Brain-computer interface (BCI) is an evolving technology having huge potential for rehabilitation of patients suffering from disorders of the nervous system, besides many other nonmedical applications. Multichannel electroencephalography (EEG) is widely used to provide input signals to a BCI system. Significant research in methodology employed to implement different stages of BCI system, has led to discovery of new issues and challenges. The raw EEG data includes artifacts from environmental and physiological sources, which is eliminated in preprocessing phase of BCI system. It is then followed by a feature extraction stage to isolate a few relevant features for further classification to a particular motor imagery (MI) activity. A feature extraction approach based on spectrally weighted common spatial pattern (SWCSP) is proposed in this paper to improve overall accuracy of a BCI system. The reported literature uses SWCSP for feature extraction, as it has outperformed other techniques. The proposed approach enhances its performance by optimizing its parameters. The independent component analysis (ICA) method is used for detection and removal of irrelevant data, while linear discriminant analysis (LDA) is used as a classifier. The proposed approach is executed on benchmark data-set 2a of BCI competition IV. It yielded classification accuracy of 70.6% across nine subjects, which is higher than all the reported approaches.
{"title":"An Optimized SWCSP Technique for Feature Extraction in EEG-based BCI System","authors":"Navtej S. Ghumman, B. Jindal","doi":"10.14500/aro.10926","DOIUrl":"https://doi.org/10.14500/aro.10926","url":null,"abstract":"Brain-computer interface (BCI) is an evolving technology having huge potential for rehabilitation of patients suffering from disorders of the nervous system, besides many other nonmedical applications. Multichannel electroencephalography (EEG) is widely used to provide input signals to a BCI system. Significant research in methodology employed to implement different stages of BCI system, has led to discovery of new issues and challenges. The raw EEG data includes artifacts from environmental and physiological sources, which is eliminated in preprocessing phase of BCI system. It is then followed by a feature extraction stage to isolate a few relevant features for further classification to a particular motor imagery (MI) activity. A feature extraction approach based on spectrally weighted common spatial pattern (SWCSP) is proposed in this paper to improve overall accuracy of a BCI system. The reported literature uses SWCSP for feature extraction, as it has outperformed other techniques. The proposed approach enhances its performance by optimizing its parameters. The independent component analysis (ICA) method is used for detection and removal of irrelevant data, while linear discriminant analysis (LDA) is used as a classifier. The proposed approach is executed on benchmark data-set 2a of BCI competition IV. It yielded classification accuracy of 70.6% across nine subjects, which is higher than all the reported approaches. ","PeriodicalId":8398,"journal":{"name":"ARO-THE SCIENTIFIC JOURNAL OF KOYA UNIVERSITY","volume":"1 1","pages":""},"PeriodicalIF":0.6,"publicationDate":"2022-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89207407","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Type 2 diabetes mellitus is the most common chronic endocrine disorder that affecting 5%–10% of adults globally. Recently, the disease has rapidly spread throughout the Kurdistan Region. This study investigates DNA methylation status in the ABCC8 gene among the study population, and it possibly used as a biomarker. One hundred and thirteen individuals were included in this study, and they were divided into three categories (47 diabetes, 36 prediabetic, and 30 controls). Blood samples were collected to investigate DNA methylation status in patients who attended private clinical sectors in Koya city, Kurdistan Region of Iraq, between August and December 2021. Methylation-specific PCR (MSP) uses paired primers for each methylated and unmethylated region. In addition, the X2 Kruskal–Wallis statistical and Wilcoxon signed-rank tests were run with a significance level of p 0.05. In comparison to the healthy group, hypermethylation of DNA is detected in the promoter region of diabetes and prediabetes. In addition, age, gender, BMI, alcohol use, family history, and physical activity all influence the degree of DNA methylation in people who have had coronavirus illness. The abovementioned findings suggest that DNA methylation alterations in the ABCC8 promoter region might be exploited as a possible predictive biomarker for type 2 diabetes mellitus diagnosis.
