IndexIntroductionSee calculationsCity calculationsTypical technologyFuture directionsConclusionThere is a growing problem with the rapid increase in the volume of data, the experience of cyber attackers and the lack of experienced cybersecurity experts. We need a new approach to compete with modern security threats. How do we address these problems? Cognitive computing improvises anyway. Cognitive computing is the interchange between machine learning, natural processing, and big data, which helps leverage structured and unstructured data. Say no to plagiarism. Get a tailor-made essay on "Why Violent Video Games Shouldn't Be Banned"? Get an Original Essay IntroductionCyber ​​refers to information, technology, the Internet, and virtual reality. Cybersecurity is a comprehensive understanding of modern information and technologies and methods of protecting and preserving data from threats such as misuse and safeguarding the system. The volume and complexity have increased, not the basic concept of information protection and espionage for industrial and military purposes. Cyber ​​law has the advantage of global connectivity: everything is connected to everything. But with people connected to such a large network, the risk of digitizing data is high. There is a sharp increase in hacktivism (the use of computer hacking for political activism), with large swathes of cybercrime and a dependency on the internet as devices proliferate. Cyber ​​threats are classified into six different categories with a higher threat level than the previous category. The first threat includes the threat from automated attacks, worms and viruses. The second concerns script kiddies (unqualified individuals who use scripts or programs to attack your system or deface websites developed by other people). The next one, i.e. the third level, is the unskilled attackers. The fourth level includes coders and programmers. The fifth type is the highly skilled and targeted attack against a company or area. And finally we have the “zero day” attacks. They cause enormous damage to property and life. See calculations Framework of Cognitive Computing and Cyber ​​Security Cognitive computing is a process of acquiring, integrating and analyzing large and heterogeneous data generated from different sources in urban spaces, such as sensors, devices, vehicles, buildings and humans, to address the main issues that cities face representing the third era of information technology. Cognitive computing being adaptive, interactive, and stateful, context enables technologies to provide deep insight into the domain. It connects discrete and ubiquitous sensing technologies, advanced data management and analytical models, and new visualization methods to create win-win solutions that improve the environment, quality of human life, and city operating systems. Cognitive computing also helps us understand the nature of urban phenomena and even predict the future. It is an interdisciplinary field that merges the field of computer science with traditional fields such as transportation, civil engineering, economics, ecology and sociology in the context of urban spaces. Computing with Advanced Soc Operations Mature cybersecurity is completely dependent on the ability to detect an error when an attack is occurring. The two basic functions of the then include the first aid function and the second level support function during attacks and accidents. But as systems and attackers became more experienced, labor costs inevitably increased. The calculationCognitive can automatically acquire data, weigh, distinguish and analyze huge amounts of data which is expected to be the main feature of the threat. A simple algorithm written in the computer way better than extreme human determination and attention since the computer is powerful is enough to control the entire system at once through the subtle anomalies and attack pattern. With automatic threat detection, the system can also verify the easing of the system configuration with system fix proposals. Using cognitive computing, SOCs were able to reduce average time from hours to minutes by determining the root cause. The benefit of doing so includes increasing coverage of the organization and also covering the skills and talent gap. IT with automated threat intelligence The dependence of cybersecurity is on reactive strategies, i.e. the response to the threat is given when it occurs. Cognitive computing has the potential to safeguard the system by transforming its massively parallelized information analysis capabilities to vast repositories of existing cybersecurity information. Urban calculations For transportation systems Improve driving experiences. Finding fast driving routes saves driver time and energy consumption as traffic congestion wastes a lot of fuel. Extensive studies have been conducted to learn historical traffic patterns, estimate traffic flows in real time, and predict future traffic conditions on individual road segments in terms of fluctuating car data, such as vehicle GPS trajectories, WiFi, and GSM signals. However, modeling work on city traffic patterns is still rare. Improve taxi services. Taxis are an important mode of travel between public and private transport, providing almost door-to-door travel services. In big cities like New York and Beijing, people usually wait a non-trivial time before catching a free taxi, while taxi drivers are eager to find passengers. Effectively connecting passengers to free taxis is of great importance to save waiting time, increase taxi drivers' profits and reduce unnecessary traffic and energy consumption. Improve public transport systems. It is predicted that by 2050, 70% of the world's population will live in cities. Municipal planners will face an increasingly