Fusion Agent Research Articles

Collaborative Damage Detection Framework for Rail Structures Based on a Multi-Agent System Embedded with Soft Multi-Functional Sensors.

With the rapid growth of railways in China, the focus has changed to the maintenance of large-scale rail structures. Multi-agent systems (MASs) based on wireless sensor network (WSNs) with soft multi-functional sensors (SMFS) are adopted cooperatively for the structural health monitoring of large-scale rail structures. An MAS framework with three layers, namely the sensing data acquisition layer, sensor data processing layer, and application layer, is built here for collaborative data collection and processing for a rail structure. WSN nodes with strain, temperature, and piezoelectric sensor units are developed for the continuous structural health monitoring of the rail structure. The feature data at different levels are extracted for the online monitoring of the rail structure. Experiments carried out at the Rail Transmit Base at East China Jiaotong University verify that the WSN nodes with SMFS are successfully assembled onto a 100-m-long track for damage detection. Based on the sensing data and feature data, a neural network data fusion agent (DFA) is applied to calculate the damage index value of the track for comprehensive decisions regarding rail damage. The use of WSNs with multi-functional sensors and intelligent algorithms is recommended for cooperative structural health monitoring in railways.

Nano-Carbon-Based Application of Parecoxib Sodium Combined with Hydromorphone in Preventing Anesthesia Hyperalgesia Caused by Remifentanil after Thyroidectomy.

Nano-carbon is often used as a tracer in thyroidectomy, to improve the accuracy of the operation. Remifentanil is the most commonly used anesthetic during thyroidectomy, but the use of remifentanil can sometimes cause patients with anesthesia hyperalgesia. Therefore, auxiliary anesthetics are often used in surgery to prevent remifentanil from causing anesthesia hyperalgesia. The purpose of this article is to explore the specific application effect of the fusion agent of hydromorphone and parecoxib sodium after thyroidectomy based on nano-carbon in the prevention of remifentanil-induced anesthesia hyperalgesia. Taking 60 patients who underwent thyroidectomy based on carbon nanotechnology in our hospital as the research object, the patients were divided into the parecoxib sodium group, hydromorphone control group and hydromorphone and parecoxib sodium fusion agent group. All patients were injected with remifentanil before surgery for general paralysis. Ten minutes before the end of the operation, the parecoxib sodium group was injected with quantitative parecoxib sodium, and the hydromorphone control group was injected with quantitative hydromorphone, hydromorphone and the parecoxib sodium fusion medicament group was injected with a quantitative combination of parecoxib sodium and hydromorphone. The patient's comfort, calmness, pain, adverse reactions and recovery time of consciousness were counted. The results of the study showed that the sedation score of the hydromorphone and parecoxib sodium fusion drug group was (15.8±1.5), the pain degree score was (1.9±0.5), lower than the other two groups, and the postoperative recovery time was (38±5.0) )min, lower than the other two groups. It can be seen that the use of a fusion agent of hydromorphone and parecoxib sodium after thyroidectomy based on nano-carbon is effective in preventing and reducing remifentanil-induced anesthesia hyperalgesia.

Slopping index for LD converters based on sound and image data fusion by fuzzy Kalman filter

ABSTRACT The LD (Linz Donawitz) steelmaking process is the most used in the steel industry due to its high-volume capacity and low cost per ton of steel produced. However, the basic oxygen steelmaking process in LD converters is subjected to potential steel charge overflows, often called ‘slopping’. Besides yield losses, slopping events can damage the environment and expose employees to danger. More than ever, steelmaking plants need to avoid this type of event to keep producing as environmental impacts are no more tolerable by society. Steelmaking plants already use different methods to monitor and detect slopping events, but they are often limited and unreliable. Therefore, this paper proposes a multi-sensor data fusion process to generate a reliable slopping index to warn operators of potential slopping events and detect the triggered ones. The work is based on sound and image data (67 heats with 27 slopping events) collected on previous trials at a 350-ton LD converter. The Kalman filter was applied as a data fusion agent of two indexes, one resulted from computer vision analysis of the LD converter mouth (image data), the other resulted from digital signal analysis of sound captured on the converter’s hood (sound data). Fuzzy sets were applied for adaptative tuning of the Kalman filter to improve the data fusion process. Besides the increase of alarm accuracy and heat classification, the data fusion index worked better on different scenarios and produced a more reliable indicator for a slopping prevention system.

Effects of the combination therapy of electric field stimulation and polyethylene glycol in the ex vivo spinal cord of female rats after compression.

