Octopus: Context-Aware CNN Inference for IoT Applications

The correct implementation and behavior of Internet of Things (IoT) applications are seldom investigated in the literature. This paper shows how the simulation mechanism can be integrated well into an IoT application development platform for correct implementation and behavior investigation. We use an IoT application development platform called IoTtalk as an example to describe how the simulation mechanism called SimTalk can be built into this IoT platform. We first elaborate on how to implement the simulator for an input IoT device (a sensor). Then we describe how an output IoT device (an actuator) can be simulated by an animated simulator. We use a smart farm application to show how the simulated sensors are used for correct implementation. We use applications including interactive art (skeleton art and water dance) and the pendulum physics experiment as examples to illustrate how IoT application behavior investigation can be achieved in SimTalk. As the main outcome of this paper, the SimTalk simulation codes can be directly reused for real IoT applications. Furthermore, SimTalk is integrated well with an IoT application verification tool in order to formally verify the IoT application configuration. Such features have not been found in any IoT simulators in the world.

Widespread adoption of Internet of Things (IoT) applications assumes a sustainable ecosystem of firms creating, distributing, and using these applications. Such an ecosystem often forms around a platform that implements commonly used functionality and offers it to the members of the ecosystem for creating applications and services. In IoT, such a platform may be materialized in a form of a cloud platform that supports the management of connected devices, and the development and use of the applications based on them. A number of cloud platforms targeting IoT applications are available in the market; to prosper, they need to assist the providers of the IoT applications in designing and developing the applications, as well as in deploying and operating the application software. In this paper, a framework for evaluating the IoT platforms from the perspective of how widely they cover the potential needs of the application providers is introduced. Based on the framework, the maturity of the available IoT platforms is evaluated, by using the publicly available information about the platforms' features and supporting services. As the results of this initial analysis suggest, none of the platforms today offers the comprehensive support. This can be seen as a factor contributing to a slow adaption of the IoT platforms, and therefore to the slower-than-expected takeoff of the IoT ecosystem in general.

The Internet of Things (IoT) is a hot topic in the engineering and technology community, and IoT-enabled devices are becoming increasingly common due to advancements in technology. IoT platforms provide valuable and specific services for IoT applications, and the number of platforms used by IoT applications is growing rapidly commensurate with the increasing number of IoT devices. However, fierce competition between IoT platforms is making it difficult for companies to select a suitable type of IoT platform for their business needs. This paper attempts to identify the important factors of IoT platforms that can be consider before selecting an IoT platform. In this paper, Twenty-one important IoT platform factors are identified from the literature and these factors were then verified by the Delphi method and categorized. This paper aims to help companies choose an appropriate IoT platform from the huge number and variety of IoT platforms available in the market.

The real-time communication requirement of the Internet of Things (IoT) applications promotes the convergence of IoT and Mobile Edge Computing (MEC). The MEC paradigm greatly shortens the IoT service delay by leveraging cloudlets (edge servers) of MEC in the proximity of IoT devices. Considering limited computing and storage resources in an MEC network, it is challenging to provide efficient IoT-enabled service provisioning in such a network. In this article, we study the service home identification problem of service provisioning for multi-source IoT applications in an MEC network, by identifying a service home (cloudlet) of each multi-source IoT application for its data processing, querying and storage. Each multi-source IoT application consists of multiple sources located at different geographical locations and each source uploads its data stream via a gateway (its nearby access point) to the MEC network and the uploaded data then is aggregated with the stream data of the other sources of the IoT application at the service home. We here focus on two novel service home identification problems: the service operational cost minimization problem with the aim to minimize the total service operational cost by admitting as many multi-source IoT applications as possible, and the online throughput maximization problem with the aim to maximize the number of multi-source IoT application requests admitted. We first show that both the problems are NP-hard. We then formulate an Integer Linear Programming (ILP) solution to the service operational cost minimization problem, and propose a randomized algorithm with high probability and a deterministic approximation algorithm respectively, at moderate resource capacity violations. We third develop an efficient heuristic algorithm for the problem without any resource violation. Furthermore, we deal with the online throughput maximization problem under an assumption that multi-source IoT application requests arrive one by one without the knowledge of future arrivals, for which we formulate an Integer Linear Programming (ILP) solution to its offline version, followed by devising an online algorithm with competitive ratio. We finally evaluate the performance of the proposed algorithms through experimental simulations. Simulation results demonstrate that the proposed algorithms are promising, and outperform their comparison counterparts.

The rapid development of low-cost sensors, smart devices, communication networks, and learning algorithms has enabled data-driven decision making in large-scale systems. However, the development platforms for such Internet of Things (IoT) applications and collecting the data in a cohesive, yet simple manner is not very well understood. MIT App Inventor [1] is an open-source, user-friendly interface to develop mobile applications and has been used by over ten million users worldwide. We have added IoT capability to the MIT App Inventor platform where people can build applications using various sensors and IoT platforms such as Raspberry Pi [2] and Android Things [3] to collect the data through mobile applications. This poster paper presents a realization of easy to program IoT applications in the mobile application space with a focus on collecting data from the connected sensors. We have integrated the Android Things platform with the MIT App Inventor and introduced the existing MIT App Inventor community to the IoT based App development. This integration allows not only the seasoned developers, but also the novice developers to make interesting IoT applications with minimal programming knowledge.

