Search results

This paper aims to present the design and implementation of an Internet of Things (IoT)-based e-learning testbed using Raspberry Pi mounted on Raspbian operating system (OS).

The testbed is composed of five Raspberry Pi B+ computers. The experiments are carried out in the department floor considering an non line of sight (NLoS) environment. Single constant bit rate (CBR) flows were transmitted over user datagram protocol (UDP), and data were collected for five metrics: throughput, packet delivery ratio (PDR), hop count, delay and jitter using the Iperf.

The implemented testbed was evaluated using experiments. The experimental results showed that the nodes in the testbed were communicating smoothly, and by using attention value, the learner concentration is increased.

The performance of the Optimized Link State Routing (OLSR) protocol was analyzed in a floor environment considering the NLoS scenario. However, this testbed can be implemented to other protocols also.

Because of the opportunities provided by the internet, people are taking advantage of e-learning courses, and enormous research efforts have been dedicated to the development of e-learning systems. To date, many e-learning systems are proposed and used practically. However, in these systems, the e-learning completion rate is low. To deal with this problem, an IoT-based e-learning system was implemented to increase the e-learning completion ratio by increasing the learner concentration.

Low-cost microcomputers such as the Raspberry Pi are common in library makerspaces. This paper aims to create an OBD-II technology to diagnose a vehicle’s condition.

An OBD-II scanner plugged into the OBD-II port or usually called the data link connector (DLC), sends diagnostics to the Raspberry Pi.

Compared with other microcontrollers such as Arduino, the Raspberry Pi was chosen because it sustains the application to receive real-time diagnostics, process the diagnostics and send commands to automobiles at the same time, rather than Arduino that must wait for another process finished to run another process.

This paper also represents the history of mobile technology and OBD-II technology, comparison between Arduino and Raspberry Pi and Node.

This paper aims to propose a maker’s approach to teaching an operating systems (OSs) course in which students apply knowledge of OSs to making a toy robot by focusing on input/outputs, hardware devices and system programming.

Classroom action research is involved in this study.

After the course was taught in this maker’s approach in two consecutive school years, some observations were reported. Students were enthusiastic in doing a series of assignments leading to the completion of a toy robot that follows a black line on the ground. In addition to enjoying the learning process by making tangible products, the students were excited to be able to demonstrate the skills and knowledge they learned with the robots they made.

The research results were based mainly on the instructor’s observations during the lectures and labs.

Lessons from this study can inspire other instructors to turn traditional engineering courses into maker courses to attract students who enjoy making. Industry should welcome engineering graduates to join the companies with more hands-on experiences they have gained from maker courses.

Although the maker movement has attracted much attention in K12 education, there is little research that studies how this maker spirit can be incorporated in traditional engineering courses that focus mainly on theories or software.

Including electronics and mechanical components in programming assignments would bring surprising effects on students’ motivation in learning.

The health crisis has highlighted the shortcomings of the industry sector which has revealed its vulnerability. To date, there is no guarantee of a return to the “world before”. The ability of companies to cope with these changes is a key competitive advantage requiring the adoption/mastery of industry 4.0 technologies. Therefore, companies must adapt their business processes to fit into similar situations.

The proposed methodology comprises three steps. First, a comparative analysis of the existing CPSs is elaborated. Second, following this analysis, a deep learning driven CPS framework is proposed highlighting its components and tiers. Third, a real industrial case is presented to demonstrate the application of the envisioned framework. Deep learning network-based methods of object detection are used to train the model and evaluation is assessed accordingly.

The analysis revealed that most of the existing CPS frameworks address manufacturing related subjects. This illustrates the need for a resilient industrial CPS targeting other areas and considering CPSs as loopback systems preserving human–machine interaction, endowed with data tiering approach for easy and fast data access and embedded with deep learning-based computer vision processing methods.

This study provides insights about what needs to be addressed in terms of challenges faced due to unforeseen situations or adapting to new ones. In this paper, the CPS framework was used as a monitoring system in compliance with the precautionary measures (social distancing) and for self-protection with wearing the necessary equipments. Nevertheless, the proposed framework can be used and adapted to any industrial or non-industrial environments by adjusting object detection purpose.

The purpose of this work is to implement an ambient intelligence (AmI) testbed to improve human sleeping conditions.

The implemented testbed is composed of the sensor node, sink node and actor node. As sensor node, the authors use a microwave sensor module (MSM) called DC6M4JN3000, which emits microwaves in the direction of a human or animal subject. These microwaves reflect back off the surface of the subject and change slightly in accordance with movements of the subject’s heart and lungs. As sink node, the authors use Raspberry Pi 3 Model B computers. In the sink node, the data are processed and then clustered by the k-means clustering algorithm. Then, the result is sent to the actor node (Reidan Shiki PAD module), which can be used for cooling and heating the bed.

