2025 29th International Computer Conference, Computer Society of Iran, CSICC 2025pp. 2336-2348
One of the most important aspects of agent design in Al is the way agent acts or responds to the environment that the agent is acting upon. An effective action selection and behavioral method gives a powerful advantage in overall agent performance. We define a new method of action selection based on probability/priority models, we thereby introduce an efficient way to determine probabilities and a new priority based system which maps the human knowledge to action selec tion method. Furthermore, a behavior model is introduced to make the model more flexible. Copyright © IICAI 2005.
Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI (10823409)2005pp. 11-18
Multi-Agent systems has generated lots of excitement in recent years because of its promise as a new paradigm for conceptualizing, designing, and implementing software systems. One of the most important aspects of agent design in AI is the way agent acts or responds to the environment that the agent is acting upon. An effective action selection and behavioral method gives a powerful advantage in overall agent performance. We define a new method of action selection based on probability/priority models in RoboCup Soccer Simulation League[6] and for simulated soccer agents, we thereby introduce an efficient way to determine probabilities and a new priority based system which maps the human knowledge to action selection method. Furthermore, a behavior model is introduced to make the model more flexible. © 2005 IEEE.
Karimian, A.R.,
Thompson, C.J.,
Sarkar s., ,
Raisali g., ,
Pani r., ,
Davilu h., ,
Sardari d., Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment (01689002)545(1-2)pp. 427-435
We propose a Cylindrical Breast PET (CYBPET) system for breast imaging with patients in the prone position. An individual pendulous breast is covered by thin plastic to provide reduced pressure fixation and surrounded by the crystals inside the CYBPET ring. Each breast is imaged separately. The rest of the body is shielded properly to minimize the contribution of scattered photons from the other breast and the rest of the body. To compare the CYBPET with whole-body PET (WB-PET) the simulations of CYBPET and a WB-PET (GE-Advance) for a 10 mm tumor inside the breast with a lesion to background (breast) activity concentration of 6 to 1 were made. The noise effective count rate (NECR) of CYBPET is about twice that of WB-PET at activity concentrations less than 3.1 μCi/cc. The spatial resolution of CYBPET is better by 25% than the WB-PET. © 2005 Elsevier B.V. All rights reserved. All rights reserved.
Jalilian, A.R.,
Fateh, B.,
Ghergherehchi, M.,
Karimian, A.R.,
Moradkhani, S.,
Kamali-dehghan, M.,
Tabeie, F. Nukleonika (15085791)50(4)pp. 143-148
Bleomycin (BLM), labeled with radioisotopes, is widely used in therapy and diagnosis. In this study, BLM was labeled with 62Zn for oncologic PET studies. The complex was obtained at pH = 2 in saline at 90°C in 25 min. Radio-TLC showed an overall radiochemical yield of 95-97% (radiochemical purity > 97%). Stability of complex was checked in vitro in mice and human plasma/urine. Preliminary in vivo studies were performed to determine complex stability and distribution of 62Zn BLM in normal and fibrosarcoma-bearing mice. 62Zn BLM accumulated significantly in induced fibrosarcoma tumors in mice according to biodistribution/imaging studies. 62Zn BLM can be used in PET oncology studies due to its suitable physicochemical properties as a diagnostic complex in vitro and in vivo. Further studies should be performed for evaluation of the complex behavior in larger mammals.
Journal of Neuroscience Methods (1650270)(2)pp. 121-133
This paper describes an interactive computer program for decomposing EMG signals into their component motor-unit potential (MUP) trains and for averaging MUP waveforms. The program is able to handle single- or multi-channel signals recorded by needle or fine-wire electrodes during low and moderate levels of muscular contraction. It includes advanced algorithms for template matching, resolving superimpositions, and waveform averaging, as well as a convenient user interface for manually editing and verifying the results. The program also provides the ability to inspect the discharges of individual motor units more closely by subtracting out interfering activity from other MUP trains. Decomposition accuracy was assessed by cross-checking pairs of signals recorded by nearby electrodes during the same contraction. The results show that 100% accuracy can be achieved for MUPs with peak-to-peak amplitudes greater than 2.5 times the rms signal amplitude. Examples are presented to show how decomposition can be used to investigate motor-unit recruitment and discharge behavior, to study motor-unit architecture, and to detect action potential blocking in doubly innervated muscle fibers. © 2005 Elsevier B.V. All rights reserved.