The term Internet of Things (IoT) refers to a technological revolution that allows nearly all environmental devices to connect to the internet and share data to create services and applications that improve our standard of living. As IoT systems generate huge amounts of data, new IoT applications and facilities arise. Machine learning has made significant progress in several fields and is now being used to solve a variety of IoT network problems. Machine learning has recently become more popular as a means of improving IoT applications. Users can find deep analytics and develop efficient intelligent IoT applications using machine learning for IoT. This chapter focuses on offering an overview of machine learning techniques in the IoT platform. The chapter begins with an overview of the IoT, including its history, architecture, and its applications. Then, many machine learning algorithms, various types, and their applications, with examples, are discussed.

Internet of Things (IoT) applications are generally developed in a vertical manner, i.e., each IoT application is developed for a certain scenario which generally does not share data with IoT applications for recommendation services. This leads to an inefficient exploitation of other IoT service applications. In fact, such recommendation services can be achieved with the help of Social IoT (SIoT) by using data generated by various IoT applications. SIoT builds a profile of objects based on IoT applications data that can be exchanged with SIoT network for accessible to other IoT applications. In this manner, the SIoT network provides recommendation services for reusability of IoT applications' data among various IoT applications, as well as adapting IoT services according to users' needs which improve user experience. Additionally, the profiles built by a SIoT network can also help a single IoT application by looking for similar conditions that have been addressed in the past for the same IoT application. We propose a concept for exploiting the SIoT for recommendation services among various IoT applications with the help of a sample application scenario that highlights how the SIoT can help by providing recommendations. We also provide some implementation challenges for this concept.

The internet of things (IoT) transforms the world in many ways. It combines many types of hardware and software with a variety of communication technologies to enable the development of innovative applications. A typical IoT system consists of IoT device, IoT gateway, IoT platform, and IoT application. Developing these elements and delivering an IoT system for fulfilling business requirements encompasses many activities to be executed and is not straightforward. To expedite these activities, some major vendors provide software development kits (SDK), integrated development environments (IDE), and utility tools for developing software to be executed on IoT devices/gateways. Moreover, these vendors utilize their cloud platforms to provide fundamental services, such as data storage, analytics, stream processing, for developing IoT systems. These vendors also developed IoT specific cloud-based services, such as connectivity and device management, to support IoT system development. This chapter presents an overview of tools and platforms provided by five major vendors.

Some Internet of Things (IoT) platforms use blockchain to transport data. The value proposition of IoT is the connection to the Internet of a myriad of devices that provide and exchange data to improve people’s lives and add value to industries. The blockchain technology transfers data and value in an immutable and decentralised fashion. Security, composed of both non-intentional and intentional risk management, is a fundamental design requirement for both IoT and blockchain. We study how blockchain answers some of the IoT security requirements with a focus on intentional risk. The review of a sample of security incidents impacting public blockchains confirm that identity and access management (IAM) is a key security requirement to build resilience against intentional risk. This fact is also applicable to IoT solutions built on a blockchain. We compare the two IoT platforms based on public permissionless distributed ledgers with the highest market capitalisation: IOTA, run on an alternative to a blockchain, which is a directed acyclic graph (DAG); and IoTeX, its contender, built on a blockchain. Our objective is to discover how we can create IAM resilience against intentional risk in these IoT platforms. For that, we turn to complex network theory: a tool to describe and compare systems with many participants. We conclude that IoTeX and possibly IOTA transaction networks are scale-free. As both platforms are vulnerable to attacks, they require resilience against intentional risk. In the case of IoTeX, DIoTA provides a resilient IAM solution. Furthermore, we suggest that resilience against intentional risk requires an IAM concept that transcends a single blockchain. Only with the interplay of edge and global ledgers can we obtain data integrity in a multi-vendor and multi-purpose IoT network.

Convolutional neural networks (CNNs) have been applied in numerous Internet of Things (IoT) devices for multifarious downstream tasks. However, with the increasing amount of data on edge devices, CNNs can hardly complete some tasks in time with limited computing and storage resources. Recently, filter pruning has been regarded as an effective technique to compress and accelerate CNNs, but existing methods rarely prune CNNs from the perspective of compressing high-dimensional tensors. In this article, we propose a novel theory to find redundant information in 3-D tensors, namely, quantified similarity between feature maps (QSFM), and utilize this theory to guide the filter pruning procedure. We perform QSFM on data sets (CIFAR-10, CIFAR-100, and ILSVRC-12) and edge devices and demonstrate that the proposed method can find the redundant information in the neural networks effectively with comparable compression and tolerable drop of accuracy. Without any fine-tuning operation, QSFM can compress ResNet-56 on CIFAR-10 significantly (48.7% FLOPs and 57.9% parameters are reduced) with only a loss of 0.54% in the top-1 accuracy. For the practical application of edge devices, QSFM can accelerate MobileNet-V2 inference speed by 1.53 times with only a loss of 1.23% in the ILSVRC-12 top-1 accuracy.