{"title":"Identification DNA Methylation Change of ABCC8 Gene in Type 2 Diabetes Mellitus as Predictive Biomarkers","authors":"Harem O. Smail, Dlnya A. Mohamad","doi":"10.14500/aro.10947","DOIUrl":"https://doi.org/10.14500/aro.10947","url":null,"abstract":"Type 2 diabetes mellitus is the most common chronic endocrine disorder that affecting 5%–10% of adults globally. Recently, the disease has rapidly spread throughout the Kurdistan Region. This study investigates DNA methylation status in the ABCC8 gene among the study population, and it possibly used as a biomarker. One hundred and thirteen individuals were included in this study, and they were divided into three categories (47 diabetes, 36 prediabetic, and 30 controls). Blood samples were collected to investigate DNA methylation status in patients who attended private clinical sectors in Koya city, Kurdistan Region of Iraq, between August and December 2021. Methylation-specific PCR (MSP) uses paired primers for each methylated and unmethylated region. In addition, the X2 Kruskal–Wallis statistical and Wilcoxon signed-rank tests were run with a significance level of p 0.05. In comparison to the healthy group, hypermethylation of DNA is detected in the promoter region of diabetes and prediabetes. In addition, age, gender, BMI, alcohol use, family history, and physical activity all influence the degree of DNA methylation in people who have had coronavirus illness. The abovementioned findings suggest that DNA methylation alterations in the ABCC8 promoter region might be exploited as a possible predictive biomarker for type 2 diabetes mellitus diagnosis.","PeriodicalId":8398,"journal":{"name":"ARO-THE SCIENTIFIC JOURNAL OF KOYA UNIVERSITY","volume":"57 1","pages":""},"PeriodicalIF":0.6,"publicationDate":"2022-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74133130","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The identical twins (Monozygotic) are siblings created from the division of one fertilized egg (zygote), so they will be identical in their genetic characteristics and therefore in their phenotypic traits to a very large extent. Among these traits is the voice or the voiceprint of these twins. This research aims to suggest a method to determine the extent of the similarity and the difference between the voiceprints between the brothers of the identical twins and thus, it is possible to distinguish between their voices. This study relied on using a number of audio clips collected from 35 identical twins. The proposed method is based on the use of the spectrogram that represents the voiceprint of the twins. The spectrogram is a two-dimensional function that can be used in the Neutrosophic Transformation to convert the voiceprints to the Neutrosophic domain represented by three membership functions (True, False, and Indeterminate). The results showed that the average extent of the similarity ratio between twins’ voices (True membership) is 67.6%, the difference ratio (False membership) is 32.3%, and the indeterminacy membership function ratio is 18.2%.
{"title":"Measuring the Voice Resemblance Extent of Identical (Monozygotic) Twins Using Voiceprints Neutrosophic Domain","authors":"Yazen A. Khaleel, Caroline Y. Daniel, S. Yahya","doi":"10.14500/aro.10925","DOIUrl":"https://doi.org/10.14500/aro.10925","url":null,"abstract":"The identical twins (Monozygotic) are siblings created from the division of one fertilized egg (zygote), so they will be identical in their genetic characteristics and therefore in their phenotypic traits to a very large extent. Among these traits is the voice or the voiceprint of these twins. This research aims to suggest a method to determine the extent of the similarity and the difference between the voiceprints between the brothers of the identical twins and thus, it is possible to distinguish between their voices. This study relied on using a number of audio clips collected from 35 identical twins. The proposed method is based on the use of the spectrogram that represents the voiceprint of the twins. The spectrogram is a two-dimensional function that can be used in the Neutrosophic Transformation to convert the voiceprints to the Neutrosophic domain represented by three membership functions (True, False, and Indeterminate). The results showed that the average extent of the similarity ratio between twins’ voices (True membership) is 67.6%, the difference ratio (False membership) is 32.3%, and the indeterminacy membership function ratio is 18.2%.","PeriodicalId":8398,"journal":{"name":"ARO-THE SCIENTIFIC JOURNAL OF KOYA UNIVERSITY","volume":"30 1","pages":""},"PeriodicalIF":0.6,"publicationDate":"2022-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84196181","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