The application of electric field stimulation (EFS) can reduce the cation influx after spinal cord injury. However, regenerated cation influx and reestablished injury potential are observed after EFS. Polyethylene glycol (PEG) is popular as an effective cell membrane fusion agent. This study aims to determine the effects of the combination therapy of EFS and PEG in the ex vivo spinal cord after compression. The ex vivo spinal cords of female rats with compression injury were incubated in a double sucrose gap recording chamber (DSGRC) and randomly divided into the following four groups: (1) compression group: compression only, (2) EFS group: EFS for 15min, (3) PEG group: PEG treatment for 4min, and (4) EFS+PEG group: EFS for 15min and PEG treatment for 4min. The hematoxylin-eosin staining was performed to measure the necrotic area of the spinal cords. The gap potential was detected, and the area under the curve of the gap potential was calculated. The intracellular cation concentration, membrane permeability, and compound action potential were measured and quantified. Results revealed no significant difference in the necrotic areas among different groups, and the compression model of the ex vivo spinal cord in the DSGRC had high consistency and stability. The combination therapy could attenuate cation inflow, promote cell membrane restoration, and promote the functional recovery of the spinal cord conduction after compression in ex vivo spinal cords.

Decision Making in Star Networks With Incorrect Beliefs

Consider a Bayesian binary decision-making problem in star networks, where local agents make selfish decisions independently, and a fusion agent makes a final decision based on aggregated decisions and its own private signal. In particular, we assume all agents have private beliefs for the true prior probability, based on which they perform Bayesian decision making. We focus on the Bayes risk of the fusion agent and counterintuitively find that incorrect beliefs could achieve a smaller risk than that when agents know the true prior. It is of independent interest for sociotechnical system design that the optimal beliefs of local agents resemble human probability reweighting models from cumulative prospect theory. We also consider asymptotic characterization of the optimal beliefs and fusion agent's risk in the number of local agents. We find that the optimal risk of the fusion agent converges to zero exponentially fast as the number of local agents grows. Furthermore, having an identical constant belief is asymptotically optimal in the sense of the risk exponent. For additive Gaussian noise, the optimal belief turns out to be a simple function of only error costs and the risk exponent can be explicitly characterized.

Magnetic Nanoparticle and Exosomal Therapeutic (M-NEXT) Effects on HIV-Associated Neurotoxicity.

The human immunodeficiency virus (HIV) envelope glycoprotein protein 120 (gp120) induces neurotoxicity associated with HIV-associated neurocognitive disorders (HAND). Mechanism of Gp120-mediated neurotoxicity is primarily apoptosis. Currently, there are no therapeutics that address gp120 neurotoxicity. A biocompatible, efficacious therapeutic that easily crosses the blood-brain barrier (BBB) is needed to treat neuronal toxicity observed in HIV-infected individuals. Magnetic nanoparticles (MNPs) have successfully delivered anti-HIV agents across in vitro BBB transwell model. However, MNPs at high doses may damage cells. Exosomal extracellular vesicles (xEVs) are endogenous nanocarriers capable of crossing the BBB. Unlike MNPs, xEVs interact with cells in a paracrine or juxtracrine manner, lacking long-range site specificity. Here we investigated the efficacy of an MNP and xEV-coupled therapeutic (M-NEXT) as a nanocarrier for targeted delivery of anti-HIV fusion agent across the BBB to inhibit HIV-gp120 associated neuropathology. M-NEXT consisting of MNPs encapsulated within xEV carrying T20 peptide on the surface was synthesized and characterized via zeta potential, dynamic light scattering, and TEM imaging. Preliminary efficacy studies using SH-SY5Y cocultured with the in vitro BBB model showed that the M-NEXT-T20-fusion peptide protected neurons from HIV gp120-mediated neurotoxicity. Additionally, BBB integrity and permeability assessed via trans-endothelial resistance (TEER) and a Dextran-FITC transport assay was unaffected. SH-SY5Y viability measured by XTT assay was not significantly modulated by M-NEXT. In summary, preliminary findings support M-NEXT as effective nanocarriers for delivery of anti-HIV gp120 associated neurotoxicity agents.

