Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

/pdf/a-break-in-the-clouds-towards-a-cloud-definition-svovsw1r5a.pdf

A Break in the Clouds: Towards a Cloud Definition

When building a unified vision system or gradually adding new capabilities to a system, the usual assumption is that training data for all tasks is always available. However, as the number of tasks grows, storing and retraining on such data becomes infeasible. A new problem arises where we add new capabilities to a Convolutional Neural Network (CNN), but the training data for its existing capabilities are unavailable. We propose our Learning without Forgetting method, which uses only new task data to train the network while preserving the original capabilities. Our method performs favorably compared to commonly used feature extraction and fine-tuning adaption techniques and performs similarly to multitask learning that uses original task data we assume unavailable. A more surprising observation is that Learning without Forgetting may be able to replace fine-tuning with similar old and new task datasets for improved new task performance.

Learning without Forgetting

To study the operational behaviour of λ-terms, we will use the denotational (mathematical) approach. A denotational semantics for a language is based on the choice of a space of semantics values, or denotations, where terms are to be interpreted. Choosing a space with nice mathematical properties can help in proving the semantic properties of terms, since to this aim standard mathematical techniques can be used.

λ Δ -Models

Information environments have the power to affect people's perceptions and behaviors. In this paper, we present the results of studies in which we characterize the gender bias present in image search results for a variety of occupations. We experimentally evaluate the effects of bias in image search results on the images people choose to represent those careers and on people's perceptions of the prevalence of men and women in each occupation. We find evidence for both stereotype exaggeration and systematic underrepresentation of women in search results. We also find that people rate search results higher when they are consistent with stereotypes for a career, and shifting the representation of gender in image search results can shift people's perceptions about real-world distributions. We also discuss tensions between desires for high-quality results and broader societal goals for equality of representation in this space.

/pdf/unequal-representation-and-gender-stereotypes-in-image-l15y9pxcq1.pdf

Unequal Representation and Gender Stereotypes in Image Search Results for Occupations

The paper presents a methodology for social distancing detection using deep learning to evaluate the distance between people to mitigate the impact of this coronavirus pandemic. The detection tool was developed to alert people to maintain a safe distance with each other by evaluating a video feed. The video frame from the camera was used as input, and the open-source object detection pre-trained model based on the YOLOv3 algorithm was employed for pedestrian detection. Later, the video frame was transformed into top-down view for distance measurement from the 2D plane. The distance between people can be estimated and any noncompliant pair of people in the display will be indicated with a red frame and red line. The proposed method was validated on a pre-recorded video of pedestrians walking on the street. The result shows that the proposed method is able to determine the social distancing measures between multiple people in the video. The developed technique can be further developed as a detection tool in realtime application.

/pdf/social-distancing-detection-with-deep-learning-model-44spcymfb3.pdf

Social Distancing Detection with Deep Learning Model

Although IEC61850 substations can provide various advantages over traditional substations, the power supplier companies are being cautious about its implementation due to security concerns. Indeed, researchers have identified a number of security vulnerabilities and weaknesses in the IEC61850 standard such as the lack of encryption used in the GOOSE messages, lack of intrusion detection system implementation in IEC61850 network, and no firewall implementation inside IEC61850 substation network. By exploiting these vulnerabilities, researchers have also discovered a number of security attacks that can be launched on IEC61850 substation network. These attacks can be categorized into two, which are common network security attacks on IEC61850 network and security attacks that exploit the IEC61850 multicast messages. This paper provides a review of these security attacks in terms of how the attacks are conducted and the subsequent damages that they may cause.

A review of security attacks on IEC61850 substation automation system network

Human behavior inside organizations is considered the main threat to organizations. Moreover, in information security the human element consider the most of weakest link in general. Therefore it is crucial to create an information security culture to protect the organization's assets from inside and to influence employees' security behavior. This paper focuses on identifying the definitions and frameworks for establishing and maintaining information security culture inside organizations. It presents work have been done to conduct a systematic literature review of papers published on information security culture from 2003 to 2016. The review identified 68 papers that focus on this area, 18 of which propose an information security culture framework. An analysis of these papers indicate there is a positive relationship between levels of knowledge and how employees behave. The level of knowledge significantly affects information security behavior and should be considered as a critical factor in the effectiveness of information security culture and in any further work that is carried out on information security culture. Therefore, there is a need for more studies to identity the security knowledge that needs to be incorporated into organizations and to find instances of best practice for building an information security culture within organizations.

A systematic literature review: Information security culture

One of the main difficulties in designing online signature verification (OSV) system is to find the most distinctive features with high discriminating capabilities for the verification, particularly, with regard to the high variability which is inherent in genuine handwritten signatures, coupled with the possibility of skilled forgeries having close resemblance to the original counterparts. In this paper, we proposed a systematic approach to online signature verification through the use of multilayer perceptron (MLP) on a subset of principal component analysis (PCA) features. The proposed approach illustrates a feature selection technique on the usually discarded information from PCA computation, which can be significant in attaining reduced error rates. The experiment is performed using 4000 signature samples from SIGMA database, which yielded a false acceptance rate (FAR) of 7.4% and a false rejection rate (FRR) of 6.4%.

/pdf/online-handwritten-signature-verification-using-neural-4ip7o26f8h.pdf

Online handwritten signature verification using neural network classifier based on principal component analysis.

Organizations share an evolving interest in adopting a cloud computing approach for Internet of Things (IoT) applications. Integrating IoT devices and cloud computing technology is considered as an effective approach to storing and managing the enormous amount of data generated by various devices. However, big data security of these organizations presents a challenge in the IoT-cloud architecture. To overcome security issues, we propose a cloud-enabled IoT environment supported by multifactor authentication and lightweight cryptography encryption schemes to protect big data system. The proposed hybrid cloud environment is aimed at protecting organizations' data in a highly secure manner. The hybrid cloud environment is a combination of private and public cloud. Our IoT devices are divided into sensitive and nonsensitive devices. Sensitive devices generate sensitive data, such as healthcare data; whereas nonsensitive devices generate nonsensitive data, such as home appliance data. IoT devices send their data to the cloud via a gateway device. Herein, sensitive data are split into two parts: one part of the data is encrypted using RC6, and the other part is encrypted using the Fiestel encryption scheme. Nonsensitive data are encrypted using the Advanced Encryption Standard (AES) encryption scheme. Sensitive and nonsensitive data are respectively stored in private and public cloud to ensure high security. The use of multifactor authentication to access the data stored in the cloud is also proposed. During login, data users send their registered credentials to the Trusted Authority (TA). The TA provides three levels of authentication to access the stored data: first-level authentication - read file, second-level authentication - download file, and third-level authentication - download file from the hybrid cloud. We implement the proposed cloud-IoT architecture in the NS3 network simulator. We evaluated the performance of the proposed architecture using metrics such as computational time, security strength, encryption time, and decryption time.

/pdf/scalable-and-secure-big-data-iot-system-based-on-multifactor-28ckezc2jb.pdf

Salman Yussof

Papers

Social Distancing Detection with Deep Learning Model

A review of security attacks on IEC61850 substation automation system network

A systematic literature review: Information security culture

Online handwritten signature verification using neural network classifier based on principal component analysis.

Scalable and Secure Big Data IoT System Based on Multifactor Authentication and Lightweight Cryptography