Free growdsourcing-based corpus annotation / Fatna Bougrine

Public ISBD Titre : Free growdsourcing-based corpus annotation Type de document : texte manuscrit Auteurs : Fatna Bougrine, Auteur ; Soumia Djellikh, Auteur ; Hadda Cherroun, Directeur de thèse Editeur : Laghouat : Université Amar Telidji - Département d'informatique Année de publication : 2017 Importance : 67 p. Format : 30 cm. Accompagnement : 1 disque optique numérique (CD-ROM) Note générale : Option : Networks, systems and distributed applications (Réseaux,systèmes et applications réparties) Langues : Anglais Mots-clés : Algerian dialects  ANLP  Corpus Annotation  Crowdcrafting  Crowdsourcing Résumé : Large corpora are very useful to develop and validate Natural Language Processing (NLP) systems. However, these corpora are generally collected and annotated automatically. To validate such annotation, two solutions are possible. We can use skills of expert, which can be costly and time consuming, or use crowdsourcing technique. Crowdsourcing can be defined as the act of attracting many non experts to complete a certain task by using paid/unpaid dedicated platform. In this work, we are interested to validate a semi-automatic dialect annotation of Kalam’DZ corpus. Our approach relies on free crowdsourcing using Crowdcrafting platform. The validation is performed on 10% (11 hours) of the total size of Kalam’DZ. A quality control of this validation is ensured through a confrontation with expert annotation, which shows that more than 80% of annotations are similar. Our results confirm that free crowdsourcing is effective for speech dialect annotation. note de thèses : Mémoire de master en informatique Free growdsourcing-based corpus annotation [texte manuscrit] / Fatna Bougrine, Auteur ; Soumia Djellikh, Auteur ; Hadda Cherroun, Directeur de thèse . - Laghouat : Université Amar Telidji - Département d'informatique, 2017 . - 67 p. ; 30 cm. + 1 disque optique numérique (CD-ROM). Option : Networks, systems and distributed applications (Réseaux,systèmes et applications réparties) Langues : Anglais Mots-clés : Algerian dialects  ANLP  Corpus Annotation  Crowdcrafting  Crowdsourcing Résumé : Large corpora are very useful to develop and validate Natural Language Processing (NLP) systems. However, these corpora are generally collected and annotated automatically. To validate such annotation, two solutions are possible. We can use skills of expert, which can be costly and time consuming, or use crowdsourcing technique. Crowdsourcing can be defined as the act of attracting many non experts to complete a certain task by using paid/unpaid dedicated platform. In this work, we are interested to validate a semi-automatic dialect annotation of Kalam’DZ corpus. Our approach relies on free crowdsourcing using Crowdcrafting platform. The validation is performed on 10% (11 hours) of the total size of Kalam’DZ. A quality control of this validation is ensured through a confrontation with expert annotation, which shows that more than 80% of annotations are similar. Our results confirm that free crowdsourcing is effective for speech dialect annotation. note de thèses : Mémoire de master en informatique

Réservation

Réserver ce document

Exemplaires

Code-barres	Cote	Support	Localisation	Section	Disponibilité
MF 01-22	MF 01-22	Thése	BIBLIOTHEQUE DE FACULTE DES SCIENCES	théses (sci)	Disponible

Multicast routing in swarm of UAVs / Soumia Djellikh

Public ISBD Titre : Multicast routing in swarm of UAVs Type de document : texte manuscrit Auteurs : Soumia Djellikh, Auteur ; Yousra Cheriguene, Auteur ; Fatima Zahra Bousbaa, Directeur de thèse Editeur : Laghouat : Université Amar Telidji - Département d'informatique Année de publication : 2020 Importance : 55 p. Format : 30 cm. Accompagnement : 1 disque optique numérique (CD-ROM) Note générale : Option : Systems and computer science networks Langues : Anglais Mots-clés : UAVS  Swarm of UAVS  Multicast Routing Protocol  SEMRP-V1  SEMRP- V2 Résumé : Recently, the deployment of a swarm of cooperative Unmanned Aerial Vehicles (UAVS) to pursue a task is enjoying increasing success, since a group of UAVS instead of one single UAV leads to many advantages, for example the possibility to extend the mission coverage, to guarantee a reliable ad-hoc network, or to enhance the service performance. However, it also poses many challenges in designing networking protocols such as, the dynamic topology change. In this work, we study the multicast routing problem in swarm of UAVS, which aims at delivering information to specific members of flying nodes. Our objective is to provide detailed classification of existing swarm routing protocols considering transmission strategies and to propose a new Energy eflicient Multicast Routing Protocol for UAVS Swarm (SEMRP) taking into consideration the aforementioned challenges and aimning to satisfy COronaVirus Disease 2019 (COVID-19) applications. The results of the simulation conducted using NS-2 simulator advocate for the efficiency of our method through two proposed versions (SEMRP-V1 and SEMRP-V2) in term of reducing the total emission energy (at least by 10 dBm), optimizing the End-to-End Delay by 44%, and increasing the packet delivery ratio by more than to 22% compared to SP-GMRF protocol. note de thèses : Mémoire de master en informatique Multicast routing in swarm of UAVs [texte manuscrit] / Soumia Djellikh, Auteur ; Yousra Cheriguene, Auteur ; Fatima Zahra Bousbaa, Directeur de thèse . - Laghouat : Université Amar Telidji - Département d'informatique, 2020 . - 55 p. ; 30 cm. + 1 disque optique numérique (CD-ROM). Option : Systems and computer science networks Langues : Anglais Mots-clés : UAVS  Swarm of UAVS  Multicast Routing Protocol  SEMRP-V1  SEMRP- V2 Résumé : Recently, the deployment of a swarm of cooperative Unmanned Aerial Vehicles (UAVS) to pursue a task is enjoying increasing success, since a group of UAVS instead of one single UAV leads to many advantages, for example the possibility to extend the mission coverage, to guarantee a reliable ad-hoc network, or to enhance the service performance. However, it also poses many challenges in designing networking protocols such as, the dynamic topology change. In this work, we study the multicast routing problem in swarm of UAVS, which aims at delivering information to specific members of flying nodes. Our objective is to provide detailed classification of existing swarm routing protocols considering transmission strategies and to propose a new Energy eflicient Multicast Routing Protocol for UAVS Swarm (SEMRP) taking into consideration the aforementioned challenges and aimning to satisfy COronaVirus Disease 2019 (COVID-19) applications. The results of the simulation conducted using NS-2 simulator advocate for the efficiency of our method through two proposed versions (SEMRP-V1 and SEMRP-V2) in term of reducing the total emission energy (at least by 10 dBm), optimizing the End-to-End Delay by 44%, and increasing the packet delivery ratio by more than to 22% compared to SP-GMRF protocol. note de thèses : Mémoire de master en informatique

Réservation

Réserver ce document

Exemplaires

Code-barres	Cote	Support	Localisation	Section	Disponibilité
MF 02-35	MF 02-35	Thése	BIBLIOTHEQUE DE FACULTE DES SCIENCES	théses (sci)	Disponible

---

page 1/1