فهرست مطالب mohammad soltanian

Recognition of visual events as a video analysis task has become popular in machine learning community. While the traditional approaches for detection of video events have been used for a long time, the recently evolved deep learning based methods have revolutionized this area. They have enabled event recognition systems to achieve detection rates which were not reachable by traditional approaches. Convolutional neural networks (CNNs) are among the most popular types of deep networks utilized in both imaga and video recognition tasks. They are initially made up of several convolutional layers, each of which followed by proper activation and possibly pooling layers. They often encompass one or more fully connected layers as the last layers. The favorite property of them in this work is the ability of CNNs to extract mid-level features from video frames. Actually, despite traditional approaches based on low-level visual features, the CNNs make it possible to extract higher level semantic features from the video frames. The focus of this paper is on recognition of visual events in video using CNNs. In this work, ‎image trained descriptor‎s are used to make video recognition can be done with low computational complexity. A tuned CNN is used as the frame descriptor and its fully connected layers are utilized as concept detectors. So, the featue maps of activation layers following fully connected layers act as feature vectors. These feature vectors (concept vectors) are actually the mid-level features which are a better video representation than the low level features. The obtained mid-level features can partially fill the semantic gap between low level features and high level semantics of video. The obtained descriptors from the CNNs for each video are varying length stack of feature vectors. To make the obtained descriptors organized and prepared for clasification, they must be properly encoded. The coded descriptors are then normalized and classified. The normaliztion may consist of conventional and  normalization or more advanced power-law normalization. The main purpose of normalization is to change the distribution of descriptor values in a way to make them more uniformly distributed. So, very large or very small descriptors could have a more balanced impact on recognition of events. The main novelty of this paper is that spatial and temporal information in mid-level features are employed to construct a suitable coding procedure. We use temporal information in coding of video descriptors. Such information is often ignored, resulting in reduced coding efficiency. Hence, a new coding is proposed which improves the trade-off between the computation complexity of the recognition scheme and the accuracy in identifying video events. It is also shown that the proposed coding is in the form of an optimization problem that can be solved with existing algorithms. The optimization problem is initially non-convex and not solvable with the existing methods in polynomial time. So, it is transformed to a convex form which makes it a well defined optimization problem. While there are many methods to handle these types of convex optimization problems, we chose to use a strong convex optimization library to efficiently solve the problem and obtain the video descriptors. To confirm the effectiveness of the proposed descriptor coding method, extensive experiments are done on two large public datasets: Columbia consumer video (CCV) dataset and ActivityNet dataset. Both CCV and ActivityNet are popular publically available video event recognition datasets, with standard train/test splits, which are large enough to be used as reasonable benchmarks in video recognition tasks. Compared to the best practices available in the field of detecting visual events, the proposed method provides a better model of video and a much better mean average precision, mean average recall, and F score on the test set of CCV and ActivityNet datasets. The presented method not only improves the performance in terms of accuracy, but also reduces the computational cost with respect to those of the state of the art. The experiments vividly confirm the potential of the proposed method in improving the performance of visual recognition systems, especially in supervised video event detection.

Background and Air pollution, especially in treatment centers is associated with several types of pathogenic microorganisms. In dental environment, dentists and patients are exposed to a great variety of infectious agents dispersed by aerosols and droplets produced during operative dentistry procedures. The aim of this study was to determine the density of airborne bacterial species in dental units in urban health centers in Kermanshah, Iran.
A total of 168 air samples was collected from 14 dental units via active sampling based on NIOSH 0800 standard. Relevant information, including the number of patients, temperature, relative humidity, space volume for each patient, type of dentistry service, and type of operational system were recorded. Density of total bacteria, Staphylococcus aureus, and Streptococcus pyogenes were determined as CFU/m3. Data was analyzed in SPSS® vs.16.0.
The mean density of total air bacteria was 338.54±120.43 CFU/m3 at the beginning of the day and 758.37 ±348.74 CFU/m3 during clinical activity. The mean values for density of Staphylococcus aureus and Streptococcus pyogenes increased after clinical activity. There were significant relationships between bacterial density with number of patients, space volume, and type of service.
The air bacterial density increased significantly during dental treatment in dentistry units. According to WHO standards, the air bacteriological quality of dentistry units studied were not acceptable during dentistry services, which leaves dentists and patients at risk of illnesses. Therefore, appropriate ventilation and using personal protective equipment are recommended.

Tetrachloroethylene (TCE) is a chlorinated aliphatic hydrocarbon, used in many industries. Effective and efficient treatment of industrial wastewater, containing TCE, is one of the environmental requirements. The purpose of this study was to determine the role of alkaline environments in TCE removal rate from aqueous solutions, using copper-doped pumice. This experimental study was performed, using granulated pumice stones with a mesh 4 (8.4 mm) in alkaline conditions; the samples were coated with copper. Copper-doped pumice was prepared as a bed at doses of 1, 2, and 3 g/L; the study was performed at pH ranges of 3, 7, and 11. Based on the results, copper-doped pumice showed good efficacy in TCE removal; in addition, its performance increased in alkaline conditions. Therefore, use of this stone for the treatment of wastewater, containing TCE, is effective due to its availability and low cost. Besides, it can be considered a good option, given its high efficiency in the absorption process.