Comparison of decomposition techniques for solid samples with emphasis on actinide content determination

Comparison of conventional acid digestion with mixtures of acids HNO3, HClO4, and HF and thermal fusion utilizing Li borate as a fusion agent was made for solid samples. In the study, various parameters such as amount of the sample taken for the analysis, as well as addition of tracers before and after dissolution procedures were investigated. The obtained results showed that dissolution without any residue was achieved only when the fusion method was used. Thus, no filtration was needed prior to the loading of the sample on the resin to perform radiochemical separation. Alpha-particle spectrometry and neutron activation analysis were used for determination of the actinides content in the investigated samples as well as in residues obtained after dissolution.

Differences in 30- and 90-Day Readmission Rates After Surgical Treatment for Lumbar Degenerative Disc Disease in Elderly Patients (³ð65 Years): A National Readmission Database Study

Abstract INTRODUCTION For spine surgery performed for degenerative disc disease (DDD), a paucity of nationwide studies exists describing common complications and readmission rates. The aim of this study was to investigate the differences and complications associated with 30- and 90-d readmissions following surgical treatment for lumbar DDD in the elderly. METHODS The Nationwide Readmission Database years 2013 to 2015 was queried. Elderly patients (>65 yr old) undergoing anterior lumbar interbody fusion (ALIF), posterior lumbar fusion (PLIF)/posterolateral lumbar fusion (PLF), or anterior and posterior lumbar fusion (APLF) for lumbar DDD were identified. Unique patient linkage numbers were used to follow patients and identify 30- and 31 to 90-d readmission rates. Patients were grouped by no readmission (Non-R), readmission within 30 d (30-R), and readmission within 31 to 90 d (90-R). RESULTS We identified 11 651 elderly patients undergoing ALIF, PLIF/PLF, or APLF for lumbar DDD, with 1213 (10.4%) patients encountering a readmission (30-R: n = 812[7.0%]; 90-R: n = 401[3.4%]; Non-R: n = 10 438). The greatest proportion of each cohort had 2 to 3 vertebral levels fused (30-R: 63.7%, 90-R: 69.2%, Non-R: 70.2%). Iliac crest bone graft was the most common fusion agent used (30-R: 59.9%, 90-R: 51.4%, Non-R: 53.5%), followed by bone morphogenetic protein (30-R: 24.6%, 90-R: 22.9%, Non-R: 21.2%). The most common inpatient complications observed were acute posthemorrhagic anemia (30-R: 26.6%, 90-R: 22.3%, Non-R: 18.2%), postoperative infection (30-R: 6.2%, 90-R: 9.7%, Non-R: 3.5%), and genitourinary complication (30-R: 7.7%, 90-R: 2.7%, Non-R: 3.5%). The most prevalent 30- and 90-d complications seen among the readmitted cohort were postoperative infection (30-R: 18.7%, 90-R: 8.9%), device complications (30-R: 5.2%, 90-R: 9.1%), and sepsis (30-R: 6.9%, 90-R: 4.9%). On multivariate regression analysis, obesity, chronic pulmonary disease, smoking, and any complication during index admission were independently associated with 30-d readmission; private insurance and coagulopathy were independently associated with 90-d readmission. CONCLUSION Our study suggests that 30- and 90-d readmissions for treatment of lumbar DDD in the elderly are common, and that multiple patient-level factors independently predict hospital readmission.

Transfer of Synthetic Human Chromosome into Human Induced Pluripotent Stem Cells for Biomedical Applications.

AlphoidtetO-type human artificial chromosome (HAC) has been recently synthetized as a novel class of gene delivery vectors for induced pluripotent stem cell (iPSC)-based tissue replacement therapeutic approach. This HAC vector was designed to deliver copies of genes into patients with genetic diseases caused by the loss of a particular gene function. The alphoidtetO-HAC vector has been successfully transferred into murine embryonic stem cells (ESCs) and maintained stably as an independent chromosome during the proliferation and differentiation of these cells. Human ESCs and iPSCs have significant differences in culturing conditions and pluripotency state in comparison with the murine naïve-type ESCs and iPSCs. To date, transferring alphoidtetO-HAC vector into human iPSCs (hiPSCs) remains a challenging task. In this study, we performed the microcell-mediated chromosome transfer (MMCT) of alphoidtetO-HAC expressing the green fluorescent protein into newly generated hiPSCs. We used a recently modified MMCT method that employs an envelope protein of amphotropic murine leukemia virus as a targeting cell fusion agent. Our data provide evidence that a totally artificial vector, alphoidtetO-HAC, can be transferred and maintained in human iPSCs as an independent autonomous chromosome without affecting pluripotent properties of the cells. These data also open new perspectives for implementing alphoidtetO-HAC as a gene therapy tool in future biomedical applications.

