Search results
1 – 10 of 155Xiaochun Guan, Sheng Lou, Han Li and Tinglong Tang
Deployment of deep neural networks on embedded devices is becoming increasingly popular because it can reduce latency and energy consumption for data communication. This paper…
Abstract
Purpose
Deployment of deep neural networks on embedded devices is becoming increasingly popular because it can reduce latency and energy consumption for data communication. This paper aims to give out a method for deployment the deep neural networks on a quad-rotor aircraft for further expanding its application scope.
Design/methodology/approach
In this paper, a design scheme is proposed to implement the flight mission of the quad-rotor aircraft based on multi-sensor fusion. It integrates attitude acquisition module, global positioning system position acquisition module, optical flow sensor, ultrasonic sensor and Bluetooth communication module, etc. A 32-bit microcontroller is adopted as the main controller for the quad-rotor aircraft. To make the quad-rotor aircraft be more intelligent, the study also proposes a method to deploy the pre-trained deep neural networks model on the microcontroller based on the software packages of the RT-Thread internet of things operating system.
Findings
This design provides a simple and efficient design scheme to further integrate artificial intelligence (AI) algorithm for the control system design of quad-rotor aircraft.
Originality/value
This method provides an application example and a design reference for the implementation of AI algorithms on unmanned aerial vehicle or terminal robots.
Details
Keywords
In the digital age, organizations want to build a more powerful machine learning model that can serve the increasing needs of people. However, enhancing privacy and data security…
Abstract
Purpose
In the digital age, organizations want to build a more powerful machine learning model that can serve the increasing needs of people. However, enhancing privacy and data security is one of the challenges for machine learning models, especially in federated learning. Parties want to collaborate with each other to build a better model, but they do not want to reveal their own data. This study aims to introduce threats and defenses to privacy leaks in the collaborative learning model.
Design/methodology/approach
In the collaborative model, the attacker was the central server or a participant. In this study, the attacker is on the side of the participant, who is “honest but curious.” Attack experiments are on the participant’s side, who performs two tasks: one is to train the collaborative learning model; the second task is to build a generative adversarial networks (GANs) model, which will perform the attack to infer more information received from the central server. There are three typical types of attacks: white box, black box without auxiliary information and black box with auxiliary information. The experimental environment is set up by PyTorch on Google Colab platform running on graphics processing unit with labeled faces in the wild and Canadian Institute For Advanced Research-10 data sets.
Findings
The paper assumes that the privacy leakage attack resides on the participant’s side, and the information in the parameter server contains too much knowledge to train a collaborative machine learning model. This study compares the success level of inference attack from model parameters based on GAN models. There are three GAN models, which are used in this method: condition GAN, control GAN and Wasserstein generative adversarial networks (WGAN). Of these three models, the WGAN model has proven to obtain the highest stability.
Originality/value
The concern about privacy and security for machine learning models are more important, especially for collaborative learning. The paper has contributed experimentally to private attack on the participant side in the collaborative learning model.
Details
Keywords
Angela Beccanulli, Silvia Biraghi and Rossella C. Gambetti
Nehemia Sugianto, Dian Tjondronegoro, Rosemary Stockdale and Elizabeth Irenne Yuwono
The paper proposes a privacy-preserving artificial intelligence-enabled video surveillance technology to monitor social distancing in public spaces.
Abstract
Purpose
The paper proposes a privacy-preserving artificial intelligence-enabled video surveillance technology to monitor social distancing in public spaces.
Design/methodology/approach
The paper proposes a new Responsible Artificial Intelligence Implementation Framework to guide the proposed solution's design and development. It defines responsible artificial intelligence criteria that the solution needs to meet and provides checklists to enforce the criteria throughout the process. To preserve data privacy, the proposed system incorporates a federated learning approach to allow computation performed on edge devices to limit sensitive and identifiable data movement and eliminate the dependency of cloud computing at a central server.
Findings
The proposed system is evaluated through a case study of monitoring social distancing at an airport. The results discuss how the system can fully address the case study's requirements in terms of its reliability, its usefulness when deployed to the airport's cameras, and its compliance with responsible artificial intelligence.
Originality/value
The paper makes three contributions. First, it proposes a real-time social distancing breach detection system on edge that extends from a combination of cutting-edge people detection and tracking algorithms to achieve robust performance. Second, it proposes a design approach to develop responsible artificial intelligence in video surveillance contexts. Third, it presents results and discussion from a comprehensive evaluation in the context of a case study at an airport to demonstrate the proposed system's robust performance and practical usefulness.
Details
Keywords
Yaqi Liu, Shuzhen Fang, Lingyu Wang, Chong Huan and Ruixue Wang
In recent years, personalized recommendations have facilitated easy access to users' personal information and historical interactions, thereby improving recommendation…
Abstract
Purpose
In recent years, personalized recommendations have facilitated easy access to users' personal information and historical interactions, thereby improving recommendation effectiveness. However, due to privacy risk concerns, it is essential to balance the accuracy of personalized recommendations with privacy protection. Accordingly, this paper aims to propose a neural graph collaborative filtering personalized recommendation framework based on federated transfer learning (FTL-NGCF), which achieves high-quality personalized recommendations with privacy protection.