Annals of DAAAM and Proceedings of the International DAAAM Symposium (17269679)pp. 345-346
One of the problems in middle size robot soccer, which also can be applied to scanner robots routing in unpredictable environments, is leading passing among robots that comprises choosing the best team-mate to receive the ball without any need to explicit communication among robots. In this paper we have developed an algorithm based on Perceptron neural network for this problem which determines the best passing angle based on the topological data of the play field (i.e. position of robots). With a modification to Perceptron structure and proper data presentation approach a considerable improvement in solution performance has been achieved.
Jalilian, A.R.,
Akhlaghi, M.,
Saddadi, F.,
Mirzaii, M.,
Karimian, A.R.,
Pouladi m., ,
Yari kamrani y., ,
Moradkhani, S.,
Shadanpour n., Iranian Journal Of Nuclear Medicine (20082509)14(26)
Introduction: [18F]-6-thia-14-fluoro-heptadecanoic acid 3b, a free fatty acid, has been used in myocardial PET imaging. In order to establish an automated synthesis module for routine production in the country, a study performed for optimization of the production conditions as well as making modifications. Methods: [18F] Benzyl-14-Fluoro-6-thia-heptadecanoate 2b was prepared in no-carrier-added (n.c.a) form from Benzyl-14-tosyloxy-6-thia- heptadecanoate 1 in one step at 90°C in Kryptofix2.2.2/[18F] and acetonitrile as the solvent followed by Silica column chromatography. The radiolabeled ester 2 was then hydrolyzed to yield [18F]-6-thia-14- fluoro-heptadecanoic 3b. The final solution was concentrated using C 18 SPE system and administered to normal rats for biodistribution as well as co-incidence imaging studies. Results: The synthesis took 15 min with overall radiochemical yield of 15-25% (EOS) and chemical-radiochemical purity more than 94%. Automation was performed using a two-pot synthesis. The best imaging time was shown to be 140-180 minutes post injection. Conclusions: Using this procedure a fast, reliable, automated synthesis for the cordial PET tracer, i.e. [18F]-FTHA can be obtained without HPLC purification step.
Jalilian, A.R.,
Hosseini, M.A.,
Karimian, A.R.,
Saddadi, F.,
Sadeghi m., M. Nukleonika (15085791)51(4)pp. 203-208
Thallium-201 (T1/2 = 3.04 days) in Tl+ form was converted to Tl3+ cation in presence of O3 in 6 M HCl controlled by RTLC/gel electrophoresis methods. The final evaporated activity was reacted with vancomycin (VAN) in water to yield [201Tl](III)VAN. The best results were obtained at room temperature in water after 30 min with a radiochemical yield > 99%, after mixing the reactants followed by SPE purification using Si Sep-Pak. The studies showed that thallic ion is mostly incorporated into vancomycin with a radiochemical purity of more than 98 ± 1% by RTLC. A specific activity of about 4.14 × 1010 Bq/mmol was obtained. Radiochemical purity and stability of 201Tl-VAN in the preparation and in presence of human serum was determined up to 5.5 days. Biodistribution study of 201Tl(III)-vancomycin in normal rats was performed up to 52 h.
Nuclear Medicine Review (16444345)9(2)pp. 108-113
Background: [18F]-6-thia-14-fluoro-heptadecanoic acid 3b, a free fatty acid, has been used in myocardial PET imaging. In order to establish an automated synthesis module for routine production in the country, a study was performed for optimization of the production conditions as well as making modifications. Material and Methods: [18F]Benzyl-14-Fluoro-6-thia- heptadecanoate 2b was prepared in no-carder-added (n.c.a) form from Benzyl-14-tosyloxy-6-thia-heptadecanoate 1 in one step at 90°C in Kryptofix2.2.2/[18F] with acetonitrile as the solvent followed by Silica column chromatography. The radiolabelled ester 2 was then hydrolysed to yield [18F]-6-thia-14-fluoro-heptadecanoic 3b. The final solution was concentrated using the C18 SPE system and administered to normal rats for biodistribution and co-incidence imaging studies. Results: The synthesis took 15 min with overall radiochemical yield of 15-25% (EOS) and chemical-radiochemical purity of more than 90%. Automation was performed using a two-pot synthesis. The best imaging time was shown to be 140-180 minutes post injection. Conclusions: Using this procedure a fast, reliable, automated synthesis for the cardial PET tracer, i.e. [18F]FTHA, can be obtained without an HPLC purification step. Copyright © 2006 Via Medica.