It is critical today to provide safe and collision-free transport. As a result, identifying the driver’s drowsiness before their capacity to drive is jeopardized. An automated hybrid drowsiness classification method that incorporates the artificial neural network (ANN) and the gray wolf optimizer (GWO) is presented to discriminate human drowsiness and fatigue for this aim. The proposed method is evaluated in alert and sleep-deprived settings on the driver drowsiness detection of video dataset from the National Tsing Hua University Computer Vision Lab. The video was subjected to various video and image processing techniques to detect the drivers’ eye condition. Four features of the eye were extracted to determine the condition of drowsiness, the percentage of eyelid closure (PERCLOS), blink frequency, maximum closure duration of the eyes, and eye aspect ratio (ARE). These parameters were then integrated into an ANN and combined with the proposed method (gray wolf optimizer with ANN [GWOANN]) for drowsiness classification. The accuracy of these models was calculated, and the results demonstrate that the proposed method is the best. An Adadelta optimizer with 3 and 4 hidden layer networks of (13, 9, 7, and 5) and (200, 150, 100, 50, and 25) neurons was utilized. The GWOANN technique had 91.18% and 97.06% accuracy, whereas the ANN model had 82.35% and 86.76%.
{"title":"Driver Drowsiness Detection Using Gray Wolf Optimizer Based on Face and Eye Tracking","authors":"S. Jasim, A. A. Abdul Hassan, Scott Turner","doi":"10.14500/aro.10928","DOIUrl":"https://doi.org/10.14500/aro.10928","url":null,"abstract":"It is critical today to provide safe and collision-free transport. As a result, identifying the driver’s drowsiness before their capacity to drive is jeopardized. An automated hybrid drowsiness classification method that incorporates the artificial neural network (ANN) and the gray wolf optimizer (GWO) is presented to discriminate human drowsiness and fatigue for this aim. The proposed method is evaluated in alert and sleep-deprived settings on the driver drowsiness detection of video dataset from the National Tsing Hua University Computer Vision Lab. The video was subjected to various video and image processing techniques to detect the drivers’ eye condition. Four features of the eye were extracted to determine the condition of drowsiness, the percentage of eyelid closure (PERCLOS), blink frequency, maximum closure duration of the eyes, and eye aspect ratio (ARE). These parameters were then integrated into an ANN and combined with the proposed method (gray wolf optimizer with ANN [GWOANN]) for drowsiness classification. The accuracy of these models was calculated, and the results demonstrate that the proposed method is the best. An Adadelta optimizer with 3 and 4 hidden layer networks of (13, 9, 7, and 5) and (200, 150, 100, 50, and 25) neurons was utilized. The GWOANN technique had 91.18% and 97.06% accuracy, whereas the ANN model had 82.35% and 86.76%.","PeriodicalId":8398,"journal":{"name":"ARO-THE SCIENTIFIC JOURNAL OF KOYA UNIVERSITY","volume":"10 1","pages":""},"PeriodicalIF":0.6,"publicationDate":"2022-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85600523","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
New SARS-CoV-2 infections are difficult to beverified, whether they are reinfections or persistent infections. The most prominent factors used for differentiating reinfections from persistent infections are whole-genome sequencing and phylogenetic analyses that require time and funds, which may not be feasible in most developing countries. This study explores reinfections with COVID-19 that harbors D614G and N501Y mutations by rapid inexpensive methods. It exploits the previously developed rapid economic methods that identified both D614G and N501Y mutations in clinical samples using real-time reverse transcriptase polymerase chain reaction (rRT-PCR) probes and conventional PCR specific primers. In the present study, an immunocompetent patient has been found with a SARS-CoV-2 N501Y reinfection without comorbidities. According to the obtained results, this study suggests that the initial infection was due to a variant that contained only D614G mutation whereas the reinfection was potentially a result of alpha variant contained three mutations confirmed by DNA sequencing, including D614G, N501Y, and A570D mutations. These techniques will support rapid detection of SARS-CoV-2 reinfections through the identification of common spike mutations in the developing countries where sequencing tools are unavailable. Furthermore, seven cases of reinfections were also confirmed by these methods. These rapid methods can also be applied to large samples of reinfections that may increase our understanding epidemiology of the pandemic.