Design/methodology/approach
FTL-NGCF uses a third-party server to coordinate local users to train the graph neural networks (GNN) model. Each user client integrates user–item interactions into the embedding and uploads the model parameters to a server. To prevent attacks during communication and thus promote privacy preservation, the authors introduce homomorphic encryption to ensure secure model aggregation between clients and the server.
Findings
Experiments on three real data sets (Gowalla, Yelp2018, Amazon-Book) show that FTL-NGCF improves the recommendation performance in terms of recall and NDCG, based on the increased consideration of privacy protection relative to original federated learning methods.
Originality/value
To the best of the authors’ knowledge, no previous research has considered federated transfer learning framework for GNN-based recommendation. It can be extended to other recommended applications while maintaining privacy protection.
Details
Keywords
Loukas Tsironis, Nikos Bilalis and Vassilis Moustakis
To demonstrate the applicability of machine‐learning tools in quality management.
Abstract
Purpose
To demonstrate the applicability of machine‐learning tools in quality management.
Design/methodology/approach
Two popular machine‐learning approaches, decision tree induction and association rules mining, were applied on a set of 960 production case records. The accuracy of results was investigated using randomized experimentation and comprehensibility of rules was assessed by experts in the field.
Findings
Both machine‐learning approaches exhibited very good accuracy of results (average error was about 9 percent); however, association rules mining outperformed decision tree induction in comprehensibility and correctness of learned rules.
Research limitations/implications
The proposed methodology is limited with respect to case representation. Production cases are described via attribute‐value sets and the relation between attribute values cannot be determined by the selected machine‐learning methods.
Practical implications
Results demonstrate that machine‐learning techniques may be effectively used to enhance quality management procedures and modeling of cause‐effect relationships, associated with faulty products.
Originality/value
The article proposes a general methodology on how to use machine‐learning techniques to support quality management. The application of the technique in ISDN modem manufacturing demonstrates the effectiveness of the proposed general methodology.
Details
Keywords
Ratnmala Nivrutti Bhimanpallewar, Sohail Imran Khan, K. Bhavana Raj, Kamal Gulati, Narinder Bhasin and Roop Raj
Federation analytics approaches are a present area of study that has already progressed beyond the analysis of metrics and counts. It is possible to acquire aggregated information…
Abstract
Purpose
Federation analytics approaches are a present area of study that has already progressed beyond the analysis of metrics and counts. It is possible to acquire aggregated information about on-device data by training machine learning models using federated learning techniques without any of the raw data ever having to leave the devices in the issue. Web browser forensics research has been focused on individual Web browsers or architectural analysis of specific log files rather than on broad topics. This paper aims to propose major tools used for Web browser analysis.
Design/methodology/approach
Each kind of Web browser has its own unique set of features. This allows the user to choose their preferred browsers or to check out many browsers at once. If a forensic examiner has access to just one Web browser's log files, he/she makes it difficult to determine which sites a person has visited. The agent must thus be capable of analyzing all currently available Web browsers on a single workstation and doing an integrated study of various Web browsers.
Findings
Federated learning has emerged as a training paradigm in such settings. Web browser forensics research in general has focused on certain browsers or the computational modeling of specific log files. Internet users engage in a wide range of activities using an internet browser, such as searching for information and sending e-mails.
Originality/value
It is also essential that the investigator have access to user activity when conducting an inquiry. This data, which may be used to assess information retrieval activities, is very critical. In this paper, the authors purposed a major tool used for Web browser analysis. This study's proposed algorithm is capable of protecting data privacy effectively in real-world experiments.
Details
Keywords
Budati Anil Kumar, George Ghinea, S.B. Goyal, Krishna Kant Singh and Shayla Islam
R. Dhanalakshmi, Monica Benjamin, Arunkumar Sivaraman, Kiran Sood and S. S. Sreedeep
Purpose: With this study, the authors aim to highlight the application of machine learning in smart appliances used in our day-to-day activities. This chapter focuses on analysing…
Abstract
Purpose: With this study, the authors aim to highlight the application of machine learning in smart appliances used in our day-to-day activities. This chapter focuses on analysing intelligent devices used in our daily lives to examine various machine learning models that can be applied to make an appliance ‘intelligent’ and discuss the different pros and cons of the implementation.
Methodology: Most smart appliances need machine learning models to decrypt the meaning and functioning behind the sensor’s data to execute accurate predictions and come to appropriate conclusions.
Findings: The future holds endless possibilities for devices to be connected in different ways, and these devices will be in our homes, offices, industries and even vehicles that can connect each other. The massive number of connected devices could congest the network; hence there is necessary to incorporate intelligence on end devices using machine learning algorithms. The connected devices that allow automatic control appliance driven by the user’s preference would avail itself to use the Network to communicate with devices close to its proximity or use other channels to liaise with external utility systems. Data processing is facilitated through edge devices, and machine learning algorithms can be applied.
Significance: This chapter overviews smart appliances that use machine learning at the edge. It highlights the effects of using these appliances and how they raise the overall living standards when smarter cities are introduced by integrating such devices.
Details