Rowshanfarzad, P.,
Jalilian, A.R.,
Kiyomarsi, M.,
Sabet, M.,
Karimian, A.R.,
Moradkhani, S.,
Mirzaii, M. Nukleonika (15085791)51(4)pp. 209-215
Rubidium-82m was prepared via 15.4 MeV proton irradiation of a krypton-82 gaseous target (30% enrichment). Washing the target chamber with hot water yielded a Rb-82m containing solution, which was further purified using short column chromatography in order to remove organic/inorganic impurities. The flowthrough was formulated in normal saline for injection. Radionuclide, radiochemical and chemical purity tests were performed prior to administration to rats for imaging (radiochemical yield: 95-97%, radiochemical purity > 97%). Preliminary dual-head coincidence studies were performed to determine the distribution of [82mRb]Rb in normal rats. For biodistribution studies, Rb-81 was injected to rats and tracer accumulation in heart, GI and bladder was determined after sacrification in time intervals. A yield of 1.3 GBq at EOB, 235.7 MBq/μAh was obtained.
Wear (00431648)260(1-2)pp. 123-127
In this research, the wear of electroless Ni-P and Ni-P-B4C composite coatings was reviewed. Auto catalytic reduction of Ni in nickel sulfate and sodium hypophosphate bath including suspended B4C particles with different concentration was used to create composite coatings with 12, 18, 25 and 33 vol.% of B4C particles. Coatings 35 μm thick were heat treated at 400 °C for one hour in an argon atmosphere and the wear resistance and friction coefficient of heat-treated samples were determined by block-on-ring tests. All wear tests were carried out at 24 °C, 35% moisture, 0.164 m/s sliding speed and about 1000 m sliding distance. Graphs show that an electroless Ni-P-B4C composite coating with 25 vol.% of B4C had the best wear resistance against a CK45 steel counterface. © 2005 Elsevier B.V. All rights reserved.
In this paper the weightlifters snatch optimization will be studied. The biomechanical model is used for two-dimensional modeling on sagittal plan. It is estimated by an error back propagation network, in a way that inputs of this network are kinematics data such as absolute angular velocity, relative angles of joints, of different body segments and output is created torque at the joints. Finally the neural network model has been optimized for minimizing the created torque at the joints.
Scientia Iranica (23453605)14(6)pp. 571-578
One of the most important challenges in automatic speech recognition is the case of mismatch between training and test data. Conventional methods for improving recognition robustness seek to eliminate or reduce the mismatch, e.g. enhancement of the speech by adapting the statistical models. Training the model in different situations is another example of these methods. The success with these techniques has been moderate compared to human performance. In this paper, an inspiration from human listeners created the motivation to develop and implement a new bidirectional neural network. This network is capable of modeling the phoneme sequence, using bidirectional connections in an isolated word recognition task. This network can correct the phoneme sequence obtained from the acoustic model to what is learned in the training phase. Acoustic feature vectors are enhanced, based on the inversion techniques in neural networks, by cascading the lexical and the acoustic model. Speech enhancement by this method has a remarkable effect in eliminating mismatch between the training and test data. The efficiency of the lexical model and speech enhancement was observed by a 17.3 percent increase in the phoneme recognition correction ratio. © Sharif University of Technology, December 2007.
International Journal of Advanced Robotic Systems (17298806)4(1)pp. 93-101
Multi-Agent systems have generated lots of excitement in recent years because of its promise as a new paradigm for conceptualizing, designing, and implementing software systems. One of the most important aspects of agent design in AI is the way agent acts or responds to the environment that the agent is acting upon. An effective action selection and behavioral method gives a powerful advantage in overall agent performance. We define a new method of action selection based on probability/priority models, we thereby introduce two efficient ways to determine probabilities using neuro-fuzzy systems and bidirectional neural networks and a new priority based system which maps the human knowledge to the action selection method. Furthermore, a behavior model is introduced to make the model more flexible.
