Collaborating Authors


Efficacy of Statistical and Artificial Intelligence-based False Information Cyberattack Detection Models for Connected Vehicles Artificial Intelligence

Connected vehicles (CVs), because of the external connectivity with other CVs and connected infrastructure, are vulnerable to cyberattacks that can instantly compromise the safety of the vehicle itself and other connected vehicles and roadway infrastructure. One such cyberattack is the false information attack, where an external attacker injects inaccurate information into the connected vehicles and eventually can cause catastrophic consequences by compromising safety-critical applications like the forward collision warning. The occurrence and target of such attack events can be very dynamic, making real-time and near-real-time detection challenging. Change point models, can be used for real-time anomaly detection caused by the false information attack. In this paper, we have evaluated three change point-based statistical models; Expectation Maximization, Cumulative Summation, and Bayesian Online Change Point Algorithms for cyberattack detection in the CV data. Also, data-driven artificial intelligence (AI) models, which can be used to detect known and unknown underlying patterns in the dataset, have the potential of detecting a real-time anomaly in the CV data. We have used six AI models to detect false information attacks and compared the performance for detecting the attacks with our developed change point models. Our study shows that change points models performed better in real-time false information attack detection compared to the performance of the AI models. Change point models having the advantage of no training requirements can be a feasible and computationally efficient alternative to AI models for false information attack detection in connected vehicles.

Google Announces Three Data & Analytics Tools At Cloud Summit


At Google I/O, the global tech giant announced the launch of Vertex AI, a managed ML platform to develop end-to-end machine learning workflows. This new platform from Google Cloud aims to help MLOPs engineers build, deploy, and scale ML models faster. Later, Google Cloud unveiled three new products--Dataplex, Datastream and Analytics Hub–at its inaugural Cloud Summit. Google said the new products and services are designed to fully unify databases, analytics and AI in an open data cloud so that enterprises can predict outcomes and make informed choices on-the-go, and in real-time. Data silos have become a significant challenge for enterprises of all shapes and sizes.

Quick Apply: 7 Lucrative Data Science Internships in May 2021


Data science is one of the ground-breaking fields for students who have a knack and a keen eye for details in the world of science and technology. Companies are in dire need of aspiring data scientists for proper usage of the continuous flow of real-time data to enhance the business in the competitive world. The future of a company is dependent on data science due to the upsurge of raw data in the tech-savvy era. So, what is the best way to kick-start your career in data science? Analytics Insight has made you a list of seven reputed companies that have vacancies for data science internships.

Pervasive AI for IoT Applications: Resource-efficient Distributed Artificial Intelligence Artificial Intelligence

Artificial intelligence (AI) has witnessed a substantial breakthrough in a variety of Internet of Things (IoT) applications and services, spanning from recommendation systems to robotics control and military surveillance. This is driven by the easier access to sensory data and the enormous scale of pervasive/ubiquitous devices that generate zettabytes (ZB) of real-time data streams. Designing accurate models using such data streams, to predict future insights and revolutionize the decision-taking process, inaugurates pervasive systems as a worthy paradigm for a better quality-of-life. The confluence of pervasive computing and artificial intelligence, Pervasive AI, expanded the role of ubiquitous IoT systems from mainly data collection to executing distributed computations with a promising alternative to centralized learning, presenting various challenges. In this context, a wise cooperation and resource scheduling should be envisaged among IoT devices (e.g., smartphones, smart vehicles) and infrastructure (e.g. edge nodes, and base stations) to avoid communication and computation overheads and ensure maximum performance. In this paper, we conduct a comprehensive survey of the recent techniques developed to overcome these resource challenges in pervasive AI systems. Specifically, we first present an overview of the pervasive computing, its architecture, and its intersection with artificial intelligence. We then review the background, applications and performance metrics of AI, particularly Deep Learning (DL) and online learning, running in a ubiquitous system. Next, we provide a deep literature review of communication-efficient techniques, from both algorithmic and system perspectives, of distributed inference, training and online learning tasks across the combination of IoT devices, edge devices and cloud servers. Finally, we discuss our future vision and research challenges.

Blockchained Federated Learning for Threat Defense Artificial Intelligence

Given the increasing complexity of threats in smart cities, the changing environment, and the weakness of traditional security systems, which in most cases fail to detect serious threats such as zero-day attacks, the need for alternative more active and more effective security methods keeps increasing. Such approaches are the adoption of intelligent solutions to prevent, detect and deal with threats or anomalies under the conditions and the operating parameters of the infrastructure in question. This research paper introduces the development of an intelligent Threat Defense system, employing Blockchain Federated Learning, which seeks to fully upgrade the way passive intelligent systems operate, aiming at implementing an Advanced Adaptive Cooperative Learning (AACL) mechanism for smart cities networks. The AACL is based on the most advanced methods of computational intelligence while ensuring privacy and anonymity for participants and stakeholders. The proposed framework combines Federated Learning for the distributed and continuously validated learning of the tracing algorithms. Learning is achieved through encrypted smart contracts within the blockchain technology, for unambiguous validation and control of the process. The aim of the proposed Framework is to intelligently classify smart cities networks traffic derived from Industrial IoT (IIoT) by Deep Content Inspection (DCI) methods, in order to identify anomalies that are usually due to Advanced Persistent Threat (APT) attacks.