The Internet of Things (IoT) platform consists of numerous IoT devices and a small number ofservers. In order for the platform to operate efficiently and reliably, servers need to have completecontrol over many IoT devices. The advantage of using network boot in this environment is thatthe server has control over the device’s boot process. When applying network boot on an IoT platform,the server needs to be able to handle the network boot that many IoT devices request. If theserver does not have enough processing power for the network boot request, IoT device boot wouldbe delayed. In this paper, we propose a resource-efficient network boot to solve this problem. Theproposed framework has three mechanism. First, the server reserves the right to control which systemimage to transfer during the network boot process on the platform. Second, the server appliesdeduplication to the system image to minimize the amount of data required for transmission. Third,the server monitors network boot requests and performs file transfers appropriate to the situation,minimizing time spent on transfers. The proposed system allows the server to efficiently control numerousIoT devices when using network boot on the IoT platform.

With the rapid development of Internet of Things (IoT) and in-depth study of Internet technology, the application of interactive system that depends on collaborative interaction of multiple business processes becomes more and more important in the IoT. In this paper, we present an event-driven multi-process collaborative interaction platform to improve the business processing capabilities of the interactive system and meet the growing business needs of the IoT environment and users. We integrate the IoT paradigm into the traditional business process to make a rapid and timely response to the IoT application. The platform provides visual business modeling (process and event), process management, and process real-time monitoring. Finally, we give an IoT application of the platform in the forest protection.

The Internet of Things (IoT) has had a considerable influence on our daily lives by enabling enhanced connection of devices, systems, and services that extends beyond machine-to-machine interactions and encompasses a wide range of protocols, domains, and applications. However, despite privacy concerns shown by IoT users, little has been done to reduce and protect individual information exposure. It is extremely difficult to mitigate IoT devices from reidentification threats which is why it is still a major challenge for IoT users to securely protect their information. The trust controls how we regulate privacy in our IoT platforms in the same way that it governs personal relationships. As IoT devices become increasingly linked, more data is shared across individuals, businesses, governments, and ecosystems. Technologies, sensors, machines, data, and cloud connections all rely largely on trust relationships that have been formed. With the rapid growth of additional types of IoT devices that are being introduced, it, therefore, expands privacy concerns and is difficult to develop trust with an IoT system or device without the option to regulate information privacy settings. Privacy has always been a barrier for many devices as they race for the early adoption of IoT technologies. Several Internet of Things devices or systems will continue to pose privacy threats. As a result, the main objective of this study was to examine the individual understanding of privacy and to promote information privacy protection awareness not only to IoT users but also to organizations that use IoT devices or platforms to run their day-to-day business operations. Furthermore, the objective extends to compare user knowledge and concerns about IoT privacy, as well as to identify any common attitudes and variances. However, in terms of enhancing individuals’ knowledge, an artifact was developed to educate and enhance information privacy awareness among IoT users. A pre- and postquestionnaire was generated to test and validate user knowledge regarding information privacy protection in IoT. The study was conducted using a quantitative research method. Findings indicate that IoT users’ awareness of information privacy protection turned out to be average, suggesting a need for education and awareness. Several participants stated that information privacy protection awareness is required within the community to educate, raise awareness, eliminate human error, and enable individuals to be conscious of their privacy when surfing the Internet.

Convolutional neural networks and Internet of Things for fault detection by aerial monitoring of photovoltaic solar plants

As a major agricultural province in China, Shandong Province has always played an important role. At the same time, it is also closely related to the strong support of science and technology. As a new technology, the Internet of things (IoT) has made positive contributions. Agricultural IoT is a mode that uses information technology, wireless communication technology and radio frequency automatic identification technology to share the identified agricultural information to the network. The application of agricultural IoT is a major change in agricultural development, which provides convenient conditions for the development of agriculture, provides a favorable environment for the agricultural products, promotes the transformation of agricultural technology, realizes the informatization of agricultural production, improves the efficiency of rural land, integrates agricultural resources and provides a foundation for food safety. In this paper, the application of IoT in the field of agriculture in Shandong Province is described from two practical cases. One is about how to use wireless sensor network technology to transmit data in the big data platform based on the Bohai granary project. The other describes how to use IoT for food quality and safety traceability. It takes pigs as the research object, runs through all links of the whole industrial chain of pig breeding, breeding, slaughtering, processing, logistics and sales, collects the data of the whole industrial chain with the help of IoT, and realizes the information tracking and traceability of the whole industrial chain. At the end of the paper, it discusses the countermeasures.