The authors carried out simulations and experiments. Based on the simulation results, it was found that the room lighting, humidity and temperature have different effects on humans during sleeping. The best performance is shown when LIG parameter is 10 units, HUM parameter is 50 and TEM parameter is 25. Based on experimental results, it was found that the implemented AmI testbed has a good effect on humans during sleeping.

For simulations, three input parameters were considered. However, new parameters that affect human sleeping conditions also need to be investigated. Further, the experiments were carried out for one person. More extensive experiments with multiple people are needed to have a better evaluation.

In this research work, a new fuzzy-based system was implemented to improve human sleeping conditions. The authors presented three new input parameters to evaluate the output (sleeping condition). The authors implemented and evaluated a testbed and showed that the implemented AmI testbed has a good effect on humans during sleeping, thus improving their quality of life (QoL).

Introduction: With many new technologies requiring real-time data processing, cloud computing has become challenging to implement due to high bandwidth and high latency requirements.

Purpose: To overcome this issue, edge computing is used to process data at the network’s edge. Edge computing is a distributed computing paradigm that brings computation and data storage closer to the location where it is needed. It is used to process time-sensitive data.

Methodology: The authors implemented the model using Linux Foundation’s open-source platform EdgeX Foundry to create an edge-computing device. The model involved getting data from an on-board sensor (on-board diagnostics (OBD-II)) and the GPS sensor of a car. The data are then observed and computed to the EdgeX server. The single server will send data to serve three real-life internet of things (IoT) use cases: auto insurance, supporting a smart city, and building a personal driving record.

Findings: The main aim of this model is to illustrate how edge computing can improve both latency and bandwidth usage needed for real-world IoT applications.

This study aims to propose novel edge device-tailored federated learning algorithms of local classifiers (stochastic gradient descent, support vector machines), namely, FL-lSGD and FL-lSVM. These algorithms are designed to address the challenge of large-scale ImageNet classification.

The authors’ FL-lSGD and FL-lSVM trains in a parallel and incremental manner to build an ensemble local classifier on Raspberry Pis without requiring data exchange. The algorithms load small data blocks of the local training subset stored on the Raspberry Pi sequentially to train the local classifiers. The data block is split into k partitions using the k-means algorithm, and models are trained in parallel on each data partition to enable local data classification.

Empirical test results on the ImageNet data set show that the authors’ FL-lSGD and FL-lSVM algorithms with 4 Raspberry Pis (Quad core Cortex-A72, ARM v8, 64-bit SoC @ 1.5GHz, 4GB RAM) are faster than the state-of-the-art LIBLINEAR algorithm run on a PC (Intel(R) Core i7-4790 CPU, 3.6 GHz, 4 cores, 32GB RAM).

Efficiently addressing the challenge of large-scale ImageNet classification, the authors’ novel federated learning algorithms of local classifiers have been tailored to work on the Raspberry Pi. These algorithms can handle 1,281,167 images and 1,000 classes effectively.

This paper aims to play catch up with important articles from this past year with interest and implications for librarians.

The approach adopted in this paper is a literature review.

This paper found that there has been important developments in popular and trade computing literature which will interest librarians.

This paper provides an update to the computing literature found in Library Hi Tech News over the previous year.

The trend of “Deep Learning for Internet of Things (IoT)” has gained fresh momentum with enormous upcoming applications employing these models as their processing engine and Cloud as their resource giant. But this picture leads to underutilization of ever-increasing device pool of IoT that has already passed 15 billion mark in 2015. Thus, it is high time to explore a different approach to tackle this issue, keeping in view the characteristics and needs of the two fields. Processing at the Edge can boost applications with real-time deadlines while complementing security.

This review paper contributes towards three cardinal directions of research in the field of DL for IoT. The first section covers the categories of IoT devices and how Fog can aid in overcoming the underutilization of millions of devices, forming the realm of the things for IoT. The second direction handles the issue of immense computational requirements of DL models by uncovering specific compression techniques. An appropriate combination of these techniques, including regularization, quantization, and pruning, can aid in building an effective compression pipeline for establishing DL models for IoT use-cases. The third direction incorporates both these views and introduces a novel approach of parallelization for setting up a distributed systems view of DL for IoT.

DL models are growing deeper with every passing year. Well-coordinated distributed execution of such models using Fog displays a promising future for the IoT application realm. It is realized that a vertically partitioned compressed deep model can handle the trade-off between size, accuracy, communication overhead, bandwidth utilization, and latency but at the expense of an additionally considerable memory footprint. To reduce the memory budget, we propose to exploit Hashed Nets as potentially favorable candidates for distributed frameworks. However, the critical point between accuracy and size for such models needs further investigation.

To the best of our knowledge, no study has explored the inherent parallelism in deep neural network architectures for their efficient distribution over the Edge-Fog continuum. Besides covering techniques and frameworks that have tried to bring inference to the Edge, the review uncovers significant issues and possible future directions for endorsing deep models as processing engines for real-time IoT. The study is directed to both researchers and industrialists to take on various applications to the Edge for better user experience.