolution tests showed an extended carmustine release (more than 86% m/m) both from systems based on silica functionalized directly by co-condensation and after synthesis. Assessment of carmustine release kinetics revealed a release through diffusion from all studied systems as a result of fitting to Higuchi model. The results of this study proved that amino-functionalized mesoporous silica may be used as a matrix for optimizing the anti-cancer topical therapy by loading carmustine and developing prolonged-release systems.

Keywords: carmustine, silica, controlled, release

Procedia PDF Downloads 232

Authors: N. Tadayon, H. Yousefnia, S. Zolghadri, A. Ramazani, A. R. Jalilian

Abstract:

In this study, 68Ga-PDTMP was prepared as a new agent for bone imaging. 68Ga was obtained from SnO2 based generator. A certain volume of the PDTMP solution was added to the vial containing 68GaCl3 and the pH of the mixture was adjusted to 4 using HEPES. Radiochemical purity of the radiolabelled complex was checked by thin layer chromatography. Biodistribution of this new agent was assessed in rats after intravenously injection of the complex. For this purpose, the rats were killed at specified times after injection and the weight and activity of each organ was measured. Injected dose per gram was calculated by dividing the activity of each organ to the total injected activity and the mass of each organ. As expected the most of the activity was accumulated in the bone tissue. The radiolabelled compound was extracted from blood very fast. This new bone-seeking complex can be considered as a good candidate of PET-based radiopharmaceutical for imaging of bone metastases.

Keywords: biodistribution, Ga-68, imaging, PDTMP

Procedia PDF Downloads 334

Authors: Taylan Kabbani, Ekrem Duman

Abstract:

The design of adaptive systems that take advantage of financial markets while reducing the risk can bring more stagnant wealth into the global market. However, most efforts made to generate successful deals in trading financial assets rely on Supervised Learning (SL), which suffered from various limitations. Deep Reinforcement Learning (DRL) offers to solve these drawbacks of SL approaches by combining the financial assets price "prediction" step and the "allocation" step of the portfolio in one unified process to produce fully autonomous systems capable of interacting with its environment to make optimal decisions through trial and error. In this paper, a continuous action space approach is adopted to give the trading agent the ability to gradually adjust the portfolio's positions with each time step (dynamically re-allocate investments), resulting in better agent-environment interaction and faster convergence of the learning process. In addition, the approach supports the managing of a portfolio with several assets instead of a single one. This work represents a novel DRL model to generate profitable trades in the stock market, effectively overcoming the limitations of supervised learning approaches. We formulate the trading problem, or what is referred to as The Agent Environment as Partially observed Markov Decision Process (POMDP) model, considering the constraints imposed by the stock market, such as liquidity and transaction costs. More specifically, we design an environment that simulates the real-world trading process by augmenting the state representation with ten different technical indicators and sentiment analysis of news articles for each stock. We then solve the formulated POMDP problem using the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm, which can learn policies in high-dimensional and continuous action spaces like those typically found in the stock market environment. From the point of view of stock market forecasting and the intelligent decision-making mechanism, this paper demonstrates the superiority of deep reinforcement learning in financial markets over other types of machine learning such as supervised learning and proves its credibility and advantages of strategic decision-making.

Keywords: the stock market, deep reinforcement learning, MDP, twin delayed deep deterministic policy gradient, sentiment analysis, technical indicators, autonomous agent

Procedia PDF Downloads 155

Authors: A. E. Delgado, W. Aperador

Abstract:

This study evaluated the incidence of concentrated natural fibre, as well as the effects of adding a crosslinking agent on the torque when those components are mixed with low density polyethylene (LDPE). The natural fibre has a particle size of between 0.8-1.2mm and a moisture content of 0.17%. An internal mixer was used to measure the torque required to mix the polymer with the fibre. The effect of the fibre content and crosslinking agent on the torque was also determined. A change was observed in the morphology of the mixes using SEM differential scanning microscopy.

Keywords: WPC, DCP, LDPE, natural fibre, torque

Procedia PDF Downloads 394

Authors: Meng-Hui Chen, Chiao-Wei Yu, Pei-Chann Chang

Abstract:

Imperial competitive algorithm (ICA) simulates a multi-agent algorithm. Each agent is like a kingdom has its country, and the strongest country in each agent is called imperialist, others are colony. Countries are competitive with imperialist which in the same kingdom by evolving. So this country will move in the search space to find better solutions with higher fitness to be a new imperialist. The main idea in this paper is using the peculiarity of ICA to explore the search space to solve the kinds of combinational problems. Otherwise, we also study to use the greed search to increase the local search ability. To verify the proposed algorithm in this paper, the experimental results of traveling salesman problem (TSP) is according to the traveling salesman problem library (TSPLIB). The results show that the proposed algorithm has higher performance than the other known methods.