{"title":"Detection of SARS-CoV-2 Reinfections by Rapid Inexpensive Methods","authors":"S. Al-jaf, S. Niranji","doi":"10.14500/aro.10916","DOIUrl":"https://doi.org/10.14500/aro.10916","url":null,"abstract":"New SARS-CoV-2 infections are difficult to beverified, whether they are reinfections or persistent infections. The most prominent factors used for differentiating reinfections from persistent infections are whole-genome sequencing and phylogenetic analyses that require time and funds, which may not be feasible in most developing countries. This study explores reinfections with COVID-19 that harbors D614G and N501Y mutations by rapid inexpensive methods. It exploits the previously developed rapid economic methods that identified both D614G and N501Y mutations in clinical samples using real-time reverse transcriptase polymerase chain reaction (rRT-PCR) probes and conventional PCR specific primers. In the present study, an immunocompetent patient has been found with a SARS-CoV-2 N501Y reinfection without comorbidities. According to the obtained results, this study suggests that the initial infection was due to a variant that contained only D614G mutation whereas the reinfection was potentially a result of alpha variant contained three mutations confirmed by DNA sequencing, including D614G, N501Y, and A570D mutations. These techniques will support rapid detection of SARS-CoV-2 reinfections through the identification of common spike mutations in the developing countries where sequencing tools are unavailable. Furthermore, seven cases of reinfections were also confirmed by these methods. These rapid methods can also be applied to large samples of reinfections that may increase our understanding epidemiology of the pandemic.","PeriodicalId":8398,"journal":{"name":"ARO-THE SCIENTIFIC JOURNAL OF KOYA UNIVERSITY","volume":"65 11","pages":""},"PeriodicalIF":0.6,"publicationDate":"2022-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72621612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract—This research is concerned with the data generated during a network transmission session to understand how to extract value from the data generated and be able to conduct tasks. Instead of comparing all of the transmission flags for a transmission session at the same time to conduct any analysis, this paper conceptualized the influence of each transmission flag on network-aware applications by comparing the flags one by one on their impact to the application during the transmission session, rather than comparing all of the transmission flags at the same time. The K-nearest neighbor (KNN) type classification was used becauseit is a simple distance-based learning algorithm that remembers earlier training samples and is suitable for taking various flags withtheir effect on application protocols by comparing each new sample with the K-nearest points to make a decision. We used transmission session datasets received from Kaggle for IP flow with 87 features and 3.577.296 instances. We picked 13 features from the datasets and ran them through KNN. RapidMiner was used for the study, and the results of the experiments revealed that the KNN-based model was not only significantly more accurate in categorizing data, but it was also significantly more efficient due to the decreased processing costs.
