The ability to predict student performance in a course or program creates opportunities to improve educational outcomes. With effective performance prediction approaches, instructors can allocate resources and instruction more accurately. Research in this area seeks to identify features that can be used to make predictions, to identify algorithms that can improve predictions, and to quantify aspects of student performance. Moreover, research in predicting student performance seeks to determine interrelated features and to identify the underlying reasons why certain features work better than others. This working group report presents a systematic literature review of work in the area of predicting student performance. Our analysis shows a clearly increasing amount of research in this area, as well as an increasing variety of techniques used. At the same time, the review uncovered a number of issues with research quality that drives a need for the community to provide more detailed reporting of methods and results and to increase efforts to validate and replicate work.

https://dl.acm.org/doi/pdf/10.1145/3293881.3295783

Predicting academic performance: a systematic literature review

Due to the interesting nonlinear dynamic properties of chaotic maps, recently chaos-based encryption algorithms have gained much attention in cryptographic communities. However, many encryption schemes do not fulfil the minimum key space requirement, which is an essential concern in many secure data applications. In this paper, an efficient chaos-based image encryption scheme with higher key space is presented. Even with a single round of encryption, a significantly larger key space can be achieved. The proposed scheme removes correlation among image pixels via random chaotic sequences, simply by XOR and addition operations. In order to resist against numerous attacks, we apply the affine transformation to get the final ciphertext image. The security of the proposed scheme is proved through histogram, contrast, PSNR, entropy, correlation, key space, key sensitivity and differential attack analysis. Many significant properties of chaotic maps, sensitivity to initial condition and control parameters, structure and attack complexity, make the anticipated scheme very reliable, practical and robust in various secure communication applications.

A secure image encryption scheme based on chaotic maps and affine transformation

Deep Neural Networks (DNNs) have achieved great success in many applications. The architectures of DNNs play a crucial role in their performance, which is usually manually designed with rich expertise. However, such a design process is labour intensive because of the trial-and-error process, and also not easy to realize due to the rare expertise in practice. Neural Architecture Search (NAS) is a type of technology that can design the architectures automatically. Among different methods to realize NAS, Evolutionary Computation (EC) methods have recently gained much attention and success. Unfortunately, there has not yet been a comprehensive summary of the EC-based NAS algorithms. This paper reviews over 200 papers of most recent EC-based NAS methods in light of the core components, to systematically discuss their design principles as well as justifications on the design. Furthermore, current challenges and issues are also discussed to identify future research in this emerging field.

A Survey on Evolutionary Neural Architecture Search

Adaptive fusion method of visible light and infrared images based on non-subsampled shearlet transform and fast non-negative matrix factorization

Renewable microgrids are new solutions for enhanced security, improved reliability and boosted power quality and operation in power systems. By deploying different sources of renewables such as solar panels and wind units, renewable microgrids can enhance reducing the greenhouse gasses and improve the efficiency. This paper proposes a machine learning based approach for energy management in renewable microgrids considering a reconfigurable structure based on remote switching of tie and sectionalizing. The suggested method considers the advanced support vector machine for modeling and estimating the charging demand of hybrid electric vehicles (HEVs). In order to mitigate the charging effects of HEVs on the system, two different scenarios are deployed; one coordinated and the other one intelligent charging. Due to the complex structure of the problem formulation, a new modified optimization method based on dragonfly is suggested. Moreover, a self-adaptive modification is suggested, which helps the solutions pick the modification method that best fits their situation. Simulation results on an IEEE microgrid test system show its appropriate and efficient quality in both scenarios. According to the prediction results for the total charging demand of the HEVs, the mean absolute percentage error is 0.978, which is very low. Moreover, the results show a 2.5% reduction in the total operation cost of the microgrid in the intelligent charging compared to the coordinated scheme.

/pdf/an-advanced-machine-learning-based-energy-management-of-3i5vwl00n8.pdf

An Advanced Machine Learning Based Energy Management of Renewable Microgrids Considering Hybrid Electric Vehicles' Charging Demand

Multi-modal images fusion is one of the most truthful and useful diagnostic techniques in medical imaging system. This study proposes an image fusion system for medical engineering based on contourlet transform and multi-level fuzzy reasoning technique in which useful information from two spatially registered medical images is integrated into a new image that can be used to make clinical diagnosis and treatment more accurate. The system applies pixel-based fuzzy fusion rule to contourlet's coefficients of high-frequency details and feature-based fuzzy fusion to its low-frequency approximations, which can help the development of sophisticated algorithms that consider not only the time cost but also the quality of the fused image. The developed fusion system eliminates undesirable effects such as fusion artefacts and loss of visually vital information that compromise their usefulness by means of taking into account the physical meaning of contourlet coefficients. The experimental results show that the proposed fusion system outperforms the existing fusion algorithms and is effective to fuse medical images from different sensors with applications in brain image processing.