Keywords: traveling salesman problem, artificial chromosomes, greedy search, imperial competitive algorithm

Procedia PDF Downloads 434

Authors: Abdelhadi Adel, Kadri Ouahab

Abstract:

This paper proposes an improved approach based on MAS Architecture and Heuristic Algorithm for systematic maintenance to minimize makespan. We have implemented a problem-solving approach for optimizing the processing time, methods based on metaheuristics. The proposed approach is inspired by the behavior of the human body. This hybridization is between a multi-agent system and inspirations of the human body, especially genetics. The effectiveness of our approach has been demonstrated repeatedly in this paper. To solve such a complex problem, we proposed an approach which we have used advanced operators such as uniform crossover set and single point mutation. The proposed approach is applied to three preventive maintenance policies. These policies are intended to maximize the availability or to maintain a minimum level of reliability during the production chain. The results show that our algorithm outperforms existing algorithms. We assumed that the machines might be unavailable periodically during the production scheduling.

Keywords: multi-agent systems, emergence, genetic algorithm, makespan, systematic maintenance, scheduling, hybrid flow shop scheduling

Procedia PDF Downloads 269

Authors: Sun Shi, Sun Cheng

Abstract:

The pedestrian corridor is the most crowded area in the public space. The crowded severity has been focused on the field of evacuation strategies of the entrance in large public spaces. The aim of this paper is to analyze the walking efficiency in different spaces of pedestrian corridor with the variation of spatial parameters. The congestion condition caused by the variation of walking efficiency is modeled as well. This study established the space model of the walking corridor by setting the width, slope, turning form and turning angle of the pedestrian corridor. The pedestrian preference of walking mode varied with the difference of the crowded severity, walking speed, field of vision, sight direction and the expected destination, which is influenced by the characters of physical space form. Swarm software is applied to build Agent model. According to the output of the Agent model, the relationship between the pedestrian corridor width, ground slope, turning forms, turning angle and the walking efficiency, crowded severity is acquired. The results of the simulation can be applied to pedestrian corridor design in order to reduce the crowded severity and the potential safety risks caused by crowded people.

Keywords: crowded severity, multi-agent, pedestrian preference, urban space design

Procedia PDF Downloads 192

Authors: Sang Hun Park, Moung Young Lee, Su Min Yu, Hyun Sang Jo, Ji Hyeon Kim, Chul Gyu Song

Abstract:

A near-infrared light source used as a light source in the fluorescence imaging system is suitable for use in real-time during the operation since it has no interference in surgical vision. However, fluorescence images do not have depth information. In this paper, we configured the device with the research on molecular imaging systems for monitoring thrombus imaging using fluorescence and photoacoustic. Fluorescence imaging was performed using a phantom experiment in order to search the exact location, and the Photoacoustic image was in order to detect the depth. Fluorescence image obtained when evaluated through current phantom experiments when the concentration of the contrast agent is 25μg / ml, it was confirmed that it looked sharper. The phantom experiment is has shown the possibility with the fluorescence image and photoacoustic image using an indocyanine green contrast agent. For early diagnosis of cardiovascular diseases, more active research with the fusion of different molecular imaging devices is required.

Keywords: fluorescence, photoacoustic, indocyanine green, carotid artery

Procedia PDF Downloads 574

Authors: You-Lin Wu, Zong-Xian Wu, Jing-Jenn Lin, Shih-Hung Lin

Abstract:

In this work, a polysilicon wire (PSW) coated with a mixture of 3-aminopropyltriethoxysilane (r-APTES) and Al2O3 nanoparticles as the sensing membrane prepared with various Al2O3/r-APTES and dispersing agent/r-APTES ratios for pH sensing is studied. The r-APTES and dispersed Al2O3 nanoparticles mixture was directly transferred to PSW surface by solution phase deposition (SPD). It is found that using a mixture of Al2O3 nanoparticles and r-APTES as the sensing membrane help in improving the pH sensing of the PSW sensor and a 5 min SPD deposition time is the best. Dispersing agent is found to be necessary for better pH sensing when preparing the mixture of Al2O3 nanoparticles and r-APTES. The optimum condition for preparing the mixture is found to be Al2O3/r-APTES ratio of 2% and dispersing agent/r-APTES ratio of 0.3%.

Keywords: al2o3 nanoparticles, ph sensing, polysilicon wire sensor, r-aptes

Procedia PDF Downloads 391

Authors: Yulin Rao, Zhixuan Li, Burra Venkata Durga Kumar

Abstract:

Intrusion detection refers to monitoring the actions of internal and external intruders on the system and detecting the behaviours that violate security policies in real-time. In intrusion detection, there has been much discussion about the application of neural network technology and artificial immune system (AIS). However, many solutions use static methods (signature-based and stateful protocol analysis) or centralized intrusion detection systems (CIDS), which are unsuitable for real-time intrusion detection systems that need to process large amounts of data and detect unknown intrusions. This article proposes a framework for a distributed intrusion detection system (DIDS) with multi-agents based on the concept of AIS and neural network technology to detect anomalies and intrusions. In this framework, multiple agents are assigned to each host and work together, improving the system's detection efficiency and robustness. The trainer agent in the central server of the framework uses the artificial neural network (ANN) rather than the negative selection algorithm of AIS to generate mature detectors. Mature detectors can distinguish between self-files and non-self-files after learning. Our analyzer agents use genetic algorithms to generate memory cell detectors. This kind of detector will effectively reduce false positive and false negative errors and act quickly on known intrusions.

Keywords: artificial immune system, distributed artificial intelligence, multi-agent, intrusion detection system, neural network

Procedia PDF Downloads 84