Review: Kinetica analyzes billions of rows in real time


In 2009, the future founders of Kinetica came up empty when trying to find an existing database that could give the United States Army Intelligence and Security Command (INSCOM) at Fort Belvoir (Virginia) the ability to track millions of different signals in real time to evaluate national security threats. So they built a new database from the ground up, centered on massive parallelization combining the power of the GPU and CPU to explore and visualize data in space and time. By 2014 they were attracting other customers, and in 2016 they incorporated as Kinetica. The current version of this database is the heart of Kinetica 7, now expanded in scope to be the Kinetica Active Analytics Platform. The platform combines historical and streaming data analytics, location intelligence, and machine learning in a high-performance, cloud-ready package.

AI in IoT for a Better Future - NASSCOM Community


Introducing IoT & AI Artificial intelligence helps machines to behave like humans such as face recognition, decision making, learning and solving problems. Artificial Intelligence are used for learning and making self-decisions by using the process of complex organized or unorganized data. This technology has given a new horizon to the digital world like the way smartphones made a change in our lives. Every day, we get to hear about new upgrades and new technologies bringing rapid change in the globe. With every change, the tech world is also growing resulting in advanced technology which is bringing us closer. Such an example is the development & advancement of IoT or internet of things. Here artificial experience plays the role to speed up user experience. Before getting into the technical skills of IoT, lets understand what is it and where is it required? (Picture Reference: Actually IoT cannot work without AI. Why? Internet of things (IoT) is a network of technologies or sensors that contains some advance technology embedded into it. It helps in communicating and interacting with their data. The process involves receiving and transferring data through the network without human interactions or human to computer involvement. These data from devices or sensors can be stored in the cloud and it can be made available for real-time analytics. IoT collects these vast amount of data from different environment. With the help of data science and applying analytics, AI converts these collective data into applications. So the whole process involves collecting and processing data. AI and IoT: Why Do We Need It? According to a report, companies like Deloitte have already using AI and IOT for establishing themselves in the market in 2017.  So why is it so important? Actually artificial intelligence has become a perfect solution to manage multiple connected IoT elements, its unlimited processing and learning abilities. These are considered to be quite useful for making sense of millions of data transmitted by IoT devices. (Reference: ) How Does The Steps Takes Place? We can call IoT as the data “supplier” while machine learning can be considered as data “miner.” The process takes place as follows: IoT sensors supplies millions of data points. The “miner” or machine learning identifies the relations between them Extract meaningful insight from these variables. Transport it to the storage for further analysis. (Picture Reference: Earlier the traditional analytical approach was used which was as follow: The system gathers past data. Data processing. Generate reports. Thus we can conclude that IoT and machine learning works more on prediction. It starts with the desired outcome and searches interactions between input variables to produce results. As more data are being received and aggregated, the system returns even more accurate predictions due to its smart thinking. In this way, businesses can conclude to a perfect decision without actual “thinking” or human interaction. How IoT Benefits From AI? Soon, IoT would produce vast amount of data due to the rapid growing of devices and sensors. According to a research, 50 billion devices will be connected to the internet by 2020, ranging from smartphones, gadgets, smart watches, various computer systems and vehicles. These data would be a lot helpful for various things such as predicting natural calamities, accidents and crimes, helps doctors getting real-time information from medical equipment, optimized productivity across industries, predictive maintenance on equipment and machinery, create smart homes with connected appliances and provide critical communication between self-driving cars. The possibilities are endless. (Picture Reference: These big data are important only when it is transformed into valuable and actionable information within a given time period. Obviously it is not possible for human hands to do it. This is where artificial intelligence comes into play. AI collects the data and extracts the meaning from it by applying analytics. When we feed data from IoT devices into an AI system, it reviews and analyzes the data, produces decisions made either by machines or humans. (Reference: Examples showing implementing AI in IoT applications. Smart decisions. When a device detects unusual conditions due to any error, it needs to know how to and when to react or whether it need human assistance. Obviously intelligent learning and decision-making capabilities are required to make such wise decisions. Google uses this approach in the Rank Brain algorithm. Once the solution is made, it responds in real-time without any human intervention. (Reference: Smart Meters. Smart meters use specially designed sensors, incorporated into smart grids to record and upload electrical and background data. Here Artificial Intelligence techniques are applied to the grid to integrate privacy. They are used in every electricity consumption unit. Not only does they have the bidirectional flow of both electricity, they are equipped with real-time sensors which collects data on relevant factors that includes frequencies used by different equipment and appliances. (Reference: Boosting efficiency. Machine learning with AI can decipher trends and make predictions about future events, by applying predictive analytics. This shows the real benefits of IoT in a variety of manufacturing industries. Healthcare. In the healthcare sector, AI with IoT can improve patient care. Sensors from medical devices such as healthcare mobile apps, fitness trackers and digital medical records have been producing and storing patient’s data. The AI and IoT approach can help predict diseases, suggest preventive maintenance, track physical activity, heart rate, body mass, temperature and provide drug administration by reviewing the medical history and identifying the health problem. When it is regarding health protection or disease control, patients and doctors would accept the benefits that come with the AI and IoT approach. (Reference: Forecasting. Accurate forecasts help farmers to plan farming or harvesting. Train or plane schedules fully depends on weather forecasting to modify for expected weather interruptions. Businesses that are weather dependent, such as landscaping or utility companies can accurately employ labor and resources according to expected weather events. AI can help make more accurate forecasting. Artificial intelligence (AI) techniques apply its method on past predictions and actual outcomes. By comparing predictions with outcomes, it produces results for the future, with greater accuracy. AI feed both old and currently available data into algorithms that effective at past occurrences with future predictions. (Reference: Scalability. IoT can scale data. It means: AI extracts information from one device. Analyses and summarizes the data. Transfer it to the other. Thus it reduces the enormous amount of data to a lesser amount and enables a larger number of IoT devices to be connected to the network. This is called scalability. (Picture Reference: ) Smart Devices: Today we have basic things fitted with technology like smart TV, smart watch, smart security system. Even we have “intelligent” vacuum cleaners, doorbells and lightning systems which have already come to the market. All this is due to artificial intelligence and it do makes life easier. AI can make life in smart homes even more comfortable. It can detect your mood and analyze your interaction with home objects such as Adjusting temperature for both heating and cooling. Adjusting lighting. Put on music of your choice. Close or open windows depending on the weather. Conclusion The IoT and Artificial Intelligence (AI) will play a vital role in the future as it has become a growing need for technologies in both private and government sectors. Engineers, scientists and technologists have already started to implement it in various levels. The potential opportunities and benefits of both AI and IoT can be gained once they are combined, both at the devices end as well as at the server. (References :, , ) Written by: Ayanti Goswami