{"title":"Network Transmission Flags Data Affinity-based Classification by K-Nearest Neighbor","authors":"N. Aljojo","doi":"10.14500/aro.10880","DOIUrl":"https://doi.org/10.14500/aro.10880","url":null,"abstract":"Abstract—This research is concerned with the data generated during a network transmission session to understand how to extract value from the data generated and be able to conduct tasks. Instead of comparing all of the transmission flags for a transmission session at the same time to conduct any analysis, this paper conceptualized the influence of each transmission flag on network-aware applications by comparing the flags one by one on their impact to the application during the transmission session, rather than comparing all of the transmission flags at the same time. The K-nearest neighbor (KNN) type classification was used becauseit is a simple distance-based learning algorithm that remembers earlier training samples and is suitable for taking various flags withtheir effect on application protocols by comparing each new sample with the K-nearest points to make a decision. We used transmission session datasets received from Kaggle for IP flow with 87 features and 3.577.296 instances. We picked 13 features from the datasets and ran them through KNN. RapidMiner was used for the study, and the results of the experiments revealed that the KNN-based model was not only significantly more accurate in categorizing data, but it was also significantly more efficient due to the decreased processing costs.","PeriodicalId":8398,"journal":{"name":"ARO-THE SCIENTIFIC JOURNAL OF KOYA UNIVERSITY","volume":"16 1","pages":""},"PeriodicalIF":0.6,"publicationDate":"2022-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75227284","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Illegal dumping is a serious problem that needs to be addressed immediately to preserve human health and the environment as if the pollution that arises from it reaches the groundwater, complications of the remediation processes will increase. To decontaminate the organic and inorganic components, bioremediation seems to be the most environmentally friendly and economically viable technique without further treatment as reported by many studies. In this investigation, samples were taken from the soil of the main dumping area in Koysinjaq in Kurdistan Region of Iraq to determine the most potent bacteria to remediate the existed pollutants. The existence of non-essential minerals and organic compounds in the soil sample was detected using X-ray fluorescence device, and ethane and 1,2-dichloroethane solvents separating technique, respectively. Then, from the same samples, three different naturally occurring bacteria were isolated and cultured under optimized conditions then stimulated for a good result. Finally, spectrophotometer was set at wavelength of 600 nm and used to detect the heaviest growth of bacteria after incubating the cultured bacteria on a mineral salt broth medium with the extracted pollutants at pH 7.0 overnight at 32°C. Based on the highest absorbance, the most effective type of bacteria (Enterobacter cloacae) was chosen among others to remediate the organic components in which approximately 90% of them are plastics, medical waste, municipal waste, electrical items, and hydrocarbons, and some heavy metals, for instance aluminum and lead, which were found in the soil.
{"title":"Bioremediation Ability of the Local Isolate Enterobacter cloacae from Disposal Site","authors":"H. A. Muhammad, H. Subhi, Khalid N. Sediq","doi":"10.14500/aro.10948","DOIUrl":"https://doi.org/10.14500/aro.10948","url":null,"abstract":"Illegal dumping is a serious problem that needs to be addressed immediately to preserve human health and the environment as if the pollution that arises from it reaches the groundwater, complications of the remediation processes will increase. To decontaminate the organic and inorganic components, bioremediation seems to be the most environmentally friendly and economically viable technique without further treatment as reported by many studies. In this investigation, samples were taken from the soil of the main dumping area in Koysinjaq in Kurdistan Region of Iraq to determine the most potent bacteria to remediate the existed pollutants. The existence of non-essential minerals and organic compounds in the soil sample was detected using X-ray fluorescence device, and ethane and 1,2-dichloroethane solvents separating technique, respectively. Then, from the same samples, three different naturally occurring bacteria were isolated and cultured under optimized conditions then stimulated for a good result. Finally, spectrophotometer was set at wavelength of 600 nm and used to detect the heaviest growth of bacteria after incubating the cultured bacteria on a mineral salt broth medium with the extracted pollutants at pH 7.0 overnight at 32°C. Based on the highest absorbance, the most effective type of bacteria (Enterobacter cloacae) was chosen among others to remediate the organic components in which approximately 90% of them are plastics, medical waste, municipal waste, electrical items, and hydrocarbons, and some heavy metals, for instance aluminum and lead, which were found in the soil.","PeriodicalId":8398,"journal":{"name":"ARO-THE SCIENTIFIC JOURNAL OF KOYA UNIVERSITY","volume":"6 1","pages":""},"PeriodicalIF":0.6,"publicationDate":"2022-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75357163","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The Bekhme Formation forms almost the bulk of the Shakrook anticline, especially the limbs. The current research deals with studying the exposed beds within the Bekhme Formation at the Shakrook anticline to check the suitability of the exposed rocks at the northeastern limb of the anticline for the cement industry. Twenty rock samples from a section which lies along a deeply cut valley that crosses the northeastern limb of the Shakrook anticline within the Bekhme Formation were collected. The channel sampling method was applied; therefore, each sample represents the concerned sampling interval and to be representative for the thickness of the sampled interval. The total thickness of the sampled section is 110 m with a covered interval of 15 m, totaling to 125 m. The collected 20 samples were prepared at the laboratory of the Koya University and were subjected to XRF test at the Tarbiat Modares University, Iran, to indicate the concentration of the main oxides (CaO, MgO, Al2O3, Fe2O3, Na2O, K2O, and SO3), and Cl and L.O.I. The indicated concentrations at each sample, from both universities, were compared and were found to be almost coinciding. The average concentrations at each sample were changed to weighted averages and the results were compared with the Iraqi standards for cement industry. The results revealed that the sampled rocks are excellent for cement production.
