1,721,144 research outputs found
ArSL-CNN: a convolutional neural network for Arabic sign language gesture recognition
No full textSign language (SL) is a visual language means of communication for people with deafness or hearing impairments. In Arabic-speaking countries, there are many arabic sign languages (ArSL) and these use the same alphabets. This study proposes ArSLCNN, a deep learning model that is based on a convolutional neural network (CNN) for translating Arabic SL (ArSL). Experiments were performed using a large ArSL dataset (ArSL2018) that contains 54,049 images of 32 sign language gestures, collected from forty participants. The results of the first experiments with the ArSL-CNN model returned a train and test accuracy of 98.80% and 96.59%, respectively. The results also revealed the impact of imbalanced data on model accuracy. For the second set of experiments, various re-sampling methods were applied to the dataset. Results revealed that applying the synthetic minority oversampling technique (SMOTE) improved the overall test accuracy from 96.59% to 97.29%, yielding a statistically significant improvement in test accuracy (p=0.016, 0:05). The proposed ArSL-CNN model can be trained on a variety of Arabic sign languages and reduce the communication barriers encountered by deaf communities in Arabic-speaking countries
ArSL-CNN: a convolutional neural network for Arabic sign language gesture recognition
No full textSign language (SL) is a visual language means of communication for people with deafness or hearing impairments. In Arabic-speaking countries, there are many arabic sign languages (ArSL) and these use the same alphabets. This study proposes ArSLCNN, a deep learning model that is based on a convolutional neural network (CNN) for translating Arabic SL (ArSL). Experiments were performed using a large ArSL dataset (ArSL2018) that contains 54,049 images of 32 sign language gestures, collected from forty participants. The results of the first experiments with the ArSL-CNN model returned a train and test accuracy of 98.80% and 96.59%, respectively. The results also revealed the impact of imbalanced data on model accuracy. For the second set of experiments, various re-sampling methods were applied to the dataset. Results revealed that applying the synthetic minority oversampling technique (SMOTE) improved the overall test accuracy from 96.59% to 97.29%, yielding a statistically significant improvement in test accuracy (p=0.016, 0:05). The proposed ArSL-CNN model can be trained on a variety of Arabic sign languages and reduce the communication barriers encountered by deaf communities in Arabic-speaking countries
Establishing a multimodal dataset for Arabic Sign Language (ArSL) production
No full textThis paper addresses the potential of Arabic Sign Language (ArSL) recognition systems to facilitate direct communication and enhance social engagement between deaf and non-deaf. Specifically, we focus on the domain of religion to address the lack of accessible religious content for the deaf community. We propose a multimodal architecture framework and develop a novel dataset for ArSL production. The dataset comprises 1950 audio signals with corresponding 131 texts, including words and phrases, and 262 ArSL videos. These videos were recorded by two expert signers and annotated using ELAN based on gloss representation. To evaluate ArSL videos, we employ Cosine similarities and mode distances based on MobileNetV2 and Euclidean distance based on MediaPipe. Additionally, we implement Jac card Similarity to evaluate the gloss representation, resulting in an overall similarity score of 85% between the glosses of the two ArSL videos. The evaluation highlights the complexity of creating an ArSL video corpus and reveals slight differences between the two videos. The findings emphasize the need for careful annotation and representation of ArSL videos to ensure accurate recognition and understanding. Overall, it contributes to bridging the gap in accessible religious content for deaf community by developing a multimodal framework and a comprehensive ArSL dataset
ArSL-CNN a convolutional neural network for Arabic sign language gesture recognition