Sulfate is one of the major ions in natural waters and wastewaters. The presence of sulfite is important in terms of that is converted into sulfate and sulfide in environment. Because of the high solubility and stability of these ions and consequently their health problems, removal of them from aqueous solutions is a sophisticated issue. This study was conducted aiming to evaluating the impact of electro coagulation process in the removal of highly concentrated sulfate and sulfite ions from aqueous.
This experimental study was carried out on laboratory scale using a glass tank with the volume of 500 ml and 2 aluminum electrodes. Then, the synthesized samples containing concentrations of 500 and 1,000 and 1,500 ppm sulfate and sulfite were transferred to a reservoir and the removal of ions in the retention time intervals of ,30, 60 and 90 min and voltages of 10, 20 and 30 volts were examined.
The most sulfite removal rate was 80 percent and voltage 30 and retention time of 90 minutes with concentration of 1000 mg/l. And the most sulfate removal rate was 72 percent and voltage10 and retention time of 90 min with concentration of 1500 mg/l.
The results show that the electrocoagulation technology can also be used in high concentrations by adjusting the suitable retention time, initial concentration and voltage.

The colors present in the effluent from dyeing and textile plants are one of the most dangerous sources of environmental pollution due to their toxicity and carcinogenesis. Dye removal is, therefore, necessary to prevent their discharge into the environment. A number of methods are available for dye removal from industrial effluents, among which Fenton/Ultrasonic oxidation process is an effective one due to its high efficiency in color removal. The objective of this pilot-scale experimental study was to investigate the operational parameters involved in the removal of Reactive Red 2 dye (RR2) using the Fenton/Ultrasonic process and its efficiency. Theeffects of pH, H2O2, and Fe2+ were evaluated using an ultrasonic reactor at 40 KHz with a power of 100W. Once the parameters had been optimized, the effects of temperature, mixing speed, and different dye concentrations on the Fenton/Ultrasonic process efficiency were measured. The optimal parameters of pH, hydrogen peroxide, and ferrous ion concentration in the were determined to be 3, 2, and 0.2 mmole, respectively, in 45 minutes so that a removal efficiency of 98.91% was obtained for an optimum hydrogen peroxide to ferrous ion ratio of 10. The results indicated that the Fenton process has a good performance in the removal of Reactive Red 2.

Industrialization and urbanization had a devastating impact on public health and caused an increase in health related morbidity and mortality. In fact, asthma is a chronic condition which is considered as one of the significant challenges of public health. In this study, we investigated the association of air pollution and weather conditions with excess emergency ward admissions of asthmatic patients in Kermanshah hospitals. This was an ecological study. The total number of hospital admissions to emergency wards from all related and major hospitals of Kermanshah was collected from September 2008 through August 2009. In addition, data on air pollution as well as meteorological data were collected from the Environmental Protection Agency and Meteorological Organization of Kermanshah. To determine the association between the number of hospitalization due to asthma with those parameters, Poisson regression was used. The results of Poisson regression revealed a significant association between carbon monoxide, ozone, nitrogen dioxide and temperature with emergency room visits due to asthma in Kermanshah. No associations were found for sulfur dioxide or for particulate matter. This study provides further evidence for the significant effect of monoxide carbon on asthma; and it suggests that temperature may have a role in the exacerbation of asthma. However, due to the multi-factorial nature of asthma, other factors also play a major role in the development and exacerbation of this illness.

Nitrite and nitrate are preservatives that have been used in meat products (sausages) and include carcinogenic effects. The aim of this study was determining the mount of nitrite and nitrate in different types of meat products marketed in Kermanshah. The method of study is descriptive – cross-sectional. 100 samples were taken from meat products factories (19 factories) randomly. Nitrite and nitrate level was determined by spectrophotometric method. The mean differences were analyzed using ANOVA and T. Test methods. Level of nitrite and nitrate in different types of meat products were between 96 – 168 ppm respectively and 167 – 763 ppm respectively. Level of nitrite and nitrate in 76% and 70% samples were up to 100 ppm and 500 ppm. The difference between the means of nitrite and nitrate level in sausages with different meat content was not significant. The differences between the means of nitrite and nitrate level in different factories were significant (P<0.05). High level of nitrite and nitrate in meat products is worrying. Consequently observation the standards and measures these food additives in sausages are essential.

