The team is working hard to make this project Success
Lets Take a look about Drafting study
Draft written Author : Khandoker Md, Mashiur Rahman
ID: 173-15-10309
Paper One:
Title: Bedside Computer Vision - Moving Artificial Intelligence from Driver Assistance to Patient Safety
Authors: Serena Yeung, N. Lance Downing, Li Fei-Fei, Arnold Milstein
Time: April, 2018
Summary:
This Paper was the Worth of reading because after analyzing this paper and its all points of quantities on Computer vision. it makes clear how computer visions are helping in various ways using its different methods alongside Image Processing. It shows some information of Google which is applying their own Computer Vision which is developing and upgrading using their algorithm. Which is helping itself to visit across the world the same as here in that it has described all its techniques such as radio Frequency Identification, hand hygiene behavior, and so on. In many cases it shows identification result at 95.5% and without learning according to database it can achieve at 84.6% which makes computer vision works really effectively to identify any object with or without learning/gaining any details of it, which will help us to ensure about the clarification our Ai Tour Guide Structure and make very safe and strong which will allow the traveller to depend her safety on this AI.
Paper Two:
Title: Understanding cities with machine eyes I review of their computer vision in urban analytics
Authors: Mohamed R Ibrahim, James Haworth, T. Cheng
Time: November, 2019
Summary:
After reading the research paper I gained knowledge about how researchers were trying to find out about the depth of computer vision and understanding all the material things. Here it has been shown that different layers of AI are working on different methods to produce understanding base knowledge about an urban city using the deep knowledge of AI and computer vision. It is also using the power of deep learning. Here in the methodology part it has been described it works in two different first method is working about the manuscript where it locates the reflect application of deep learning and computer vision understanding the cities from the previous record on the other hand it presents only the measure methodological approaches that they write and improve on this main approaches are excluded. And this computer vision is also working on different peer reviewed journals. This computer vision is narrowed to task of learning the qualitative representation of visual elements in their raw form in order to quantify them. Here logic of the computer vision and deep learning is to understand and analyse the city in proper way to get the proper information and provide the correct information from the view perspective. Depending on the type of visual task that models can be trained differently with different layers to produce different set of algorithms. There are various types of process of deep learning and computer vision which are also defined as segmentation and localisation , tracking of object, perception, generative models, clustering, decision making, the built environment seeing cities from above these all methods are working a great role.while seeing the cities from the vision of computer it has made more easier to us to locate any object definition to to detect any objects all the possibilities outcome all the possibilities of structure is making more is here to find out many perception analysis and also the prediction analysis to judge any kind of topic which relates to urban cities and although it has also defines about the human direction with the computer vision and deep learning AI based system which is made clear that it is so more comfortable to interact with the help of this process. Using all this process we are not only defining many kinds of situations but also we are analysing different types of protocols such as transportation in traffic, the natural environment, integrated models of the layers of the city, scale of applying computer vision in cities and so on. Even though we are also developing an AI based tour guide which will help us to guide the tourist in a proper way with the help of understanding the urban city according to these types of methods. So this paper has attempted to highlight the potential role of computer vision in understanding the interactions between the built environment people and transportation in order to take in all the complexity and nonlinearity of many urban and different issues for better policy making and planning processes for safest cities.
Paper Three:
Title: Smart audio tour system using TTS
Authors: K. Kang, J. Jwa, S.E. Park
Time: January, 2017
Summary:
The title of this paper is a smart audio tour system using TTS. TTS means the text to speech recognition which allows the audio tour guide system using the TTS engine to the traveler to provide the big information in a comfortable way. Digital tourism is gaining more popularity day by day which allows the people to stay in the ecosystem and enjoy the energetic movement of the tool as they feel like yesterday. And to make it more comfortable here comes the system which is allowing the user to use a smartphone which has GPS, Bluetooth and other capabilities to experience the better speech recognition system and to provide him the best outcome for the analysis from the stored knowledge. In this paper it has also mentioned about the system capability which will allow the user to comfort them by allowing different languages to use which they are comfortable with.
