Page 2
Page 2
Generative adversarial text to image synthesis
Synthesizing high-quality images from text descriptions is a challenging problem in computer vision and has many practical applications. Samples generated by existing text-to-image approaches can roughly reflect the meaning of the given descriptions, but they fail to contain necessary details and vivid object parts. In order to make the project more specialized, it was approved that the project be dedicated to fashion image generation, we present an effective approach for generating new clothing through generative adversarial learning. Generative Adversarial Networks (GANs) successfully show the capability of synthesizing sharper images compared to other generative models.
Fashionity
This project is an AI fashion design system to generate fashion images based on user textual description. The proposed system incorporates advanced technology for dissemination and machine translation with the aim of facilitating a seamless user experience for input in both Arabic and English languages. Moreover, the project encompasses the incorporation of a recommendation system that proposes appropriate visual content based on user style. The primary objective of this project is to develop a robust framework capable of generating high-quality images based on textual descriptions, providing recommendations for similar clothing items, and facilitating the retrieval of photographic and apparel articles through image search.
Encyclopaedia of the History of Science, Technology, and Medicine in Non-Western Cultures
The second edition of this landmark encyclopaedia will contain approximately 1000 entries dealing in depth with the history of the scientific, technological and medical accomplishments of cultures outside of the United States and Europe. The entries consist of fully updated articles together with hundreds of entirely new topics.This unique reference work includes: Intercultural articles on broad topics such as Mathematics and Astronomy Philosophical articles on concepts and ideas related to the study of non-Western Science, such as Rationality, Objectivity, and Method, Religion and Science, East and West, and Magic and Science Articles on topics such as Native American Mathematics, Polynesian Navigation, Korean Maps, and African Metallurgy Biographical articles for those cultures where individual scientists are known to us, such as China and the Islamic world.
Electromagnetic Compatibility of Integrated Circuits : Techniques for low emission and susceptibility
Electromagnetic Compatibility of Integrated Circuits: Techniques for Low Emission and Susceptibility focuses on the electromagnetic compatibility of integrated circuits. The basic concepts, theory, and an extensive historical review of integrated circuit emission and susceptibility are provided. Standardized measurement methods are detailed through various case studies. EMC models for the core, I/Os, supply network, and packaging are described with applications to conducted switching noise, signal integrity, near-field and radiated noise. Case studies from different companies and research laboratories are presented with in-depth descriptions of the ICs, test set-ups, and comparisons between measurements and simulations. Specific guidelines for achieving low emission and susceptibility derived from the experience of EMC experts are presented.
Egocentric video summarization
Video summarization is defined as the generation of a summary of extensive video content that comes from all kinds of videos including egocentric videos by detecting and presenting the material to potential users which is most informative and contains interesting information. Video summarization has many practical applications and Egocentric video summarization approaches have been proposed to solve various problems in the healthcare industry. This work focuses on Alzheimer. Patients suffering from Alzheimer’s face difficulties in remembering what happened during their day, the identity of persons and medicine they took.
Dependable Systems : Software, Computing, Networks : Research Results of the DICS Program
The present volume documents the results of a research program on Dependable Information and Communication Systems (DICS). The members of the project met in two workshops organized by the Hasler Foundation. This state-of-the-art survey contains 3 overview articles identifying major issues of dependability and presenting the latest solutions, as well as 10 carefully selected and revised papers depicting the research results originating from those workshops. The first workshop took place in Münchenwiler, Switzerland, in March 2004, and the second workshop, which marked the conclusion of the projects, in Löwenberg, Switzerland, in October 2005. The papers are organized in topical sections on surveys, dependable software, dependable computing, and dependable networks.
Dentofacial anomalies : Implications for voice and wind instrument performance
Discusses how dentofacial anomalies affect voice and wind instrument playing with emphasis on upper airway space shape and volume Comprehensively reviews the anatomy and physiology of phonation, with guidelines on the work-up of patients with voice disorders Provides a concise and well-focused description of the common orthodontic disorders, both skeletal and non-skeletal, and their means of diagnosis and treatment
Dental implants and bone grafts : materials and biological issues
Provides detailed coverage of biomaterials for dental implants and bone graft, enabling scientists and clinicians to gain a thorough knowledge of advances and applications in this field. As tooth loss and alveolar bony defects are common and pose a significant health problem in dental clinics, this book deals with timely topics, including alveolar bone structures and pathological changes, reviews of indications and advantages of biomaterials for dental implants and bone graft, design and surface modification, biological interaction and biocompatibility of modern dental implants and bone graft, and new frontiers.This book is a highly valuable resource for scientists, clinicians and implantologists interested in biomaterial and regenerative strategies for alveolar bone reconstruction.
Deepfake detection
Recently, various techniques of manipulating the video content have become available to everyone – online, one can find free applications e.g., for face swapping in videos. Such universal accessibility carries a notable risk of flooding online content with false information, affecting not only the greats of this world, but also the whole societies, also the rapid progress in synthetic image generation and manipulation has now come to a point where it raises significant concerns for the implications towards society. It is therefore necessary to develop a verification tool that will help assess the authenticity of the videos posted on the internet. This project describes the approach of using artificial intelligence solutions to detect doctored videos.