Get PDFSign language (SL) is a visual language means of communication for people who are Deaf or have hearing impairments. In Arabic-speaking countries, there are many Arabic sign languages (ArSL) and these use the same alphabets. This study proposes ArSL-CNN, a deep learning model that is based on a convolutional neural network (CNN) for translating Arabic SL (ArSL). Experiments were performed using a large ArSL dataset (ArSL2018) that contains 54049 images of 32 sign language gestures, collected from forty participants. The results of the first experiments with the ArSL-CNN model returned a train and test accuracy of 98.80% and 96.59%, respectively. The results also revealed the impact of imbalanced data on model accuracy. For the second set of experiments, various re-sampling methods were applied to the dataset. Results revealed that applying the synthetic minority oversampling technique (SMOTE) improved the overall test accuracy from 96.59% to 97.29%, yielding a statistically signicant improvement in test accuracy (p=0.016, α<0=05). The proposed ArSL-CNN model can be trained on a variety of Arabic sign languages and reduce the communication barriers encountered by Deaf communities in Arabic-speaking countries
Construction and Characterization of Deletion Mutations in Domain C of ARSl
No full text115 p.Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 1987.Autonomously Replicating Sequences, or ARS elements, promote high-frequency transformation and extrachromosomal maintenance of plasmids in Saccharomyces cerevisiae, properties expected of DNA replication origins. A series of overlapping deletions in one flanking region (Domain C) of the ARSl element was constructed, and the effect of the deletions on the maintenance of various multicopy and single-copy plasmids examined. Analysis of the stabilities and copy numbers of multicopy plasmids indicated that while the core consensus element is absolutely required for extrachromosomal maintenance, the absence of Domain C has little effect. The loss rates of centromere (single-copy) plasmids increased slightly as the deletions approached the core consensus, suggesting that a block of sequence between 225 and 255 nucleotides from the consensus contains an element important to the maximal function of ARSl. These results also suggested that ARSl plays a role in replication, but has no effect on the segregation of centromere plasmids.Comparison of multicopy plasmids of different sizes, each with an intact ARSl element, indicated a destabilizing effect of sequences derived from the E. coli cloning vector pBR322. A small amount of pBR322 (about a kilobase) was tolerated, and the bacterial ori was not responsible for the destabilizing effect.Made available in DSpace on 2014-12-16T06:13:01Z (GMT). No. of bitstreams: 1
8803241.pdf: 3849495 bytes, checksum: 9f936a56720c80f33e27202bc97a7ca2 (MD5)
Previous issue date: 1987Embargo set by: Seth Robbins for item 71354
Lift date: Forever
Reason: Restricted to the U of I community idenfinitely during batch ingest of legacy ETDsRestricted to the U of I community idenfinitely during batch ingest of legacy ETDsU of I Onl
THE LAST ATABEG OF IRAQ SALDJ??IDS ?AL??AL-D?N KORPE-ARSL?N
No full textSelçuklulara bağlı olarak Merâga, Tebriz civarlarında hüküm süren ve Ahmedîlîler adıylabilinen Merâga Atabegleri (501-624/1108-1227) içerisinde Irak Selçuklu Devleti Sultanlarınınçocuklarına atabeg olarak tayin edilmiş önemli tarihî şahsiyetler bulunmaktadır. AlâeddinKörpearslan (ö. 604/1207-1208) Ahmedîlî hânedanına mensup olup Irak Selçuklu Sultanı II.Tuğrul (1176-1194) tarafından görevlendirilmiş olan son Merâga Atabegi’dir. Hayatı hakkındasınırlı bilgiye sahip olduğumuz Alâeddin Körpearslan, Irak Selçukluları ile dostane ilişkiler kurmuş,Azerbaycan Atabegleri ile rekabet etmekten kaçınmamış ve Erbil hâkimleriyle yaşanan siyasîgelişmeler üzerine işbirliği yapmıştır. Alâeddin Körpearslan komşu hânedanlar ve devletlernazarında itibar sahibi bir hükümdar olarak hadiselerde etkin rol oynamaktan çekinmemiş, bir kısmıAzerbaycan Atabegleri tarafından ele geçirilmiş olan Ahmedîli hânedanı topraklarını korumak içingayret göstermiştir. İlmî ve kültürel faaliyetlere de oldukça önem veren, âlimleri himaye edenAlâeddin Körpearslan dönemin âdil hükümdarları arasında yer almıştır.Reigning around Mar?gha, Tabr?z as subjects of Saldj??ids and also known as A?mad?l?s, Atabeg of Mar?gha (501-624/1108-1227), have significant historical figures appointed as atabegs to children of Iraq Saldj??id State Sul??ns. ?Al??al-d?n Korpe-Arsl?n (d. 604/1207-1208), a member of the A?mad?l? dynasty, is the last Atabeg of Mar?gha and was appointed by Iraq Saldj??id Sul??n ?oghril II. Although little is known about his life, ?Al??al-d?n Korpe-Arsl?n has established amicable relations with Iraq Saldj??ids, has not avoided competing with Atabegs of ?dharbaydj?n, and has collaborated on political developments with Am?rs of Irbil. As a respected ruler among neighbouring dynasties and states, ?Al??al-d?n Korpe-Arsl?n has not refrained from playing an active role in the events and has strived to protect the land of A?mad?l? dynasty occupied by Atabegs of ?dharbaydj?n. ?Al??al-d?n Korpe-Arsl?n was among the fair rulers of his period by attaching importance to scientific and cultural activities and acting as patron of the ?ulam??