IFMBE Proceedings (16800737)14(1)pp. 1698-1699
The main aim of this work is the investigation of using new lanthanum bromide (LaBr3) in whole body PET scanners and compares its results with LSO and BGO crystals which are using in conventional and dedicated PET systems. Our results show that there is a gain in noise effective count rate (NECR) arising from the reduced scatter and random fractions in a LaBr3 scanner. © International Federation for Medical and Biological Engineering 2007.
Jalilian, A.R.,
Garosi, J.,
Gholami, E.,
Akhlaghi, M.,
Saddadi, F.,
Bolourinovin, F.,
Karimian, A.R. Nuclear Medicine Review (16444345)10(2)pp. 71-75
Background: Radiolabelled human recombinant insulin can be used for the imaging of insulin receptors in some tumours where FDG has natural uptake and diminishes the value of its imaging. Material and methods: Insulin was successively labelled with [67Ga]-gallium chloride after conjugation with freshly prepared cyclic DTPA-dianhydride (HPLC radiochemical purity assay > 96%) followed by biodistribution studies in normal rats, white blood cell labelling and preliminary SPECT studies. Results: In vitro studies demonstrated the retention of radiolabelled insulin receptor affinity using freshly prepared human white blood cells at different blood sugar conditions. Preliminary in vivo studies in a normal rat model was performed to determine the biodistribution of the radioimmunoconjugate at up to 44 h. SPECT images revealed high uptake of the liver. Conclusion: Radiolabelled insulin is stable enough to be used in biological studies in order to image insulin receptors in diabetic conditions as well as possible tumour imaging applications. The data was consistent with other radiolabelled insulin studies. Copyright © 2007 Via Medica.
Jalilian, A.R.,
Aboudzadeh, R.,
Akhlaghi, M.,
Shirazi, B.,
Moradkhani, S.,
Salouti, M.,
Karimian, A.R.,
Babaii, M.H.,
Raisali g., G. Journal of Labelled Compounds and Radiopharmaceuticals (03624803)50(5-6)pp. 556-557
Nukleonika (15085791)53(1)pp. 3-6
The main aim of this work is to investigate the use of new lanthanum bromide (LaBr3) in whole body PET (WB-PET) scanners and to compare the obtained results with those for BGO and LSO crystals which are currently used in conventional and dedicated PET systems. Our results show that there is a gain in noise effective count rate (NECR) arising from the reduced scatter and random fractions in a LaBr3 scanner. The spatial resolution of the WB-PET with LaBr3 is slightly worse than the LSO and BGO crystals because of its low density and effective atomic number. But our study showed the increased NECR, excellent energy resolution and low decay time of LaBr 3 which promise a significant improvement in WB-PET performances especially for narrow coincidence windows.
Yazdchi, M.,
Golibagh Mahyari A.,
Nazeri A.,
Yazdchi, M.,
Yazdchi, M.,
Yazdchi, M.,
Golibagh Mahyari A.,
Golibagh Mahyari A.,
Golibagh Mahyari A.,
Nazeri A.,
Nazeri A. 2025 29th International Computer Conference, Computer Society of Iran, CSICC 2025pp. 1071-1076
As manufacturing speed increases in the steel industry, fast and exact product inspection becomes more important. This paper deals with defect detection and classification algorithm for high-speed steel bar in coil. We enhance an acquired image by use of a special subtractive method and find the position of defect using local entropy and morphology. The extracted statistical features are then presented to a classifier. We use neural network and fuzzy inference system as a classifier and compare their results. The best accuracy, % 97.19, is obtained by the neural network. © 2008 IEEE.
The aim of this paper was to present the optimum parameters of an ankle foot Orthosis (AFO) using dashpot-spring modeling. Using kinematic and force data joints moment were determined through the calculations of inverse dynamics. In the proposed dynamic model selected muscles of shank and foot were replaced by spring-damper The generated torque in ankle could be modifided by changing the spring constant. Therefore it was possible to design a more comfortable AFO by modifying the parametes of the dashpot-spring of the model. Therefore, in this paper, the final goal was to help design AFOs which are more suitable to offset the deficiency of the lower limb muscles. © 2008 IEEE.