Deepfake detection
The rise of large language models (LLMs) and the increasing sophistication of deepfake images have made detecting synthetic content a pressing challenge. Several approaches have been proposed to tackle this problem, including statistical analysis, and machine learning algorithms. In this project, A novel zero-shot approach is proposed that utilizes the power of LLMs to detect fake text. The pre-trained LLM is fine-tuned to enhance its ability to differentiate real and fake text. The approach uses the LLM to detect text by analyzing the log probabilities of the text. For detecting fake images, computer vision algorithms and neural networks are used to analyze facial features. The facial region is cropped and preprocessed and the neural network identifies patterns indicative of synthetic content.
Deepfake
The technology used to create such digital content has quickly become accessible to the masses, such as “DEEPFAKE.” Deep fakes refer to manipulated videos, or other digital representations produced by sophisticated artificial intelligence, that yields to synthesize a sequence of face images and voices of characters corresponding to their identities, such as voice tone, facial expression, with a good lip synchronization. Therefore, this study is about developing real-time video generation software, which generates a target video from a single input image. Several methods and algorithms have been applied to detect, analyze personalize facial expression, voice and natural head poses to present a life-like image instead of a low quality one.
Crime detection camera
This paper presents a comprehensive crime detection system that uses a combination of hardware and software to monitor homes and communities in real time. The system consists of a Raspberry Pi 4B, a Raspberry Pi Camera V2, a flame sensor, an MQ-6 gas sensor, and a microphone, which are all connected to a database management system powered by MySQL. The data collected from these devices is analyzed by machine learning algorithms to detect crimes, such as theft or robbery, as well as fires and gas leaks. The system also includes a mobile app, ‘Safe Home’ which provides live video monitoring and real-time notifications to users, and an employee dashboard to monitor all statistics and manage all implemented systems.
Corporate Data Quality : Voraussetzung erfolgreicher Geschäftsmodelle
Data is the basis of the digitized economy. Industry 4.0 and digital services produce unprecedented amounts of data and enable new business models. Data quality is becoming a critical success factor. This book presents an approach to quality-oriented data management and ten case studies for practitioners and scientists alike. The book was created in the Competence Center Corporate Data Quality in close cooperation between researchers from the University of St. Gallen and the Fraunhofer IML as well as numerous representatives from more than twenty large companies.
Cooperative tool
Online collaboration is fast becoming a permanent feature of the modern workplace. Companies and organizations are attracted by the cost-effective technology allowing employees to work together anywhere, at any time using any internet-enabled device. Online collaboration gives team members the tools they need to work with others from any location, including from home and while travelling. This drastically reduces “downtime” and allows people to be productive when it best suits them therefore we propose a website that provides content (videoconference, real-time Chat, whiteboard).
Manual of laboratory testing methods for dental restorative materials
Delivers a comprehensive and accessible review of the materials used in restorative dentistry. The book offers readers an evidence-based application of the materials and their mechanical, physical, and optical properties. Each chapter begins with key points and includes a glossary to aid in the learning and retention of the material contained within. The book also covers the methods used to study the properties and the advantages and disadvantages of various dental restorative materials as well as why they are selected.
BioMEMS and biomedical nanotechnology ; Vol. IV : Biomolecular Sensing, Processing and Analysis
This volume contains 18 chapters focused on ‘Biomolecular Sensing, Processing and Analysis’, written by experts in the field of BioMEMS and biomedical nanotechnology. The chapters are groups into three broad categories of Sensors and Materials, Processing and Integrated Systems, and Microfluidics.Prof. Taun Vo-Dinh from Oakridge National Labs begins the Sensors and Materials section by providing a review of biosensors and biochips. This review is followed by an example of mechanical cantilever sensor work described by Prof. Arun Majumdar’s group at UC Berkeley and Prof. Tom Thundat at Oakridge National Laboratory.
Biological and medical data analysis ; Vol. 4345 : 7th International Symposium, ISBMDA 2006, Thessaloniki, Greece, December 7-8, 2006. Proceeding
This book constitutes the refereed proceedings of the 7th International Symposium on Biological and Medical Data Analysis, ISBMDA 2006, held in Thessaloniki, Greece, December 2006. Coverage in this volume includes functional genomics, sequence analysis, biomedical models, information modeling, biomedical signal processing, biomedical image analysis, biomedical data analysis, as well as decision support systems and diagnostic tools.
Biological and medical data analysis ; Vol. 3745 ; 6th International symposium, ISBMDA 2005, Aveiro, Portugal, November 10-11, 2005, Proceedings
The 6th International Symposium on Biological and Medical Data Analysisaimed to become a place where researchersinvolved in these diverse but increas-ingly complementary areas could meet topresent and discuss their scientificresults.The papers in this volume discuss issues from statistical models to archi-tectures and applications to bioinformatics and biomedicine. They cover bothpractical experience and novel research ideas and concepts.
Automatic video editor
Searching in a large database of videos is one of the challenges faced by the user today as most of the results are inaccurate or correct. In our project, we worked on developing a system that receives the search word from the user and searches for it among a large number of videos using MSR-VTT dataset and COCO data set based on the elements that we see inside the video. Entered by the user. We have also worked on adding other options that the user can benefit from in modifying the videos, such as entering a black and white video clip and returning the result in color. The user can also enter a low-resolution video clip, and the system improves the accuracy of the video and sends it.
Assessment of climate change over the Indian Region : A report of the Ministry of Earth Sciences (MoES), Government of India
Discusses the impact of human-induced global climate change on the Indian subcontinent and regional monsoon, the adjoining Indian Ocean and the Himalayas. It also examines the regional climate change projections based on the climate models used by the IPCC Fifth Assessment Report (AR5) and national climate change modeling studies using the IITM Earth System Model (ESM) and CORDEX South Asia datasets