The application of microwave digestion in decomposing some refractory ore samples with solid fusion agent

It is known that most of the refractory ore are the basis of national economy and widely applied in various fields, however, the complexity of the chemical composition and the diversity of the crystallinity in the mineral phases make the sample pre-treatment of refractory ore still remains a challenge. In this work, the complete decomposition of the refractory ore sample can be achieved just by exposing the solid fusion agent and the refractory ore sample in the microwave irradiation environment for a few minutes, and induced by a drop of water. A digestion time of 15 min for 3.0 g solid fusion agent mixture of sodium peroxide/sodium carbonate (Na2O2/Na2CO3) in a corundum crucible via microwave heating is sufficient to decompose 0.1 g refractory ore sample. An excellent microwave digestion solid agent should meet the following conditions, a good decomposition ability, an outstanding ability of absorbing microwave energy and converting it into heat quickly, a higher melting point than the decomposing temperature of the ore sample. In the research, the induction effect of water plays an important role for the microwave digestion. The energy which is released by the reaction of water and the solid fusion agent (Na2O2) is the key to decompose refractory ore samples with solid fusion agent, which replenished the total energy required for the microwave digestion and made the microwave digestion completed successfully. This microwave digestion technique has good reproducibility and precision, RSD % for Mo, Fe, Ti, Cr and W in the refractory ore samples were all better than 6, except RSD % for Be of about 8 because of the influence of matrix-effect. Meanwhile, the analysis results of the elements in the refractory ore samples provided by the microwave digestion technique were all in good agreement with the analysis results provided by the traditional fusion method except for Cr in the mixture ore samples. In the study, the non-linear dependence of the electromagnetic and thermal properties of the solid fusion agent on temperature under microwave irradiation and the selective heating of microwave are fully applied in this simple microwave technique. Comparing to the traditional fusion decomposition method, this microwave digestion technique is a simple, economical, fast and energy-saving sample pre-treatment technique.

Immediate Enhancement of Nerve Function Using a Novel Axonal Fusion Device After Neurotmesis.

BackgroundThe management of peripheral nerve injuries remains a large challenge for plastic surgeons. With the inability to fuse axonal endings, results after microsurgical nerve repair have been inconsistent. Our current nerve repair strategies rely upon the slow and lengthy process of axonal regeneration (~1 mm/d). Polyethylene glycol (PEG) has been investigated as a potential axonal fusion agent; however, the percentage of axonal fusion has been inconsistent. The purpose of this study was to identify a PEG delivery device to standardize outcomes after attempted axonal fusion with PEG.Materials and MethodsWe used a rat sciatic nerve injury model in which we completely transected and repaired the left sciatic nerve to evaluate the efficacy of PEG fusion over a span of 12 weeks. In addition, we evaluated the effectiveness of a delivery device's ability to optimize results after PEG fusion.ResultsWe found that PEG rapidly (within minutes) restores axonal continuity as assessed by electrophysiology, fluorescent retrograde tracer, and diffusion tensor imaging. Immunohistochemical analysis shows that motor axon counts are significantly increased at 1 week, 4 weeks, and 12 weeks postoperatively in PEG-treated animals. Furthermore, PEG restored behavioral functions up to 50% compared with animals that received the criterion standard epineurial repair (control animals).ConclusionsThe ability of PEG to rapidly restore nerve function after neurotmesis could have vast implications on the clinical management of traumatic injuries to peripheral nerves.

Lead recovery from waste CRT funnel glass by high-temperature melting process

In this research, a novel and effective process for waste CRT funnel glass treatment was developed. The key to this process is removal of lead from the CRT funnel glass by high-temperature melting process. Sodium carbonate powder was used as a fusion agent, sodium sulfide serves as a catalytic agent and carbon powder acts as reducing agent. Experimental results showed that lead recovery rate increased with an increase in the amount of added sodium carbonate, sodium sulfide, carbonate, temperature and holding time initially, and then reached a stable value. The maximum lead recovery rate was approximately 94%, when the optimum adding amount of sodium carbonate, sodium sulfide, carbonate, temperature and holding time were 25%, 8%, 3.6%, 1200°C and 120min, respectively. In the high-temperature melting process, lead silicate in the funnel glass was firstly reduced, and then removed. The glass slag can be made into sodium and potassium silicate by hydrolysis process. This study proposed a practical and economical process for recovery of lead and utilization of waste glass slag.