Data Stream Clustering: A Review Artificial Intelligence

Number of connected devices is steadily increasing and these devices continuously generate data streams. Real-time processing of data streams is arousing interest despite many challenges. Clustering is one of the most suitable methods for real-time data stream processing, because it can be applied with less prior information about the data and it does not need labeled instances. However, data stream clustering differs from traditional clustering in many aspects and it has several challenging issues. Here, we provide information regarding the concepts and common characteristics of data streams, such as concept drift, data structures for data streams, time window models and outlier detection. We comprehensively review recent data stream clustering algorithms and analyze them in terms of the base clustering technique, computational complexity and clustering accuracy. A comparison of these algorithms is given along with still open problems. We indicate popular data stream repositories and datasets, stream processing tools and platforms. Open problems about data stream clustering are also discussed.

6G White Paper on Edge Intelligence Artificial Intelligence

In this white paper we provide a vision for 6G Edge Intelligence. Moving towards 5G and beyond the future 6G networks, intelligent solutions utilizing data-driven machine learning and artificial intelligence become crucial for several real-world applications including but not limited to, more efficient manufacturing, novel personal smart device environments and experiences, urban computing and autonomous traffic settings. We present edge computing along with other 6G enablers as a key component to establish the future 2030 intelligent Internet technologies as shown in this series of 6G White Papers. In this white paper, we focus in the domains of edge computing infrastructure and platforms, data and edge network management, software development for edge, and real-time and distributed training of ML/AI algorithms, along with security, privacy, pricing, and end-user aspects. We discuss the key enablers and challenges and identify the key research questions for the development of the Intelligent Edge services. As a main outcome of this white paper, we envision a transition from Internet of Things to Intelligent Internet of Intelligent Things and provide a roadmap for development of 6G Intelligent Edge.

pAElla: Edge-AI based Real-Time Malware Detection in Data Centers Machine Learning

The increasing use of Internet-of-Things (IoT) devices for monitoring a wide spectrum of applications, along with the challenges of "big data" streaming support they often require for data analysis, is nowadays pushing for an increased attention to the emerging edge computing paradigm. In particular, smart approaches to manage and analyze data directly on the network edge, are more and more investigated, and Artificial Intelligence (AI) powered edge computing is envisaged to be a promising direction. In this paper, we focus on Data Centers (DCs) and Supercomputers (SCs), where a new generation of high-resolution monitoring systems is being deployed, opening new opportunities for analysis like anomaly detection and security, but introducing new challenges for handling the vast amount of data it produces. In detail, we report on a novel lightweight and scalable approach to increase the security of DCs/SCs, that involves AI-powered edge computing on high-resolution power consumption. The method -- called pAElla -- targets real-time Malware Detection (MD), it runs on an out-of-band IoT-based monitoring system for DCs/SCs, and involves Power Spectral Density of power measurements, along with AutoEncoders. Results are promising, with an F1-score close to 1, and a False Alarm and Malware Miss rate close to 0%. We compare our method with State-of-the-Art MD techniques and show that, in the context of DCs/SCs, pAElla can cover a wider range of malware, significantly outperforming SoA approaches in terms of accuracy. Moreover, we propose a methodology for online training suitable for DCs/SCs in production, and release open dataset and code.