urbanized and polluted world, with cities around the world suffering from an overly stressed road transport network. Building more effective public transport systems, as alternatives to private vehicles, has therefore become an urgent priority, both to ensure a good quality of life and a cleaner environment, and to remain economically attractive to potential investors and employees. Mass public transport systems, combined with integrated fare management and advanced traveler information systems, are considered key enablers to better manage mobility. For the environment Without effective and adaptive planning, the rapid progress of urbanization will become a potential threat to the environment of cities. Recently, we have witnessed an increasing trend of pollution in different aspects of the environment, such as air quality, noise and waste, across the world. Protecting the environment while modernizing people's lives is of paramount importance in urban computing. Urban Informatics for Urban Energy Consumption The rapid progress of urbanization is consuming more and more energy, requiring technologies that can detect city-scale energy costs, improveenergy infrastructure and, finally, reduce energy consumption. Urban Informatics for the Economy The dynamics of a city (for example, human mobility and the number of changes in a POI category) can indicate the performance of the city's economy. For example, the number of movie theaters in Beijing continued to increase from 2008 to 2012, reaching 260. This could mean that more and more people living in Beijing would like to watch a movie in a movie theater. Conversely, some POI categories will disappear in a city, denoting declining business. Similarly, human mobility could indicate the unemployment rate of some large cities, thus helping to predict the performance of a stock market. Urban IT for public safety Major events, pandemics, serious accidents, environmental disasters and terrorist attacks represent additional threats to public safety and order. It provides the wide availability of different types of urban data with the ability, on the one hand, to learn from history how to correctly manage the aforementioned threats and, on the other hand, to detect them in a timely manner or even predict them in advance. Typical technologies Management techniques of urban dataData generated in urban spaces is usually associated with a spatial or spatiotemporal property. For example, road networks and POIs are the frequently used spatial data in urban spaces; Weather data, surveillance video, and electricity consumption are temporal data (also called time series or flow). Other data sources, such as traffic flows and human mobility, simultaneously have spatiotemporal properties. Sometimes temporal data can also be associated with a location, thus becoming a kind of spatiotemporal data (for example, the temperature of a region and the electricity consumption of a building). Therefore, good urban data management techniques should be able to handle spatial data and spatiotemporal data efficiently. Furthermore, an urban information system usually needs to exploit a variety of heterogeneous data. In many cases, these systems are needed to quickly respond to instant user queries (for example, predict traffic conditions and predict air pollution). Without data management techniques that can organize multiple heterogeneous data sources, it becomes impossible for the subsequent data mining process to quickly gain knowledge from these data sources. For example, without an efficient spatiotemporal indexing structure that organizes POI, road networks, traffic, and human mobility data well in advance, the unique feature extraction process of the U-Air project will take a few hours. The delay will prevent this application from telling people about a city's air quality every hour. Techniques to Handle Data Scarcity There are many reasons that lead to a data shortage problem. For example, a user would only check in to certain places in a location-based social networking service, and some places might not have people visiting them. If we enter the user's location into a matrix where each entry denotes the number of user visits to a location, the matrix is ​​very sparse; that is, many items have no value. If we further consider the activities (such as shopping, eating, and playing sports) that a user can perform in a location as a third dimension, a tensor can be formulated. Naturally the tensor is even more sparse. Data sparsity is a general challenge that has been studied for years in many computing tasks. Big Data Visualization When it comes to data visualization, many people only think of (1) visualizing raw data and (2) presenting data.results generated from the data. -mining processes. The former can reveal the correlation between different factors, thus suggesting characteristics for a machine learning model. As mentioned above, spatiotemporal data is widely used in urban computing. For a complete analysis, the data must be considered from two complementary perspectives: (1) as spatial distributions that change over time (i.e. spaces in time) and (2) as profiles of local temporal variation distributed in space. However, data visualization is not just about displaying raw data and presenting the results. Exploratory visualization becomes even more important in urban computing. Semi-supervised learning and transfer learning. Semi-supervised learning is a class of supervised learning tasks and techniques that also use unlabeled data for training, typically a small amount of labeled data with a large amount of unlabeled data. data. Many researchers in the field of machine learning have found that unlabeled data, when used in conjunction with a small amount of labeled