The debut of all-boron fullerene

Boron is the fifth element and next to carbon in the periodic table of the elements, but boron has been researched less than its neighbor carbon. Borax sourced from a natural boronrich mine in Yamdrok Lake, Tibet, China, has been used as a fusion agent to make glass from ancient times. Elemental boron, however, was elusive until 1808 when it was prepared from electrolysis of melted boron trioxide or by reducing boric acid with potassium. Structures of elemental boron include an icosahedral (Ih) B12 motif connected in an ordered manner, as exemplified by α-rhombohedral boron (Fig. 1a). The dangling bonds in each Ih-B12 unit can be saturated by hydrogen to produce borane species. In stark contrast to the ubiquitous Ih-B12 unit in elemental boron allotropes and boranes, a different B12 all-boron clusterwith aC3v-symmetric planar structure that resembles a solid disk with three boron atoms in the center surrounded by a peripheral ring of boron atoms has also been observed (Fig. 1b) [1]. With six delocalized π electrons that exhibit ‘disk delocalization’, the planar B12 cluster is analogous to benzene with its wellknown cyclic delocalization. Bn clusters adopt 2D planar or quasi-planar structures even up to n = 36 [2]. Because of their diverse set of structural and bonding characteristics, scientists believe that boron and carbon form a set of complementary chemical systems and have long been fascinated with whether or not structures such as cage-like all-boron clusters are as prevalent as all-carbon fullerenes. A series of all-boron cage configurations stabilized by three-center Figure 1. The structures of all-boron clusters (B12 and B40). (a) Icosahedral B12 motifs bound by threecenter two-electronσ bonds (indicated by dashed lines) to form a B12 layer inα-rhombohedral boron; (b) Top and side views of a C3v-symmetric B12 cluster; (c) Top and side views of Cs-symmetric B40 with two adjacent hexagonal holes; (d) Top and side views of a neutral B40 cluster with two hexagonal and four heptagonal holes. This figure was redrawn according to the coordinates of a B40 cluster provided in the supplementary information of [5].

Modeling Extenics Innovation Software by Intelligent Service Components

Independent innovation is the core of the national development strategy. After twenty years, Extenics made great progress in innovation theory, formal method and real application. Developing and manufacturing innovation software to help people develop intelligence, inspire creation is key for Extenics further developing. Now software model cannot meet the requirements of flexible alternate in innovation activities. To address this challenge, we propose to fusion agent, service and component for building autonomy, dynamic evolved, intelligent accumulated, great granularity intelligent service component (ISC), provide the good software entity for realization extension flexible thought. We try to expand extensible analysis, extension transformation, extension evaluation, dependent function and so on to services, according to extension innovation method dynamic integrate them into extension intelligent service system (EISS), finally establish a wise extension innovation software model. For software modeling provides a new way.

Computer Vision Architecture using Fusion Technique

Humans want to communicate with the computers in the same way as they communicate with other humans. Speech is the most natural and spontaneous form of communication. Speech is bimodal in nature and it combines audio and visual information to enhance speech recognition rate especially under poor audio conditions. This paper proposes novel computer vision architecture using fusion technique. This architecture combines or fuses more than one modality using multi-agents. In this we have used two modalities- audio and video. The audio part extracts the speech of a person and the video part extracts the face and lip information of the person. Here, different agents process the modalities and the fusion agent fuses these modalities for effective and efficient automatic speech recognition.

Portfolio of Automated Trading Systems: Complexity and Learning Set Size Issues

In this paper, we consider using profit/loss histories of multiple automated trading systems (ATSs) as N input variables in portfolio management. By means of multivariate statistical analysis and simulation studies, we analyze the influences of sample size (L) and input dimensionality on the accuracy of determining the portfolio weights. We find that degradation in portfolio performance due to inexact estimation of N means and N(N - 1)/2 correlations is proportional to N/L; however, estimation of N variances does not worsen the result. To reduce unhelpful sample size/dimensionality effects, we perform a clustering of N time series and split them into a small number of blocks. Each block is composed of mutually correlated ATSs. It generates an expert trading agent based on a nontrainable 1/N portfolio rule. To increase the diversity of the expert agents, we use training sets of different lengths for clustering. In the output of the portfolio management system, the regularized mean-variance framework-based fusion agent is developed in each walk-forward step of an out-of-sample portfolio validation experiment. Experiments with the real financial data (2003-2012) confirm the effectiveness of the suggested approach.

