The Virginia Tech University Libraries (VTUL) Digital Library Platform (DLP) hosts digital collections that offer our users access to a wide variety of documents of historical and cultural importance. These collections are not only of academic importance but also provide our users with a glance at local historical events. Our DLP contains collections comprising digital objects featuring complex layouts, faded imagery, and hard-to-read handwritten text, which makes providing online access to these materials challenging. To address these issues, we integrate AI into our DLP workflow and convert the text in the digital objects into a machine-readable format. To enhance the user experience with our historical collections, we use custom AI agents for handwriting recognition, text extraction, and large language models (LLMs) for summarization. This poster highlights three collections focusing on handwritten letters, newspapers, and digitized topographic maps. We discuss the challenges with each collection and detail our approaches to address them. Our proposed methods aim to enhance the user experience by making the contents in these collections easier to search and navigate.

People turn to AI for career advice, meal ideas and travel tips, but with the new year started, DailyMail.com Research shows that 23 percent of Americans ditch their New Year's resolutions by the end of the first week, and 43 percent quit by the end of January. The failures stem from people'thinking too big,' but Google's Bard, Microsoft's Bing and ChatGPT have curated 10 realistic but unconventional resolutions for 2024. These included hosting a monthly themed dinner party to build stronger bonds with others, eating a vegan meal each week to improve health and starting a digital detox. Google's Bard said: 'Host a themed dinner party every month.

Distinguishing letters is usually easy for the human brain. The lines on p and d are flipped, for example, and the curves in an a and the cross of a t are dead giveaways. As we read text on a page, neurons in our brain fire, propelling sensory input through complex networks that allow us to interpret and categorize the letters. Computer chips, particularly graphics processing units (GPUs), can achieve the same task with neural networks of their own. When used for applications such as facial recognition, GPUs transform the impinging optical information into electrical signals.

Running a bootstrapped startup is tough, so Alexander Rinke, co-CEO and co-founder of Celonis, tried a quirky way to cut marketing costs: send handwritten letters to would-be clients. He and his team also figured it could be more effective, thinking a typical formal letter to a top exec would routinely be opened and thrown in the garbage by an executive assistant. "We thought if we hand-write the letter and the address on the envelope an executive assistant can't just open it because it might be a personal letter, from a grandmother, a father-in-law or somebody," he told Business Insider. They sent 1,500 handwritten letters to executives of German businesses, dozens of which turned into solid sales leads. Nowadays, Celonis, which uses AI to help businesses evaluate and fix IT processes, doesn't have to worry too much about using offbeat cost-cutting tricks.

This week we speak to Alexander Rinke, co-founder of German technology company Celonis. When Alexander Rinke wanted some of the world's biggest companies to employ his small start-up business he came up with a novel approach - he would send their bosses handwritten letters. "We knew if we sent an email it could just be deleted," he says. "And if we sent out typed letters then their secretaries would open them, and bin them as junk mail. "But with a handwritten note, it seems more personal, it could have been a letter from a family member, or a friend." Alexander launched Celonis when he was 22 with two friends, Martin Klenk and Bastian Nominacher, in 2011 after they had finished maths and computer science degrees at the Technical University of Munich. Expanding on a project they had worked on as part of their courses, Celonis is a hi-tech data mining company that uses software and artificial intelligence to monitor the performance of businesses, to help them become more efficient and work better. In very simple terms, Celonis's software will monitor a company's computer system, and find out things such as which employees are being unproductive, which suppliers are too slow, and which production processes could be streamlined. The three friends were confident about what they could offer businesses, but they just needed to get themselves noticed. They worked like a treat, leading to meetings with some of the largest companies in Europe. Today, eight years later, Celonis's customers include BMW, Exxon-Mobile, General Motors, L'Oreal, Siemens, Uber and Vodafone. And after securing an additional $50m (£39m) of investment last year, Celonis says it is now valued at more than $1bn (£780m). Born and raised in Berlin, Alexander says he started his first company when he was just 15, supplying tutors to high school students. "It was great to get my first idea of how a business ran," he says. "But ultimately I knew it wouldn't last forever." Fast-forward to 2011 in Munich, and Alexander came up with the idea for Celonis when, as part of their studies, he, Martin and Bastian were helping a real world business improve its customer service. The three students found that the firm was taking about five days to come up with fixes to problems, and they thought there must be a quicker way. "We interviewed people in the company to try and understand why it took so long," says Alexander, who is now 29. "But we quickly realised that no-one was going to take the blame.

Schoolgirl Chloe Bridgewater melted hearts around the world when she sent a handwritten letter to Google asking for a job for when she grows up. Google CEO Sundar Pichai replied telling Chloe that he looks'forward to receiving' her job application and encouraged the young girl to follow her dreams. But now the seven-year-old has bagged her first job as a product tester for children's computing company Kano. Chloe, who lives in Hereford, was inspired to write the letter after seeing images of Google offices filled with comfy bean-bags, go-karts and slides. Now Chloe and her five-year-old sister Hollie have been asked to become product testers for Kano, a company that makes DIY computer kits for children.

Some kids want to be astronauts, firefighters or chefs when they grow up – but one little girl has her sights set on one of the biggest tech companies in the world. Chloe Bridgewater, age 7, sent Google a handwritten letter noting her computer skills and expressing interest in working at a place that provides bean-bag chairs and go-karts for their employees. The'Google boss', CEO Sundar Pichai, replied telling Chloe that he looks'forward to receiving' her job application and encouraged the young girl to follow her dreams. Chloe, who lives in Hereford, England, was inspired to write the letter after seeing images of Google offices filled with comfy bean-bags, go-karts and slides. And the original letter was shared with Matt Weinberger of Business Insider by Chloe's father Andy Bridgewater.

Classification Ensemble, which uses the weighed polling of outputs, is the art of combining a set of basic classifiers for generating high-performance, robust and more stable results. This study aims to improve the results of identifying the Persian handwritten letters using Error Correcting Output Coding (ECOC) ensemble method. Furthermore, the feature selection is used to reduce the costs of errors in our proposed method. ECOC is a method for decomposing a multi-way classification problem into many binary classification tasks; and then combining the results of the subtasks into a hypothesized solution to the original problem. Firstly, the image features are extracted by Principal Components Analysis (PCA). After that, ECOC is used for identification the Persian handwritten letters which it uses Support Vector Machine (SVM) as the base classifier. The empirical results of applying this ensemble method using 10 real-world data sets of Persian handwritten letters indicate that this method has better results in identifying the Persian handwritten letters than other ensemble methods and also single classifications. Moreover, by testing a number of different features, this paper found that we can reduce the additional cost in feature selection stage by using this method.