data, can produce a dramatic improvement in learning accuracy. There are multiple semi-supervised learning methods, such as generative models, graph-based methods, and co-training. Specifically, co-training is a semi-supervised learning technique that requires two views of the data. Each example is described by two different sets of features that provide different and complementary information about an instance. Ideally, the two feature sets of each instance are conditionally independent given the class, and the class of an instance can only be accurately predicted from each view. Co-training can generate a better inference result because one of the classifiers correctly labels data that the other classifier had previously misclassified. Transfer learning: An important assumption in many machine learning and data mining algorithms is that training and future data must be in the same format. same feature space and have the same distribution. However, in many real-world applications, this assumption may not hold. For example, sometimes we have a classification task in one domain of interest, but we only have enough training data in another domain of interest, where the latter data might be in a different feature space or follow a different data distribution . Different from semi-supervised learning, which assumes that the distributions of labeled and unlabeled data are the same, transfer learning, in contrast, allows the domains, tasks, and distributions used in training and testing to be different. In the real world, we see many examples of learning transfer. For example, learning to recognize tables can help you recognize chairs. Optimization Techniques First, many data mining tasks can be solved using optimization methods, such as matrix factorization and tensor decomposition. Examples include location and activity recommendations and inference research on refueling behavior. Second, the learning process of many machine learning models is actually based on optimization and approximation algorithms, such as maximum likelihood, gradient descent, and EM (estimation and maximization). Third, the results of operations research can be applied to solving an urban computing task when combined with other techniques, such asdatabases. For example, the ridesharing problem has been studied in operations research for many years. It has been shown to be an NP-hard problem if we want to minimize the total travel distance of a group of people expecting to share rides. As a result, it is really difficult to apply existing solutions to a large group of users, especially in an online application. In the dynamic taxi ridesharing system, T-Share combined spatiotemporal database techniques with optimization algorithms to significantly reduce the number of taxis to control. Finally, the service can be provided online to answer instant questions from millions of users. Another example combined a PCA-based anomaly detection algorithm with L1 minimization techniques to diagnose traffic flows leading to a traffic anomaly. The spatiotemporal properties and dynamics of urban computing applications also pose new challenges to current operations research. Information Security Information security is also not trivial for an urban computing system that can collect data from multiple sources and communicate with millions of devices and users. Common problems that might occur in urban computing systems include data security (e.g., ensuring that received data is integrated, up-to-date, and undeniable), authentication between different sources and clients, and intrusion detection in a hybrid system ( connecting digital and physical worlds).Future DirectionsAlthough many research projects on urban computing have been conducted in recent years, there are still some technologies that are missing or not well studied. Balanced Crowd Sensor: Data generated through a crowd sensing method is not evenly distributed across geographic areas and time spaces. In some locations we may have much more data than we actually need. A downsampling method (e.g., compressive sensing) might be useful to reduce the communication loads of a system. Conversely, in places where we may not have enough data or even have it at all, some incentives should be considered that can motivate users to provide data. Given a limited budget, it still needs to be explored how to configure the incentive for different locations and time periods so as to maximize the quality of the data received (e.g., coverage or accuracy) for a specific application. Skewed data distribution: in many In some cases, what we can get is a sample of urban data, the distribution of which may be skewed compared to the full dataset. Having the entire data set may always be infeasible in an urban computing system. Some information is transferable from partial data to the entire data set. For example, the travel speed of taxis on the road can be transferred to other vehicles traveling on the same road section. Similarly, the waiting time of a taxi at a petrol station can be used to deduce the queuing time of other vehicles. Other information, however, cannot be transferred directly. For example, the traffic volume of taxis on a street may be different from that of private vehicles. As a result, seeing multiple taxis on a stretch of road does not always suggest multiple other vehicles. Management and indexing of multimodal data sources: Different types of index structures have been proposed to handle different types of data individually, while the hybrid index that can simultaneously handle multiple types of data (e.g. spatial, temporal and social media) need to yet to be studied. The hybrid index is a foundation that enables efficient and effective learning of multiple heterogeneous data sources..