Development of monoclonal antibodies against bovine herpesvirus-1 (BHV-1)

The BHV-1 antigen was produced in bulk by propagating BHV-1 in Madin Darby bovine kidney cell line. The antigen purified by 20–40% sucrose density gradient centrifugation was confirmed for presence of virus. The BALB/C mice were immunized by purified virus via intraperitoneal route. The spleenic lymphocytes from immunized mice were fused with myeloma cells using polyethylene glycol as a fusion agent and suspended in HAT (hypoxanthine aminopterin thymidine) medium for differentiation of hybrids. A total of 11 clones were observed, out of which 7 were positive for antibody production. The supernatant of all the positive clones showed very low concentration of antibody, except the clone B6.1, where the concentration of antibody was higher than other positive clones. The culture supernatant of B6.1 hybrid clone was isotyped by enzyme linked immunosorbent assay (ELISA) based isotyping kit and isotype of monoclonal antibody was of IgM class. In western blotting, the IgM monoclonal antibody identified the 27 KD protein of BHV-1.

Outsmarting Cutaneous T-Cell Lymphoma Cells by Decoding the Language They Speak: Focusing Past and Present Insights on Future Prospects

Since the term “Cutaneous T Cell Lymphoma” (CTCL) was introduced in 1974, investigation of the biology of the malignant T cells has contributed heavily to understanding of the clinically important biology of benign and neoplastic T cells. Availability of large numbers of clonal skin-homing CTCL cells facilitated the discovery of T cell-specific monoclonal antibodies and identification of “helper-T cells.” Tight linkage between the biology and clinical manifestations of CTCL cells has enabled major, and accelerating, scientific and practical advances. CTCL cells are now well defined by their distinctive features: membrane molecules which direct them to the skin; growth dependency on signaling from immature dendritic antigen presenting cells; origin from the large set of normal “cutaneous T cells” which recirculate between skin and blood; differentiation markers controlling the way they interact with antigen presenting cells, maintain memory for their cognate antigen and regulate normal T cells (CD4/CD45Ro/Treg); secretion of a Th2 set of cytokines; and surface expression of clinically targetable tumor distinctive antigens. CTCL provided the point of entry for now widely used biologically-based therapies: anti-lymphocyte antibodies to treat malignancies; cellular immunotherapy for cancer (Extracorporeal Photochemotherapy); IL2-diphtheria toxin fusion agent (Ontac); anti-cancer retinoid (Targretin); and anti-cancer inhibitors of histone deacetylase. On this rich foundation, we are now poised to resolve a next set of major questions. What are the skin-localized antigens that stimulate memory “cutaneous T cells” to clonally expand, prior to their malignant transformation? How can we best exploit the critical growth requirements and antigenicity of CTCL cells to develop even better therapies? Can we ultimately outsmart CTCL cells by interrupting their capacity to receive the growth stimulatory signals that they require to grow and spread?

BUGS ON A BUDGET: DISTRIBUTED SENSING WITH COST FOR REPORTING AND NONREPORTING

We consider a simple model of sequential decisions made by a fusion agent that receives binary-passive reports from distributed sensors. The main result is an explicit formula for the probability of making a decision before a fixed budget is exhausted. These results depend on the relationship between a special ruin problem for a “lazy random walk” and a traditional biased walk.

Data fusion to improve trajectory tracking in a Cooperative Surveillance Multi-Agent Architecture

In this paper we present a Cooperative Surveillance Multi-Agent System (CS-MAS) architecture extended to incorporate dynamic coalition formation. We illustrate specific coalition formation using fusion skills. In this case, the fusion process is divided into two layers: (i) a global layer in the fusion center, which initializes the coalitions and (ii) a local layer within coalitions, where a local fusion agent is dynamically instantiated. There are several types of autonomous agent: surveillance–sensor agents, a fusion center agent, a local fusion agent, interface agents, record agents, planning agents, etc. Autonomous agents differ in their ability to carry out a specific surveillance task. A surveillance–sensor agent controls and manages individual sensors (usually video cameras). It has different capabilities depending on its functional complexity and limitations related to sensor-specific aspects. In the work presented here we add a new autonomous agent, called the local fusion agent, to the CS-MAS architecture, addressing specific problems of on-line sensor alignment, registration, bias removal and data fusion. The local fusion agent is dynamically created by the fusion center agent and involves several surveillance–sensor agents working in a coalition. We show how the inclusion of this new dynamic local fusion agent guarantees that, in a video-surveillance system, objects of interest are successfully tracked across the whole area, assuring continuity and seamless transitions.