{"title":"Suitability of the Carbonate Rocks of the Bekhme Formation Exposed in Shakrook Anticline, Iraqi Kurdistan region, for Cement Industry","authors":"Mohammed J. Hamwandy, R. K. Ibrahim, V. Sissakian","doi":"10.14500/aro.10907","DOIUrl":"https://doi.org/10.14500/aro.10907","url":null,"abstract":"The Bekhme Formation forms almost the bulk of the Shakrook anticline, especially the limbs. The current research deals with studying the exposed beds within the Bekhme Formation at the Shakrook anticline to check the suitability of the exposed rocks at the northeastern limb of the anticline for the cement industry. Twenty rock samples from a section which lies along a deeply cut valley that crosses the northeastern limb of the Shakrook anticline within the Bekhme Formation were collected. The channel sampling method was applied; therefore, each sample represents the concerned sampling interval and to be representative for the thickness of the sampled interval. The total thickness of the sampled section is 110 m with a covered interval of 15 m, totaling to 125 m. The collected 20 samples were prepared at the laboratory of the Koya University and were subjected to XRF test at the Tarbiat Modares University, Iran, to indicate the concentration of the main oxides (CaO, MgO, Al2O3, Fe2O3, Na2O, K2O, and SO3), and Cl and L.O.I. The indicated concentrations at each sample, from both universities, were compared and were found to be almost coinciding. The average concentrations at each sample were changed to weighted averages and the results were compared with the Iraqi standards for cement industry. The results revealed that the sampled rocks are excellent for cement production.","PeriodicalId":8398,"journal":{"name":"ARO-THE SCIENTIFIC JOURNAL OF KOYA UNIVERSITY","volume":"61 1","pages":""},"PeriodicalIF":0.6,"publicationDate":"2022-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85782081","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The proliferation of many editing programs based on artificial intelligence techniques has contributed to the emergence of deepfake technology. Deepfakes are committed to fabricating and falsifying facts by making a person do actions or say words that he never did or said. So that developing an algorithm for deepfakes detection is very important to discriminate real from fake media. Convolutional neural networks (CNNs) are among the most complex classifiers, but choosing the nature of the data fed to these networks is extremely important. For this reason, we capture fine texture details of input data frames using 16 Gabor filters indifferent directions and then feed them to a binary CNN classifier instead of using the red-green-blue color information. The purpose of this paper is to give the reader a deeper view of (1) enhancing the efficiency of distinguishing fake facial images from real facial images by developing a novel model based on deep learning and Gabor filters and (2) how deep learning (CNN) if combined with forensic tools (Gabor filters) contributed to the detection of deepfakes. Our experiment shows that the training accuracy reaches about 98.06% and 97.50% validation. Likened to the state-of-the-art methods, the proposed model has higher efficiency.