American Journal of Applied Sciences (discontinued) (15469239)5(9)pp. 1175-1181
This paper deals with dynamic optimization of biped locomotion. The main focus of this research is motion optimization of double support phase. The optimization problem is dealt by using Pontryagins; Maximum Principal. For motion optimization of double support phase, the closed kinematic chain has been considered to be opened at appropriate joint and the components of ground reaction forces has been applied on the tip of front leg and finally the penalty method has been used to tighten the leg to its prescribed location. The feasible sets of motion are taken into consideration by using inequality constraint to limit the joint motion. Also the components of ground reaction forces on front leg have been introduced as control variables in optimization of double support phase. The proposed technique has the ability to generate optimal free motions without specifying joint trajectories and minimized the performance criterion based on joint actuating torques. The two point boundary value problem has been solved by implementing a shooting method. This technique allows for specifying a few parameters to characterize gait pattern. The optimization process has the ability to generate a motion with a minimum of postural and kinematics data. Unlike previous research which used computational intelligent techniques for biped gait optimization, this study focuses on development of purely dynamic synthesis of biped motion during the double support phase. © 2008 Science Publications.
American Journal of Applied Sciences (discontinued) (15469239)5(12)pp. 1670-1675
In this research, an athlete's body on sagittal plane in tension phase of snatch weightlifting has been modeled in two dimensions for calculating the generated torques in joints. The error back propagation multi-layer perceptrons has been used for modeling the torque through changing the angular velocity, angular acceleration and absolute angle of each segment. Finally, the torque in joints has been minimized by particle swarm optimization technique and the power of athlete has been maximized. The method of weightlifting has been captured by high speed camera and the films have been analyzed through motion analysis software. Consequently, the required kinematic data for mathematical model of weightlifter has been produced. Unlike previous research reports, the technique of weightlifting has been modified with the aid of artificial neural network modeling to enhance athlete's power, instead of optimizing the effect of body parameters and sport facilities. In addition, this study focuses on computational intelligent techniques for optimization instead of classical methods. © 2008 Science Publications.
Jamshidi, N.,
Rostami, M.,
Najarian, S.,
Menhaj, M.B.,
Saadatnia, M.,
Firooz, S. Journal of Musculoskeletal Research (17936497)12(1)pp. 45-52
Background: This pilot study aimed to assess quantitative differences between normal and steppage gait by analyzing force plate data. Materials and Methods: We studied 25 subjects with drop foot, who were treated in the orthopedic center for drop foot brace. Twenty healthy students were included as a control group. There were no differences in the age, weight, height, and body mass index between the patients and the controls (p > 0.05). They walked at self-selected speed with a mean of 10 trials (+2) to collect their ground reaction forces data by force plate. Results: There were no significant differences between the groups in antero-posterior component of ground reaction force (p > 0.05). There was significant relationship between the time parameters in vertical and medio-lateral components of ground reaction forces (p > 0.05). We have found that the medio-lateral impulse in the patients group is negative (p > 0.05), which means instability in patients' gait. Conclusion: The result of this research reveals that the analysis of ground reaction force quantitatively describes steppage gait. The average stance time among patients is longer than control group. Further work with a larger database of subjects is required to confirm our findings. © 2009 World Scientific Publishing Company.
