This document discusses a novel approach to gesture recognition using Neo4j graph database integrated with the Leap Motion controller. It summarizes the limitations of current gesture recognition techniques and proposes representing hand motions as graphs stored in Neo4j to overcome issues like data inconsistencies and storage requirements. Preliminary results show 93.4% accuracy for constrained digit recognition and learning rates for gesture interfaces are 40% faster than non-gesture interfaces. The approach aims to advance the future of natural human-interface design.
Senior Design Project: team of four engineers and one professor - Developed a 3-D printed prosthetic robot hand to have: 1) Servo operated fingers and thumb 2) Voice commands for basic gestures The project would take 2 semesters to complete, the 1st semester spent planning with development and prototyping in the 2nd semester. Project requirements: - Project Poster - Prototype - Slideshow Presentation (to be presented in class) - Full Research Report
Keynote given by John Newton, CTO at Alfresco, during Alfresco DevCon 2018. Content management has been called a mature discipline, but emerging technologies like machine learning, cloud services, consumer friendly interfaces, and the block chain promise new capabilities that we need to be prepared to embrace in order for our organizations to successfully navigate the industry's digital transformation. https://www.youtube.com/watch?v=VwC_Ko6Wk-0&list=PLyJdWuUHM3igOUt49uiFqs-6DCQAgJ1vs&index=2
Rersponsive design has changed how we build sites, however whilst we've addressed many of the technical challenges of devices we haven't understood the underlying behaviour that is occurring. This talk highlights how context is increasingly important and how data can be used to create responsive experiences beyond simply reflowing of web pages.
This document discusses challenges facing the open web in a mobile-dominated world. It describes how mobile native platforms are stacked against the mobile web, providing better monetization and a perception that everything must work offline. It discusses the five stages of mourning for the open web, from denial to acceptance. It argues for focusing on simplicity, understanding other perspectives, and promoting the web through love instead of criticism.
This document discusses the development of a sign language recognition system using computer vision and machine learning techniques. It begins with background on the need for such a system to help deaf individuals communicate using technology. The system works by detecting hand signs with a camera and identifying them using a convolutional neural network model. It follows a waterfall development approach with requirements including a laptop, Python software, and sufficient lighting. Benefits are helping learn sign language, while limitations include needing good lighting conditions. Future work could add subtitles to make the system more useful for media applications.
1) Deep neural networks are difficult to understand and analyze due to their complex architectures and large number of parameters. Understanding why neural networks make certain predictions is an important area of research. 2) Influence functions can be used to analyze the effect that individual training samples have on a neural network model's parameters and predictions. This helps explain model behavior and identify influential training points. 3) Identifying influential training samples allows experts to prioritize data points to check for label noise, which can improve model performance. Influence functions also enable crafting adversarial training examples that subtly change a model's predictions without appearing different to humans.
This document summarizes a research paper on developing a hand gesture recognition system using the Holistic Mediapipe framework. The system aims to recognize Indian sign language gestures in real-time using pose estimation and LSTM neural networks. It extracts 3D keypoints of the hands using Mediapipe and feeds this input into an LSTM model for classification. The system was able to achieve higher accuracy compared to models using only CNN layers, and was also faster to train due to using fewer parameters. Limitations of current pose estimation approaches for sign language recognition are also discussed.
With the explosion of new frameworks, a mountain of automation, and our applications distributed across hundreds of services in the cloud, the level of complexity in software development is growing at an insane pace. With increased complexity comes increased costs and risks. When diagnosing unexpected behavior can take days, weeks, or sometimes months, all while our release is on the line, our projects plunge into chaos. In the invisible world of software development, how do we identify what's causing our pain? How do we escape the chaos? Janelle Klein presents a novel approach to measuring the chaos, identifying the causes, and systematically driving improvement with a data-driven feedback loop. Rather than measuring the problems in the code, Janelle suggests measuring the "friction in Idea Flow", the time it takes a developer to diagnose and resolve unexpected confusion, which disrupts the flow of progress during development. With visibility of the symptoms, we can identify the cause—whether it's bad architecture, collaboration problems, or technical debt. Janelle discusses how to measure Idea Flow, why it matters, and the implications for our teams, our organizations, and our industry.
