scholarly journals Machine Learning at the Network Edge: A Survey

2022 ◽  
Vol 54 (8) ◽  
pp. 1-37
Author(s):  
M. G. Sarwar Murshed ◽  
Christopher Murphy ◽  
Daqing Hou ◽  
Nazar Khan ◽  
Ganesh Ananthanarayanan ◽  
...  

Resource-constrained IoT devices, such as sensors and actuators, have become ubiquitous in recent years. This has led to the generation of large quantities of data in real-time, which is an appealing target for AI systems. However, deploying machine learning models on such end-devices is nearly impossible. A typical solution involves offloading data to external computing systems (such as cloud servers) for further processing but this worsens latency, leads to increased communication costs, and adds to privacy concerns. To address this issue, efforts have been made to place additional computing devices at the edge of the network, i.e., close to the IoT devices where the data is generated. Deploying machine learning systems on such edge computing devices alleviates the above issues by allowing computations to be performed close to the data sources. This survey describes major research efforts where machine learning systems have been deployed at the edge of computer networks, focusing on the operational aspects including compression techniques, tools, frameworks, and hardware used in successful applications of intelligent edge systems.

Author(s):  
Madhuri Kumar ◽  
John Alen

The terminology Artificial Intelligence (AI) describes the application computing systems and technology to effectively simulate smart actions and smart thinking compared to the human mind. The concept of AI was introduced as the engineering and science of making smart machines that can operate without the engagement of humans using Machine Learning (ML). This research provides a wider scope of the concept of AI in the medical field, handling the various concepts and terms associated with the concept, including the present and future implementation of the concept. The major research materials applied are Google and PubMed searches, which were conducted using the “Artificial Intelligence” as the basic keyword. More references were retrieved by cross-referencing major publications. The advancements in AI technology in recent times and the present application of medicine have been analyzed critically. This paper ends with an assumption that AI focuses on implementing changes in the medical practices in previously unidentified ways. However, many of the application are still in the initial stages and require exploration and development. In addition, clinical experts have to comprehend and adapt with development for effective delivery of medical services.


Author(s):  
Cate Dowd

Semantic news tags processed via cloud servers are in amongst big data and machine learning systems. The latter may have influenced Murdoch’s acquisition of a ‘social media news agency’, and other partnerships, as a mix of new roles across journalism, analytics, and search emerged. Some editing roles in journalism focus on SEO, but Murdoch’s Storyful, which started as a verification business created jobs for cloud operations engineers, viral video editors, and trends editors. Data-mining techniques were a lure for news and social media partnerships circa 2013–2016. In the name of verification, access to big data was matched by social media gaining credibility, evident in Facebook Newswire and other journalism projects. Deep learning methods in search, referrals, and automated tagging have also produced mutual benefits, mostly via third party agreements. However, data sharing for political ends by targeting particular users, and verification projects, have not stopped fake news.


2020 ◽  
Vol 34 (05) ◽  
pp. 7179-7186
Author(s):  
Hanpeng Hu ◽  
Dan Wang ◽  
Chuan Wu

Many emerging AI applications request distributed machine learning (ML) among edge systems (e.g., IoT devices and PCs at the edge of the Internet), where data cannot be uploaded to a central venue for model training, due to their large volumes and/or security/privacy concerns. Edge devices are intrinsically heterogeneous in computing capacity, posing significant challenges to parameter synchronization for parallel training with the parameter server (PS) architecture. This paper proposes ADSP, a parameter synchronization model for distributed machine learning (ML) with heterogeneous edge systems. Eliminating the significant waiting time occurring with existing parameter synchronization models, the core idea of ADSP is to let faster edge devices continue training, while committing their model updates at strategically decided intervals. We design algorithms that decide time points for each worker to commit its model update, and ensure not only global model convergence but also faster convergence. Our testbed implementation and experiments show that ADSP outperforms existing parameter synchronization models significantly in terms of ML model convergence time, scalability and adaptability to large heterogeneity.


Author(s):  
A. V. Deorankar ◽  
Shiwani S. Thakare

IoT is the network which connects and communicates with billions of devices through the internet and due to the massive use of IoT devices, the shared data between the devices or over the network is not confidential because of increasing growth of cyberattacks. The network traffic via loT systems is growing widely and introducing new cybersecurity challenges since these loT devices are connected to sensors that are directly connected to large-scale cloud servers. In order to reduce these cyberattacks, the developers need to raise new techniques for detecting infected loT devices. In this work, to control over this cyberattacks, the fog layer is introduced, to maintain the security of data on a cloud. Also the working of fog layer and different anomaly detection techniques to prevent the cyberattacks has been studied. The proposed AD-IoT can significantly detect malicious behavior using anomalies based on machine learning classification before distributing on a cloud layer. This work discusses the role of machine learning techniques for identifying the type of Cyberattacks. There are two ML techniques i.e. RF and MLP evaluated on the USNW-NB15 dataset. The accuracy and false alarm rate of the techniques are assessed, and the results revealed the superiority of the RF compared with MLP. The Accuracy measures by classifiers are 98 and 53 of RF and MLP respectively, which shows a huge difference and prove the RF as most efficient algorithm with binary classification as well as multi- classification.