IFMBE Proceedings (16800737)25(2)pp. 414-416
In nuclear medicine imaging systems such as Gamma camera and SPECT, currently uses a mechanical collimator and a scintillation detector to detect distribution of gamma emitter radiopharmaceuticals. The detection technique, however, suffers from spatial resolution and sensitivity trade-off because of mechanical collimation. Compton camera principle is a suggested alternative which avoids the mentioned trade-off. Compton camera consists of one scattering detector and one absorber detector. Compton scattering of emitted photons from the source is detected in a special scattering detector which replaces the mechanical collimator. This research study simulated a Compton camera which is composed of a "Si" scattering detector (dimensions: 22.4 × 22.4 × 14 mm3) in a distance of "D" from an absorber detector (NaI(Tl), dimensions: 20 × 20 × 1 cm3). To evaluate the image quality of the designed Compton camera in different and inside the spread range of energies which uses for nuclear medicine studies, the point sources of Tc-99m (140 keV), I-131 (364.4 keV) and C-11 (511 keV) are assumed to be located in the front of the scattering detector and in the distance of "h= 10 mm" from it, and important parameters which affects on image quality, were calculated, analyzed and the best thickness for scattering detector were found. The thickness of absorber detector was assumed 10 mm which is about the thickness of detectors in SPECT systems. This study modeled the Compton camera realistically with all the details of the Compton camera such as Doppler broadening. Our results showed the spatial resolution would improve while the sensitivity would decrease by increasing the distance between scattering and absorber "D". Also the optimum "D = 20 cm" at "h=1 cm" were found. Furthermore our results showed by increasing the photo peak energy of isotope the spatial resolution and sensitivity would improve significantly. © 2009 Springer-Verlag.
IFMBE Proceedings (16800737)25(2)pp. 741-744
Brain disorders are divided into two categories: anatomic and metabolic. Since brain disorders initially appear as metabolic abnormalities and ultimately result in anatomic defects, it is necessary to analyze the metabolic along with the anatomic aspect of the brain tissue in the preliminary stages of diagnosis to greatly increase the chances of a cure. It is possible that metabolic abnormalities exist without an anatomic defect such as Alzheimer disease. The brain anatomic images may achieve from MRI and physiologic and metabolic brain data can achieve from DHC-SPECT or PET system when a radiopharmaceutical such as FDG have been injected to the patient. For fusion of the brain MRI and DHC-SPECT images obtained from individual scanners, we developed the userfriendly FMDIB software in the MATLAB environment. With the help of this software, we resolved the geometrical misalignment of the brain images and subsequently co-registered them with a 1 mm precision. This software enabled us to perform the three dimensional rendering of the image, re-slicing the image with thickness of 1 to 3 mm, slicing the two dimensional DHC-SPECT projections into an arbitrary direction. © 2009 Springer-Verlag.
Jamshidi, N.,
Rostami, M.,
Najarian, S.,
Menhaj, M.B.,
Saadatnia, M.,
Firooz, S. Singapore Medical Journal (00375675)50(4)pp. 412-417
Introduction: This paper deals with the dynamic modelling of human walking. The main focus of this research was to optimise the function of the orthosis in patients with neuropathic feet, based on the kinematics data from different categories of neuropathic patients. Methods: The patient's body on the sagittal plane was modelled for calculating the torques generated in joints. The kinematics data required for mathematical modelling of the patients were obtained from the films of patients captured by high speed camera, and then the films were analysed through a motion analysis software. An inverse dynamic model was used for estimating the spring coefficient. Results: In our dynamic model, the role of muscles was substituted by adding a spring-damper between the shank and ankle that could compensate for their weakness by designing ankle-foot orthoses based on the kinematics data obtained from the patients. The torque generated in the ankle was varied by changing the spring constant. Therefore, it was possible to decrease the torque generated in muscles which could lead to the design of more comfortable and efficient orthoses. Conclusion: In this research, unlike previous research activities, instead of studying the abnormal gait or modelling the ankle-foot orthosis separately, the function of the ankle-foot orthosis on the abnormal gait has been quantitatively improved through a correction of the torque.
Moghaddam, N.M.,
Karimian, A.R.,
Mostajaboddavati, S.M.,
Vondervoort, E.,
Sossi, V. Nukleonika (15085791)54(1)pp. 33-38
Preliminary design of a spherical brain PET (SBPET) using liquid xenon (LXe) as detector is considered in this research work. The major advantage of a spherical design is the large solid angle of acceptance which improves the sensitivity and increases signal-to-noise ratio (SNR) of the image. The use of a liquid active medium enabled us to design a spherical detector. LXe, due to the intrinsic physical properties, is an excellent liquid medium for accurate tracking of gamma rays in the relevant energy range. The performance of SBPET was evaluated by Monte Carlo simulation tools (GATE) and compared to ECAT HRRT. The numerical results showed the SBPET has a sensitivity of 1.14% and spatial resolution of ~2.7 mm FWHM which is superior to ECAT HRRT especially at high-count rates.