Abstract: DevOps has been one of the game changers to accelerate Collaboration and Automation to drive Speed to Market (Development priorities) and Availability/ Stability/ Performance etc. (IT Operations priorities) for last 8+ yrs. Fast forwarding, Gartner’s 2018 Hype Cycle for Performance Analysis named DevOps and AIOps as two areas that have gained the most momentum in the industry .In essence , AIOPS has helped in shaping DevOp smarter and intelligent i.e. DevOps Systems that Do -> Think -> Learn. Engineering maturity of FAANG (Facebook, Amazon, Apple, Netflix, Google) companies are already in the journey of NoOps - the point where an IT environment becomes so automated that a dedicated team isn’t even needed for managing tasks anymore. For engineering teams to nurture the belief that “machines should solve known problems and engineers must focus on solving new problems,” which essentially means saying NO to manual IT operations. Key Takeaways: 1. Everything As Code 2. Platform as Service 3. DevOps maturity beyond automation 4. Site Reliability Engineering (SRE) 5. Software Engineering Culture.
This talk is about how we applied deep learning techinques to achieve state-of-the-art results in various NLP tasks like sentiment analysis and aspect identification, and how we deployed these models at Flipkart
Richard Tibbetts, CTO, StreamBase Systems. StreamSQL EventFlow is one of the most popular languages for Complex Event Processing (CEP), a data management paradigm for real-time applications. Based on a stream-relational data model common to other CEP languages, EventFlow is unique in that it is a visual language. This talk will focus on the design of visual representations for key features including event dispatch, modularity, data parallelism, polymorphism, and dependency injection, and on the co-development of an Eclipse-based IDE along with a new programming language. StreamSQL EventFlow is the primary programming language for the StreamBase Event Processing Platform. Complex Event Processing platforms are used to process large volumes of event-oriented data in real-time, often in latency-critical applications such as securities trading. Combining clustering, messaging, queuing, data storage, and application logic into one system minimizes latency and gives the programmer control over all aspects of the application. StreamSQL EventFlow is an executable visual language for building CEP applications, unlike visual environments designed for non-developers, or architecture-focused modeling tools. The talk will cover experiences overcoming prejudice against visual programming languages, and how critical development tools are to that process. We will also discuss some details of the implementation including the compiler, a visual debugger, and diff/merge functionality.
There are many ways how application developers using Firebird could paint themselves in the corner. Beside well-known design and development errors, there are also subtle mistakes that could have dire consequences. This talk will guide you through twisted maze of design and development decisions, pointing out the traps, hidden horrors and dead-ends, and strategies how to avoid them.
The document discusses challenges faced by a development team working within a large organization on a SOA project. Key challenges included long development cycles, separate testing teams, infrequent releases, and a lack of feedback mechanisms. The team adopted practices like TDD, trunk-based development, service mocking, and telemetry to reduce their cycle times, minimize risks, and improve quality despite the constraints of the larger organization. While integration issues persisted due to assumptions between teams, the team was able to react quickly to changes and had very low defect rates, though they did not significantly influence practices outside their team.
The document discusses challenges faced by a development team working within a large organization on a SOA project. Key challenges included long development cycles, separate testing teams, infrequent releases, and outdated technologies like SOAP. The team adopted practices like test-driven development, service mocking, telemetry, and exploratory testing to help improve their process under these constraints. While integration issues persisted, the team was able to keep their own defect rates low through these practices.
There is 100% chances you are going to engage your customers on mobile first, but converting them into lifetime and faithful promoters is a multi-screen journey. For brands, media and retailers it is then critical to select the most relevant device-agnostic technology and the
Slides from Deeson's Creative Director, Andrew Larking, and Technical Director, Ronald Ashri, at Museum Association's 'Museum Tech 2017' in London on 29th June. Their keynote focussed on conversational interfaces, their drivers and challenges, and some key guiding principles.
Guidelines for mere mortals. These are a collection of guidelines picked up in the field... hopefully they would help developers and SREs building or modernizing apps ensuring the highest level of availability to their applications.
Presented at Gartner Data & Analytics, London Maty 2024. BT Group has used the Neo4j Graph Database to enable impressive digital transformation programs over the last 6 years. By re-imagining their operational support systems to adopt self-serve and data lead principles they have substantially reduced the number of applications and complexity of their operations. The result has been a substantial reduction in risk and costs while improving time to value, innovation, and process automation. Join this session to hear their story, the lessons they learned along the way and how their future innovation plans include the exploration of uses of EKG + Generative AI.
Gursev Pirge, PhD Senior Data Scientist - JohnSnowLabs
Tomaz Bratanic Graph ML and GenAI Expert - Neo4j
Katja Glaß OpenStudyBuilder Community Manager - Katja Glaß Consulting Marius Conjeaud Principal Consultant - Neo4j