The Last Atabeg Of Iraq Saldj??ıds ?al??al-D?n Korpe-Arsl?n
No full textSelçuklulara bağlı olarak Merâga, Tebriz civarlarında hüküm süren ve Ahmedîlîler adıyla bilinen Merâga Atabegleri (501-624/1108-1227) içerisinde Irak Selçuklu Devleti Sultanlarının çocuklarına atabeg olarak tayin edilmiş önemli tarihî şahsiyetler bulunmaktadır. Alâeddin Körpearslan (ö. 604/1207-1208) Ahmedîlî hânedanına mensup olup Irak Selçuklu Sultanı II. Tuğrul (1176-1194) tarafından görevlendirilmiş olan son Merâga Atabegi’dir. Hayatı hakkında sınırlı bilgiye sahip olduğumuz Alâeddin Körpearslan, Irak Selçukluları ile dostane ilişkiler kurmuş, Azerbaycan Atabegleri ile rekabet etmekten kaçınmamış ve Erbil hâkimleriyle yaşanan siyasî gelişmeler üzerine işbirliği yapmıştır. Alâeddin Körpearslan komşu hânedanlar ve devletler nazarında itibar sahibi bir hükümdar olarak hadiselerde etkin rol oynamaktan çekinmemiş, bir kısmı Azerbaycan Atabegleri tarafından ele geçirilmiş olan Ahmedîli hânedanı topraklarını korumak için gayret göstermiştir. İlmî ve kültürel faaliyetlere de oldukça önem veren, âlimleri himaye eden Alâeddin Körpearslan dönemin âdil hükümdarları arasında yer almıştır.Reigning around Mar?gha, Tabr?z as subjects of Saldj??ids and also known as A?mad?l?s, Atabeg of Mar?gha (501-624/1108-1227), have significant historical figures appointed as atabegs to children of Iraq Saldj??id State Sul??ns. ?Al??al-d?n Korpe-Arsl?n (d. 604/1207-1208), a member of the A?mad?l? dynasty, is the last Atabeg of Mar?gha and was appointed by Iraq Saldj??id Sul??n ?oghril II. Although little is known about his life, ?Al??al-d?n Korpe-Arsl?n has established amicable relations with Iraq Saldj??ids, has not avoided competing with Atabegs of ?dharbaydj?n, and has collaborated on political developments with Am?rs of Irbil. As a respected ruler among neighbouring dynasties and states, ?Al??al-d?n Korpe-Arsl?n has not refrained from playing an active role in the events and has strived to protect the land of A?mad?l? dynasty occupied by Atabegs of ?dharbaydj?n. ?Al??al-d?n Korpe-Arsl?n was among the fair rulers of his period by attaching importance to scientific and cultural activities and acting as patron of the ?ulam??
Spectroscopic and Biochemical Characterization of the Noncanonical Radical SAM Enzyme ArsL, Involved in Arsinothricin Biosynthesis
No full textInternational audienceRadical SAM enzymes are the most widespread biocatalysts. These metalloenzymes, using S-adenosyl-l-methionine (SAM) and a [4Fe-4S] cluster as central cofactors, catalyze a broad range of chemically challenging transformations. The vast majority of radical SAM enzymes initiate their reaction by the homolytic cleavage of the SAM C5'-S bond and the generation of the central 5'-deoxyadenosyl radical (5'-dA·). In this study, by combining spectroscopic approaches with labeling and biochemical analyses, we show that ArsL, the key enzyme in the biosynthesis of the arsenic-containing antibiotic arsinothricin, catalyzes a unique reaction: the addition of the 3-amino-3-carboxypropyl radical (ACP·) to As(III). Remarkably, by exploiting several radical trapping strategies, we demonstrate that in sharp contrast to canonical radical SAM enzymes ArsL cleaves the SAM Cγ-S bond. In addition, using electron paramagnetic resonance (EPR) and hyperfine sublevel correlation (HYSCORE) spectroscopies, we establish that ArsL has a unique SAM binding mode, consistent with its catalytic properties and predicted structure. Notably, EPR and HYSCORE analyses support that SAM interacts with the radical SAM [4Fe-4S] cluster in an uncharacteristic conformation to form ACP·. Collectively, our study reveals that members of the superfamily of radical SAM enzymes are able to finely tune the binding of the SAM cofactor in order to perform unique chemistries
ARSL Annual Conference 2015: Bringing Rural Librarians Together in the Land of Bill & Hillary
No full textOn July 16th an email from ULA graced my inbox reading “Hurry! Grant deadline is tomorrow!” Because this sounded so urgent I quickly opened the message out of mild curiosity for which grant deadline was approaching. Turns out it was the UPLIFT Professional Excellence Grant: ARSL Grant
- …