{"title":"Detecting Deepfakes with Deep Learning and Gabor Filters","authors":"Wildan J. Jameel, S. Kadhem, A. Abbas","doi":"10.14500/aro.10917","DOIUrl":"https://doi.org/10.14500/aro.10917","url":null,"abstract":"The proliferation of many editing programs based on artificial intelligence techniques has contributed to the emergence of deepfake technology. Deepfakes are committed to fabricating and falsifying facts by making a person do actions or say words that he never did or said. So that developing an algorithm for deepfakes detection is very important to discriminate real from fake media. Convolutional neural networks (CNNs) are among the most complex classifiers, but choosing the nature of the data fed to these networks is extremely important. For this reason, we capture fine texture details of input data frames using 16 Gabor filters indifferent directions and then feed them to a binary CNN classifier instead of using the red-green-blue color information. The purpose of this paper is to give the reader a deeper view of (1) enhancing the efficiency of distinguishing fake facial images from real facial images by developing a novel model based on deep learning and Gabor filters and (2) how deep learning (CNN) if combined with forensic tools (Gabor filters) contributed to the detection of deepfakes. Our experiment shows that the training accuracy reaches about 98.06% and 97.50% validation. Likened to the state-of-the-art methods, the proposed model has higher efficiency.","PeriodicalId":8398,"journal":{"name":"ARO-THE SCIENTIFIC JOURNAL OF KOYA UNIVERSITY","volume":"55 1","pages":""},"PeriodicalIF":0.6,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80215957","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This research presents a new biocomposite adsorbents using response surface methodology (RSM) to find the best conditions for highest adsorption of Brilliant Blue G250 (BBG) from aqueous solution by Amberlite XAD-4/Agaricus campestris. The most effective parameters are determined by Plackett–Burman design (PBD) with specific ranges initial dye concentration (5–150 mg.L-1), temperature (20–50°C), contact time (5–100 min), pH (3–11), shaking speed (150–300 rpm), sample volume (5–75 mL), and adsorbent dosage (0.05–0.6 g). Then, in the second step, the optimum condition of effective factors is predicted using steepest ascent design. Finally, optimal medium conditions of effective parameters with central composite design are located. According to RSM, the best adsorbent amount, contact time, initial dye concentration, and sample volume for maximum removal% of BBG (96.72%) are 0.38 g, 60.78 min, 107.13 mg.L-1, and 28.6 mL, respectively. The adsorption of brilliant blue is approved by scanning electron microscopy. Under optimum conditions, it is concluded that XAD4/A. campestr is biocomposite is a suitable adsorbent for removing BBG from aqueous solution.
{"title":"Application of Experimental Design Methodology for Adsorption of Brilliant Blue onto Amberlite XAD-4/Agaricus campestris as a New Biocomposite Adsorbent","authors":"Ahmed A. Ahmed, V. Yönten","doi":"10.14500/aro.10903","DOIUrl":"https://doi.org/10.14500/aro.10903","url":null,"abstract":"This research presents a new biocomposite adsorbents using response surface methodology (RSM) to find the best conditions for highest adsorption of Brilliant Blue G250 (BBG) from aqueous solution by Amberlite XAD-4/Agaricus campestris. The most effective parameters are determined by Plackett–Burman design (PBD) with specific ranges initial dye concentration (5–150 mg.L-1), temperature (20–50°C), contact time (5–100 min), pH (3–11), shaking speed (150–300 rpm), sample volume (5–75 mL), and adsorbent dosage (0.05–0.6 g). Then, in the second step, the optimum condition of effective factors is predicted using steepest ascent design. Finally, optimal medium conditions of effective parameters with central composite design are located. According to RSM, the best adsorbent amount, contact time, initial dye concentration, and sample volume for maximum removal% of BBG (96.72%) are 0.38 g, 60.78 min, 107.13 mg.L-1, and 28.6 mL, respectively. The adsorption of brilliant blue is approved by scanning electron microscopy. Under optimum conditions, it is concluded that XAD4/A. campestr is biocomposite is a suitable adsorbent for removing BBG from aqueous solution.","PeriodicalId":8398,"journal":{"name":"ARO-THE SCIENTIFIC JOURNAL OF KOYA UNIVERSITY","volume":"62 1","pages":""},"PeriodicalIF":0.6,"publicationDate":"2022-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84262217","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：