Tetrachloroethylene is a chlorinated aliphatic hydrocarbon, which is widely used in many industrial processes. Efficient filtration of industrial wastewater containing tetrachloroethylene is an environmental necessity. The aim of this experimental study was to determine the efficiency of copper-supported pumice in removing tetracholoroethylene from aqueous solutions. This experimental study was performed, using granules of pumice stone (about 4 mesh, 4.8 mm). The pumice was coated by copper sulfate and was prepared as an absorbent at doses of 1, 2, and 3 g/L. The study was performed on samples containing tetracholoroethylene at 3 concentrations (25, 75, and 125 mg/L) by considering four contact times (20, 40, 60, and 80 minutes) and 3 pH ranges (3, 7, and 11). The structural study of SEM images (with an accuracy of 100 micrometers) of copper-supported pumice indicated cavities with a more or less homogenous pattern. Removal of tetrachloroethylene was a function of the absorbent dose and tetrachloroethylene concentration. The maximum capacity to remove tetrachloroethylene by copper-supported pumice was 120.86 mg/g. Also, the minimum and maximum of tetrachloroethylene removal by copper-supported pumice were 80% and 99.7%, respectively. The results showed that copper-supported pumice was efficient in removing tetrachloroethylene. Considering the availability, cost-effectiveness, high absorption, and reuse of pumice, this stone can be used for removing industrial wastewater containing tetrachloroethylene.

Background and Geographic information system (GIS) and appropriate statistical method for management and analysis of groundwater has been growing rapidly. New devices and information support system has a significant role in management of water resources, especially in limited and valuable water resources. The aim of this study was to evaluate the changes in the physicochemical quality of groundwater watershed in Gharehsou during a ten year period (2003-2012). The results of water physicochemical parameters analysis were obtained from the regional water authority. The annual average of parameters were determined using descriptive statistics in SPSS Ver.16 by applying Friedman Test and MEASURE with significant level α= 0.05. The annual parameters changes were compared and zoning of different parameters for groundwater quality of gharasoo watershed was determined through ArcGIS9.3 software. The results showed that physicochemical parameters had an increasing trend during the first five years while in the next five years despite annual fluctuations a decreasing trend was observed. No significant correlation was found in annual variation of potassium, calcium, chloride, and conductivity (P> 0.05). Geographically, density and high concentration of chemical compounds in groundwater was seen more in north west, west and south west areas. The most increases of cation and anion concentrations were observed between 2005-2008. The results showed that most of the groundwater watershed contained bicarbonate, and the changes in chemical composition of groundwater watershed depended on rain fall, water harvesting, and type of soil.

Industrialization and urbanization have had a devastating impact on public health. Asthma is considered as one of the major challenges of public health. The purpose of this study was to determine the association between air pollution and the number of asthma patients admitted to hospitals in Kermanshah, Iran.

In this cross-sectional and ecological study, the data on the number of asthma patients, the concentration levels of air pollutants and weather conditions were collected from the city of Kermanshah. To determine the association between asthma patients admitted to hospitals and air pollutants, Poisson regression was used (P<0.05).

according to the statistical analysis, air pollutants had significant correlation with each other. Based on the results of multiple Poisson regression, among air pollutants CO and O3 were significantly correlated with the number of asthma patients referred to hospitals, with relative risk of 1.18 and 1.016, respectively, and based on the results of single Poisson regression, among air pollutants NOx, NO, NO2 and CO were significantly correlated with the number of asthma patients referred to hospitals with relative risk of 1.011, 1.012, 1.054 and 1.247, respectively.

according to the results of the present study, there was a significant association between air pollutants (mainly carbon monoxide and ozone) and the total number of asthma patients referred to the hospitals in Kermanshah.

With the growing industrial and social development through time, toxic substances such as phenol and its derivatives are increasingly released into the environment from a variety of sources. The present study aims to investigate the effects of molasses on phenol removal. For this purpose, five pilot scale batch reactors (5 Erlenmeyer flasks equipped with the air and gas diffusion control system) were used in the laboratory scale. The volumes of the reactors were kept constant with a final volume content of 550 ml in each reactor. Phenol with a fixed concentration of 100 mg/l was tested under anaerobic conditions in each reactor in contact with beet molasses (organic matter used as the auxiliary substrate) with COD concentrations of 10000, 5000, 2000, 1000, and 500 mg/l over 5 retention times (10, 20, 30, 40, and 50 days). All the sampling and testing procedures wer e performed according to the standard methods. The results showed that in all the five experimental reactors, increasing retention time was accompanied by a continuous decline in initial phenol and COD concentrations. However, for each retention time, increasing COD concentration led to a decrease in COD removal efficiency such that increasing the initial COD concentration up to a certain level was associated with an increase in chemical oxygen demanding materials, but beyond this range, COD removal decreased slowly. It was also found that phenol removal increased with increasing retention time but it was not proportional to the concentration of the biodegradable COD. After 50 days of contact with 1000 mg/l of the supporting substrate, phenol removal in the reactors reached 98.62%. Another finding of the study was the fact that the highest phenol removal was achieved when 1000-2000 mg/l of biodegradable COD was used over 50 days of retention time.