2018 ◽  
Vol 12 ◽  
pp. 85-98
Author(s):  
Bojan Kostadinov ◽  
Mile Jovanov ◽  
Emil STANKOV

Data collection and machine learning are changing the world. Whether it is medicine, sports or education, companies and institutions are investing a lot of time and money in systems that gather, process and analyse data. Likewise, to improve competitiveness, a lot of countries are making changes to their educational policy by supporting STEM disciplines. Therefore, it’s important to put effort into using various data sources to help students succeed in STEM. In this paper, we present a platform that can analyse student’s activity on various contest and e-learning systems, combine and process the data, and then present it in various ways that are easy to understand. This in turn enables teachers and organizers to recognize talented and hardworking students, identify issues, and/or motivate students to practice and work on areas where they’re weaker.


Author(s):  
P. Sudheer ◽  
T. Lakshmi Surekha

Cloud computing is a revolutionary computing paradigm, which enables flexible, on-demand, and low-cost usage of computing resources, but the data is outsourced to some cloud servers, and various privacy concerns emerge from it. Various schemes based on the attribute-based encryption have been to secure the cloud storage. Data content privacy. A semi anonymous privilege control scheme AnonyControl to address not only the data privacy. But also the user identity privacy. AnonyControl decentralizes the central authority to limit the identity leakage and thus achieves semi anonymity. The  Anonymity –F which fully prevent the identity leakage and achieve the full anonymity.


Sensors ◽  
2021 ◽  
Vol 21 (10) ◽  
pp. 3515
Author(s):  
Sung-Ho Sim ◽  
Yoon-Su Jeong

As the development of IoT technologies has progressed rapidly recently, most IoT data are focused on monitoring and control to process IoT data, but the cost of collecting and linking various IoT data increases, requiring the ability to proactively integrate and analyze collected IoT data so that cloud servers (data centers) can process smartly. In this paper, we propose a blockchain-based IoT big data integrity verification technique to ensure the safety of the Third Party Auditor (TPA), which has a role in auditing the integrity of AIoT data. The proposed technique aims to minimize IoT information loss by multiple blockchain groupings of information and signature keys from IoT devices. The proposed technique allows IoT information to be effectively guaranteed the integrity of AIoT data by linking hash values designated as arbitrary, constant-size blocks with previous blocks in hierarchical chains. The proposed technique performs synchronization using location information between the central server and IoT devices to manage the cost of the integrity of IoT information at low cost. In order to easily control a large number of locations of IoT devices, we perform cross-distributed and blockchain linkage processing under constant rules to improve the load and throughput generated by IoT devices.


IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 65066-65077
Author(s):  
Wei Ma ◽  
Xing Wang ◽  
Mingsheng Hu ◽  
Qinglei Zhou

Sensors ◽  
2021 ◽  
Vol 21 (7) ◽  
pp. 2514
Author(s):  
Tharindu Kaluarachchi ◽  
Andrew Reis ◽  
Suranga Nanayakkara

After Deep Learning (DL) regained popularity recently, the Artificial Intelligence (AI) or Machine Learning (ML) field is undergoing rapid growth concerning research and real-world application development. Deep Learning has generated complexities in algorithms, and researchers and users have raised concerns regarding the usability and adoptability of Deep Learning systems. These concerns, coupled with the increasing human-AI interactions, have created the emerging field that is Human-Centered Machine Learning (HCML). We present this review paper as an overview and analysis of existing work in HCML related to DL. Firstly, we collaborated with field domain experts to develop a working definition for HCML. Secondly, through a systematic literature review, we analyze and classify 162 publications that fall within HCML. Our classification is based on aspects including contribution type, application area, and focused human categories. Finally, we analyze the topology of the HCML landscape by identifying research gaps, highlighting conflicting interpretations, addressing current challenges, and presenting future HCML research opportunities.


Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1044
Author(s):  
Yassine Bouabdallaoui ◽  
Zoubeir Lafhaj ◽  
Pascal Yim ◽  
Laure Ducoulombier ◽  
Belkacem Bennadji

The operation and maintenance of buildings has seen several advances in recent years. Multiple information and communication technology (ICT) solutions have been introduced to better manage building maintenance. However, maintenance practices in buildings remain less efficient and lead to significant energy waste. In this paper, a predictive maintenance framework based on machine learning techniques is proposed. This framework aims to provide guidelines to implement predictive maintenance for building installations. The framework is organised into five steps: data collection, data processing, model development, fault notification and model improvement. A sport facility was selected as a case study in this work to demonstrate the framework. Data were collected from different heating ventilation and air conditioning (HVAC) installations using Internet of Things (IoT) devices and a building automation system (BAS). Then, a deep learning model was used to predict failures. The case study showed the potential of this framework to predict failures. However, multiple obstacles and barriers were observed related to data availability and feedback collection. The overall results of this paper can help to provide guidelines for scientists and practitioners to implement predictive maintenance approaches in buildings.


Sign in / Sign up

Export Citation Format

Share Document