Multi-level fuzzy contourlet-based image fusion for medical applications

Accurate brain tumor segmentation from 3D Magnetic Resonance Imaging (3D-MRI) is an important method for obtaining information required for diagnosis and disease therapy planning. Variation in the brain tumor’s size, structure, and form is one of the main challenges in tumor segmentation, and selecting the initial contour plays a significant role in reducing the segmentation error and the number of iterations in the level set method. To overcome this issue, this paper suggests a two-step dragonfly algorithm (DA) clustering technique to extract initial contour points accurately. The brain is extracted from the head in the preprocessing step, then tumor edges are extracted using the two-step DA, and these extracted edges are used as an initial contour for the MRI sequence. Lastly, the tumor region is extracted from all volume slices using a level set segmentation method. The results of applying the proposed technique on 3D-MRI images from the multimodal brain tumor segmentation challenge (BRATS) 2017 dataset show that the proposed method for brain tumor segmentation is comparable to the state-of-the-art methods.

3D-MRI Brain Tumor Detection Model Using Modified Version of Level Set Segmentation Based on Dragonfly Algorithm

The advances in digital image processing and communications have created a great demand for real–time secure image transmission over the networks. However, the development of effective, fast and secure dependent image compression encryption systems are still a research problem as the intrinsic features of images such as bulk data capacity and high correlation among pixels hinds the use of the traditional joint encryption compression methods. A new approach is suggested in this paper for partial image encryption compression that adopts chaotic 3D cat map to de-correlate relations among pixels in conjunction with an adaptive thresholding technique that is utilized as a lossy compression technique instead of using complex quantization techniques and also as a substitution technique to increase the security of the cipher image. The proposed scheme is based on employing both of lossless compression with encryption on the most significant part of the image after contourlet transform. However the least significant parts are lossy compressed by employing a simple thresholding rule and arithmetic coding to render the image totally unrecognizable. Due to the weakness of 3D cat map to chosen plain text attack, the suggested scheme incorporates a mechanism to generate random key depending on the contents of the image (context key). Several experiments were done on benchmark images to insure the validity of the proposed technique. The compression analysis and security outcomes indicate that the suggested technique is an efficacious and safe for real time image’s applications.

A modified image selective encryption-compression technique based on 3D chaotic maps and arithmetic coding

Developing cash demand forecasting model for ATM network is a challenging task as the chronological cash demand for every ATM fluctuates with time and often superimposed with non-stationary behavior of users. In order to improve the forecasting precision of ATM cash demand, an Interval Type-2 Fuzzy Neural Network (IT2FNN) has been utilized in this paper. The antecedent parts in each rule of the IT2FNN are interval type-2 fuzzy sets in view of conditions regarding time, location, cash residual and other factors that could lead to consider cash upload able to keep cash at the right levels to meet user demand. The employed IT2FNN has both on-line structure and parameter learning abilities. Simulation results for ATM cash forecasting show the feasibility and effectiveness of the proposed method.

/pdf/a-methodology-to-improve-cash-demand-forecasting-for-atm-3ehahslnf6.pdf

A Methodology to Improve Cash Demand Forecasting for ATM Network

As digital images are increasing exponentially; it is very attractive to develop more effective machine learning frameworks for automatic image annotation. In order to address the most prominent issues (huge inter-concept visual similarity and huge intra-concept visual diversity) more effectively, an inter-related non-parametric Bayesian classifier training framework to support multi-label image annotation is developed. For this purpose, an image is viewed as a bag, and its instances are the over-segmented regions within it found automatically with an adopted Otsu's method segmentation algorithm. Here firefly algorithm (FA) is utilised to enhance Otsu's method in the direction of finding optimal multilevel thresholds using the maximum variance intra-clusters. FA has high convergence speed and less computation rate as compared with some evolutionary algorithms. By generating blobs, the extracted features for segmented regions, the concepts which are learned by the classifier tend to relate textually to the words which occur most often in the data and visually to the easiest to recognise segments. This allowing the opportunity to assign a word to each object (localised labelling). Extensive experiments on Corel benchmark image datasets will validate the effectiveness of the proposed solution to multi-label image annotation and label ranking problem.

https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/iet-ipr.2015.0492

Saad M. Darwish

Papers

Multi-level fuzzy contourlet-based image fusion for medical applications

3D-MRI Brain Tumor Detection Model Using Modified Version of Level Set Segmentation Based on Dragonfly Algorithm

A modified image selective encryption-compression technique based on 3D chaotic maps and arithmetic coding

A Methodology to Improve Cash Demand Forecasting for ATM Network

Combining firefly algorithm and Bayesian classifier: new direction for automatic multilabel image annotation