Using this method travellers can travel from many countries around the world and visit any country without any hesitation and without any warning about travelling periods. Also this paper has mentioned about the TTS engine I will collect all the wiki based information collection system using Google docs in this case many many travellers can store their information and variety of experience of their travelling experience into the database, which will be very useful for others which will lead to smart tourism through it will provide the real-time and personalized tourism information based on recent technologies.
Paper Four:
Title: Design and development mobile campus and Android based mobile application for university campus tour guide
Authors: Sagnik Bhattacharya, M.B. Panbu
Time: February, 2013
Summary:
In this research paper the design and development of a mobile campus based application which introduces a campus tour guide and also it includes some technologies of usefulness on our daily drivers which seems like mostly portable devices such as Android and other OS based devices. But an interesting thing is in this case this tour guide is working on the NFC enabled devices. So the tour guide is working only Android device and it is also communicating with the another server which is helping him to provide the right information as he needed in the particular time which is also included the Google map activities and other information such as recently event, location, directions, other way to reach principles room and so on. In this paper it has also introduces us architecture of the proposed system and there are also some use case diagram and detailed diagram for the information of the system to prepare create the AI based program to help to guide us in the proper destination though it is not that big why to implement in our part but it does give a hint to work on it and which will help to make a suitable program based AI tour guide.
Paper Five:
Title: Smart tourist information points by combining agents, semantics and AI techniques
Authors: Piedad Garrido, J. Barrachina, Francisco J. Martinez, Francisco J. Serón
Time: January, 2016
Summary:
This paper has given all the information about this topic target points info which includes the smart tourist information and it refers to combining agents and semantic and also relevant to AI techniques. Basically this project's motive was to provide the information about the place of Spain which is also known as Teruel which has some beautiful insights. So this project has the definition of making a prototype in a simulation project as it includes an animated interface of a human which will be a tour guide of the user and it will give all of the tourist information about that place by searching in a way of using AI techniques and also some other criteria. After studying this paper we have acknowledged many things about the techniques of using AI to text to speech and also gaining the information from user to the AI to provide every information according to the knowledge database. As our project has the target to work with the help of GPS and the location track but this paper will also help us to define other corrections which will give the perfection about our real project.
If you talk about that how they were using the methodology to build their technique is more reliable and workable as you can see they have use the type of using ontology which is very unique and it is very new to us also on the other hand they have used the ontology which is also known as in a short form owl and which defines ontology web language also it has use this owl techniques because they are haven't used the RDF technology because that doesn't give the proper result with the AI techniques which they are providing through their project. From this paper we have also learn some other techniques which which is required for us to understand this technique to use those in our project and also in this case we have learn some other techniques which is known as cement equipped and also AIML which define artificial intelligence meta-data language also we have known some other words which is LWOS and ECAS and also we need to understand about the modelling language and also we have known some other techniques which is required to use them in an AIML database which is graphmaster philosophy e and AIML PadLoq program. This technique has made a great change to make a great impact on the project also they have combined their agents to build TITERIA which is tourist information of Teruel for intelligent agents. And to interact with the user they have made a 3D character of a i which will interact with them to give provide all the information which day we get from the user and the collect those answers from the database and according to those questions they will give the proper answer using the AIML database and that engineer has called as Maxine, who is your given as new inspiration to add a similar kind of interface into our project too. Also on the other hand owl has made great impact to make a relation with one tourist spot with another tourist spot which will combine the Search tree to make a proper decision as a decision tree with the help of an AI techniques.
In the final stage if we talk about the test method as we can see the result has been given the most of the accurate results as because they have tested those things in a simulation way and they have provide a great information about this and their biggest disadvantages was while testing their project prototype they were facing the the problem of of taking the input from the user which is a quite normal for this days and these problems can be solved easily nowadays. And at the last point, as you can see this research topic has given some main points about the way of talking about the tourist spot, also with the AI interface with the help of proper AI techniques, also give us a hint of using this technique combination properly.